| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright 2011-2014 Autronica Fire and Security AS * * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * include file for HSR and PRP. */ #ifndef __HSR_SLAVE_H #define __HSR_SLAVE_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include "hsr_main.h" int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, enum hsr_port_type pt, struct netlink_ext_ack *extack); void hsr_del_port(struct hsr_port *port); bool hsr_port_exists(const struct net_device *dev); static inline struct hsr_port *hsr_port_get_rtnl(const struct net_device *dev) { ASSERT_RTNL(); return hsr_port_exists(dev) ? rtnl_dereference(dev->rx_handler_data) : NULL; } static inline struct hsr_port *hsr_port_get_rcu(const struct net_device *dev) { return hsr_port_exists(dev) ? rcu_dereference(dev->rx_handler_data) : NULL; } bool hsr_invalid_dan_ingress_frame(__be16 protocol); #endif /* __HSR_SLAVE_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 | /* * Copyright IBM Corporation, 2012 * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License * as published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. * */ #ifndef _LINUX_HUGETLB_CGROUP_H #define _LINUX_HUGETLB_CGROUP_H #include <linux/mmdebug.h> struct hugetlb_cgroup; struct resv_map; struct file_region; #ifdef CONFIG_CGROUP_HUGETLB enum hugetlb_memory_event { HUGETLB_MAX, HUGETLB_NR_MEMORY_EVENTS, }; struct hugetlb_cgroup_per_node { /* hugetlb usage in pages over all hstates. */ unsigned long usage[HUGE_MAX_HSTATE]; }; struct hugetlb_cgroup { struct cgroup_subsys_state css; /* * the counter to account for hugepages from hugetlb. */ struct page_counter hugepage[HUGE_MAX_HSTATE]; /* * the counter to account for hugepage reservations from hugetlb. */ struct page_counter rsvd_hugepage[HUGE_MAX_HSTATE]; atomic_long_t events[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; atomic_long_t events_local[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; /* Handle for "hugetlb.events" */ struct cgroup_file events_file[HUGE_MAX_HSTATE]; /* Handle for "hugetlb.events.local" */ struct cgroup_file events_local_file[HUGE_MAX_HSTATE]; struct hugetlb_cgroup_per_node *nodeinfo[]; }; static inline struct hugetlb_cgroup * __hugetlb_cgroup_from_folio(struct folio *folio, bool rsvd) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); if (rsvd) return folio->_hugetlb_cgroup_rsvd; else return folio->_hugetlb_cgroup; } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { return __hugetlb_cgroup_from_folio(folio, false); } static inline struct hugetlb_cgroup * hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { return __hugetlb_cgroup_from_folio(folio, true); } static inline void __set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg, bool rsvd) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); if (rsvd) folio->_hugetlb_cgroup_rsvd = h_cg; else folio->_hugetlb_cgroup = h_cg; } static inline void set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg) { __set_hugetlb_cgroup(folio, h_cg, false); } static inline void set_hugetlb_cgroup_rsvd(struct folio *folio, struct hugetlb_cgroup *h_cg) { __set_hugetlb_cgroup(folio, h_cg, true); } static inline bool hugetlb_cgroup_disabled(void) { return !cgroup_subsys_enabled(hugetlb_cgrp_subsys); } static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) { css_put(&h_cg->css); } static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { if (resv_map->css) css_get(resv_map->css); } static inline void resv_map_put_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { if (resv_map->css) css_put(resv_map->css); } extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio); extern void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio); extern void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio); extern void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, struct folio *folio); extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); extern void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); extern void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, unsigned long end); extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, unsigned long nr_pages, bool region_del); extern void hugetlb_cgroup_file_init(void) __init; extern void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio); #else static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, unsigned long nr_pages, bool region_del) { } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { return NULL; } static inline struct hugetlb_cgroup * hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { return NULL; } static inline void set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg) { } static inline void set_hugetlb_cgroup_rsvd(struct folio *folio, struct hugetlb_cgroup *h_cg) { } static inline bool hugetlb_cgroup_disabled(void) { return true; } static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) { } static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { } static inline void resv_map_put_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { } static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return 0; } static inline int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return 0; } static inline void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { } static inline void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { } static inline void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { } static inline void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, unsigned long end) { } static inline void hugetlb_cgroup_file_init(void) { } static inline void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio) { } #endif /* CONFIG_MEM_RES_CTLR_HUGETLB */ #endif |
| 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 35 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 13 36 36 36 36 36 36 36 36 36 36 36 35 36 36 35 36 36 36 36 36 36 36 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/signal.c * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-11-02 Modified for POSIX.1b signals by Richard Henderson * * 2003-06-02 Jim Houston - Concurrent Computer Corp. * Changes to use preallocated sigqueue structures * to allow signals to be sent reliably. */ #include <linux/slab.h> #include <linux/export.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/user.h> #include <linux/sched/debug.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/proc_fs.h> #include <linux/tty.h> #include <linux/binfmts.h> #include <linux/coredump.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/signalfd.h> #include <linux/ratelimit.h> #include <linux/task_work.h> #include <linux/capability.h> #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <linux/nsproxy.h> #include <linux/user_namespace.h> #include <linux/uprobes.h> #include <linux/compat.h> #include <linux/cn_proc.h> #include <linux/compiler.h> #include <linux/posix-timers.h> #include <linux/cgroup.h> #include <linux/audit.h> #include <linux/sysctl.h> #include <uapi/linux/pidfd.h> #define CREATE_TRACE_POINTS #include <trace/events/signal.h> #include <asm/param.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/siginfo.h> #include <asm/cacheflush.h> #include <asm/syscall.h> /* for syscall_get_* */ /* * SLAB caches for signal bits. */ static struct kmem_cache *sigqueue_cachep; int print_fatal_signals __read_mostly; static void __user *sig_handler(struct task_struct *t, int sig) { return t->sighand->action[sig - 1].sa.sa_handler; } static inline bool sig_handler_ignored(void __user *handler, int sig) { /* Is it explicitly or implicitly ignored? */ return handler == SIG_IGN || (handler == SIG_DFL && sig_kernel_ignore(sig)); } static bool sig_task_ignored(struct task_struct *t, int sig, bool force) { void __user *handler; handler = sig_handler(t, sig); /* SIGKILL and SIGSTOP may not be sent to the global init */ if (unlikely(is_global_init(t) && sig_kernel_only(sig))) return true; if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) && handler == SIG_DFL && !(force && sig_kernel_only(sig))) return true; /* Only allow kernel generated signals to this kthread */ if (unlikely((t->flags & PF_KTHREAD) && (handler == SIG_KTHREAD_KERNEL) && !force)) return true; return sig_handler_ignored(handler, sig); } static bool sig_ignored(struct task_struct *t, int sig, bool force) { /* * Blocked signals are never ignored, since the * signal handler may change by the time it is * unblocked. */ if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig)) return false; /* * Tracers may want to know about even ignored signal unless it * is SIGKILL which can't be reported anyway but can be ignored * by SIGNAL_UNKILLABLE task. */ if (t->ptrace && sig != SIGKILL) return false; return sig_task_ignored(t, sig, force); } /* * Re-calculate pending state from the set of locally pending * signals, globally pending signals, and blocked signals. */ static inline bool has_pending_signals(sigset_t *signal, sigset_t *blocked) { unsigned long ready; long i; switch (_NSIG_WORDS) { default: for (i = _NSIG_WORDS, ready = 0; --i >= 0 ;) ready |= signal->sig[i] &~ blocked->sig[i]; break; case 4: ready = signal->sig[3] &~ blocked->sig[3]; ready |= signal->sig[2] &~ blocked->sig[2]; ready |= signal->sig[1] &~ blocked->sig[1]; ready |= signal->sig[0] &~ blocked->sig[0]; break; case 2: ready = signal->sig[1] &~ blocked->sig[1]; ready |= signal->sig[0] &~ blocked->sig[0]; break; case 1: ready = signal->sig[0] &~ blocked->sig[0]; } return ready != 0; } #define PENDING(p,b) has_pending_signals(&(p)->signal, (b)) static bool recalc_sigpending_tsk(struct task_struct *t) { if ((t->jobctl & (JOBCTL_PENDING_MASK | JOBCTL_TRAP_FREEZE)) || PENDING(&t->pending, &t->blocked) || PENDING(&t->signal->shared_pending, &t->blocked) || cgroup_task_frozen(t)) { set_tsk_thread_flag(t, TIF_SIGPENDING); return true; } /* * We must never clear the flag in another thread, or in current * when it's possible the current syscall is returning -ERESTART*. * So we don't clear it here, and only callers who know they should do. */ return false; } void recalc_sigpending(void) { if (!recalc_sigpending_tsk(current) && !freezing(current)) clear_thread_flag(TIF_SIGPENDING); } EXPORT_SYMBOL(recalc_sigpending); void calculate_sigpending(void) { /* Have any signals or users of TIF_SIGPENDING been delayed * until after fork? */ spin_lock_irq(¤t->sighand->siglock); set_tsk_thread_flag(current, TIF_SIGPENDING); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); } /* Given the mask, find the first available signal that should be serviced. */ #define SYNCHRONOUS_MASK \ (sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \ sigmask(SIGTRAP) | sigmask(SIGFPE) | sigmask(SIGSYS)) int next_signal(struct sigpending *pending, sigset_t *mask) { unsigned long i, *s, *m, x; int sig = 0; s = pending->signal.sig; m = mask->sig; /* * Handle the first word specially: it contains the * synchronous signals that need to be dequeued first. */ x = *s &~ *m; if (x) { if (x & SYNCHRONOUS_MASK) x &= SYNCHRONOUS_MASK; sig = ffz(~x) + 1; return sig; } switch (_NSIG_WORDS) { default: for (i = 1; i < _NSIG_WORDS; ++i) { x = *++s &~ *++m; if (!x) continue; sig = ffz(~x) + i*_NSIG_BPW + 1; break; } break; case 2: x = s[1] &~ m[1]; if (!x) break; sig = ffz(~x) + _NSIG_BPW + 1; break; case 1: /* Nothing to do */ break; } return sig; } static inline void print_dropped_signal(int sig) { static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); if (!print_fatal_signals) return; if (!__ratelimit(&ratelimit_state)) return; pr_info("%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n", current->comm, current->pid, sig); } /** * task_set_jobctl_pending - set jobctl pending bits * @task: target task * @mask: pending bits to set * * Clear @mask from @task->jobctl. @mask must be subset of * %JOBCTL_PENDING_MASK | %JOBCTL_STOP_CONSUME | %JOBCTL_STOP_SIGMASK | * %JOBCTL_TRAPPING. If stop signo is being set, the existing signo is * cleared. If @task is already being killed or exiting, this function * becomes noop. * * CONTEXT: * Must be called with @task->sighand->siglock held. * * RETURNS: * %true if @mask is set, %false if made noop because @task was dying. */ bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask) { BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME | JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING)); BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK)); if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING))) return false; if (mask & JOBCTL_STOP_SIGMASK) task->jobctl &= ~JOBCTL_STOP_SIGMASK; task->jobctl |= mask; return true; } /** * task_clear_jobctl_trapping - clear jobctl trapping bit * @task: target task * * If JOBCTL_TRAPPING is set, a ptracer is waiting for us to enter TRACED. * Clear it and wake up the ptracer. Note that we don't need any further * locking. @task->siglock guarantees that @task->parent points to the * ptracer. * * CONTEXT: * Must be called with @task->sighand->siglock held. */ void task_clear_jobctl_trapping(struct task_struct *task) { if (unlikely(task->jobctl & JOBCTL_TRAPPING)) { task->jobctl &= ~JOBCTL_TRAPPING; smp_mb(); /* advised by wake_up_bit() */ wake_up_bit(&task->jobctl, JOBCTL_TRAPPING_BIT); } } /** * task_clear_jobctl_pending - clear jobctl pending bits * @task: target task * @mask: pending bits to clear * * Clear @mask from @task->jobctl. @mask must be subset of * %JOBCTL_PENDING_MASK. If %JOBCTL_STOP_PENDING is being cleared, other * STOP bits are cleared together. * * If clearing of @mask leaves no stop or trap pending, this function calls * task_clear_jobctl_trapping(). * * CONTEXT: * Must be called with @task->sighand->siglock held. */ void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask) { BUG_ON(mask & ~JOBCTL_PENDING_MASK); if (mask & JOBCTL_STOP_PENDING) mask |= JOBCTL_STOP_CONSUME | JOBCTL_STOP_DEQUEUED; task->jobctl &= ~mask; if (!(task->jobctl & JOBCTL_PENDING_MASK)) task_clear_jobctl_trapping(task); } /** * task_participate_group_stop - participate in a group stop * @task: task participating in a group stop * * @task has %JOBCTL_STOP_PENDING set and is participating in a group stop. * Group stop states are cleared and the group stop count is consumed if * %JOBCTL_STOP_CONSUME was set. If the consumption completes the group * stop, the appropriate `SIGNAL_*` flags are set. * * CONTEXT: * Must be called with @task->sighand->siglock held. * * RETURNS: * %true if group stop completion should be notified to the parent, %false * otherwise. */ static bool task_participate_group_stop(struct task_struct *task) { struct signal_struct *sig = task->signal; bool consume = task->jobctl & JOBCTL_STOP_CONSUME; WARN_ON_ONCE(!(task->jobctl & JOBCTL_STOP_PENDING)); task_clear_jobctl_pending(task, JOBCTL_STOP_PENDING); if (!consume) return false; if (!WARN_ON_ONCE(sig->group_stop_count == 0)) sig->group_stop_count--; /* * Tell the caller to notify completion iff we are entering into a * fresh group stop. Read comment in do_signal_stop() for details. */ if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) { signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED); return true; } return false; } void task_join_group_stop(struct task_struct *task) { unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK; struct signal_struct *sig = current->signal; if (sig->group_stop_count) { sig->group_stop_count++; mask |= JOBCTL_STOP_CONSUME; } else if (!(sig->flags & SIGNAL_STOP_STOPPED)) return; /* Have the new thread join an on-going signal group stop */ task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING); } /* * allocate a new signal queue record * - this may be called without locks if and only if t == current, otherwise an * appropriate lock must be held to stop the target task from exiting */ static struct sigqueue * __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, int override_rlimit, const unsigned int sigqueue_flags) { struct sigqueue *q = NULL; struct ucounts *ucounts; long sigpending; /* * Protect access to @t credentials. This can go away when all * callers hold rcu read lock. * * NOTE! A pending signal will hold on to the user refcount, * and we get/put the refcount only when the sigpending count * changes from/to zero. */ rcu_read_lock(); ucounts = task_ucounts(t); sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); rcu_read_unlock(); if (!sigpending) return NULL; if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, gfp_flags); } else { print_dropped_signal(sig); } if (unlikely(q == NULL)) { dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); } else { INIT_LIST_HEAD(&q->list); q->flags = sigqueue_flags; q->ucounts = ucounts; } return q; } static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; if (q->ucounts) { dec_rlimit_put_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING); q->ucounts = NULL; } kmem_cache_free(sigqueue_cachep, q); } void flush_sigqueue(struct sigpending *queue) { struct sigqueue *q; sigemptyset(&queue->signal); while (!list_empty(&queue->list)) { q = list_entry(queue->list.next, struct sigqueue , list); list_del_init(&q->list); __sigqueue_free(q); } } /* * Flush all pending signals for this kthread. */ void flush_signals(struct task_struct *t) { unsigned long flags; spin_lock_irqsave(&t->sighand->siglock, flags); clear_tsk_thread_flag(t, TIF_SIGPENDING); flush_sigqueue(&t->pending); flush_sigqueue(&t->signal->shared_pending); spin_unlock_irqrestore(&t->sighand->siglock, flags); } EXPORT_SYMBOL(flush_signals); #ifdef CONFIG_POSIX_TIMERS static void __flush_itimer_signals(struct sigpending *pending) { sigset_t signal, retain; struct sigqueue *q, *n; signal = pending->signal; sigemptyset(&retain); list_for_each_entry_safe(q, n, &pending->list, list) { int sig = q->info.si_signo; if (likely(q->info.si_code != SI_TIMER)) { sigaddset(&retain, sig); } else { sigdelset(&signal, sig); list_del_init(&q->list); __sigqueue_free(q); } } sigorsets(&pending->signal, &signal, &retain); } void flush_itimer_signals(void) { struct task_struct *tsk = current; unsigned long flags; spin_lock_irqsave(&tsk->sighand->siglock, flags); __flush_itimer_signals(&tsk->pending); __flush_itimer_signals(&tsk->signal->shared_pending); spin_unlock_irqrestore(&tsk->sighand->siglock, flags); } #endif void ignore_signals(struct task_struct *t) { int i; for (i = 0; i < _NSIG; ++i) t->sighand->action[i].sa.sa_handler = SIG_IGN; flush_signals(t); } /* * Flush all handlers for a task. */ void flush_signal_handlers(struct task_struct *t, int force_default) { int i; struct k_sigaction *ka = &t->sighand->action[0]; for (i = _NSIG ; i != 0 ; i--) { if (force_default || ka->sa.sa_handler != SIG_IGN) ka->sa.sa_handler = SIG_DFL; ka->sa.sa_flags = 0; #ifdef __ARCH_HAS_SA_RESTORER ka->sa.sa_restorer = NULL; #endif sigemptyset(&ka->sa.sa_mask); ka++; } } bool unhandled_signal(struct task_struct *tsk, int sig) { void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler; if (is_global_init(tsk)) return true; if (handler != SIG_IGN && handler != SIG_DFL) return false; /* If dying, we handle all new signals by ignoring them */ if (fatal_signal_pending(tsk)) return false; /* if ptraced, let the tracer determine */ return !tsk->ptrace; } static void collect_signal(int sig, struct sigpending *list, kernel_siginfo_t *info, bool *resched_timer) { struct sigqueue *q, *first = NULL; /* * Collect the siginfo appropriate to this signal. Check if * there is another siginfo for the same signal. */ list_for_each_entry(q, &list->list, list) { if (q->info.si_signo == sig) { if (first) goto still_pending; first = q; } } sigdelset(&list->signal, sig); if (first) { still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); *resched_timer = (first->flags & SIGQUEUE_PREALLOC) && (info->si_code == SI_TIMER) && (info->si_sys_private); __sigqueue_free(first); } else { /* * Ok, it wasn't in the queue. This must be * a fast-pathed signal or we must have been * out of queue space. So zero out the info. */ clear_siginfo(info); info->si_signo = sig; info->si_errno = 0; info->si_code = SI_USER; info->si_pid = 0; info->si_uid = 0; } } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, kernel_siginfo_t *info, bool *resched_timer) { int sig = next_signal(pending, mask); if (sig) collect_signal(sig, pending, info, resched_timer); return sig; } /* * Try to dequeue a signal. If a deliverable signal is found fill in the * caller provided siginfo and return the signal number. Otherwise return * 0. */ int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) { struct task_struct *tsk = current; bool resched_timer = false; int signr; lockdep_assert_held(&tsk->sighand->siglock); *type = PIDTYPE_PID; signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { *type = PIDTYPE_TGID; signr = __dequeue_signal(&tsk->signal->shared_pending, mask, info, &resched_timer); #ifdef CONFIG_POSIX_TIMERS /* * itimer signal ? * * itimers are process shared and we restart periodic * itimers in the signal delivery path to prevent DoS * attacks in the high resolution timer case. This is * compliant with the old way of self-restarting * itimers, as the SIGALRM is a legacy signal and only * queued once. Changing the restart behaviour to * restart the timer in the signal dequeue path is * reducing the timer noise on heavy loaded !highres * systems too. */ if (unlikely(signr == SIGALRM)) { struct hrtimer *tmr = &tsk->signal->real_timer; if (!hrtimer_is_queued(tmr) && tsk->signal->it_real_incr != 0) { hrtimer_forward(tmr, tmr->base->get_time(), tsk->signal->it_real_incr); hrtimer_restart(tmr); } } #endif } recalc_sigpending(); if (!signr) return 0; if (unlikely(sig_kernel_stop(signr))) { /* * Set a marker that we have dequeued a stop signal. Our * caller might release the siglock and then the pending * stop signal it is about to process is no longer in the * pending bitmasks, but must still be cleared by a SIGCONT * (and overruled by a SIGKILL). So those cases clear this * shared flag after we've set it. Note that this flag may * remain set after the signal we return is ignored or * handled. That doesn't matter because its only purpose * is to alert stop-signal processing code when another * processor has come along and cleared the flag. */ current->jobctl |= JOBCTL_STOP_DEQUEUED; } #ifdef CONFIG_POSIX_TIMERS if (resched_timer) { /* * Release the siglock to ensure proper locking order * of timer locks outside of siglocks. Note, we leave * irqs disabled here, since the posix-timers code is * about to disable them again anyway. */ spin_unlock(&tsk->sighand->siglock); posixtimer_rearm(info); spin_lock(&tsk->sighand->siglock); /* Don't expose the si_sys_private value to userspace */ info->si_sys_private = 0; } #endif return signr; } EXPORT_SYMBOL_GPL(dequeue_signal); static int dequeue_synchronous_signal(kernel_siginfo_t *info) { struct task_struct *tsk = current; struct sigpending *pending = &tsk->pending; struct sigqueue *q, *sync = NULL; /* * Might a synchronous signal be in the queue? */ if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK)) return 0; /* * Return the first synchronous signal in the queue. */ list_for_each_entry(q, &pending->list, list) { /* Synchronous signals have a positive si_code */ if ((q->info.si_code > SI_USER) && (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) { sync = q; goto next; } } return 0; next: /* * Check if there is another siginfo for the same signal. */ list_for_each_entry_continue(q, &pending->list, list) { if (q->info.si_signo == sync->info.si_signo) goto still_pending; } sigdelset(&pending->signal, sync->info.si_signo); recalc_sigpending(); still_pending: list_del_init(&sync->list); copy_siginfo(info, &sync->info); __sigqueue_free(sync); return info->si_signo; } /* * Tell a process that it has a new active signal.. * * NOTE! we rely on the previous spin_lock to * lock interrupts for us! We can only be called with * "siglock" held, and the local interrupt must * have been disabled when that got acquired! * * No need to set need_resched since signal event passing * goes through ->blocked */ void signal_wake_up_state(struct task_struct *t, unsigned int state) { lockdep_assert_held(&t->sighand->siglock); set_tsk_thread_flag(t, TIF_SIGPENDING); /* * TASK_WAKEKILL also means wake it up in the stopped/traced/killable * case. We don't check t->state here because there is a race with it * executing another processor and just now entering stopped state. * By using wake_up_state, we ensure the process will wake up and * handle its death signal. */ if (!wake_up_state(t, state | TASK_INTERRUPTIBLE)) kick_process(t); } /* * Remove signals in mask from the pending set and queue. * Returns 1 if any signals were found. * * All callers must be holding the siglock. */ static void flush_sigqueue_mask(sigset_t *mask, struct sigpending *s) { struct sigqueue *q, *n; sigset_t m; sigandsets(&m, mask, &s->signal); if (sigisemptyset(&m)) return; sigandnsets(&s->signal, &s->signal, mask); list_for_each_entry_safe(q, n, &s->list, list) { if (sigismember(mask, q->info.si_signo)) { list_del_init(&q->list); __sigqueue_free(q); } } } static inline int is_si_special(const struct kernel_siginfo *info) { return info <= SEND_SIG_PRIV; } static inline bool si_fromuser(const struct kernel_siginfo *info) { return info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)); } /* * called with RCU read lock from check_kill_permission() */ static bool kill_ok_by_cred(struct task_struct *t) { const struct cred *cred = current_cred(); const struct cred *tcred = __task_cred(t); return uid_eq(cred->euid, tcred->suid) || uid_eq(cred->euid, tcred->uid) || uid_eq(cred->uid, tcred->suid) || uid_eq(cred->uid, tcred->uid) || ns_capable(tcred->user_ns, CAP_KILL); } /* * Bad permissions for sending the signal * - the caller must hold the RCU read lock */ static int check_kill_permission(int sig, struct kernel_siginfo *info, struct task_struct *t) { struct pid *sid; int error; if (!valid_signal(sig)) return -EINVAL; if (!si_fromuser(info)) return 0; error = audit_signal_info(sig, t); /* Let audit system see the signal */ if (error) return error; if (!same_thread_group(current, t) && !kill_ok_by_cred(t)) { switch (sig) { case SIGCONT: sid = task_session(t); /* * We don't return the error if sid == NULL. The * task was unhashed, the caller must notice this. */ if (!sid || sid == task_session(current)) break; fallthrough; default: return -EPERM; } } return security_task_kill(t, info, sig, NULL); } /** * ptrace_trap_notify - schedule trap to notify ptracer * @t: tracee wanting to notify tracer * * This function schedules sticky ptrace trap which is cleared on the next * TRAP_STOP to notify ptracer of an event. @t must have been seized by * ptracer. * * If @t is running, STOP trap will be taken. If trapped for STOP and * ptracer is listening for events, tracee is woken up so that it can * re-trap for the new event. If trapped otherwise, STOP trap will be * eventually taken without returning to userland after the existing traps * are finished by PTRACE_CONT. * * CONTEXT: * Must be called with @task->sighand->siglock held. */ static void ptrace_trap_notify(struct task_struct *t) { WARN_ON_ONCE(!(t->ptrace & PT_SEIZED)); lockdep_assert_held(&t->sighand->siglock); task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY); ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING); } /* * Handle magic process-wide effects of stop/continue signals. Unlike * the signal actions, these happen immediately at signal-generation * time regardless of blocking, ignoring, or handling. This does the * actual continuing for SIGCONT, but not the actual stopping for stop * signals. The process stop is done as a signal action for SIG_DFL. * * Returns true if the signal should be actually delivered, otherwise * it should be dropped. */ static bool prepare_signal(int sig, struct task_struct *p, bool force) { struct signal_struct *signal = p->signal; struct task_struct *t; sigset_t flush; if (signal->flags & SIGNAL_GROUP_EXIT) { if (signal->core_state) return sig == SIGKILL; /* * The process is in the middle of dying, drop the signal. */ return false; } else if (sig_kernel_stop(sig)) { /* * This is a stop signal. Remove SIGCONT from all queues. */ siginitset(&flush, sigmask(SIGCONT)); flush_sigqueue_mask(&flush, &signal->shared_pending); for_each_thread(p, t) flush_sigqueue_mask(&flush, &t->pending); } else if (sig == SIGCONT) { unsigned int why; /* * Remove all stop signals from all queues, wake all threads. */ siginitset(&flush, SIG_KERNEL_STOP_MASK); flush_sigqueue_mask(&flush, &signal->shared_pending); for_each_thread(p, t) { flush_sigqueue_mask(&flush, &t->pending); task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING); if (likely(!(t->ptrace & PT_SEIZED))) { t->jobctl &= ~JOBCTL_STOPPED; wake_up_state(t, __TASK_STOPPED); } else ptrace_trap_notify(t); } /* * Notify the parent with CLD_CONTINUED if we were stopped. * * If we were in the middle of a group stop, we pretend it * was already finished, and then continued. Since SIGCHLD * doesn't queue we report only CLD_STOPPED, as if the next * CLD_CONTINUED was dropped. */ why = 0; if (signal->flags & SIGNAL_STOP_STOPPED) why |= SIGNAL_CLD_CONTINUED; else if (signal->group_stop_count) why |= SIGNAL_CLD_STOPPED; if (why) { /* * The first thread which returns from do_signal_stop() * will take ->siglock, notice SIGNAL_CLD_MASK, and * notify its parent. See get_signal(). */ signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED); signal->group_stop_count = 0; signal->group_exit_code = 0; } } return !sig_ignored(p, sig, force); } /* * Test if P wants to take SIG. After we've checked all threads with this, * it's equivalent to finding no threads not blocking SIG. Any threads not * blocking SIG were ruled out because they are not running and already * have pending signals. Such threads will dequeue from the shared queue * as soon as they're available, so putting the signal on the shared queue * will be equivalent to sending it to one such thread. */ static inline bool wants_signal(int sig, struct task_struct *p) { if (sigismember(&p->blocked, sig)) return false; if (p->flags & PF_EXITING) return false; if (sig == SIGKILL) return true; if (task_is_stopped_or_traced(p)) return false; return task_curr(p) || !task_sigpending(p); } static void complete_signal(int sig, struct task_struct *p, enum pid_type type) { struct signal_struct *signal = p->signal; struct task_struct *t; /* * Now find a thread we can wake up to take the signal off the queue. * * Try the suggested task first (may or may not be the main thread). */ if (wants_signal(sig, p)) t = p; else if ((type == PIDTYPE_PID) || thread_group_empty(p)) /* * There is just one thread and it does not need to be woken. * It will dequeue unblocked signals before it runs again. */ return; else { /* * Otherwise try to find a suitable thread. */ t = signal->curr_target; while (!wants_signal(sig, t)) { t = next_thread(t); if (t == signal->curr_target) /* * No thread needs to be woken. * Any eligible threads will see * the signal in the queue soon. */ return; } signal->curr_target = t; } /* * Found a killable thread. If the signal will be fatal, * then start taking the whole group down immediately. */ if (sig_fatal(p, sig) && (signal->core_state || !(signal->flags & SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && (sig == SIGKILL || !p->ptrace)) { /* * This signal will be fatal to the whole group. */ if (!sig_kernel_coredump(sig)) { /* * Start a group exit and wake everybody up. * This way we don't have other threads * running and doing things after a slower * thread has the fatal signal pending. */ signal->flags = SIGNAL_GROUP_EXIT; signal->group_exit_code = sig; signal->group_stop_count = 0; __for_each_thread(signal, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); } return; } } /* * The signal is already in the shared-pending queue. * Tell the chosen thread to wake up and dequeue it. */ signal_wake_up(t, sig == SIGKILL); return; } static inline bool legacy_queue(struct sigpending *signals, int sig) { return (sig < SIGRTMIN) && sigismember(&signals->signal, sig); } static int __send_signal_locked(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type, bool force) { struct sigpending *pending; struct sigqueue *q; int override_rlimit; int ret = 0, result; lockdep_assert_held(&t->sighand->siglock); result = TRACE_SIGNAL_IGNORED; if (!prepare_signal(sig, t, force)) goto ret; pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; /* * Short-circuit ignored signals and support queuing * exactly one non-rt signal, so that we can get more * detailed information about the cause of the signal. */ result = TRACE_SIGNAL_ALREADY_PENDING; if (legacy_queue(pending, sig)) goto ret; result = TRACE_SIGNAL_DELIVERED; /* * Skip useless siginfo allocation for SIGKILL and kernel threads. */ if ((sig == SIGKILL) || (t->flags & PF_KTHREAD)) goto out_set; /* * Real-time signals must be queued if sent by sigqueue, or * some other real-time mechanism. It is implementation * defined whether kill() does so. We attempt to do so, on * the principle of least surprise, but since kill is not * allowed to fail with EAGAIN when low on memory we just * make sure at least one signal gets delivered and don't * pass on the info struct. */ if (sig < SIGRTMIN) override_rlimit = (is_si_special(info) || info->si_code >= 0); else override_rlimit = 0; q = __sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit, 0); if (q) { list_add_tail(&q->list, &pending->list); switch ((unsigned long) info) { case (unsigned long) SEND_SIG_NOINFO: clear_siginfo(&q->info); q->info.si_signo = sig; q->info.si_errno = 0; q->info.si_code = SI_USER; q->info.si_pid = task_tgid_nr_ns(current, task_active_pid_ns(t)); rcu_read_lock(); q->info.si_uid = from_kuid_munged(task_cred_xxx(t, user_ns), current_uid()); rcu_read_unlock(); break; case (unsigned long) SEND_SIG_PRIV: clear_siginfo(&q->info); q->info.si_signo = sig; q->info.si_errno = 0; q->info.si_code = SI_KERNEL; q->info.si_pid = 0; q->info.si_uid = 0; break; default: copy_siginfo(&q->info, info); break; } } else if (!is_si_special(info) && sig >= SIGRTMIN && info->si_code != SI_USER) { /* * Queue overflow, abort. We may abort if the * signal was rt and sent by user using something * other than kill(). */ result = TRACE_SIGNAL_OVERFLOW_FAIL; ret = -EAGAIN; goto ret; } else { /* * This is a silent loss of information. We still * send the signal, but the *info bits are lost. */ result = TRACE_SIGNAL_LOSE_INFO; } out_set: signalfd_notify(t, sig); sigaddset(&pending->signal, sig); /* Let multiprocess signals appear after on-going forks */ if (type > PIDTYPE_TGID) { struct multiprocess_signals *delayed; hlist_for_each_entry(delayed, &t->signal->multiprocess, node) { sigset_t *signal = &delayed->signal; /* Can't queue both a stop and a continue signal */ if (sig == SIGCONT) sigdelsetmask(signal, SIG_KERNEL_STOP_MASK); else if (sig_kernel_stop(sig)) sigdelset(signal, SIGCONT); sigaddset(signal, sig); } } complete_signal(sig, t, type); ret: trace_signal_generate(sig, info, t, type != PIDTYPE_PID, result); return ret; } static inline bool has_si_pid_and_uid(struct kernel_siginfo *info) { bool ret = false; switch (siginfo_layout(info->si_signo, info->si_code)) { case SIL_KILL: case SIL_CHLD: case SIL_RT: ret = true; break; case SIL_TIMER: case SIL_POLL: case SIL_FAULT: case SIL_FAULT_TRAPNO: case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: case SIL_FAULT_PERF_EVENT: case SIL_SYS: ret = false; break; } return ret; } int send_signal_locked(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type) { /* Should SIGKILL or SIGSTOP be received by a pid namespace init? */ bool force = false; if (info == SEND_SIG_NOINFO) { /* Force if sent from an ancestor pid namespace */ force = !task_pid_nr_ns(current, task_active_pid_ns(t)); } else if (info == SEND_SIG_PRIV) { /* Don't ignore kernel generated signals */ force = true; } else if (has_si_pid_and_uid(info)) { /* SIGKILL and SIGSTOP is special or has ids */ struct user_namespace *t_user_ns; rcu_read_lock(); t_user_ns = task_cred_xxx(t, user_ns); if (current_user_ns() != t_user_ns) { kuid_t uid = make_kuid(current_user_ns(), info->si_uid); info->si_uid = from_kuid_munged(t_user_ns, uid); } rcu_read_unlock(); /* A kernel generated signal? */ force = (info->si_code == SI_KERNEL); /* From an ancestor pid namespace? */ if (!task_pid_nr_ns(current, task_active_pid_ns(t))) { info->si_pid = 0; force = true; } } return __send_signal_locked(sig, info, t, type, force); } static void print_fatal_signal(int signr) { struct pt_regs *regs = task_pt_regs(current); struct file *exe_file; exe_file = get_task_exe_file(current); if (exe_file) { pr_info("%pD: %s: potentially unexpected fatal signal %d.\n", exe_file, current->comm, signr); fput(exe_file); } else { pr_info("%s: potentially unexpected fatal signal %d.\n", current->comm, signr); } #if defined(__i386__) && !defined(__arch_um__) pr_info("code at %08lx: ", regs->ip); { int i; for (i = 0; i < 16; i++) { unsigned char insn; if (get_user(insn, (unsigned char *)(regs->ip + i))) break; pr_cont("%02x ", insn); } } pr_cont("\n"); #endif preempt_disable(); show_regs(regs); preempt_enable(); } static int __init setup_print_fatal_signals(char *str) { get_option (&str, &print_fatal_signals); return 1; } __setup("print-fatal-signals=", setup_print_fatal_signals); int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type) { unsigned long flags; int ret = -ESRCH; if (lock_task_sighand(p, &flags)) { ret = send_signal_locked(sig, info, p, type); unlock_task_sighand(p, &flags); } return ret; } enum sig_handler { HANDLER_CURRENT, /* If reachable use the current handler */ HANDLER_SIG_DFL, /* Always use SIG_DFL handler semantics */ HANDLER_EXIT, /* Only visible as the process exit code */ }; /* * Force a signal that the process can't ignore: if necessary * we unblock the signal and change any SIG_IGN to SIG_DFL. * * Note: If we unblock the signal, we always reset it to SIG_DFL, * since we do not want to have a signal handler that was blocked * be invoked when user space had explicitly blocked it. * * We don't want to have recursive SIGSEGV's etc, for example, * that is why we also clear SIGNAL_UNKILLABLE. */ static int force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, enum sig_handler handler) { unsigned long int flags; int ret, blocked, ignored; struct k_sigaction *action; int sig = info->si_signo; spin_lock_irqsave(&t->sighand->siglock, flags); action = &t->sighand->action[sig-1]; ignored = action->sa.sa_handler == SIG_IGN; blocked = sigismember(&t->blocked, sig); if (blocked || ignored || (handler != HANDLER_CURRENT)) { action->sa.sa_handler = SIG_DFL; if (handler == HANDLER_EXIT) action->sa.sa_flags |= SA_IMMUTABLE; if (blocked) sigdelset(&t->blocked, sig); } /* * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect * debugging to leave init killable. But HANDLER_EXIT is always fatal. */ if (action->sa.sa_handler == SIG_DFL && (!t->ptrace || (handler == HANDLER_EXIT))) t->signal->flags &= ~SIGNAL_UNKILLABLE; ret = send_signal_locked(sig, info, t, PIDTYPE_PID); /* This can happen if the signal was already pending and blocked */ if (!task_sigpending(t)) signal_wake_up(t, 0); spin_unlock_irqrestore(&t->sighand->siglock, flags); return ret; } int force_sig_info(struct kernel_siginfo *info) { return force_sig_info_to_task(info, current, HANDLER_CURRENT); } /* * Nuke all other threads in the group. */ int zap_other_threads(struct task_struct *p) { struct task_struct *t; int count = 0; p->signal->group_stop_count = 0; for_other_threads(p, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); count++; /* Don't bother with already dead threads */ if (t->exit_state) continue; sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); } return count; } struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, unsigned long *flags) { struct sighand_struct *sighand; rcu_read_lock(); for (;;) { sighand = rcu_dereference(tsk->sighand); if (unlikely(sighand == NULL)) break; /* * This sighand can be already freed and even reused, but * we rely on SLAB_TYPESAFE_BY_RCU and sighand_ctor() which * initializes ->siglock: this slab can't go away, it has * the same object type, ->siglock can't be reinitialized. * * We need to ensure that tsk->sighand is still the same * after we take the lock, we can race with de_thread() or * __exit_signal(). In the latter case the next iteration * must see ->sighand == NULL. */ spin_lock_irqsave(&sighand->siglock, *flags); if (likely(sighand == rcu_access_pointer(tsk->sighand))) break; spin_unlock_irqrestore(&sighand->siglock, *flags); } rcu_read_unlock(); return sighand; } #ifdef CONFIG_LOCKDEP void lockdep_assert_task_sighand_held(struct task_struct *task) { struct sighand_struct *sighand; rcu_read_lock(); sighand = rcu_dereference(task->sighand); if (sighand) lockdep_assert_held(&sighand->siglock); else WARN_ON_ONCE(1); rcu_read_unlock(); } #endif /* * send signal info to all the members of a thread group or to the * individual thread if type == PIDTYPE_PID. */ int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type) { int ret; rcu_read_lock(); ret = check_kill_permission(sig, info, p); rcu_read_unlock(); if (!ret && sig) ret = do_send_sig_info(sig, info, p, type); return ret; } /* * __kill_pgrp_info() sends a signal to a process group: this is what the tty * control characters do (^C, ^Z etc) * - the caller must hold at least a readlock on tasklist_lock */ int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) { struct task_struct *p = NULL; int ret = -ESRCH; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { int err = group_send_sig_info(sig, info, p, PIDTYPE_PGID); /* * If group_send_sig_info() succeeds at least once ret * becomes 0 and after that the code below has no effect. * Otherwise we return the last err or -ESRCH if this * process group is empty. */ if (ret) ret = err; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return ret; } static int kill_pid_info_type(int sig, struct kernel_siginfo *info, struct pid *pid, enum pid_type type) { int error = -ESRCH; struct task_struct *p; for (;;) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) error = group_send_sig_info(sig, info, p, type); rcu_read_unlock(); if (likely(!p || error != -ESRCH)) return error; /* * The task was unhashed in between, try again. If it * is dead, pid_task() will return NULL, if we race with * de_thread() it will find the new leader. */ } } int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) { return kill_pid_info_type(sig, info, pid, PIDTYPE_TGID); } static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid) { int error; rcu_read_lock(); error = kill_pid_info(sig, info, find_vpid(pid)); rcu_read_unlock(); return error; } static inline bool kill_as_cred_perm(const struct cred *cred, struct task_struct *target) { const struct cred *pcred = __task_cred(target); return uid_eq(cred->euid, pcred->suid) || uid_eq(cred->euid, pcred->uid) || uid_eq(cred->uid, pcred->suid) || uid_eq(cred->uid, pcred->uid); } /* * The usb asyncio usage of siginfo is wrong. The glibc support * for asyncio which uses SI_ASYNCIO assumes the layout is SIL_RT. * AKA after the generic fields: * kernel_pid_t si_pid; * kernel_uid32_t si_uid; * sigval_t si_value; * * Unfortunately when usb generates SI_ASYNCIO it assumes the layout * after the generic fields is: * void __user *si_addr; * * This is a practical problem when there is a 64bit big endian kernel * and a 32bit userspace. As the 32bit address will encoded in the low * 32bits of the pointer. Those low 32bits will be stored at higher * address than appear in a 32 bit pointer. So userspace will not * see the address it was expecting for it's completions. * * There is nothing in the encoding that can allow * copy_siginfo_to_user32 to detect this confusion of formats, so * handle this by requiring the caller of kill_pid_usb_asyncio to * notice when this situration takes place and to store the 32bit * pointer in sival_int, instead of sival_addr of the sigval_t addr * parameter. */ int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *pid, const struct cred *cred) { struct kernel_siginfo info; struct task_struct *p; unsigned long flags; int ret = -EINVAL; if (!valid_signal(sig)) return ret; clear_siginfo(&info); info.si_signo = sig; info.si_errno = errno; info.si_code = SI_ASYNCIO; *((sigval_t *)&info.si_pid) = addr; rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (!p) { ret = -ESRCH; goto out_unlock; } if (!kill_as_cred_perm(cred, p)) { ret = -EPERM; goto out_unlock; } ret = security_task_kill(p, &info, sig, cred); if (ret) goto out_unlock; if (sig) { if (lock_task_sighand(p, &flags)) { ret = __send_signal_locked(sig, &info, p, PIDTYPE_TGID, false); unlock_task_sighand(p, &flags); } else ret = -ESRCH; } out_unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(kill_pid_usb_asyncio); /* * kill_something_info() interprets pid in interesting ways just like kill(2). * * POSIX specifies that kill(-1,sig) is unspecified, but what we have * is probably wrong. Should make it like BSD or SYSV. */ static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid) { int ret; if (pid > 0) return kill_proc_info(sig, info, pid); /* -INT_MIN is undefined. Exclude this case to avoid a UBSAN warning */ if (pid == INT_MIN) return -ESRCH; read_lock(&tasklist_lock); if (pid != -1) { ret = __kill_pgrp_info(sig, info, pid ? find_vpid(-pid) : task_pgrp(current)); } else { int retval = 0, count = 0; struct task_struct * p; for_each_process(p) { if (task_pid_vnr(p) > 1 && !same_thread_group(p, current)) { int err = group_send_sig_info(sig, info, p, PIDTYPE_MAX); ++count; if (err != -EPERM) retval = err; } } ret = count ? retval : -ESRCH; } read_unlock(&tasklist_lock); return ret; } /* * These are for backward compatibility with the rest of the kernel source. */ int send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p) { /* * Make sure legacy kernel users don't send in bad values * (normal paths check this in check_kill_permission). */ if (!valid_signal(sig)) return -EINVAL; return do_send_sig_info(sig, info, p, PIDTYPE_PID); } EXPORT_SYMBOL(send_sig_info); #define __si_special(priv) \ ((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO) int send_sig(int sig, struct task_struct *p, int priv) { return send_sig_info(sig, __si_special(priv), p); } EXPORT_SYMBOL(send_sig); void force_sig(int sig) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = SI_KERNEL; info.si_pid = 0; info.si_uid = 0; force_sig_info(&info); } EXPORT_SYMBOL(force_sig); void force_fatal_sig(int sig) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = SI_KERNEL; info.si_pid = 0; info.si_uid = 0; force_sig_info_to_task(&info, current, HANDLER_SIG_DFL); } void force_exit_sig(int sig) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = SI_KERNEL; info.si_pid = 0; info.si_uid = 0; force_sig_info_to_task(&info, current, HANDLER_EXIT); } /* * When things go south during signal handling, we * will force a SIGSEGV. And if the signal that caused * the problem was already a SIGSEGV, we'll want to * make sure we don't even try to deliver the signal.. */ void force_sigsegv(int sig) { if (sig == SIGSEGV) force_fatal_sig(SIGSEGV); else force_sig(SIGSEGV); } int force_sig_fault_to_task(int sig, int code, void __user *addr, struct task_struct *t) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = code; info.si_addr = addr; return force_sig_info_to_task(&info, t, HANDLER_CURRENT); } int force_sig_fault(int sig, int code, void __user *addr) { return force_sig_fault_to_task(sig, code, addr, current); } int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = code; info.si_addr = addr; return send_sig_info(info.si_signo, &info, t); } int force_sig_mceerr(int code, void __user *addr, short lsb) { struct kernel_siginfo info; WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR)); clear_siginfo(&info); info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = code; info.si_addr = addr; info.si_addr_lsb = lsb; return force_sig_info(&info); } int send_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t) { struct kernel_siginfo info; WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR)); clear_siginfo(&info); info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = code; info.si_addr = addr; info.si_addr_lsb = lsb; return send_sig_info(info.si_signo, &info, t); } EXPORT_SYMBOL(send_sig_mceerr); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSEGV; info.si_errno = 0; info.si_code = SEGV_BNDERR; info.si_addr = addr; info.si_lower = lower; info.si_upper = upper; return force_sig_info(&info); } #ifdef SEGV_PKUERR int force_sig_pkuerr(void __user *addr, u32 pkey) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSEGV; info.si_errno = 0; info.si_code = SEGV_PKUERR; info.si_addr = addr; info.si_pkey = pkey; return force_sig_info(&info); } #endif int send_sig_perf(void __user *addr, u32 type, u64 sig_data) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGTRAP; info.si_errno = 0; info.si_code = TRAP_PERF; info.si_addr = addr; info.si_perf_data = sig_data; info.si_perf_type = type; /* * Signals generated by perf events should not terminate the whole * process if SIGTRAP is blocked, however, delivering the signal * asynchronously is better than not delivering at all. But tell user * space if the signal was asynchronous, so it can clearly be * distinguished from normal synchronous ones. */ info.si_perf_flags = sigismember(¤t->blocked, info.si_signo) ? TRAP_PERF_FLAG_ASYNC : 0; return send_sig_info(info.si_signo, &info, current); } /** * force_sig_seccomp - signals the task to allow in-process syscall emulation * @syscall: syscall number to send to userland * @reason: filter-supplied reason code to send to userland (via si_errno) * @force_coredump: true to trigger a coredump * * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info. */ int force_sig_seccomp(int syscall, int reason, bool force_coredump) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSYS; info.si_code = SYS_SECCOMP; info.si_call_addr = (void __user *)KSTK_EIP(current); info.si_errno = reason; info.si_arch = syscall_get_arch(current); info.si_syscall = syscall; return force_sig_info_to_task(&info, current, force_coredump ? HANDLER_EXIT : HANDLER_CURRENT); } /* For the crazy architectures that include trap information in * the errno field, instead of an actual errno value. */ int force_sig_ptrace_errno_trap(int errno, void __user *addr) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGTRAP; info.si_errno = errno; info.si_code = TRAP_HWBKPT; info.si_addr = addr; return force_sig_info(&info); } /* For the rare architectures that include trap information using * si_trapno. */ int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = code; info.si_addr = addr; info.si_trapno = trapno; return force_sig_info(&info); } /* For the rare architectures that include trap information using * si_trapno. */ int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, struct task_struct *t) { struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; info.si_code = code; info.si_addr = addr; info.si_trapno = trapno; return send_sig_info(info.si_signo, &info, t); } static int kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) { int ret; read_lock(&tasklist_lock); ret = __kill_pgrp_info(sig, info, pgrp); read_unlock(&tasklist_lock); return ret; } int kill_pgrp(struct pid *pid, int sig, int priv) { return kill_pgrp_info(sig, __si_special(priv), pid); } EXPORT_SYMBOL(kill_pgrp); int kill_pid(struct pid *pid, int sig, int priv) { return kill_pid_info(sig, __si_special(priv), pid); } EXPORT_SYMBOL(kill_pid); /* * These functions support sending signals using preallocated sigqueue * structures. This is needed "because realtime applications cannot * afford to lose notifications of asynchronous events, like timer * expirations or I/O completions". In the case of POSIX Timers * we allocate the sigqueue structure from the timer_create. If this * allocation fails we are able to report the failure to the application * with an EAGAIN error. */ struct sigqueue *sigqueue_alloc(void) { return __sigqueue_alloc(-1, current, GFP_KERNEL, 0, SIGQUEUE_PREALLOC); } void sigqueue_free(struct sigqueue *q) { spinlock_t *lock = ¤t->sighand->siglock; unsigned long flags; if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC))) return; /* * We must hold ->siglock while testing q->list * to serialize with collect_signal() or with * __exit_signal()->flush_sigqueue(). */ spin_lock_irqsave(lock, flags); q->flags &= ~SIGQUEUE_PREALLOC; /* * If it is queued it will be freed when dequeued, * like the "regular" sigqueue. */ if (!list_empty(&q->list)) q = NULL; spin_unlock_irqrestore(lock, flags); if (q) __sigqueue_free(q); } int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type) { int sig = q->info.si_signo; struct sigpending *pending; struct task_struct *t; unsigned long flags; int ret, result; if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC))) return 0; if (WARN_ON_ONCE(q->info.si_code != SI_TIMER)) return 0; ret = -1; rcu_read_lock(); /* * This function is used by POSIX timers to deliver a timer signal. * Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID * set), the signal must be delivered to the specific thread (queues * into t->pending). * * Where type is not PIDTYPE_PID, signals must be delivered to the * process. In this case, prefer to deliver to current if it is in * the same thread group as the target process, which avoids * unnecessarily waking up a potentially idle task. */ t = pid_task(pid, type); if (!t) goto ret; if (type != PIDTYPE_PID && same_thread_group(t, current)) t = current; if (!likely(lock_task_sighand(t, &flags))) goto ret; ret = 1; /* the signal is ignored */ result = TRACE_SIGNAL_IGNORED; if (!prepare_signal(sig, t, false)) goto out; ret = 0; if (unlikely(!list_empty(&q->list))) { /* * If an SI_TIMER entry is already queue just increment * the overrun count. */ q->info.si_overrun++; result = TRACE_SIGNAL_ALREADY_PENDING; goto out; } q->info.si_overrun = 0; signalfd_notify(t, sig); pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; list_add_tail(&q->list, &pending->list); sigaddset(&pending->signal, sig); complete_signal(sig, t, type); result = TRACE_SIGNAL_DELIVERED; out: trace_signal_generate(sig, &q->info, t, type != PIDTYPE_PID, result); unlock_task_sighand(t, &flags); ret: rcu_read_unlock(); return ret; } void do_notify_pidfd(struct task_struct *task) { struct pid *pid = task_pid(task); WARN_ON(task->exit_state == 0); __wake_up(&pid->wait_pidfd, TASK_NORMAL, 0, poll_to_key(EPOLLIN | EPOLLRDNORM)); } /* * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. * * Returns true if our parent ignored us and so we've switched to * self-reaping. */ bool do_notify_parent(struct task_struct *tsk, int sig) { struct kernel_siginfo info; unsigned long flags; struct sighand_struct *psig; bool autoreap = false; u64 utime, stime; WARN_ON_ONCE(sig == -1); /* do_notify_parent_cldstop should have been called instead. */ WARN_ON_ONCE(task_is_stopped_or_traced(tsk)); WARN_ON_ONCE(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); /* * tsk is a group leader and has no threads, wake up the * non-PIDFD_THREAD waiters. */ if (thread_group_empty(tsk)) do_notify_pidfd(tsk); if (sig != SIGCHLD) { /* * This is only possible if parent == real_parent. * Check if it has changed security domain. */ if (tsk->parent_exec_id != READ_ONCE(tsk->parent->self_exec_id)) sig = SIGCHLD; } clear_siginfo(&info); info.si_signo = sig; info.si_errno = 0; /* * We are under tasklist_lock here so our parent is tied to * us and cannot change. * * task_active_pid_ns will always return the same pid namespace * until a task passes through release_task. * * write_lock() currently calls preempt_disable() which is the * same as rcu_read_lock(), but according to Oleg, this is not * correct to rely on this */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(tsk->parent)); info.si_uid = from_kuid_munged(task_cred_xxx(tsk->parent, user_ns), task_uid(tsk)); rcu_read_unlock(); task_cputime(tsk, &utime, &stime); info.si_utime = nsec_to_clock_t(utime + tsk->signal->utime); info.si_stime = nsec_to_clock_t(stime + tsk->signal->stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) info.si_code = CLD_DUMPED; else if (tsk->exit_code & 0x7f) info.si_code = CLD_KILLED; else { info.si_code = CLD_EXITED; info.si_status = tsk->exit_code >> 8; } psig = tsk->parent->sighand; spin_lock_irqsave(&psig->siglock, flags); if (!tsk->ptrace && sig == SIGCHLD && (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN || (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) { /* * We are exiting and our parent doesn't care. POSIX.1 * defines special semantics for setting SIGCHLD to SIG_IGN * or setting the SA_NOCLDWAIT flag: we should be reaped * automatically and not left for our parent's wait4 call. * Rather than having the parent do it as a magic kind of * signal handler, we just set this to tell do_exit that we * can be cleaned up without becoming a zombie. Note that * we still call __wake_up_parent in this case, because a * blocked sys_wait4 might now return -ECHILD. * * Whether we send SIGCHLD or not for SA_NOCLDWAIT * is implementation-defined: we do (if you don't want * it, just use SIG_IGN instead). */ autoreap = true; if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) sig = 0; } /* * Send with __send_signal as si_pid and si_uid are in the * parent's namespaces. */ if (valid_signal(sig) && sig) __send_signal_locked(sig, &info, tsk->parent, PIDTYPE_TGID, false); __wake_up_parent(tsk, tsk->parent); spin_unlock_irqrestore(&psig->siglock, flags); return autoreap; } /** * do_notify_parent_cldstop - notify parent of stopped/continued state change * @tsk: task reporting the state change * @for_ptracer: the notification is for ptracer * @why: CLD_{CONTINUED|STOPPED|TRAPPED} to report * * Notify @tsk's parent that the stopped/continued state has changed. If * @for_ptracer is %false, @tsk's group leader notifies to its real parent. * If %true, @tsk reports to @tsk->parent which should be the ptracer. * * CONTEXT: * Must be called with tasklist_lock at least read locked. */ static void do_notify_parent_cldstop(struct task_struct *tsk, bool for_ptracer, int why) { struct kernel_siginfo info; unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; u64 utime, stime; if (for_ptracer) { parent = tsk->parent; } else { tsk = tsk->group_leader; parent = tsk->real_parent; } clear_siginfo(&info); info.si_signo = SIGCHLD; info.si_errno = 0; /* * see comment in do_notify_parent() about the following 4 lines */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(parent)); info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk)); rcu_read_unlock(); task_cputime(tsk, &utime, &stime); info.si_utime = nsec_to_clock_t(utime); info.si_stime = nsec_to_clock_t(stime); info.si_code = why; switch (why) { case CLD_CONTINUED: info.si_status = SIGCONT; break; case CLD_STOPPED: info.si_status = tsk->signal->group_exit_code & 0x7f; break; case CLD_TRAPPED: info.si_status = tsk->exit_code & 0x7f; break; default: BUG(); } sighand = parent->sighand; spin_lock_irqsave(&sighand->siglock, flags); if (sighand->action[SIGCHLD-1].sa.sa_handler != SIG_IGN && !(sighand->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP)) send_signal_locked(SIGCHLD, &info, parent, PIDTYPE_TGID); /* * Even if SIGCHLD is not generated, we must wake up wait4 calls. */ __wake_up_parent(tsk, parent); spin_unlock_irqrestore(&sighand->siglock, flags); } /* * This must be called with current->sighand->siglock held. * * This should be the path for all ptrace stops. * We always set current->last_siginfo while stopped here. * That makes it a way to test a stopped process for * being ptrace-stopped vs being job-control-stopped. * * Returns the signal the ptracer requested the code resume * with. If the code did not stop because the tracer is gone, * the stop signal remains unchanged unless clear_code. */ static int ptrace_stop(int exit_code, int why, unsigned long message, kernel_siginfo_t *info) __releases(¤t->sighand->siglock) __acquires(¤t->sighand->siglock) { bool gstop_done = false; if (arch_ptrace_stop_needed()) { /* * The arch code has something special to do before a * ptrace stop. This is allowed to block, e.g. for faults * on user stack pages. We can't keep the siglock while * calling arch_ptrace_stop, so we must release it now. * To preserve proper semantics, we must do this before * any signal bookkeeping like checking group_stop_count. */ spin_unlock_irq(¤t->sighand->siglock); arch_ptrace_stop(); spin_lock_irq(¤t->sighand->siglock); } /* * After this point ptrace_signal_wake_up or signal_wake_up * will clear TASK_TRACED if ptrace_unlink happens or a fatal * signal comes in. Handle previous ptrace_unlinks and fatal * signals here to prevent ptrace_stop sleeping in schedule. */ if (!current->ptrace || __fatal_signal_pending(current)) return exit_code; set_special_state(TASK_TRACED); current->jobctl |= JOBCTL_TRACED; /* * We're committing to trapping. TRACED should be visible before * TRAPPING is cleared; otherwise, the tracer might fail do_wait(). * Also, transition to TRACED and updates to ->jobctl should be * atomic with respect to siglock and should be done after the arch * hook as siglock is released and regrabbed across it. * * TRACER TRACEE * * ptrace_attach() * [L] wait_on_bit(JOBCTL_TRAPPING) [S] set_special_state(TRACED) * do_wait() * set_current_state() smp_wmb(); * ptrace_do_wait() * wait_task_stopped() * task_stopped_code() * [L] task_is_traced() [S] task_clear_jobctl_trapping(); */ smp_wmb(); current->ptrace_message = message; current->last_siginfo = info; current->exit_code = exit_code; /* * If @why is CLD_STOPPED, we're trapping to participate in a group * stop. Do the bookkeeping. Note that if SIGCONT was delievered * across siglock relocks since INTERRUPT was scheduled, PENDING * could be clear now. We act as if SIGCONT is received after * TASK_TRACED is entered - ignore it. */ if (why == CLD_STOPPED && (current->jobctl & JOBCTL_STOP_PENDING)) gstop_done = task_participate_group_stop(current); /* any trap clears pending STOP trap, STOP trap clears NOTIFY */ task_clear_jobctl_pending(current, JOBCTL_TRAP_STOP); if (info && info->si_code >> 8 == PTRACE_EVENT_STOP) task_clear_jobctl_pending(current, JOBCTL_TRAP_NOTIFY); /* entering a trap, clear TRAPPING */ task_clear_jobctl_trapping(current); spin_unlock_irq(¤t->sighand->siglock); read_lock(&tasklist_lock); /* * Notify parents of the stop. * * While ptraced, there are two parents - the ptracer and * the real_parent of the group_leader. The ptracer should * know about every stop while the real parent is only * interested in the completion of group stop. The states * for the two don't interact with each other. Notify * separately unless they're gonna be duplicates. */ if (current->ptrace) do_notify_parent_cldstop(current, true, why); if (gstop_done && (!current->ptrace || ptrace_reparented(current))) do_notify_parent_cldstop(current, false, why); /* * The previous do_notify_parent_cldstop() invocation woke ptracer. * One a PREEMPTION kernel this can result in preemption requirement * which will be fulfilled after read_unlock() and the ptracer will be * put on the CPU. * The ptracer is in wait_task_inactive(, __TASK_TRACED) waiting for * this task wait in schedule(). If this task gets preempted then it * remains enqueued on the runqueue. The ptracer will observe this and * then sleep for a delay of one HZ tick. In the meantime this task * gets scheduled, enters schedule() and will wait for the ptracer. * * This preemption point is not bad from a correctness point of * view but extends the runtime by one HZ tick time due to the * ptracer's sleep. The preempt-disable section ensures that there * will be no preemption between unlock and schedule() and so * improving the performance since the ptracer will observe that * the tracee is scheduled out once it gets on the CPU. * * On PREEMPT_RT locking tasklist_lock does not disable preemption. * Therefore the task can be preempted after do_notify_parent_cldstop() * before unlocking tasklist_lock so there is no benefit in doing this. * * In fact disabling preemption is harmful on PREEMPT_RT because * the spinlock_t in cgroup_enter_frozen() must not be acquired * with preemption disabled due to the 'sleeping' spinlock * substitution of RT. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_disable(); read_unlock(&tasklist_lock); cgroup_enter_frozen(); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable_no_resched(); schedule(); cgroup_leave_frozen(true); /* * We are back. Now reacquire the siglock before touching * last_siginfo, so that we are sure to have synchronized with * any signal-sending on another CPU that wants to examine it. */ spin_lock_irq(¤t->sighand->siglock); exit_code = current->exit_code; current->last_siginfo = NULL; current->ptrace_message = 0; current->exit_code = 0; /* LISTENING can be set only during STOP traps, clear it */ current->jobctl &= ~(JOBCTL_LISTENING | JOBCTL_PTRACE_FROZEN); /* * Queued signals ignored us while we were stopped for tracing. * So check for any that we should take before resuming user mode. * This sets TIF_SIGPENDING, but never clears it. */ recalc_sigpending_tsk(current); return exit_code; } static int ptrace_do_notify(int signr, int exit_code, int why, unsigned long message) { kernel_siginfo_t info; clear_siginfo(&info); info.si_signo = signr; info.si_code = exit_code; info.si_pid = task_pid_vnr(current); info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); /* Let the debugger run. */ return ptrace_stop(exit_code, why, message, &info); } int ptrace_notify(int exit_code, unsigned long message) { int signr; BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); if (unlikely(task_work_pending(current))) task_work_run(); spin_lock_irq(¤t->sighand->siglock); signr = ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED, message); spin_unlock_irq(¤t->sighand->siglock); return signr; } /** * do_signal_stop - handle group stop for SIGSTOP and other stop signals * @signr: signr causing group stop if initiating * * If %JOBCTL_STOP_PENDING is not set yet, initiate group stop with @signr * and participate in it. If already set, participate in the existing * group stop. If participated in a group stop (and thus slept), %true is * returned with siglock released. * * If ptraced, this function doesn't handle stop itself. Instead, * %JOBCTL_TRAP_STOP is scheduled and %false is returned with siglock * untouched. The caller must ensure that INTERRUPT trap handling takes * places afterwards. * * CONTEXT: * Must be called with @current->sighand->siglock held, which is released * on %true return. * * RETURNS: * %false if group stop is already cancelled or ptrace trap is scheduled. * %true if participated in group stop. */ static bool do_signal_stop(int signr) __releases(¤t->sighand->siglock) { struct signal_struct *sig = current->signal; if (!(current->jobctl & JOBCTL_STOP_PENDING)) { unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; struct task_struct *t; /* signr will be recorded in task->jobctl for retries */ WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK); if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) || unlikely(sig->flags & SIGNAL_GROUP_EXIT) || unlikely(sig->group_exec_task)) return false; /* * There is no group stop already in progress. We must * initiate one now. * * While ptraced, a task may be resumed while group stop is * still in effect and then receive a stop signal and * initiate another group stop. This deviates from the * usual behavior as two consecutive stop signals can't * cause two group stops when !ptraced. That is why we * also check !task_is_stopped(t) below. * * The condition can be distinguished by testing whether * SIGNAL_STOP_STOPPED is already set. Don't generate * group_exit_code in such case. * * This is not necessary for SIGNAL_STOP_CONTINUED because * an intervening stop signal is required to cause two * continued events regardless of ptrace. */ if (!(sig->flags & SIGNAL_STOP_STOPPED)) sig->group_exit_code = signr; sig->group_stop_count = 0; if (task_set_jobctl_pending(current, signr | gstop)) sig->group_stop_count++; for_other_threads(current, t) { /* * Setting state to TASK_STOPPED for a group * stop is always done with the siglock held, * so this check has no races. */ if (!task_is_stopped(t) && task_set_jobctl_pending(t, signr | gstop)) { sig->group_stop_count++; if (likely(!(t->ptrace & PT_SEIZED))) signal_wake_up(t, 0); else ptrace_trap_notify(t); } } } if (likely(!current->ptrace)) { int notify = 0; /* * If there are no other threads in the group, or if there * is a group stop in progress and we are the last to stop, * report to the parent. */ if (task_participate_group_stop(current)) notify = CLD_STOPPED; current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); spin_unlock_irq(¤t->sighand->siglock); /* * Notify the parent of the group stop completion. Because * we're not holding either the siglock or tasklist_lock * here, ptracer may attach inbetween; however, this is for * group stop and should always be delivered to the real * parent of the group leader. The new ptracer will get * its notification when this task transitions into * TASK_TRACED. */ if (notify) { read_lock(&tasklist_lock); do_notify_parent_cldstop(current, false, notify); read_unlock(&tasklist_lock); } /* Now we don't run again until woken by SIGCONT or SIGKILL */ cgroup_enter_frozen(); schedule(); return true; } else { /* * While ptraced, group stop is handled by STOP trap. * Schedule it and let the caller deal with it. */ task_set_jobctl_pending(current, JOBCTL_TRAP_STOP); return false; } } /** * do_jobctl_trap - take care of ptrace jobctl traps * * When PT_SEIZED, it's used for both group stop and explicit * SEIZE/INTERRUPT traps. Both generate PTRACE_EVENT_STOP trap with * accompanying siginfo. If stopped, lower eight bits of exit_code contain * the stop signal; otherwise, %SIGTRAP. * * When !PT_SEIZED, it's used only for group stop trap with stop signal * number as exit_code and no siginfo. * * CONTEXT: * Must be called with @current->sighand->siglock held, which may be * released and re-acquired before returning with intervening sleep. */ static void do_jobctl_trap(void) { struct signal_struct *signal = current->signal; int signr = current->jobctl & JOBCTL_STOP_SIGMASK; if (current->ptrace & PT_SEIZED) { if (!signal->group_stop_count && !(signal->flags & SIGNAL_STOP_STOPPED)) signr = SIGTRAP; WARN_ON_ONCE(!signr); ptrace_do_notify(signr, signr | (PTRACE_EVENT_STOP << 8), CLD_STOPPED, 0); } else { WARN_ON_ONCE(!signr); ptrace_stop(signr, CLD_STOPPED, 0, NULL); } } /** * do_freezer_trap - handle the freezer jobctl trap * * Puts the task into frozen state, if only the task is not about to quit. * In this case it drops JOBCTL_TRAP_FREEZE. * * CONTEXT: * Must be called with @current->sighand->siglock held, * which is always released before returning. */ static void do_freezer_trap(void) __releases(¤t->sighand->siglock) { /* * If there are other trap bits pending except JOBCTL_TRAP_FREEZE, * let's make another loop to give it a chance to be handled. * In any case, we'll return back. */ if ((current->jobctl & (JOBCTL_PENDING_MASK | JOBCTL_TRAP_FREEZE)) != JOBCTL_TRAP_FREEZE) { spin_unlock_irq(¤t->sighand->siglock); return; } /* * Now we're sure that there is no pending fatal signal and no * pending traps. Clear TIF_SIGPENDING to not get out of schedule() * immediately (if there is a non-fatal signal pending), and * put the task into sleep. */ __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); clear_thread_flag(TIF_SIGPENDING); spin_unlock_irq(¤t->sighand->siglock); cgroup_enter_frozen(); schedule(); /* * We could've been woken by task_work, run it to clear * TIF_NOTIFY_SIGNAL. The caller will retry if necessary. */ clear_notify_signal(); if (unlikely(task_work_pending(current))) task_work_run(); } static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type) { /* * We do not check sig_kernel_stop(signr) but set this marker * unconditionally because we do not know whether debugger will * change signr. This flag has no meaning unless we are going * to stop after return from ptrace_stop(). In this case it will * be checked in do_signal_stop(), we should only stop if it was * not cleared by SIGCONT while we were sleeping. See also the * comment in dequeue_signal(). */ current->jobctl |= JOBCTL_STOP_DEQUEUED; signr = ptrace_stop(signr, CLD_TRAPPED, 0, info); /* We're back. Did the debugger cancel the sig? */ if (signr == 0) return signr; /* * Update the siginfo structure if the signal has * changed. If the debugger wanted something * specific in the siginfo structure then it should * have updated *info via PTRACE_SETSIGINFO. */ if (signr != info->si_signo) { clear_siginfo(info); info->si_signo = signr; info->si_errno = 0; info->si_code = SI_USER; rcu_read_lock(); info->si_pid = task_pid_vnr(current->parent); info->si_uid = from_kuid_munged(current_user_ns(), task_uid(current->parent)); rcu_read_unlock(); } /* If the (new) signal is now blocked, requeue it. */ if (sigismember(¤t->blocked, signr) || fatal_signal_pending(current)) { send_signal_locked(signr, info, current, type); signr = 0; } return signr; } static void hide_si_addr_tag_bits(struct ksignal *ksig) { switch (siginfo_layout(ksig->sig, ksig->info.si_code)) { case SIL_FAULT: case SIL_FAULT_TRAPNO: case SIL_FAULT_MCEERR: case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: case SIL_FAULT_PERF_EVENT: ksig->info.si_addr = arch_untagged_si_addr( ksig->info.si_addr, ksig->sig, ksig->info.si_code); break; case SIL_KILL: case SIL_TIMER: case SIL_POLL: case SIL_CHLD: case SIL_RT: case SIL_SYS: break; } } bool get_signal(struct ksignal *ksig) { struct sighand_struct *sighand = current->sighand; struct signal_struct *signal = current->signal; int signr; clear_notify_signal(); if (unlikely(task_work_pending(current))) task_work_run(); if (!task_sigpending(current)) return false; if (unlikely(uprobe_deny_signal())) return false; /* * Do this once, we can't return to user-mode if freezing() == T. * do_signal_stop() and ptrace_stop() do freezable_schedule() and * thus do not need another check after return. */ try_to_freeze(); relock: spin_lock_irq(&sighand->siglock); /* * Every stopped thread goes here after wakeup. Check to see if * we should notify the parent, prepare_signal(SIGCONT) encodes * the CLD_ si_code into SIGNAL_CLD_MASK bits. */ if (unlikely(signal->flags & SIGNAL_CLD_MASK)) { int why; if (signal->flags & SIGNAL_CLD_CONTINUED) why = CLD_CONTINUED; else why = CLD_STOPPED; signal->flags &= ~SIGNAL_CLD_MASK; spin_unlock_irq(&sighand->siglock); /* * Notify the parent that we're continuing. This event is * always per-process and doesn't make whole lot of sense * for ptracers, who shouldn't consume the state via * wait(2) either, but, for backward compatibility, notify * the ptracer of the group leader too unless it's gonna be * a duplicate. */ read_lock(&tasklist_lock); do_notify_parent_cldstop(current, false, why); if (ptrace_reparented(current->group_leader)) do_notify_parent_cldstop(current->group_leader, true, why); read_unlock(&tasklist_lock); goto relock; } for (;;) { struct k_sigaction *ka; enum pid_type type; /* Has this task already been marked for death? */ if ((signal->flags & SIGNAL_GROUP_EXIT) || signal->group_exec_task) { signr = SIGKILL; sigdelset(¤t->pending.signal, SIGKILL); trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO, &sighand->action[SIGKILL-1]); recalc_sigpending(); /* * implies do_group_exit() or return to PF_USER_WORKER, * no need to initialize ksig->info/etc. */ goto fatal; } if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) && do_signal_stop(0)) goto relock; if (unlikely(current->jobctl & (JOBCTL_TRAP_MASK | JOBCTL_TRAP_FREEZE))) { if (current->jobctl & JOBCTL_TRAP_MASK) { do_jobctl_trap(); spin_unlock_irq(&sighand->siglock); } else if (current->jobctl & JOBCTL_TRAP_FREEZE) do_freezer_trap(); goto relock; } /* * If the task is leaving the frozen state, let's update * cgroup counters and reset the frozen bit. */ if (unlikely(cgroup_task_frozen(current))) { spin_unlock_irq(&sighand->siglock); cgroup_leave_frozen(false); goto relock; } /* * Signals generated by the execution of an instruction * need to be delivered before any other pending signals * so that the instruction pointer in the signal stack * frame points to the faulting instruction. */ type = PIDTYPE_PID; signr = dequeue_synchronous_signal(&ksig->info); if (!signr) signr = dequeue_signal(¤t->blocked, &ksig->info, &type); if (!signr) break; /* will return 0 */ if (unlikely(current->ptrace) && (signr != SIGKILL) && !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) { signr = ptrace_signal(signr, &ksig->info, type); if (!signr) continue; } ka = &sighand->action[signr-1]; /* Trace actually delivered signals. */ trace_signal_deliver(signr, &ksig->info, ka); if (ka->sa.sa_handler == SIG_IGN) /* Do nothing. */ continue; if (ka->sa.sa_handler != SIG_DFL) { /* Run the handler. */ ksig->ka = *ka; if (ka->sa.sa_flags & SA_ONESHOT) ka->sa.sa_handler = SIG_DFL; break; /* will return non-zero "signr" value */ } /* * Now we are doing the default action for this signal. */ if (sig_kernel_ignore(signr)) /* Default is nothing. */ continue; /* * Global init gets no signals it doesn't want. * Container-init gets no signals it doesn't want from same * container. * * Note that if global/container-init sees a sig_kernel_only() * signal here, the signal must have been generated internally * or must have come from an ancestor namespace. In either * case, the signal cannot be dropped. */ if (unlikely(signal->flags & SIGNAL_UNKILLABLE) && !sig_kernel_only(signr)) continue; if (sig_kernel_stop(signr)) { /* * The default action is to stop all threads in * the thread group. The job control signals * do nothing in an orphaned pgrp, but SIGSTOP * always works. Note that siglock needs to be * dropped during the call to is_orphaned_pgrp() * because of lock ordering with tasklist_lock. * This allows an intervening SIGCONT to be posted. * We need to check for that and bail out if necessary. */ if (signr != SIGSTOP) { spin_unlock_irq(&sighand->siglock); /* signals can be posted during this window */ if (is_current_pgrp_orphaned()) goto relock; spin_lock_irq(&sighand->siglock); } if (likely(do_signal_stop(signr))) { /* It released the siglock. */ goto relock; } /* * We didn't actually stop, due to a race * with SIGCONT or something like that. */ continue; } fatal: spin_unlock_irq(&sighand->siglock); if (unlikely(cgroup_task_frozen(current))) cgroup_leave_frozen(true); /* * Anything else is fatal, maybe with a core dump. */ current->flags |= PF_SIGNALED; if (sig_kernel_coredump(signr)) { if (print_fatal_signals) print_fatal_signal(signr); proc_coredump_connector(current); /* * If it was able to dump core, this kills all * other threads in the group and synchronizes with * their demise. If we lost the race with another * thread getting here, it set group_exit_code * first and our do_group_exit call below will use * that value and ignore the one we pass it. */ do_coredump(&ksig->info); } /* * PF_USER_WORKER threads will catch and exit on fatal signals * themselves. They have cleanup that must be performed, so we * cannot call do_exit() on their behalf. Note that ksig won't * be properly initialized, PF_USER_WORKER's shouldn't use it. */ if (current->flags & PF_USER_WORKER) goto out; /* * Death signals, no core dump. */ do_group_exit(signr); /* NOTREACHED */ } spin_unlock_irq(&sighand->siglock); ksig->sig = signr; if (signr && !(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS)) hide_si_addr_tag_bits(ksig); out: return signr > 0; } /** * signal_delivered - called after signal delivery to update blocked signals * @ksig: kernel signal struct * @stepping: nonzero if debugger single-step or block-step in use * * This function should be called when a signal has successfully been * delivered. It updates the blocked signals accordingly (@ksig->ka.sa.sa_mask * is always blocked), and the signal itself is blocked unless %SA_NODEFER * is set in @ksig->ka.sa.sa_flags. Tracing is notified. */ static void signal_delivered(struct ksignal *ksig, int stepping) { sigset_t blocked; /* A signal was successfully delivered, and the saved sigmask was stored on the signal frame, and will be restored by sigreturn. So we can simply clear the restore sigmask flag. */ clear_restore_sigmask(); sigorsets(&blocked, ¤t->blocked, &ksig->ka.sa.sa_mask); if (!(ksig->ka.sa.sa_flags & SA_NODEFER)) sigaddset(&blocked, ksig->sig); set_current_blocked(&blocked); if (current->sas_ss_flags & SS_AUTODISARM) sas_ss_reset(current); if (stepping) ptrace_notify(SIGTRAP, 0); } void signal_setup_done(int failed, struct ksignal *ksig, int stepping) { if (failed) force_sigsegv(ksig->sig); else signal_delivered(ksig, stepping); } /* * It could be that complete_signal() picked us to notify about the * group-wide signal. Other threads should be notified now to take * the shared signals in @which since we will not. */ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which) { sigset_t retarget; struct task_struct *t; sigandsets(&retarget, &tsk->signal->shared_pending.signal, which); if (sigisemptyset(&retarget)) return; for_other_threads(tsk, t) { if (t->flags & PF_EXITING) continue; if (!has_pending_signals(&retarget, &t->blocked)) continue; /* Remove the signals this thread can handle. */ sigandsets(&retarget, &retarget, &t->blocked); if (!task_sigpending(t)) signal_wake_up(t, 0); if (sigisemptyset(&retarget)) break; } } void exit_signals(struct task_struct *tsk) { int group_stop = 0; sigset_t unblocked; /* * @tsk is about to have PF_EXITING set - lock out users which * expect stable threadgroup. */ cgroup_threadgroup_change_begin(tsk); if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) { sched_mm_cid_exit_signals(tsk); tsk->flags |= PF_EXITING; cgroup_threadgroup_change_end(tsk); return; } spin_lock_irq(&tsk->sighand->siglock); /* * From now this task is not visible for group-wide signals, * see wants_signal(), do_signal_stop(). */ sched_mm_cid_exit_signals(tsk); tsk->flags |= PF_EXITING; cgroup_threadgroup_change_end(tsk); if (!task_sigpending(tsk)) goto out; unblocked = tsk->blocked; signotset(&unblocked); retarget_shared_pending(tsk, &unblocked); if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) && task_participate_group_stop(tsk)) group_stop = CLD_STOPPED; out: spin_unlock_irq(&tsk->sighand->siglock); /* * If group stop has completed, deliver the notification. This * should always go to the real parent of the group leader. */ if (unlikely(group_stop)) { read_lock(&tasklist_lock); do_notify_parent_cldstop(tsk, false, group_stop); read_unlock(&tasklist_lock); } } /* * System call entry points. */ /** * sys_restart_syscall - restart a system call */ SYSCALL_DEFINE0(restart_syscall) { struct restart_block *restart = ¤t->restart_block; return restart->fn(restart); } long do_no_restart_syscall(struct restart_block *param) { return -EINTR; } static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset) { if (task_sigpending(tsk) && !thread_group_empty(tsk)) { sigset_t newblocked; /* A set of now blocked but previously unblocked signals. */ sigandnsets(&newblocked, newset, ¤t->blocked); retarget_shared_pending(tsk, &newblocked); } tsk->blocked = *newset; recalc_sigpending(); } /** * set_current_blocked - change current->blocked mask * @newset: new mask * * It is wrong to change ->blocked directly, this helper should be used * to ensure the process can't miss a shared signal we are going to block. */ void set_current_blocked(sigset_t *newset) { sigdelsetmask(newset, sigmask(SIGKILL) | sigmask(SIGSTOP)); __set_current_blocked(newset); } void __set_current_blocked(const sigset_t *newset) { struct task_struct *tsk = current; /* * In case the signal mask hasn't changed, there is nothing we need * to do. The current->blocked shouldn't be modified by other task. */ if (sigequalsets(&tsk->blocked, newset)) return; spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, newset); spin_unlock_irq(&tsk->sighand->siglock); } /* * This is also useful for kernel threads that want to temporarily * (or permanently) block certain signals. * * NOTE! Unlike the user-mode sys_sigprocmask(), the kernel * interface happily blocks "unblockable" signals like SIGKILL * and friends. */ int sigprocmask(int how, sigset_t *set, sigset_t *oldset) { struct task_struct *tsk = current; sigset_t newset; /* Lockless, only current can change ->blocked, never from irq */ if (oldset) *oldset = tsk->blocked; switch (how) { case SIG_BLOCK: sigorsets(&newset, &tsk->blocked, set); break; case SIG_UNBLOCK: sigandnsets(&newset, &tsk->blocked, set); break; case SIG_SETMASK: newset = *set; break; default: return -EINVAL; } __set_current_blocked(&newset); return 0; } EXPORT_SYMBOL(sigprocmask); /* * The api helps set app-provided sigmasks. * * This is useful for syscalls such as ppoll, pselect, io_pgetevents and * epoll_pwait where a new sigmask is passed from userland for the syscalls. * * Note that it does set_restore_sigmask() in advance, so it must be always * paired with restore_saved_sigmask_unless() before return from syscall. */ int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize) { sigset_t kmask; if (!umask) return 0; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&kmask, umask, sizeof(sigset_t))) return -EFAULT; set_restore_sigmask(); current->saved_sigmask = current->blocked; set_current_blocked(&kmask); return 0; } #ifdef CONFIG_COMPAT int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize) { sigset_t kmask; if (!umask) return 0; if (sigsetsize != sizeof(compat_sigset_t)) return -EINVAL; if (get_compat_sigset(&kmask, umask)) return -EFAULT; set_restore_sigmask(); current->saved_sigmask = current->blocked; set_current_blocked(&kmask); return 0; } #endif /** * sys_rt_sigprocmask - change the list of currently blocked signals * @how: whether to add, remove, or set signals * @nset: stores pending signals * @oset: previous value of signal mask if non-null * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, nset, sigset_t __user *, oset, size_t, sigsetsize) { sigset_t old_set, new_set; int error; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; old_set = current->blocked; if (nset) { if (copy_from_user(&new_set, nset, sizeof(sigset_t))) return -EFAULT; sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); error = sigprocmask(how, &new_set, NULL); if (error) return error; } if (oset) { if (copy_to_user(oset, &old_set, sizeof(sigset_t))) return -EFAULT; } return 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_sigprocmask, int, how, compat_sigset_t __user *, nset, compat_sigset_t __user *, oset, compat_size_t, sigsetsize) { sigset_t old_set = current->blocked; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (nset) { sigset_t new_set; int error; if (get_compat_sigset(&new_set, nset)) return -EFAULT; sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); error = sigprocmask(how, &new_set, NULL); if (error) return error; } return oset ? put_compat_sigset(oset, &old_set, sizeof(*oset)) : 0; } #endif static void do_sigpending(sigset_t *set) { spin_lock_irq(¤t->sighand->siglock); sigorsets(set, ¤t->pending.signal, ¤t->signal->shared_pending.signal); spin_unlock_irq(¤t->sighand->siglock); /* Outside the lock because only this thread touches it. */ sigandsets(set, ¤t->blocked, set); } /** * sys_rt_sigpending - examine a pending signal that has been raised * while blocked * @uset: stores pending signals * @sigsetsize: size of sigset_t type or larger */ SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, uset, size_t, sigsetsize) { sigset_t set; if (sigsetsize > sizeof(*uset)) return -EINVAL; do_sigpending(&set); if (copy_to_user(uset, &set, sigsetsize)) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset, compat_size_t, sigsetsize) { sigset_t set; if (sigsetsize > sizeof(*uset)) return -EINVAL; do_sigpending(&set); return put_compat_sigset(uset, &set, sigsetsize); } #endif static const struct { unsigned char limit, layout; } sig_sicodes[] = { [SIGILL] = { NSIGILL, SIL_FAULT }, [SIGFPE] = { NSIGFPE, SIL_FAULT }, [SIGSEGV] = { NSIGSEGV, SIL_FAULT }, [SIGBUS] = { NSIGBUS, SIL_FAULT }, [SIGTRAP] = { NSIGTRAP, SIL_FAULT }, #if defined(SIGEMT) [SIGEMT] = { NSIGEMT, SIL_FAULT }, #endif [SIGCHLD] = { NSIGCHLD, SIL_CHLD }, [SIGPOLL] = { NSIGPOLL, SIL_POLL }, [SIGSYS] = { NSIGSYS, SIL_SYS }, }; static bool known_siginfo_layout(unsigned sig, int si_code) { if (si_code == SI_KERNEL) return true; else if ((si_code > SI_USER)) { if (sig_specific_sicodes(sig)) { if (si_code <= sig_sicodes[sig].limit) return true; } else if (si_code <= NSIGPOLL) return true; } else if (si_code >= SI_DETHREAD) return true; else if (si_code == SI_ASYNCNL) return true; return false; } enum siginfo_layout siginfo_layout(unsigned sig, int si_code) { enum siginfo_layout layout = SIL_KILL; if ((si_code > SI_USER) && (si_code < SI_KERNEL)) { if ((sig < ARRAY_SIZE(sig_sicodes)) && (si_code <= sig_sicodes[sig].limit)) { layout = sig_sicodes[sig].layout; /* Handle the exceptions */ if ((sig == SIGBUS) && (si_code >= BUS_MCEERR_AR) && (si_code <= BUS_MCEERR_AO)) layout = SIL_FAULT_MCEERR; else if ((sig == SIGSEGV) && (si_code == SEGV_BNDERR)) layout = SIL_FAULT_BNDERR; #ifdef SEGV_PKUERR else if ((sig == SIGSEGV) && (si_code == SEGV_PKUERR)) layout = SIL_FAULT_PKUERR; #endif else if ((sig == SIGTRAP) && (si_code == TRAP_PERF)) layout = SIL_FAULT_PERF_EVENT; else if (IS_ENABLED(CONFIG_SPARC) && (sig == SIGILL) && (si_code == ILL_ILLTRP)) layout = SIL_FAULT_TRAPNO; else if (IS_ENABLED(CONFIG_ALPHA) && ((sig == SIGFPE) || ((sig == SIGTRAP) && (si_code == TRAP_UNK)))) layout = SIL_FAULT_TRAPNO; } else if (si_code <= NSIGPOLL) layout = SIL_POLL; } else { if (si_code == SI_TIMER) layout = SIL_TIMER; else if (si_code == SI_SIGIO) layout = SIL_POLL; else if (si_code < 0) layout = SIL_RT; } return layout; } static inline char __user *si_expansion(const siginfo_t __user *info) { return ((char __user *)info) + sizeof(struct kernel_siginfo); } int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from) { char __user *expansion = si_expansion(to); if (copy_to_user(to, from , sizeof(struct kernel_siginfo))) return -EFAULT; if (clear_user(expansion, SI_EXPANSION_SIZE)) return -EFAULT; return 0; } static int post_copy_siginfo_from_user(kernel_siginfo_t *info, const siginfo_t __user *from) { if (unlikely(!known_siginfo_layout(info->si_signo, info->si_code))) { char __user *expansion = si_expansion(from); char buf[SI_EXPANSION_SIZE]; int i; /* * An unknown si_code might need more than * sizeof(struct kernel_siginfo) bytes. Verify all of the * extra bytes are 0. This guarantees copy_siginfo_to_user * will return this data to userspace exactly. */ if (copy_from_user(&buf, expansion, SI_EXPANSION_SIZE)) return -EFAULT; for (i = 0; i < SI_EXPANSION_SIZE; i++) { if (buf[i] != 0) return -E2BIG; } } return 0; } static int __copy_siginfo_from_user(int signo, kernel_siginfo_t *to, const siginfo_t __user *from) { if (copy_from_user(to, from, sizeof(struct kernel_siginfo))) return -EFAULT; to->si_signo = signo; return post_copy_siginfo_from_user(to, from); } int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from) { if (copy_from_user(to, from, sizeof(struct kernel_siginfo))) return -EFAULT; return post_copy_siginfo_from_user(to, from); } #ifdef CONFIG_COMPAT /** * copy_siginfo_to_external32 - copy a kernel siginfo into a compat user siginfo * @to: compat siginfo destination * @from: kernel siginfo source * * Note: This function does not work properly for the SIGCHLD on x32, but * fortunately it doesn't have to. The only valid callers for this function are * copy_siginfo_to_user32, which is overriden for x32 and the coredump code. * The latter does not care because SIGCHLD will never cause a coredump. */ void copy_siginfo_to_external32(struct compat_siginfo *to, const struct kernel_siginfo *from) { memset(to, 0, sizeof(*to)); to->si_signo = from->si_signo; to->si_errno = from->si_errno; to->si_code = from->si_code; switch(siginfo_layout(from->si_signo, from->si_code)) { case SIL_KILL: to->si_pid = from->si_pid; to->si_uid = from->si_uid; break; case SIL_TIMER: to->si_tid = from->si_tid; to->si_overrun = from->si_overrun; to->si_int = from->si_int; break; case SIL_POLL: to->si_band = from->si_band; to->si_fd = from->si_fd; break; case SIL_FAULT: to->si_addr = ptr_to_compat(from->si_addr); break; case SIL_FAULT_TRAPNO: to->si_addr = ptr_to_compat(from->si_addr); to->si_trapno = from->si_trapno; break; case SIL_FAULT_MCEERR: to->si_addr = ptr_to_compat(from->si_addr); to->si_addr_lsb = from->si_addr_lsb; break; case SIL_FAULT_BNDERR: to->si_addr = ptr_to_compat(from->si_addr); to->si_lower = ptr_to_compat(from->si_lower); to->si_upper = ptr_to_compat(from->si_upper); break; case SIL_FAULT_PKUERR: to->si_addr = ptr_to_compat(from->si_addr); to->si_pkey = from->si_pkey; break; case SIL_FAULT_PERF_EVENT: to->si_addr = ptr_to_compat(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; to->si_perf_flags = from->si_perf_flags; break; case SIL_CHLD: to->si_pid = from->si_pid; to->si_uid = from->si_uid; to->si_status = from->si_status; to->si_utime = from->si_utime; to->si_stime = from->si_stime; break; case SIL_RT: to->si_pid = from->si_pid; to->si_uid = from->si_uid; to->si_int = from->si_int; break; case SIL_SYS: to->si_call_addr = ptr_to_compat(from->si_call_addr); to->si_syscall = from->si_syscall; to->si_arch = from->si_arch; break; } } int __copy_siginfo_to_user32(struct compat_siginfo __user *to, const struct kernel_siginfo *from) { struct compat_siginfo new; copy_siginfo_to_external32(&new, from); if (copy_to_user(to, &new, sizeof(struct compat_siginfo))) return -EFAULT; return 0; } static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, const struct compat_siginfo *from) { clear_siginfo(to); to->si_signo = from->si_signo; to->si_errno = from->si_errno; to->si_code = from->si_code; switch(siginfo_layout(from->si_signo, from->si_code)) { case SIL_KILL: to->si_pid = from->si_pid; to->si_uid = from->si_uid; break; case SIL_TIMER: to->si_tid = from->si_tid; to->si_overrun = from->si_overrun; to->si_int = from->si_int; break; case SIL_POLL: to->si_band = from->si_band; to->si_fd = from->si_fd; break; case SIL_FAULT: to->si_addr = compat_ptr(from->si_addr); break; case SIL_FAULT_TRAPNO: to->si_addr = compat_ptr(from->si_addr); to->si_trapno = from->si_trapno; break; case SIL_FAULT_MCEERR: to->si_addr = compat_ptr(from->si_addr); to->si_addr_lsb = from->si_addr_lsb; break; case SIL_FAULT_BNDERR: to->si_addr = compat_ptr(from->si_addr); to->si_lower = compat_ptr(from->si_lower); to->si_upper = compat_ptr(from->si_upper); break; case SIL_FAULT_PKUERR: to->si_addr = compat_ptr(from->si_addr); to->si_pkey = from->si_pkey; break; case SIL_FAULT_PERF_EVENT: to->si_addr = compat_ptr(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; to->si_perf_flags = from->si_perf_flags; break; case SIL_CHLD: to->si_pid = from->si_pid; to->si_uid = from->si_uid; to->si_status = from->si_status; #ifdef CONFIG_X86_X32_ABI if (in_x32_syscall()) { to->si_utime = from->_sifields._sigchld_x32._utime; to->si_stime = from->_sifields._sigchld_x32._stime; } else #endif { to->si_utime = from->si_utime; to->si_stime = from->si_stime; } break; case SIL_RT: to->si_pid = from->si_pid; to->si_uid = from->si_uid; to->si_int = from->si_int; break; case SIL_SYS: to->si_call_addr = compat_ptr(from->si_call_addr); to->si_syscall = from->si_syscall; to->si_arch = from->si_arch; break; } return 0; } static int __copy_siginfo_from_user32(int signo, struct kernel_siginfo *to, const struct compat_siginfo __user *ufrom) { struct compat_siginfo from; if (copy_from_user(&from, ufrom, sizeof(struct compat_siginfo))) return -EFAULT; from.si_signo = signo; return post_copy_siginfo_from_user32(to, &from); } int copy_siginfo_from_user32(struct kernel_siginfo *to, const struct compat_siginfo __user *ufrom) { struct compat_siginfo from; if (copy_from_user(&from, ufrom, sizeof(struct compat_siginfo))) return -EFAULT; return post_copy_siginfo_from_user32(to, &from); } #endif /* CONFIG_COMPAT */ /** * do_sigtimedwait - wait for queued signals specified in @which * @which: queued signals to wait for * @info: if non-null, the signal's siginfo is returned here * @ts: upper bound on process time suspension */ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, const struct timespec64 *ts) { ktime_t *to = NULL, timeout = KTIME_MAX; struct task_struct *tsk = current; sigset_t mask = *which; enum pid_type type; int sig, ret = 0; if (ts) { if (!timespec64_valid(ts)) return -EINVAL; timeout = timespec64_to_ktime(*ts); to = &timeout; } /* * Invert the set of allowed signals to get those we want to block. */ sigdelsetmask(&mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); signotset(&mask); spin_lock_irq(&tsk->sighand->siglock); sig = dequeue_signal(&mask, info, &type); if (!sig && timeout) { /* * None ready, temporarily unblock those we're interested * while we are sleeping in so that we'll be awakened when * they arrive. Unblocking is always fine, we can avoid * set_current_blocked(). */ tsk->real_blocked = tsk->blocked; sigandsets(&tsk->blocked, &tsk->blocked, &mask); recalc_sigpending(); spin_unlock_irq(&tsk->sighand->siglock); __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); ret = schedule_hrtimeout_range(to, tsk->timer_slack_ns, HRTIMER_MODE_REL); spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, &tsk->real_blocked); sigemptyset(&tsk->real_blocked); sig = dequeue_signal(&mask, info, &type); } spin_unlock_irq(&tsk->sighand->siglock); if (sig) return sig; return ret ? -EINTR : -EAGAIN; } /** * sys_rt_sigtimedwait - synchronously wait for queued signals specified * in @uthese * @uthese: queued signals to wait for * @uinfo: if non-null, the signal's siginfo is returned here * @uts: upper bound on process time suspension * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, siginfo_t __user *, uinfo, const struct __kernel_timespec __user *, uts, size_t, sigsetsize) { sigset_t these; struct timespec64 ts; kernel_siginfo_t info; int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&these, uthese, sizeof(these))) return -EFAULT; if (uts) { if (get_timespec64(&ts, uts)) return -EFAULT; } ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL); if (ret > 0 && uinfo) { if (copy_siginfo_to_user(uinfo, &info)) ret = -EFAULT; } return ret; } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE4(rt_sigtimedwait_time32, const sigset_t __user *, uthese, siginfo_t __user *, uinfo, const struct old_timespec32 __user *, uts, size_t, sigsetsize) { sigset_t these; struct timespec64 ts; kernel_siginfo_t info; int ret; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&these, uthese, sizeof(these))) return -EFAULT; if (uts) { if (get_old_timespec32(&ts, uts)) return -EFAULT; } ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL); if (ret > 0 && uinfo) { if (copy_siginfo_to_user(uinfo, &info)) ret = -EFAULT; } return ret; } #endif #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time64, compat_sigset_t __user *, uthese, struct compat_siginfo __user *, uinfo, struct __kernel_timespec __user *, uts, compat_size_t, sigsetsize) { sigset_t s; struct timespec64 t; kernel_siginfo_t info; long ret; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (get_compat_sigset(&s, uthese)) return -EFAULT; if (uts) { if (get_timespec64(&t, uts)) return -EFAULT; } ret = do_sigtimedwait(&s, &info, uts ? &t : NULL); if (ret > 0 && uinfo) { if (copy_siginfo_to_user32(uinfo, &info)) ret = -EFAULT; } return ret; } #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time32, compat_sigset_t __user *, uthese, struct compat_siginfo __user *, uinfo, struct old_timespec32 __user *, uts, compat_size_t, sigsetsize) { sigset_t s; struct timespec64 t; kernel_siginfo_t info; long ret; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (get_compat_sigset(&s, uthese)) return -EFAULT; if (uts) { if (get_old_timespec32(&t, uts)) return -EFAULT; } ret = do_sigtimedwait(&s, &info, uts ? &t : NULL); if (ret > 0 && uinfo) { if (copy_siginfo_to_user32(uinfo, &info)) ret = -EFAULT; } return ret; } #endif #endif static void prepare_kill_siginfo(int sig, struct kernel_siginfo *info, enum pid_type type) { clear_siginfo(info); info->si_signo = sig; info->si_errno = 0; info->si_code = (type == PIDTYPE_PID) ? SI_TKILL : SI_USER; info->si_pid = task_tgid_vnr(current); info->si_uid = from_kuid_munged(current_user_ns(), current_uid()); } /** * sys_kill - send a signal to a process * @pid: the PID of the process * @sig: signal to be sent */ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { struct kernel_siginfo info; prepare_kill_siginfo(sig, &info, PIDTYPE_TGID); return kill_something_info(sig, &info, pid); } /* * Verify that the signaler and signalee either are in the same pid namespace * or that the signaler's pid namespace is an ancestor of the signalee's pid * namespace. */ static bool access_pidfd_pidns(struct pid *pid) { struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *p = ns_of_pid(pid); for (;;) { if (!p) return false; if (p == active) break; p = p->parent; } return true; } static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t __user *info) { #ifdef CONFIG_COMPAT /* * Avoid hooking up compat syscalls and instead handle necessary * conversions here. Note, this is a stop-gap measure and should not be * considered a generic solution. */ if (in_compat_syscall()) return copy_siginfo_from_user32( kinfo, (struct compat_siginfo __user *)info); #endif return copy_siginfo_from_user(kinfo, info); } static struct pid *pidfd_to_pid(const struct file *file) { struct pid *pid; pid = pidfd_pid(file); if (!IS_ERR(pid)) return pid; return tgid_pidfd_to_pid(file); } #define PIDFD_SEND_SIGNAL_FLAGS \ (PIDFD_SIGNAL_THREAD | PIDFD_SIGNAL_THREAD_GROUP | \ PIDFD_SIGNAL_PROCESS_GROUP) /** * sys_pidfd_send_signal - Signal a process through a pidfd * @pidfd: file descriptor of the process * @sig: signal to send * @info: signal info * @flags: future flags * * Send the signal to the thread group or to the individual thread depending * on PIDFD_THREAD. * In the future extension to @flags may be used to override the default scope * of @pidfd. * * Return: 0 on success, negative errno on failure */ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, siginfo_t __user *, info, unsigned int, flags) { int ret; struct fd f; struct pid *pid; kernel_siginfo_t kinfo; enum pid_type type; /* Enforce flags be set to 0 until we add an extension. */ if (flags & ~PIDFD_SEND_SIGNAL_FLAGS) return -EINVAL; /* Ensure that only a single signal scope determining flag is set. */ if (hweight32(flags & PIDFD_SEND_SIGNAL_FLAGS) > 1) return -EINVAL; f = fdget(pidfd); if (!fd_file(f)) return -EBADF; /* Is this a pidfd? */ pid = pidfd_to_pid(fd_file(f)); if (IS_ERR(pid)) { ret = PTR_ERR(pid); goto err; } ret = -EINVAL; if (!access_pidfd_pidns(pid)) goto err; switch (flags) { case 0: /* Infer scope from the type of pidfd. */ if (fd_file(f)->f_flags & PIDFD_THREAD) type = PIDTYPE_PID; else type = PIDTYPE_TGID; break; case PIDFD_SIGNAL_THREAD: type = PIDTYPE_PID; break; case PIDFD_SIGNAL_THREAD_GROUP: type = PIDTYPE_TGID; break; case PIDFD_SIGNAL_PROCESS_GROUP: type = PIDTYPE_PGID; break; } if (info) { ret = copy_siginfo_from_user_any(&kinfo, info); if (unlikely(ret)) goto err; ret = -EINVAL; if (unlikely(sig != kinfo.si_signo)) goto err; /* Only allow sending arbitrary signals to yourself. */ ret = -EPERM; if ((task_pid(current) != pid || type > PIDTYPE_TGID) && (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) goto err; } else { prepare_kill_siginfo(sig, &kinfo, type); } if (type == PIDTYPE_PGID) ret = kill_pgrp_info(sig, &kinfo, pid); else ret = kill_pid_info_type(sig, &kinfo, pid, type); err: fdput(f); return ret; } static int do_send_specific(pid_t tgid, pid_t pid, int sig, struct kernel_siginfo *info) { struct task_struct *p; int error = -ESRCH; rcu_read_lock(); p = find_task_by_vpid(pid); if (p && (tgid <= 0 || task_tgid_vnr(p) == tgid)) { error = check_kill_permission(sig, info, p); /* * The null signal is a permissions and process existence * probe. No signal is actually delivered. */ if (!error && sig) { error = do_send_sig_info(sig, info, p, PIDTYPE_PID); /* * If lock_task_sighand() failed we pretend the task * dies after receiving the signal. The window is tiny, * and the signal is private anyway. */ if (unlikely(error == -ESRCH)) error = 0; } } rcu_read_unlock(); return error; } static int do_tkill(pid_t tgid, pid_t pid, int sig) { struct kernel_siginfo info; prepare_kill_siginfo(sig, &info, PIDTYPE_PID); return do_send_specific(tgid, pid, sig, &info); } /** * sys_tgkill - send signal to one specific thread * @tgid: the thread group ID of the thread * @pid: the PID of the thread * @sig: signal to be sent * * This syscall also checks the @tgid and returns -ESRCH even if the PID * exists but it's not belonging to the target process anymore. This * method solves the problem of threads exiting and PIDs getting reused. */ SYSCALL_DEFINE3(tgkill, pid_t, tgid, pid_t, pid, int, sig) { /* This is only valid for single tasks */ if (pid <= 0 || tgid <= 0) return -EINVAL; return do_tkill(tgid, pid, sig); } /** * sys_tkill - send signal to one specific task * @pid: the PID of the task * @sig: signal to be sent * * Send a signal to only one task, even if it's a CLONE_THREAD task. */ SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig) { /* This is only valid for single tasks */ if (pid <= 0) return -EINVAL; return do_tkill(0, pid, sig); } static int do_rt_sigqueueinfo(pid_t pid, int sig, kernel_siginfo_t *info) { /* Not even root can pretend to send signals from the kernel. * Nor can they impersonate a kill()/tgkill(), which adds source info. */ if ((info->si_code >= 0 || info->si_code == SI_TKILL) && (task_pid_vnr(current) != pid)) return -EPERM; /* POSIX.1b doesn't mention process groups. */ return kill_proc_info(sig, info, pid); } /** * sys_rt_sigqueueinfo - send signal information to a signal * @pid: the PID of the thread * @sig: signal to be sent * @uinfo: signal info to be sent */ SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { kernel_siginfo_t info; int ret = __copy_siginfo_from_user(sig, &info, uinfo); if (unlikely(ret)) return ret; return do_rt_sigqueueinfo(pid, sig, &info); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, compat_pid_t, pid, int, sig, struct compat_siginfo __user *, uinfo) { kernel_siginfo_t info; int ret = __copy_siginfo_from_user32(sig, &info, uinfo); if (unlikely(ret)) return ret; return do_rt_sigqueueinfo(pid, sig, &info); } #endif static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, kernel_siginfo_t *info) { /* This is only valid for single tasks */ if (pid <= 0 || tgid <= 0) return -EINVAL; /* Not even root can pretend to send signals from the kernel. * Nor can they impersonate a kill()/tgkill(), which adds source info. */ if ((info->si_code >= 0 || info->si_code == SI_TKILL) && (task_pid_vnr(current) != pid)) return -EPERM; return do_send_specific(tgid, pid, sig, info); } SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { kernel_siginfo_t info; int ret = __copy_siginfo_from_user(sig, &info, uinfo); if (unlikely(ret)) return ret; return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, compat_pid_t, tgid, compat_pid_t, pid, int, sig, struct compat_siginfo __user *, uinfo) { kernel_siginfo_t info; int ret = __copy_siginfo_from_user32(sig, &info, uinfo); if (unlikely(ret)) return ret; return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); } #endif /* * For kthreads only, must not be used if cloned with CLONE_SIGHAND */ void kernel_sigaction(int sig, __sighandler_t action) { spin_lock_irq(¤t->sighand->siglock); current->sighand->action[sig - 1].sa.sa_handler = action; if (action == SIG_IGN) { sigset_t mask; sigemptyset(&mask); sigaddset(&mask, sig); flush_sigqueue_mask(&mask, ¤t->signal->shared_pending); flush_sigqueue_mask(&mask, ¤t->pending); recalc_sigpending(); } spin_unlock_irq(¤t->sighand->siglock); } EXPORT_SYMBOL(kernel_sigaction); void __weak sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) { } int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) { struct task_struct *p = current, *t; struct k_sigaction *k; sigset_t mask; if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig))) return -EINVAL; k = &p->sighand->action[sig-1]; spin_lock_irq(&p->sighand->siglock); if (k->sa.sa_flags & SA_IMMUTABLE) { spin_unlock_irq(&p->sighand->siglock); return -EINVAL; } if (oact) *oact = *k; /* * Make sure that we never accidentally claim to support SA_UNSUPPORTED, * e.g. by having an architecture use the bit in their uapi. */ BUILD_BUG_ON(UAPI_SA_FLAGS & SA_UNSUPPORTED); /* * Clear unknown flag bits in order to allow userspace to detect missing * support for flag bits and to allow the kernel to use non-uapi bits * internally. */ if (act) act->sa.sa_flags &= UAPI_SA_FLAGS; if (oact) oact->sa.sa_flags &= UAPI_SA_FLAGS; sigaction_compat_abi(act, oact); if (act) { sigdelsetmask(&act->sa.sa_mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); *k = *act; /* * POSIX 3.3.1.3: * "Setting a signal action to SIG_IGN for a signal that is * pending shall cause the pending signal to be discarded, * whether or not it is blocked." * * "Setting a signal action to SIG_DFL for a signal that is * pending and whose default action is to ignore the signal * (for example, SIGCHLD), shall cause the pending signal to * be discarded, whether or not it is blocked" */ if (sig_handler_ignored(sig_handler(p, sig), sig)) { sigemptyset(&mask); sigaddset(&mask, sig); flush_sigqueue_mask(&mask, &p->signal->shared_pending); for_each_thread(p, t) flush_sigqueue_mask(&mask, &t->pending); } } spin_unlock_irq(&p->sighand->siglock); return 0; } #ifdef CONFIG_DYNAMIC_SIGFRAME static inline void sigaltstack_lock(void) __acquires(¤t->sighand->siglock) { spin_lock_irq(¤t->sighand->siglock); } static inline void sigaltstack_unlock(void) __releases(¤t->sighand->siglock) { spin_unlock_irq(¤t->sighand->siglock); } #else static inline void sigaltstack_lock(void) { } static inline void sigaltstack_unlock(void) { } #endif static int do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp, size_t min_ss_size) { struct task_struct *t = current; int ret = 0; if (oss) { memset(oss, 0, sizeof(stack_t)); oss->ss_sp = (void __user *) t->sas_ss_sp; oss->ss_size = t->sas_ss_size; oss->ss_flags = sas_ss_flags(sp) | (current->sas_ss_flags & SS_FLAG_BITS); } if (ss) { void __user *ss_sp = ss->ss_sp; size_t ss_size = ss->ss_size; unsigned ss_flags = ss->ss_flags; int ss_mode; if (unlikely(on_sig_stack(sp))) return -EPERM; ss_mode = ss_flags & ~SS_FLAG_BITS; if (unlikely(ss_mode != SS_DISABLE && ss_mode != SS_ONSTACK && ss_mode != 0)) return -EINVAL; /* * Return before taking any locks if no actual * sigaltstack changes were requested. */ if (t->sas_ss_sp == (unsigned long)ss_sp && t->sas_ss_size == ss_size && t->sas_ss_flags == ss_flags) return 0; sigaltstack_lock(); if (ss_mode == SS_DISABLE) { ss_size = 0; ss_sp = NULL; } else { if (unlikely(ss_size < min_ss_size)) ret = -ENOMEM; if (!sigaltstack_size_valid(ss_size)) ret = -ENOMEM; } if (!ret) { t->sas_ss_sp = (unsigned long) ss_sp; t->sas_ss_size = ss_size; t->sas_ss_flags = ss_flags; } sigaltstack_unlock(); } return ret; } SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss) { stack_t new, old; int err; if (uss && copy_from_user(&new, uss, sizeof(stack_t))) return -EFAULT; err = do_sigaltstack(uss ? &new : NULL, uoss ? &old : NULL, current_user_stack_pointer(), MINSIGSTKSZ); if (!err && uoss && copy_to_user(uoss, &old, sizeof(stack_t))) err = -EFAULT; return err; } int restore_altstack(const stack_t __user *uss) { stack_t new; if (copy_from_user(&new, uss, sizeof(stack_t))) return -EFAULT; (void)do_sigaltstack(&new, NULL, current_user_stack_pointer(), MINSIGSTKSZ); /* squash all but EFAULT for now */ return 0; } int __save_altstack(stack_t __user *uss, unsigned long sp) { struct task_struct *t = current; int err = __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | __put_user(t->sas_ss_flags, &uss->ss_flags) | __put_user(t->sas_ss_size, &uss->ss_size); return err; } #ifdef CONFIG_COMPAT static int do_compat_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr) { stack_t uss, uoss; int ret; if (uss_ptr) { compat_stack_t uss32; if (copy_from_user(&uss32, uss_ptr, sizeof(compat_stack_t))) return -EFAULT; uss.ss_sp = compat_ptr(uss32.ss_sp); uss.ss_flags = uss32.ss_flags; uss.ss_size = uss32.ss_size; } ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, compat_user_stack_pointer(), COMPAT_MINSIGSTKSZ); if (ret >= 0 && uoss_ptr) { compat_stack_t old; memset(&old, 0, sizeof(old)); old.ss_sp = ptr_to_compat(uoss.ss_sp); old.ss_flags = uoss.ss_flags; old.ss_size = uoss.ss_size; if (copy_to_user(uoss_ptr, &old, sizeof(compat_stack_t))) ret = -EFAULT; } return ret; } COMPAT_SYSCALL_DEFINE2(sigaltstack, const compat_stack_t __user *, uss_ptr, compat_stack_t __user *, uoss_ptr) { return do_compat_sigaltstack(uss_ptr, uoss_ptr); } int compat_restore_altstack(const compat_stack_t __user *uss) { int err = do_compat_sigaltstack(uss, NULL); /* squash all but -EFAULT for now */ return err == -EFAULT ? err : 0; } int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp) { int err; struct task_struct *t = current; err = __put_user(ptr_to_compat((void __user *)t->sas_ss_sp), &uss->ss_sp) | __put_user(t->sas_ss_flags, &uss->ss_flags) | __put_user(t->sas_ss_size, &uss->ss_size); return err; } #endif #ifdef __ARCH_WANT_SYS_SIGPENDING /** * sys_sigpending - examine pending signals * @uset: where mask of pending signal is returned */ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, uset) { sigset_t set; if (sizeof(old_sigset_t) > sizeof(*uset)) return -EINVAL; do_sigpending(&set); if (copy_to_user(uset, &set, sizeof(old_sigset_t))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set32) { sigset_t set; do_sigpending(&set); return put_user(set.sig[0], set32); } #endif #endif #ifdef __ARCH_WANT_SYS_SIGPROCMASK /** * sys_sigprocmask - examine and change blocked signals * @how: whether to add, remove, or set signals * @nset: signals to add or remove (if non-null) * @oset: previous value of signal mask if non-null * * Some platforms have their own version with special arguments; * others support only sys_rt_sigprocmask. */ SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, nset, old_sigset_t __user *, oset) { old_sigset_t old_set, new_set; sigset_t new_blocked; old_set = current->blocked.sig[0]; if (nset) { if (copy_from_user(&new_set, nset, sizeof(*nset))) return -EFAULT; new_blocked = current->blocked; switch (how) { case SIG_BLOCK: sigaddsetmask(&new_blocked, new_set); break; case SIG_UNBLOCK: sigdelsetmask(&new_blocked, new_set); break; case SIG_SETMASK: new_blocked.sig[0] = new_set; break; default: return -EINVAL; } set_current_blocked(&new_blocked); } if (oset) { if (copy_to_user(oset, &old_set, sizeof(*oset))) return -EFAULT; } return 0; } #endif /* __ARCH_WANT_SYS_SIGPROCMASK */ #ifndef CONFIG_ODD_RT_SIGACTION /** * sys_rt_sigaction - alter an action taken by a process * @sig: signal to be sent * @act: new sigaction * @oact: used to save the previous sigaction * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE4(rt_sigaction, int, sig, const struct sigaction __user *, act, struct sigaction __user *, oact, size_t, sigsetsize) { struct k_sigaction new_sa, old_sa; int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (act && copy_from_user(&new_sa.sa, act, sizeof(new_sa.sa))) return -EFAULT; ret = do_sigaction(sig, act ? &new_sa : NULL, oact ? &old_sa : NULL); if (ret) return ret; if (oact && copy_to_user(oact, &old_sa.sa, sizeof(old_sa.sa))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_sigaction, int, sig, const struct compat_sigaction __user *, act, struct compat_sigaction __user *, oact, compat_size_t, sigsetsize) { struct k_sigaction new_ka, old_ka; #ifdef __ARCH_HAS_SA_RESTORER compat_uptr_t restorer; #endif int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(compat_sigset_t)) return -EINVAL; if (act) { compat_uptr_t handler; ret = get_user(handler, &act->sa_handler); new_ka.sa.sa_handler = compat_ptr(handler); #ifdef __ARCH_HAS_SA_RESTORER ret |= get_user(restorer, &act->sa_restorer); new_ka.sa.sa_restorer = compat_ptr(restorer); #endif ret |= get_compat_sigset(&new_ka.sa.sa_mask, &act->sa_mask); ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags); if (ret) return -EFAULT; } ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { ret = put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler); ret |= put_compat_sigset(&oact->sa_mask, &old_ka.sa.sa_mask, sizeof(oact->sa_mask)); ret |= put_user(old_ka.sa.sa_flags, &oact->sa_flags); #ifdef __ARCH_HAS_SA_RESTORER ret |= put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer); #endif } return ret; } #endif #endif /* !CONFIG_ODD_RT_SIGACTION */ #ifdef CONFIG_OLD_SIGACTION SYSCALL_DEFINE3(sigaction, int, sig, const struct old_sigaction __user *, act, struct old_sigaction __user *, oact) { struct k_sigaction new_ka, old_ka; int ret; if (act) { old_sigset_t mask; if (!access_ok(act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || __get_user(new_ka.sa.sa_flags, &act->sa_flags) || __get_user(mask, &act->sa_mask)) return -EFAULT; #ifdef __ARCH_HAS_KA_RESTORER new_ka.ka_restorer = NULL; #endif siginitset(&new_ka.sa.sa_mask, mask); } ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { if (!access_ok(oact, sizeof(*oact)) || __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; } return ret; } #endif #ifdef CONFIG_COMPAT_OLD_SIGACTION COMPAT_SYSCALL_DEFINE3(sigaction, int, sig, const struct compat_old_sigaction __user *, act, struct compat_old_sigaction __user *, oact) { struct k_sigaction new_ka, old_ka; int ret; compat_old_sigset_t mask; compat_uptr_t handler, restorer; if (act) { if (!access_ok(act, sizeof(*act)) || __get_user(handler, &act->sa_handler) || __get_user(restorer, &act->sa_restorer) || __get_user(new_ka.sa.sa_flags, &act->sa_flags) || __get_user(mask, &act->sa_mask)) return -EFAULT; #ifdef __ARCH_HAS_KA_RESTORER new_ka.ka_restorer = NULL; #endif new_ka.sa.sa_handler = compat_ptr(handler); new_ka.sa.sa_restorer = compat_ptr(restorer); siginitset(&new_ka.sa.sa_mask, mask); } ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { if (!access_ok(oact, sizeof(*oact)) || __put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler) || __put_user(ptr_to_compat(old_ka.sa.sa_restorer), &oact->sa_restorer) || __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; } return ret; } #endif #ifdef CONFIG_SGETMASK_SYSCALL /* * For backwards compatibility. Functionality superseded by sigprocmask. */ SYSCALL_DEFINE0(sgetmask) { /* SMP safe */ return current->blocked.sig[0]; } SYSCALL_DEFINE1(ssetmask, int, newmask) { int old = current->blocked.sig[0]; sigset_t newset; siginitset(&newset, newmask); set_current_blocked(&newset); return old; } #endif /* CONFIG_SGETMASK_SYSCALL */ #ifdef __ARCH_WANT_SYS_SIGNAL /* * For backwards compatibility. Functionality superseded by sigaction. */ SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler) { struct k_sigaction new_sa, old_sa; int ret; new_sa.sa.sa_handler = handler; new_sa.sa.sa_flags = SA_ONESHOT | SA_NOMASK; sigemptyset(&new_sa.sa.sa_mask); ret = do_sigaction(sig, &new_sa, &old_sa); return ret ? ret : (unsigned long)old_sa.sa.sa_handler; } #endif /* __ARCH_WANT_SYS_SIGNAL */ #ifdef __ARCH_WANT_SYS_PAUSE SYSCALL_DEFINE0(pause) { while (!signal_pending(current)) { __set_current_state(TASK_INTERRUPTIBLE); schedule(); } return -ERESTARTNOHAND; } #endif static int sigsuspend(sigset_t *set) { current->saved_sigmask = current->blocked; set_current_blocked(set); while (!signal_pending(current)) { __set_current_state(TASK_INTERRUPTIBLE); schedule(); } set_restore_sigmask(); return -ERESTARTNOHAND; } /** * sys_rt_sigsuspend - replace the signal mask for a value with the * @unewset value until a signal is received * @unewset: new signal mask value * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize) { sigset_t newset; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&newset, unewset, sizeof(newset))) return -EFAULT; return sigsuspend(&newset); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(rt_sigsuspend, compat_sigset_t __user *, unewset, compat_size_t, sigsetsize) { sigset_t newset; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) return -EINVAL; if (get_compat_sigset(&newset, unewset)) return -EFAULT; return sigsuspend(&newset); } #endif #ifdef CONFIG_OLD_SIGSUSPEND SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask) { sigset_t blocked; siginitset(&blocked, mask); return sigsuspend(&blocked); } #endif #ifdef CONFIG_OLD_SIGSUSPEND3 SYSCALL_DEFINE3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask) { sigset_t blocked; siginitset(&blocked, mask); return sigsuspend(&blocked); } #endif __weak const char *arch_vma_name(struct vm_area_struct *vma) { return NULL; } static inline void siginfo_buildtime_checks(void) { BUILD_BUG_ON(sizeof(struct siginfo) != SI_MAX_SIZE); /* Verify the offsets in the two siginfos match */ #define CHECK_OFFSET(field) \ BUILD_BUG_ON(offsetof(siginfo_t, field) != offsetof(kernel_siginfo_t, field)) /* kill */ CHECK_OFFSET(si_pid); CHECK_OFFSET(si_uid); /* timer */ CHECK_OFFSET(si_tid); CHECK_OFFSET(si_overrun); CHECK_OFFSET(si_value); /* rt */ CHECK_OFFSET(si_pid); CHECK_OFFSET(si_uid); CHECK_OFFSET(si_value); /* sigchld */ CHECK_OFFSET(si_pid); CHECK_OFFSET(si_uid); CHECK_OFFSET(si_status); CHECK_OFFSET(si_utime); CHECK_OFFSET(si_stime); /* sigfault */ CHECK_OFFSET(si_addr); CHECK_OFFSET(si_trapno); CHECK_OFFSET(si_addr_lsb); CHECK_OFFSET(si_lower); CHECK_OFFSET(si_upper); CHECK_OFFSET(si_pkey); CHECK_OFFSET(si_perf_data); CHECK_OFFSET(si_perf_type); CHECK_OFFSET(si_perf_flags); /* sigpoll */ CHECK_OFFSET(si_band); CHECK_OFFSET(si_fd); /* sigsys */ CHECK_OFFSET(si_call_addr); CHECK_OFFSET(si_syscall); CHECK_OFFSET(si_arch); #undef CHECK_OFFSET /* usb asyncio */ BUILD_BUG_ON(offsetof(struct siginfo, si_pid) != offsetof(struct siginfo, si_addr)); if (sizeof(int) == sizeof(void __user *)) { BUILD_BUG_ON(sizeof_field(struct siginfo, si_pid) != sizeof(void __user *)); } else { BUILD_BUG_ON((sizeof_field(struct siginfo, si_pid) + sizeof_field(struct siginfo, si_uid)) != sizeof(void __user *)); BUILD_BUG_ON(offsetofend(struct siginfo, si_pid) != offsetof(struct siginfo, si_uid)); } #ifdef CONFIG_COMPAT BUILD_BUG_ON(offsetof(struct compat_siginfo, si_pid) != offsetof(struct compat_siginfo, si_addr)); BUILD_BUG_ON(sizeof_field(struct compat_siginfo, si_pid) != sizeof(compat_uptr_t)); BUILD_BUG_ON(sizeof_field(struct compat_siginfo, si_pid) != sizeof_field(struct siginfo, si_pid)); #endif } #if defined(CONFIG_SYSCTL) static struct ctl_table signal_debug_table[] = { #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { .procname = "exception-trace", .data = &show_unhandled_signals, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, #endif }; static int __init init_signal_sysctls(void) { register_sysctl_init("debug", signal_debug_table); return 0; } early_initcall(init_signal_sysctls); #endif /* CONFIG_SYSCTL */ void __init signals_init(void) { siginfo_buildtime_checks(); sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC | SLAB_ACCOUNT); } #ifdef CONFIG_KGDB_KDB #include <linux/kdb.h> /* * kdb_send_sig - Allows kdb to send signals without exposing * signal internals. This function checks if the required locks are * available before calling the main signal code, to avoid kdb * deadlocks. */ void kdb_send_sig(struct task_struct *t, int sig) { static struct task_struct *kdb_prev_t; int new_t, ret; if (!spin_trylock(&t->sighand->siglock)) { kdb_printf("Can't do kill command now.\n" "The sigmask lock is held somewhere else in " "kernel, try again later\n"); return; } new_t = kdb_prev_t != t; kdb_prev_t = t; if (!task_is_running(t) && new_t) { spin_unlock(&t->sighand->siglock); kdb_printf("Process is not RUNNING, sending a signal from " "kdb risks deadlock\n" "on the run queue locks. " "The signal has _not_ been sent.\n" "Reissue the kill command if you want to risk " "the deadlock.\n"); return; } ret = send_signal_locked(sig, SEND_SIG_PRIV, t, PIDTYPE_PID); spin_unlock(&t->sighand->siglock); if (ret) kdb_printf("Fail to deliver Signal %d to process %d.\n", sig, t->pid); else kdb_printf("Signal %d is sent to process %d.\n", sig, t->pid); } #endif /* CONFIG_KGDB_KDB */ |
| 194 194 47 47 138 47 49 148 39 148 185 186 186 186 320 180 185 318 184 186 186 186 319 320 122 247 61 314 3 104 61 45 22 319 80 80 80 1 56 1 1 94 95 59 123 41 41 108 141 133 141 142 59 27 17 17 27 27 48 17 57 59 13 13 58 59 59 95 86 19 62 95 95 95 95 17 250 250 200 95 54 76 250 315 315 315 314 313 315 315 315 314 38 313 320 319 318 319 319 320 219 219 219 218 218 218 219 219 218 219 219 218 219 218 219 219 219 218 218 219 219 219 219 219 219 219 219 219 219 166 51 8 8 8 8 3 5 3 39 6 30 110 64 39 63 39 15 15 8 15 15 15 15 15 15 15 3 15 15 3 15 15 15 15 15 15 15 164 51 128 164 64 128 58 128 128 128 128 128 164 164 3 51 44 11 6 45 10 35 45 45 35 8 6 45 147 79 45 14 38 8 29 25 25 45 45 11 35 45 45 45 45 20 16 32 31 7 7 32 32 39 4 35 35 2 8 8 2 6 6 2 3 8 8 8 39 8 8 49 2 81 151 150 197 15 15 15 3 3 3 3 198 199 199 199 190 19 198 166 81 198 199 233 233 49 81 137 233 124 156 234 233 233 179 87 233 43 179 87 87 234 155 9 17 17 6 17 153 155 75 106 17 106 105 28 9 86 36 27 28 28 28 639 2 643 124 86 40 123 86 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * demand-loading started 01.12.91 - seems it is high on the list of * things wanted, and it should be easy to implement. - Linus */ /* * Ok, demand-loading was easy, shared pages a little bit tricker. Shared * pages started 02.12.91, seems to work. - Linus. * * Tested sharing by executing about 30 /bin/sh: under the old kernel it * would have taken more than the 6M I have free, but it worked well as * far as I could see. * * Also corrected some "invalidate()"s - I wasn't doing enough of them. */ /* * Real VM (paging to/from disk) started 18.12.91. Much more work and * thought has to go into this. Oh, well.. * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. * Found it. Everything seems to work now. * 20.12.91 - Ok, making the swap-device changeable like the root. */ /* * 05.04.94 - Multi-page memory management added for v1.1. * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) * * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include <linux/kernel_stat.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/kmsan.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/pfn_t.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/swapops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> #include <linux/memory-tiers.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <linux/sched/sysctl.h> #include <trace/events/kmem.h> #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "pgalloc-track.h" #include "internal.h" #include "swap.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif #ifndef CONFIG_NUMA unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif static vm_fault_t do_fault(struct vm_fault *vmf); static vm_fault_t do_anonymous_page(struct vm_fault *vmf); static bool vmf_pte_changed(struct vm_fault *vmf); /* * Return true if the original pte was a uffd-wp pte marker (so the pte was * wr-protected). */ static __always_inline bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf) { if (!userfaultfd_wp(vmf->vma)) return false; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return false; return pte_marker_uffd_wp(vmf->orig_pte); } /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end * of ZONE_NORMAL. */ void *high_memory; EXPORT_SYMBOL(high_memory); /* * Randomize the address space (stacks, mmaps, brk, etc.). * * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, * as ancient (libc5 based) binaries can segfault. ) */ int randomize_va_space __read_mostly = #ifdef CONFIG_COMPAT_BRK 1; #else 2; #endif #ifndef arch_wants_old_prefaulted_pte static inline bool arch_wants_old_prefaulted_pte(void) { /* * Transitioning a PTE from 'old' to 'young' can be expensive on * some architectures, even if it's performed in hardware. By * default, "false" means prefaulted entries will be 'young'. */ return false; } #endif static int __init disable_randmaps(char *s) { randomize_va_space = 0; return 1; } __setup("norandmaps", disable_randmaps); unsigned long zero_pfn __read_mostly; EXPORT_SYMBOL(zero_pfn); unsigned long highest_memmap_pfn __read_mostly; /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ static int __init init_zero_pfn(void) { zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member) { trace_rss_stat(mm, member); } /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmd; unsigned long next; unsigned long start; start = addr; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; if (start < floor) return; if (ceiling) { ceiling &= PUD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pud; unsigned long next; unsigned long start; start = addr; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; if (start < floor) return; if (ceiling) { ceiling &= P4D_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pud = pud_offset(p4d, start); p4d_clear(p4d); pud_free_tlb(tlb, pud, start); mm_dec_nr_puds(tlb->mm); } static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4d; unsigned long next; unsigned long start; start = addr; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end); start &= PGDIR_MASK; if (start < floor) return; if (ceiling) { ceiling &= PGDIR_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start); } /* * This function frees user-level page tables of a process. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; /* * The next few lines have given us lots of grief... * * Why are we testing PMD* at this top level? Because often * there will be no work to do at all, and we'd prefer not to * go all the way down to the bottom just to discover that. * * Why all these "- 1"s? Because 0 represents both the bottom * of the address space and the top of it (using -1 for the * top wouldn't help much: the masks would do the wrong thing). * The rule is that addr 0 and floor 0 refer to the bottom of * the address space, but end 0 and ceiling 0 refer to the top * Comparisons need to use "end - 1" and "ceiling - 1" (though * that end 0 case should be mythical). * * Wherever addr is brought up or ceiling brought down, we must * be careful to reject "the opposite 0" before it confuses the * subsequent tests. But what about where end is brought down * by PMD_SIZE below? no, end can't go down to 0 there. * * Whereas we round start (addr) and ceiling down, by different * masks at different levels, in order to test whether a table * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ addr &= PMD_MASK; if (addr < floor) { addr += PMD_SIZE; if (!addr) return; } if (ceiling) { ceiling &= PMD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) end -= PMD_SIZE; if (addr > end - 1) return; /* * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling, bool mm_wr_locked) { struct unlink_vma_file_batch vb; do { unsigned long addr = vma->vm_start; struct vm_area_struct *next; /* * Note: USER_PGTABLES_CEILING may be passed as ceiling and may * be 0. This will underflow and is okay. */ next = mas_find(mas, ceiling - 1); if (unlikely(xa_is_zero(next))) next = NULL; /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ if (mm_wr_locked) vma_start_write(vma); unlink_anon_vmas(vma); if (is_vm_hugetlb_page(vma)) { unlink_file_vma(vma); hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } else { unlink_file_vma_batch_init(&vb); unlink_file_vma_batch_add(&vb, vma); /* * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) { vma = next; next = mas_find(mas, ceiling - 1); if (unlikely(xa_is_zero(next))) next = NULL; if (mm_wr_locked) vma_start_write(vma); unlink_anon_vmas(vma); unlink_file_vma_batch_add(&vb, vma); } unlink_file_vma_batch_final(&vb); free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } vma = next; } while (vma); } void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte) { spinlock_t *ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); /* * Ensure all pte setup (eg. pte page lock and page clearing) are * visible before the pte is made visible to other CPUs by being * put into page tables. * * The other side of the story is the pointer chasing in the page * table walking code (when walking the page table without locking; * ie. most of the time). Fortunately, these data accesses consist * of a chain of data-dependent loads, meaning most CPUs (alpha * being the notable exception) will already guarantee loads are * seen in-order. See the alpha page table accessors for the * smp_rmb() barriers in page table walking code. */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ pmd_populate(mm, pmd, *pte); *pte = NULL; } spin_unlock(ptl); } int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; pmd_install(mm, pmd, &new); if (new) pte_free(mm, new); return 0; } int __pte_alloc_kernel(pmd_t *pmd) { pte_t *new = pte_alloc_one_kernel(&init_mm); if (!new) return -ENOMEM; spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ smp_wmb(); /* See comment in pmd_install() */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); return 0; } static inline void init_rss_vec(int *rss) { memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); } static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); } /* * This function is called to print an error when a bad pte * is found. For example, we might have a PFN-mapped pte in * a region that doesn't allow it. * * The calling function must still handle the error. */ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; return; } if (nr_unshown) { pr_alert("BUG: Bad page map: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; index = linear_page_index(vma, addr); pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps read_folio:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, mapping ? mapping->a_ops->read_folio : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this * case, NULL is returned here. "Normal" mappings do have a struct page. * * There are 2 broad cases. Firstly, an architecture may define a pte_special() * pte bit, in which case this function is trivial. Secondly, an architecture * may not have a spare pte bit, which requires a more complicated scheme, * described below. * * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a * special mapping (even if there are underlying and valid "struct pages"). * COWed pages of a VM_PFNMAP are always normal. * * The way we recognize COWed pages within VM_PFNMAP mappings is through the * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit * set, and the vm_pgoff will point to the first PFN mapped: thus every special * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * * And for normal mappings this is false. * * This restricts such mappings to be a linear translation from virtual address * to pfn. To get around this restriction, we allow arbitrary mappings so long * as the vma is not a COW mapping; in that case, we know that all ptes are * special (because none can have been COWed). * * * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. * * VM_MIXEDMAP mappings can likewise contain memory with or without "struct * page" backing, however the difference is that _all_ pages with a struct * page (that is, those where pfn_valid is true) are refcounted and considered * normal pages by the VM. The only exception are zeropages, which are * *never* refcounted. * * The disadvantage is that pages are refcounted (which can be slower and * simply not an option for some PFNMAP users). The advantage is that we * don't have to follow the strict linearity rule of PFNMAP mappings in * order to support COWable mappings. * */ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { unsigned long pfn = pte_pfn(pte); if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { if (likely(!pte_special(pte))) goto check_pfn; if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) /* * NOTE: New users of ZONE_DEVICE will not set pte_devmap() * and will have refcounts incremented on their struct pages * when they are inserted into PTEs, thus they are safe to * return here. Legacy ZONE_DEVICE pages that set pte_devmap() * do not have refcounts. Example of legacy ZONE_DEVICE is * MEMORY_DEVICE_FS_DAX type in pmem or virtio_fs drivers. */ return NULL; print_bad_pte(vma, addr, pte, NULL); return NULL; } /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; if (is_zero_pfn(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (is_zero_pfn(pfn)) return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: VM_WARN_ON_ONCE(is_zero_pfn(pfn)); return pfn_to_page(pfn); } struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { struct page *page = vm_normal_page(vma, addr, pte); if (page) return page_folio(page); return NULL; } #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { unsigned long pfn = pmd_pfn(pmd); /* Currently it's only used for huge pfnmaps */ if (unlikely(pmd_special(pmd))) return NULL; if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (pmd_devmap(pmd)) return NULL; if (is_huge_zero_pmd(pmd)) return NULL; if (unlikely(pfn > highest_memmap_pfn)) return NULL; /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { struct page *page = vm_normal_page_pmd(vma, addr, pmd); if (page) return page_folio(page); return NULL; } #endif static void restore_exclusive_pte(struct vm_area_struct *vma, struct page *page, unsigned long address, pte_t *ptep) { struct folio *folio = page_folio(page); pte_t orig_pte; pte_t pte; swp_entry_t entry; orig_pte = ptep_get(ptep); pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot))); if (pte_swp_soft_dirty(orig_pte)) pte = pte_mksoft_dirty(pte); entry = pte_to_swp_entry(orig_pte); if (pte_swp_uffd_wp(orig_pte)) pte = pte_mkuffd_wp(pte); else if (is_writable_device_exclusive_entry(entry)) pte = maybe_mkwrite(pte_mkdirty(pte), vma); VM_BUG_ON_FOLIO(pte_write(pte) && (!folio_test_anon(folio) && PageAnonExclusive(page)), folio); /* * No need to take a page reference as one was already * created when the swap entry was made. */ if (folio_test_anon(folio)) folio_add_anon_rmap_pte(folio, page, vma, address, RMAP_NONE); else /* * Currently device exclusive access only supports anonymous * memory so the entry shouldn't point to a filebacked page. */ WARN_ON_ONCE(1); set_pte_at(vma->vm_mm, address, ptep, pte); /* * No need to invalidate - it was non-present before. However * secondary CPUs may have mappings that need invalidating. */ update_mmu_cache(vma, address, ptep); } /* * Tries to restore an exclusive pte if the page lock can be acquired without * sleeping. */ static int try_restore_exclusive_pte(pte_t *src_pte, struct vm_area_struct *vma, unsigned long addr) { swp_entry_t entry = pte_to_swp_entry(ptep_get(src_pte)); struct page *page = pfn_swap_entry_to_page(entry); if (trylock_page(page)) { restore_exclusive_pte(vma, page, addr, src_pte); unlock_page(page); return 0; } return -EBUSY; } /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. */ static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long addr, int *rss) { unsigned long vm_flags = dst_vma->vm_flags; pte_t orig_pte = ptep_get(src_pte); pte_t pte = orig_pte; struct folio *folio; struct page *page; swp_entry_t entry = pte_to_swp_entry(orig_pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) return -EIO; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); if (list_empty(&dst_mm->mmlist)) list_add(&dst_mm->mmlist, &src_mm->mmlist); spin_unlock(&mmlist_lock); } /* Mark the swap entry as shared. */ if (pte_swp_exclusive(orig_pte)) { pte = pte_swp_clear_exclusive(orig_pte); set_pte_at(src_mm, addr, src_pte, pte); } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { folio = pfn_swap_entry_folio(entry); rss[mm_counter(folio)]++; if (!is_readable_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both parent and child * to be set to read. A previously exclusive entry is * now shared. */ entry = make_readable_migration_entry( swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(orig_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(orig_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { page = pfn_swap_entry_to_page(entry); folio = page_folio(page); /* * Update rss count even for unaddressable pages, as * they should treated just like normal pages in this * respect. * * We will likely want to have some new rss counters * for unaddressable pages, at some point. But for now * keep things as they are. */ folio_get(folio); rss[mm_counter(folio)]++; /* Cannot fail as these pages cannot get pinned. */ folio_try_dup_anon_rmap_pte(folio, page, src_vma); /* * We do not preserve soft-dirty information, because so * far, checkpoint/restore is the only feature that * requires that. And checkpoint/restore does not work * when a device driver is involved (you cannot easily * save and restore device driver state). */ if (is_writable_device_private_entry(entry) && is_cow_mapping(vm_flags)) { entry = make_readable_device_private_entry( swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(orig_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_exclusive_entry(entry)) { /* * Make device exclusive entries present by restoring the * original entry then copying as for a present pte. Device * exclusive entries currently only support private writable * (ie. COW) mappings. */ VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags)); if (try_restore_exclusive_pte(src_pte, src_vma, addr)) return -EBUSY; return -ENOENT; } else if (is_pte_marker_entry(entry)) { pte_marker marker = copy_pte_marker(entry, dst_vma); if (marker) set_pte_at(dst_mm, addr, dst_pte, make_pte_marker(marker)); return 0; } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } /* * Copy a present and normal page. * * NOTE! The usual case is that this isn't required; * instead, the caller can just increase the page refcount * and re-use the pte the traditional way. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation * code know so that it can do so outside the page table * lock. */ static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct folio **prealloc, struct page *page) { struct folio *new_folio; pte_t pte; new_folio = *prealloc; if (!new_folio) return -EAGAIN; /* * We have a prealloc page, all good! Take it * over and copy the page & arm it. */ if (copy_mc_user_highpage(&new_folio->page, page, addr, src_vma)) return -EHWPOISON; *prealloc = NULL; __folio_mark_uptodate(new_folio); folio_add_new_anon_rmap(new_folio, dst_vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(new_folio, dst_vma); rss[MM_ANONPAGES]++; /* All done, just insert the new page copy in the child */ pte = mk_pte(&new_folio->page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); if (userfaultfd_pte_wp(dst_vma, ptep_get(src_pte))) /* Uffd-wp needs to be delivered to dest pte as well */ pte = pte_mkuffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } static __always_inline void __copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, pte_t pte, unsigned long addr, int nr) { struct mm_struct *src_mm = src_vma->vm_mm; /* If it's a COW mapping, write protect it both processes. */ if (is_cow_mapping(src_vma->vm_flags) && pte_write(pte)) { wrprotect_ptes(src_mm, addr, src_pte, nr); pte = pte_wrprotect(pte); } /* If it's a shared mapping, mark it clean in the child. */ if (src_vma->vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_ptes(dst_vma->vm_mm, addr, dst_pte, pte, nr); } /* * Copy one present PTE, trying to batch-process subsequent PTEs that map * consecutive pages of the same folio by copying them as well. * * Returns -EAGAIN if one preallocated page is required to copy the next PTE. * Otherwise, returns the number of copied PTEs (at least 1). */ static inline int copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, pte_t pte, unsigned long addr, int max_nr, int *rss, struct folio **prealloc) { struct page *page; struct folio *folio; bool any_writable; fpb_t flags = 0; int err, nr; page = vm_normal_page(src_vma, addr, pte); if (unlikely(!page)) goto copy_pte; folio = page_folio(page); /* * If we likely have to copy, just don't bother with batching. Make * sure that the common "small folio" case is as fast as possible * by keeping the batching logic separate. */ if (unlikely(!*prealloc && folio_test_large(folio) && max_nr != 1)) { if (src_vma->vm_flags & VM_SHARED) flags |= FPB_IGNORE_DIRTY; if (!vma_soft_dirty_enabled(src_vma)) flags |= FPB_IGNORE_SOFT_DIRTY; nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags, &any_writable, NULL, NULL); folio_ref_add(folio, nr); if (folio_test_anon(folio)) { if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page, nr, src_vma))) { folio_ref_sub(folio, nr); return -EAGAIN; } rss[MM_ANONPAGES] += nr; VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio); } else { folio_dup_file_rmap_ptes(folio, page, nr); rss[mm_counter_file(folio)] += nr; } if (any_writable) pte = pte_mkwrite(pte, src_vma); __copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, addr, nr); return nr; } folio_get(folio); if (folio_test_anon(folio)) { /* * If this page may have been pinned by the parent process, * copy the page immediately for the child so that we'll always * guarantee the pinned page won't be randomly replaced in the * future. */ if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, src_vma))) { /* Page may be pinned, we have to copy. */ folio_put(folio); err = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, addr, rss, prealloc, page); return err ? err : 1; } rss[MM_ANONPAGES]++; VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio); } else { folio_dup_file_rmap_pte(folio, page); rss[mm_counter_file(folio)]++; } copy_pte: __copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, addr, 1); return 1; } static inline struct folio *folio_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, unsigned long addr, bool need_zero) { struct folio *new_folio; if (need_zero) new_folio = vma_alloc_zeroed_movable_folio(vma, addr); else new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false); if (!new_folio) return NULL; if (mem_cgroup_charge(new_folio, src_mm, GFP_KERNEL)) { folio_put(new_folio); return NULL; } folio_throttle_swaprate(new_folio, GFP_KERNEL); return new_folio; } static int copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; pte_t ptent; spinlock_t *src_ptl, *dst_ptl; int progress, max_nr, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; struct folio *prealloc = NULL; int nr; again: progress = 0; init_rss_vec(rss); /* * copy_pmd_range()'s prior pmd_none_or_clear_bad(src_pmd), and the * error handling here, assume that exclusive mmap_lock on dst and src * protects anon from unexpected THP transitions; with shmem and file * protected by mmap_lock-less collapse skipping areas with anon_vma * (whereas vma_needs_copy() skips areas without anon_vma). A rework * can remove such assumptions later, but this is good enough for now. */ dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) { ret = -ENOMEM; goto out; } src_pte = pte_offset_map_nolock(src_mm, src_pmd, addr, &src_ptl); if (!src_pte) { pte_unmap_unlock(dst_pte, dst_ptl); /* ret == 0 */ goto out; } spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { nr = 1; /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ if (progress >= 32) { progress = 0; if (need_resched() || spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } ptent = ptep_get(src_pte); if (pte_none(ptent)) { progress++; continue; } if (unlikely(!pte_present(ptent))) { ret = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, dst_vma, src_vma, addr, rss); if (ret == -EIO) { entry = pte_to_swp_entry(ptep_get(src_pte)); break; } else if (ret == -EBUSY) { break; } else if (!ret) { progress += 8; continue; } ptent = ptep_get(src_pte); VM_WARN_ON_ONCE(!pte_present(ptent)); /* * Device exclusive entry restored, continue by copying * the now present pte. */ WARN_ON_ONCE(ret != -ENOENT); } /* copy_present_ptes() will clear `*prealloc' if consumed */ max_nr = (end - addr) / PAGE_SIZE; ret = copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, ptent, addr, max_nr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. * If copy failed due to hwpoison in source page, break out. */ if (unlikely(ret == -EAGAIN || ret == -EHWPOISON)) break; if (unlikely(prealloc)) { /* * pre-alloc page cannot be reused by next time so as * to strictly follow mempolicy (e.g., alloc_page_vma() * will allocate page according to address). This * could only happen if one pinned pte changed. */ folio_put(prealloc); prealloc = NULL; } nr = ret; progress += 8 * nr; } while (dst_pte += nr, src_pte += nr, addr += PAGE_SIZE * nr, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(orig_src_pte, src_ptl); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (ret == -EIO) { VM_WARN_ON_ONCE(!entry.val); if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; } else if (ret == -EBUSY || unlikely(ret == -EHWPOISON)) { goto out; } else if (ret == -EAGAIN) { prealloc = folio_prealloc(src_mm, src_vma, addr, false); if (!prealloc) return -ENOMEM; } else if (ret < 0) { VM_WARN_ON_ONCE(1); } /* We've captured and resolved the error. Reset, try again. */ ret = 0; if (addr != end) goto again; out: if (unlikely(prealloc)) folio_put(prealloc); return ret; } static inline int copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); if (!dst_pmd) return -ENOMEM; src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } static inline int copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } static inline int copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); if (!dst_p4d) return -ENOMEM; src_p4d = p4d_offset(src_pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } /* * Return true if the vma needs to copy the pgtable during this fork(). Return * false when we can speed up fork() by allowing lazy page faults later until * when the child accesses the memory range. */ static bool vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { /* * Always copy pgtables when dst_vma has uffd-wp enabled even if it's * file-backed (e.g. shmem). Because when uffd-wp is enabled, pgtable * contains uffd-wp protection information, that's something we can't * retrieve from page cache, and skip copying will lose those info. */ if (userfaultfd_wp(dst_vma)) return true; if (src_vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return true; if (src_vma->anon_vma) return true; /* * Don't copy ptes where a page fault will fill them correctly. Fork * becomes much lighter when there are big shared or private readonly * mappings. The tradeoff is that copy_page_range is more efficient * than faulting. */ return false; } int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; if (!vma_needs_copy(dst_vma, src_vma)) return 0; if (is_vm_hugetlb_page(src_vma)) return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ ret = track_pfn_copy(src_vma); if (ret) return ret; } /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as * the read side doesn't spin, but goes to the mmap_lock. * * Use the raw variant of the seqcount_t write API to avoid * lockdep complaining about preemptibility. */ vma_assert_write_locked(src_vma); raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { untrack_pfn_clear(dst_vma); ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); if (is_cow) { raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } return ret; } /* Whether we should zap all COWed (private) pages too */ static inline bool should_zap_cows(struct zap_details *details) { /* By default, zap all pages */ if (!details) return true; /* Or, we zap COWed pages only if the caller wants to */ return details->even_cows; } /* Decides whether we should zap this folio with the folio pointer specified */ static inline bool should_zap_folio(struct zap_details *details, struct folio *folio) { /* If we can make a decision without *folio.. */ if (should_zap_cows(details)) return true; /* Otherwise we should only zap non-anon folios */ return !folio_test_anon(folio); } static inline bool zap_drop_file_uffd_wp(struct zap_details *details) { if (!details) return false; return details->zap_flags & ZAP_FLAG_DROP_MARKER; } /* * This function makes sure that we'll replace the none pte with an uffd-wp * swap special pte marker when necessary. Must be with the pgtable lock held. */ static inline void zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, int nr, struct zap_details *details, pte_t pteval) { /* Zap on anonymous always means dropping everything */ if (vma_is_anonymous(vma)) return; if (zap_drop_file_uffd_wp(details)) return; for (;;) { /* the PFN in the PTE is irrelevant. */ pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); if (--nr == 0) break; pte++; addr += PAGE_SIZE; } } static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, struct folio *folio, struct page *page, pte_t *pte, pte_t ptent, unsigned int nr, unsigned long addr, struct zap_details *details, int *rss, bool *force_flush, bool *force_break) { struct mm_struct *mm = tlb->mm; bool delay_rmap = false; if (!folio_test_anon(folio)) { ptent = get_and_clear_full_ptes(mm, addr, pte, nr, tlb->fullmm); if (pte_dirty(ptent)) { folio_mark_dirty(folio); if (tlb_delay_rmap(tlb)) { delay_rmap = true; *force_flush = true; } } if (pte_young(ptent) && likely(vma_has_recency(vma))) folio_mark_accessed(folio); rss[mm_counter(folio)] -= nr; } else { /* We don't need up-to-date accessed/dirty bits. */ clear_full_ptes(mm, addr, pte, nr, tlb->fullmm); rss[MM_ANONPAGES] -= nr; } /* Checking a single PTE in a batch is sufficient. */ arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entries(tlb, pte, nr, addr); if (unlikely(userfaultfd_pte_wp(vma, ptent))) zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); if (!delay_rmap) { folio_remove_rmap_ptes(folio, page, nr, vma); if (unlikely(folio_mapcount(folio) < 0)) print_bad_pte(vma, addr, ptent, page); } if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) { *force_flush = true; *force_break = true; } } /* * Zap or skip at least one present PTE, trying to batch-process subsequent * PTEs that map consecutive pages of the same folio. * * Returns the number of processed (skipped or zapped) PTEs (at least 1). */ static inline int zap_present_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, pte_t *pte, pte_t ptent, unsigned int max_nr, unsigned long addr, struct zap_details *details, int *rss, bool *force_flush, bool *force_break) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; struct mm_struct *mm = tlb->mm; struct folio *folio; struct page *page; int nr; page = vm_normal_page(vma, addr, ptent); if (!page) { /* We don't need up-to-date accessed/dirty bits. */ ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entry(tlb, pte, addr); if (userfaultfd_pte_wp(vma, ptent)) zap_install_uffd_wp_if_needed(vma, addr, pte, 1, details, ptent); ksm_might_unmap_zero_page(mm, ptent); return 1; } folio = page_folio(page); if (unlikely(!should_zap_folio(details, folio))) return 1; /* * Make sure that the common "small folio" case is as fast as possible * by keeping the batching logic separate. */ if (unlikely(folio_test_large(folio) && max_nr != 1)) { nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags, NULL, NULL, NULL); zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, addr, details, rss, force_flush, force_break); return nr; } zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr, details, rss, force_flush, force_break); return 1; } static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { bool force_flush = false, force_break = false; struct mm_struct *mm = tlb->mm; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; swp_entry_t entry; int nr; tlb_change_page_size(tlb, PAGE_SIZE); init_rss_vec(rss); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!pte) return addr; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = ptep_get(pte); struct folio *folio; struct page *page; int max_nr; nr = 1; if (pte_none(ptent)) continue; if (need_resched()) break; if (pte_present(ptent)) { max_nr = (end - addr) / PAGE_SIZE; nr = zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr, details, rss, &force_flush, &force_break); if (unlikely(force_break)) { addr += nr * PAGE_SIZE; break; } continue; } entry = pte_to_swp_entry(ptent); if (is_device_private_entry(entry) || is_device_exclusive_entry(entry)) { page = pfn_swap_entry_to_page(entry); folio = page_folio(page); if (unlikely(!should_zap_folio(details, folio))) continue; /* * Both device private/exclusive mappings should only * work with anonymous page so far, so we don't need to * consider uffd-wp bit when zap. For more information, * see zap_install_uffd_wp_if_needed(). */ WARN_ON_ONCE(!vma_is_anonymous(vma)); rss[mm_counter(folio)]--; if (is_device_private_entry(entry)) folio_remove_rmap_pte(folio, page, vma); folio_put(folio); } else if (!non_swap_entry(entry)) { max_nr = (end - addr) / PAGE_SIZE; nr = swap_pte_batch(pte, max_nr, ptent); /* Genuine swap entries, hence a private anon pages */ if (!should_zap_cows(details)) continue; rss[MM_SWAPENTS] -= nr; free_swap_and_cache_nr(entry, nr); } else if (is_migration_entry(entry)) { folio = pfn_swap_entry_folio(entry); if (!should_zap_folio(details, folio)) continue; rss[mm_counter(folio)]--; } else if (pte_marker_entry_uffd_wp(entry)) { /* * For anon: always drop the marker; for file: only * drop the marker if explicitly requested. */ if (!vma_is_anonymous(vma) && !zap_drop_file_uffd_wp(details)) continue; } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { if (!should_zap_cows(details)) continue; } else { /* We should have covered all the swap entry types */ pr_alert("unrecognized swap entry 0x%lx\n", entry.val); WARN_ON_ONCE(1); } clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ if (force_flush) { tlb_flush_mmu_tlbonly(tlb); tlb_flush_rmaps(tlb, vma); } pte_unmap_unlock(start_pte, ptl); /* * If we forced a TLB flush (either due to running out of * batch buffers or because we needed to flush dirty TLB * entries before releasing the ptl), free the batched * memory too. Come back again if we didn't do everything. */ if (force_flush) tlb_flush_mmu(tlb); return addr; } static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); else if (zap_huge_pmd(tlb, vma, pmd, addr)) { addr = next; continue; } /* fall through */ } else if (details && details->single_folio && folio_test_pmd_mappable(details->single_folio) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* * Take and drop THP pmd lock so that we cannot return * prematurely, while zap_huge_pmd() has cleared *pmd, * but not yet decremented compound_mapcount(). */ spin_unlock(ptl); } if (pmd_none(*pmd)) { addr = next; continue; } addr = zap_pte_range(tlb, vma, pmd, addr, next, details); if (addr != next) pmd--; } while (pmd++, cond_resched(), addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { if (next - addr != HPAGE_PUD_SIZE) { mmap_assert_locked(tlb->mm); split_huge_pud(vma, pud, addr); } else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); next: cond_resched(); } while (pud++, addr = next, addr != end); return addr; } static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end); return addr; } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details) { pgd_t *pgd; unsigned long next; BUG_ON(addr >= end); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } static void unmap_single_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details, bool mm_wr_locked) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; if (start >= vma->vm_end) return; end = min(vma->vm_end, end_addr); if (end <= vma->vm_start) return; if (vma->vm_file) uprobe_munmap(vma, start, end); if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn(vma, 0, 0, mm_wr_locked); if (start != end) { if (unlikely(is_vm_hugetlb_page(vma))) { /* * It is undesirable to test vma->vm_file as it * should be non-null for valid hugetlb area. * However, vm_file will be NULL in the error * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. */ if (vma->vm_file) { zap_flags_t zap_flags = details ? details->zap_flags : 0; __unmap_hugepage_range(tlb, vma, start, end, NULL, zap_flags); } } else unmap_page_range(tlb, vma, start, end, details); } } /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather * @mas: the maple state * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping * @tree_end: The maximum index to check * @mm_wr_locked: lock flag * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. * * unmap_vmas() assumes that the caller will flush the whole unmapped address * range after unmap_vmas() returns. So the only responsibility here is to * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, unsigned long tree_end, bool mm_wr_locked) { struct mmu_notifier_range range; struct zap_details details = { .zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP, /* Careful - we need to zap private pages too! */ .even_cows = true, }; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); do { unsigned long start = start_addr; unsigned long end = end_addr; hugetlb_zap_begin(vma, &start, &end); unmap_single_vma(tlb, vma, start, end, &details, mm_wr_locked); hugetlb_zap_end(vma, &details); vma = mas_find(mas, tree_end - 1); } while (vma && likely(!xa_is_zero(vma))); mmu_notifier_invalidate_range_end(&range); } /** * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of shared cache invalidation * * The range must fit into one VMA. */ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { const unsigned long end = address + size; struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, end); hugetlb_zap_begin(vma, &range.start, &range.end); tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); /* * unmap 'address-end' not 'range.start-range.end' as range * could have been expanded for hugetlb pmd sharing. */ unmap_single_vma(&tlb, vma, address, end, details, false); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); hugetlb_zap_end(vma, details); } /** * zap_vma_ptes - remove ptes mapping the vma * @vma: vm_area_struct holding ptes to be zapped * @address: starting address of pages to zap * @size: number of bytes to zap * * This function only unmaps ptes assigned to VM_PFNMAP vmas. * * The entire address range must be fully contained within the vma. * */ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (!range_in_vma(vma, address, address + size) || !(vma->vm_flags & VM_PFNMAP)) return; zap_page_range_single(vma, address, size, NULL); } EXPORT_SYMBOL_GPL(zap_vma_ptes); static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; } pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pmd_t *pmd = walk_to_pmd(mm, addr); if (!pmd) return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } static bool vm_mixed_zeropage_allowed(struct vm_area_struct *vma) { VM_WARN_ON_ONCE(vma->vm_flags & VM_PFNMAP); /* * Whoever wants to forbid the zeropage after some zeropages * might already have been mapped has to scan the page tables and * bail out on any zeropages. Zeropages in COW mappings can * be unshared using FAULT_FLAG_UNSHARE faults. */ if (mm_forbids_zeropage(vma->vm_mm)) return false; /* zeropages in COW mappings are common and unproblematic. */ if (is_cow_mapping(vma->vm_flags)) return true; /* Mappings that do not allow for writable PTEs are unproblematic. */ if (!(vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) return true; /* * Why not allow any VMA that has vm_ops->pfn_mkwrite? GUP could * find the shared zeropage and longterm-pin it, which would * be problematic as soon as the zeropage gets replaced by a different * page due to vma->vm_ops->pfn_mkwrite, because what's mapped would * now differ to what GUP looked up. FSDAX is incompatible to * FOLL_LONGTERM and VM_IO is incompatible to GUP completely (see * check_vma_flags). */ return vma->vm_ops && vma->vm_ops->pfn_mkwrite && (vma_is_fsdax(vma) || vma->vm_flags & VM_IO); } static int validate_page_before_insert(struct vm_area_struct *vma, struct page *page) { struct folio *folio = page_folio(page); if (!folio_ref_count(folio)) return -EINVAL; if (unlikely(is_zero_folio(folio))) { if (!vm_mixed_zeropage_allowed(vma)) return -EINVAL; return 0; } if (folio_test_anon(folio) || folio_test_slab(folio) || page_has_type(page)) return -EINVAL; flush_dcache_folio(folio); return 0; } static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { struct folio *folio = page_folio(page); pte_t pteval; if (!pte_none(ptep_get(pte))) return -EBUSY; /* Ok, finally just insert the thing.. */ pteval = mk_pte(page, prot); if (unlikely(is_zero_folio(folio))) { pteval = pte_mkspecial(pteval); } else { folio_get(folio); inc_mm_counter(vma->vm_mm, mm_counter_file(folio)); folio_add_file_rmap_pte(folio, page, vma); } set_pte_at(vma->vm_mm, addr, pte, pteval); return 0; } static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { int retval; pte_t *pte; spinlock_t *ptl; retval = validate_page_before_insert(vma, page); if (retval) goto out; retval = -ENOMEM; pte = get_locked_pte(vma->vm_mm, addr, &ptl); if (!pte) goto out; retval = insert_page_into_pte_locked(vma, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; err = validate_page_before_insert(vma, page); if (err) return err; return insert_page_into_pte_locked(vma, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations * when inserting pages in a loop. */ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; pte_t *start_pte, *pte; spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; unsigned long pages_to_write_in_pmd; int ret; more: ret = -EFAULT; pmd = walk_to_pmd(mm, addr); if (!pmd) goto out; pages_to_write_in_pmd = min_t(unsigned long, remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); /* Allocate the PTE if necessary; takes PMD lock once only. */ ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); if (!start_pte) { ret = -EFAULT; goto out; } for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { int err = insert_page_in_batch_locked(vma, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; } addr += PAGE_SIZE; ++curr_page_idx; } pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } if (remaining_pages_total) goto more; ret = 0; out: *num = remaining_pages_total; return ret; } /** * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. * @vma: user vma to map to * @addr: target start user address of these pages * @pages: source kernel pages * @num: in: number of pages to map. out: number of pages that were *not* * mapped. (0 means all pages were successfully mapped). * * Preferred over vm_insert_page() when inserting multiple pages. * * In case of error, we may have mapped a subset of the provided * pages. It is the caller's responsibility to account for this case. * * The same restrictions apply as in vm_insert_page(). */ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num) { const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; if (addr < vma->vm_start || end_addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vm_flags_set(vma, VM_MIXEDMAP); } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_pages); /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to * @addr: target user address of this page * @page: source kernel page * * This allows drivers to insert individual pages they've allocated * into a user vma. The zeropage is supported in some VMAs, * see vm_mixed_zeropage_allowed(). * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as * such (__GFP_COMP), or manually just split the page up yourself * (see split_page()). * * NOTE! Traditionally this was done with "remap_pfn_range()" which * took an arbitrary page protection parameter. This doesn't allow * that. Your vma protection will have to be set up correctly, which * means that if you want a shared writable mapping, you'd better * ask for a shared writable mapping! * * The page does not need to be reserved. * * Usually this function is called from f_op->mmap() handler * under mm->mmap_lock write-lock, so it can change vma->vm_flags. * Caller must set VM_MIXEDMAP on vma if it wants to call this * function from other places, for example from page-fault handler. * * Return: %0 on success, negative error code otherwise. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vm_flags_set(vma, VM_MIXEDMAP); } return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); /* * __vm_map_pages - maps range of kernel pages into user vma * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * @offset: user's requested vm_pgoff * * This allows drivers to map range of kernel pages into a user vma. * The zeropage is supported in some VMAs, see * vm_mixed_zeropage_allowed(). * * Return: 0 on success and error code otherwise. */ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num, unsigned long offset) { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; int ret, i; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ if (count > num - offset) return -ENXIO; for (i = 0; i < count; i++) { ret = vm_insert_page(vma, uaddr, pages[offset + i]); if (ret < 0) return ret; uaddr += PAGE_SIZE; } return 0; } /** * vm_map_pages - maps range of kernel pages starts with non zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Maps an object consisting of @num pages, catering for the user's * requested vm_pgoff * * If we fail to insert any page into the vma, the function will return * immediately leaving any previously inserted pages present. Callers * from the mmap handler may immediately return the error as their caller * will destroy the vma, removing any successfully inserted pages. Other * callers should make their own arrangements for calling unmap_region(). * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, vma->vm_pgoff); } EXPORT_SYMBOL(vm_map_pages); /** * vm_map_pages_zero - map range of kernel pages starts with zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Similar to vm_map_pages(), except that it explicitly sets the offset * to 0. This function is intended for the drivers that did not consider * vm_pgoff. * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, 0); } EXPORT_SYMBOL(vm_map_pages_zero); static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, entry; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) return VM_FAULT_OOM; entry = ptep_get(pte); if (!pte_none(entry)) { if (mkwrite) { /* * For read faults on private mappings the PFN passed * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared * mapping and we expect the PFNs to match. If they * don't match, we are likely racing with block * allocation and mapping invalidation so just skip the * update. */ if (pte_pfn(entry) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(entry))); goto out_unlock; } entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } goto out_unlock; } /* Ok, finally just insert the thing.. */ if (pfn_t_devmap(pfn)) entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); } set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ out_unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * * pgprot typically only differs from @vma->vm_page_prot when drivers set * caching- and encryption bits different than those of @vma->vm_page_prot, * because the caching- or encryption mode may not be known at mmap() time. * * This is ok as long as @vma->vm_page_prot is not used by the core vm * to set caching and encryption bits for those vmas (except for COW pages). * This is ensured by core vm only modifying these page table entries using * functions that don't touch caching- or encryption bits, using pte_modify() * if needed. (See for example mprotect()). * * Also when new page-table entries are created, this is only done using the * fault() callback, and never using the value of vma->vm_page_prot, * except for page-table entries that point to anonymous pages as the result * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like * consistency in testing and feature parity among all, so we should * try to keep these invariants in place for everybody. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, false); } EXPORT_SYMBOL(vmf_insert_pfn_prot); /** * vmf_insert_pfn - insert single pfn into user vma * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * * Similar to vm_insert_page, this allows drivers to insert individual pages * they've allocated into a user vma. Same comments apply. * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return the result of this function. * * vma cannot be a COW mapping. * * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); } EXPORT_SYMBOL(vmf_insert_pfn); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn, bool mkwrite) { if (unlikely(is_zero_pfn(pfn_t_to_pfn(pfn))) && (mkwrite || !vm_mixed_zeropage_allowed(vma))) return false; /* these checks mirror the abort conditions in vm_normal_page */ if (vma->vm_flags & VM_MIXEDMAP) return true; if (pfn_t_devmap(pfn)) return true; if (pfn_t_special(pfn)) return true; if (is_zero_pfn(pfn_t_to_pfn(pfn))) return true; return false; } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, bool mkwrite) { pgprot_t pgprot = vma->vm_page_prot; int err; if (!vm_mixed_ok(vma, pfn, mkwrite)) return VM_FAULT_SIGBUS; if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; /* * At this point we are committed to insert_page() * regardless of whether the caller specified flags that * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); err = insert_page(vma, addr, page, pgprot); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, false); } EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, true); } /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results * in null mappings (currently treated as "copy-on-access") */ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(ptep_get(pte))); if (!pfn_modify_allowed(pfn, prot)) { err = -EACCES; break; } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(mapped_pte, ptl); return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); err = remap_pte_range(mm, pmd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pmd++, addr = next, addr != end); return 0; } static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); err = remap_pmd_range(mm, pud, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pud++, addr = next, addr != end); return 0; } static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { p4d_t *p4d; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); err = remap_pud_range(mm, p4d, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (p4d++, addr = next, addr != end); return 0; } static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; int err; if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; /* * Physically remapped pages are special. Tell the * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). * VM_PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. * VM_DONTEXPAND * Disable vma merging and expanding with mremap(). * VM_DONTDUMP * Omit vma from core dump, even when VM_IO turned off. * * There's a horrible special case to handle copy-on-write * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". * See vm_normal_page() for details. */ if (is_cow_mapping(vma->vm_flags)) { if (addr != vma->vm_start || end != vma->vm_end) return -EINVAL; vma->vm_pgoff = pfn; } vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pgd++, addr = next, addr != end); return 0; } /* * Variant of remap_pfn_range that does not call track_pfn_remap. The caller * must have pre-validated the caching bits of the pgprot_t. */ int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int error = remap_pfn_range_internal(vma, addr, pfn, size, prot); if (!error) return 0; /* * A partial pfn range mapping is dangerous: it does not * maintain page reference counts, and callers may free * pages due to the error. So zap it early. */ zap_page_range_single(vma, addr, size, NULL); return error; } /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to * @addr: target page aligned user address to start at * @pfn: page frame number of kernel physical memory address * @size: size of mapping area * @prot: page protection flags for this mapping * * Note: this is only safe if the mm semaphore is held when called. * * Return: %0 on success, negative error code otherwise. */ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int err; err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; err = remap_pfn_range_notrack(vma, addr, pfn, size, prot); if (err) untrack_pfn(vma, pfn, PAGE_ALIGN(size), true); return err; } EXPORT_SYMBOL(remap_pfn_range); /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The * driver just needs to give us the physical memory range to be mapped, * we'll figure out the rest from the vma information. * * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get * whatever write-combining details or similar. * * Return: %0 on success, negative error code otherwise. */ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) { unsigned long vm_len, pfn, pages; /* Check that the physical memory area passed in looks valid */ if (start + len < start) return -EINVAL; /* * You *really* shouldn't map things that aren't page-aligned, * but we've historically allowed it because IO memory might * just have smaller alignment. */ len += start & ~PAGE_MASK; pfn = start >> PAGE_SHIFT; pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; if (pfn + pages < pfn) return -EINVAL; /* We start the mapping 'vm_pgoff' pages into the area */ if (vma->vm_pgoff > pages) return -EINVAL; pfn += vma->vm_pgoff; pages -= vma->vm_pgoff; /* Can we fit all of the mapping? */ vm_len = vma->vm_end - vma->vm_start; if (vm_len >> PAGE_SHIFT > pages) return -EINVAL; /* Ok, let it rip */ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); } EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pte_t *pte, *mapped_pte; int err = 0; spinlock_t *ptl; if (create) { mapped_pte = pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; } else { mapped_pte = pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); if (!pte) return -EINVAL; } arch_enter_lazy_mmu_mode(); if (fn) { do { if (create || !pte_none(ptep_get(pte))) { err = fn(pte++, addr, data); if (err) break; } } while (addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; arch_leave_lazy_mmu_mode(); if (mm != &init_mm) pte_unmap_unlock(mapped_pte, ptl); return err; } static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; BUG_ON(pud_leaf(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { pmd = pmd_offset(pud, addr); } do { next = pmd_addr_end(addr, end); if (pmd_none(*pmd) && !create) continue; if (WARN_ON_ONCE(pmd_leaf(*pmd))) return -EINVAL; if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) { if (!create) continue; pmd_clear_bad(pmd); } err = apply_to_pte_range(mm, pmd, addr, next, fn, data, create, mask); if (err) break; } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { pud = pud_offset(p4d, addr); } do { next = pud_addr_end(addr, end); if (pud_none(*pud) && !create) continue; if (WARN_ON_ONCE(pud_leaf(*pud))) return -EINVAL; if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) { if (!create) continue; pud_clear_bad(pud); } err = apply_to_pmd_range(mm, pud, addr, next, fn, data, create, mask); if (err) break; } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { p4d = p4d_offset(pgd, addr); } do { next = p4d_addr_end(addr, end); if (p4d_none(*p4d) && !create) continue; if (WARN_ON_ONCE(p4d_leaf(*p4d))) return -EINVAL; if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) { if (!create) continue; p4d_clear_bad(p4d); } err = apply_to_pud_range(mm, p4d, addr, next, fn, data, create, mask); if (err) break; } while (p4d++, addr = next, addr != end); return err; } static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data, bool create) { pgd_t *pgd; unsigned long start = addr, next; unsigned long end = addr + size; pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none(*pgd) && !create) continue; if (WARN_ON_ONCE(pgd_leaf(*pgd))) return -EINVAL; if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) { if (!create) continue; pgd_clear_bad(pgd); } err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, start + size); return err; } /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, true); } EXPORT_SYMBOL_GPL(apply_to_page_range); /* * Scan a region of virtual memory, calling a provided function on * each leaf page table where it exists. * * Unlike apply_to_page_range, this does _not_ fill in page tables * where they are absent. */ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, false); } EXPORT_SYMBOL_GPL(apply_to_existing_page_range); /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct vm_fault *vmf) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { spin_lock(vmf->ptl); same = pte_same(ptep_get(vmf->pte), vmf->orig_pte); spin_unlock(vmf->ptl); } #endif pte_unmap(vmf->pte); vmf->pte = NULL; return same; } /* * Return: * 0: copied succeeded * -EHWPOISON: copy failed due to hwpoison in source page * -EAGAIN: copied failed (some other reason) */ static inline int __wp_page_copy_user(struct page *dst, struct page *src, struct vm_fault *vmf) { int ret; void *kaddr; void __user *uaddr; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; if (likely(src)) { if (copy_mc_user_highpage(dst, src, addr, vma)) return -EHWPOISON; return 0; } /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ kaddr = kmap_local_page(dst); pagefault_disable(); uaddr = (void __user *)(addr & PAGE_MASK); /* * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ vmf->pte = NULL; if (!arch_has_hw_pte_young() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { /* * Other thread has already handled the fault * and update local tlb only */ if (vmf->pte) update_mmu_tlb(vma, addr, vmf->pte); ret = -EAGAIN; goto pte_unlock; } entry = pte_mkyoung(vmf->orig_pte); if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) update_mmu_cache_range(vmf, vma, addr, vmf->pte, 1); } /* * This really shouldn't fail, because the page is there * in the page tables. But it might just be unreadable, * in which case we just give up and fill the result with * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (vmf->pte) goto warn; /* Re-validate under PTL if the page is still mapped */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { /* The PTE changed under us, update local tlb */ if (vmf->pte) update_mmu_tlb(vma, addr, vmf->pte); ret = -EAGAIN; goto pte_unlock; } /* * The same page can be mapped back since last copy attempt. * Try to copy again under PTL. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* * Give a warn in case there can be some obscure * use-case */ warn: WARN_ON_ONCE(1); clear_page(kaddr); } } ret = 0; pte_unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); pagefault_enable(); kunmap_local(kaddr); flush_dcache_page(dst); return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) { struct file *vm_file = vma->vm_file; if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; /* * Special mappings (e.g. VDSO) do not have any file so fake * a default GFP_KERNEL for them. */ return GFP_KERNEL; } /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. * * We do this without the lock held, so that it can sleep if it needs to. */ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf, struct folio *folio) { vm_fault_t ret; unsigned int old_flags = vmf->flags; vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; if (vmf->vma->vm_file && IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) return VM_FAULT_SIGBUS; ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; if (unlikely(!(ret & VM_FAULT_LOCKED))) { folio_lock(folio); if (!folio->mapping) { folio_unlock(folio); return 0; /* retry */ } ret |= VM_FAULT_LOCKED; } else VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); return ret; } /* * Handle dirtying of a page in shared file mapping on a write fault. * * The function expects the page to be locked and unlocks it. */ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; struct folio *folio = page_folio(vmf->page); bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; dirtied = folio_mark_dirty(folio); VM_BUG_ON_FOLIO(folio_test_anon(folio), folio); /* * Take a local copy of the address_space - folio.mapping may be zeroed * by truncate after folio_unlock(). The address_space itself remains * pinned by vma->vm_file's reference. We rely on folio_unlock()'s * release semantics to prevent the compiler from undoing this copying. */ mapping = folio_raw_mapping(folio); folio_unlock(folio); if (!page_mkwrite) file_update_time(vma->vm_file); /* * Throttle page dirtying rate down to writeback speed. * * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * * Drop the mmap_lock before waiting on IO, if we can. The file * is pinning the mapping, as per above. */ if ((dirtied || page_mkwrite) && mapping) { struct file *fpin; fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); return VM_FAULT_COMPLETED; } } return 0; } /* * Handle write page faults for pages that can be reused in the current vma * * This can happen either due to the mapping being with the VM_SHARED flag, * or due to us being the last reference standing to the page. In either * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ static inline void wp_page_reuse(struct vm_fault *vmf, struct folio *folio) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; pte_t entry; VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE)); VM_WARN_ON(is_zero_pfn(pte_pfn(vmf->orig_pte))); if (folio) { VM_BUG_ON(folio_test_anon(folio) && !PageAnonExclusive(vmf->page)); /* * Clear the folio's cpupid information as the existing * information potentially belongs to a now completely * unrelated process. */ folio_xchg_last_cpupid(folio, (1 << LAST_CPUPID_SHIFT) - 1); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1); pte_unmap_unlock(vmf->pte, vmf->ptl); count_vm_event(PGREUSE); } /* * We could add a bitflag somewhere, but for now, we know that all * vm_ops that have a ->map_pages have been audited and don't need * the mmap_lock to be held. */ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops->map_pages || !(vmf->flags & FAULT_FLAG_VMA_LOCK)) return 0; vma_end_read(vma); return VM_FAULT_RETRY; } /** * __vmf_anon_prepare - Prepare to handle an anonymous fault. * @vmf: The vm_fault descriptor passed from the fault handler. * * When preparing to insert an anonymous page into a VMA from a * fault handler, call this function rather than anon_vma_prepare(). * If this vma does not already have an associated anon_vma and we are * only protected by the per-VMA lock, the caller must retry with the * mmap_lock held. __anon_vma_prepare() will look at adjacent VMAs to * determine if this VMA can share its anon_vma, and that's not safe to * do with only the per-VMA lock held for this VMA. * * Return: 0 if fault handling can proceed. Any other value should be * returned to the caller. */ vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; if (likely(vma->anon_vma)) return 0; if (vmf->flags & FAULT_FLAG_VMA_LOCK) { if (!mmap_read_trylock(vma->vm_mm)) return VM_FAULT_RETRY; } if (__anon_vma_prepare(vma)) ret = VM_FAULT_OOM; if (vmf->flags & FAULT_FLAG_VMA_LOCK) mmap_read_unlock(vma->vm_mm); return ret; } /* * Handle the case of a page which we actually need to copy to a new page, * either due to COW or unsharing. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: * * - Allocate a page, copy the content of the old page to the new one. * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. * - Take the PTL. If the pte changed, bail out and release the allocated page * - If the pte is still the way we remember it, update the page table and all * relevant references. This includes dropping the reference the page-table * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct folio *old_folio = NULL; struct folio *new_folio = NULL; pte_t entry; int page_copied = 0; struct mmu_notifier_range range; vm_fault_t ret; bool pfn_is_zero; delayacct_wpcopy_start(); if (vmf->page) old_folio = page_folio(vmf->page); ret = vmf_anon_prepare(vmf); if (unlikely(ret)) goto out; pfn_is_zero = is_zero_pfn(pte_pfn(vmf->orig_pte)); new_folio = folio_prealloc(mm, vma, vmf->address, pfn_is_zero); if (!new_folio) goto oom; if (!pfn_is_zero) { int err; err = __wp_page_copy_user(&new_folio->page, vmf->page, vmf); if (err) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on * the same address and we will handle the fault * from the second attempt. * The -EHWPOISON case will not be retried. */ folio_put(new_folio); if (old_folio) folio_put(old_folio); delayacct_wpcopy_end(); return err == -EHWPOISON ? VM_FAULT_HWPOISON : 0; } kmsan_copy_page_meta(&new_folio->page, vmf->page); } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); /* * Re-check the pte - we dropped the lock */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { if (old_folio) { if (!folio_test_anon(old_folio)) { dec_mm_counter(mm, mm_counter_file(old_folio)); inc_mm_counter(mm, MM_ANONPAGES); } } else { ksm_might_unmap_zero_page(mm, vmf->orig_pte); inc_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(&new_folio->page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (unlikely(unshare)) { if (pte_soft_dirty(vmf->orig_pte)) entry = pte_mksoft_dirty(entry); if (pte_uffd_wp(vmf->orig_pte)) entry = pte_mkuffd_wp(entry); } else { entry = maybe_mkwrite(pte_mkdirty(entry), vma); } /* * Clear the pte entry and flush it first, before updating the * pte with the new entry, to keep TLBs on different CPUs in * sync. This code used to set the new PTE then flush TLBs, but * that left a window where the new PTE could be loaded into * some TLBs while the old PTE remains in others. */ ptep_clear_flush(vma, vmf->address, vmf->pte); folio_add_new_anon_rmap(new_folio, vma, vmf->address, RMAP_EXCLUSIVE); folio_add_lru_vma(new_folio, vma); BUG_ON(unshare && pte_write(entry)); set_pte_at(mm, vmf->address, vmf->pte, entry); update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1); if (old_folio) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another * process may come and find the rmap count decremented * before the pte is switched to the new page, and * "reuse" the old page writing into it while our pte * here still points into it and can be read by other * threads. * * The critical issue is to order this * folio_remove_rmap_pte() with the ptp_clear_flush * above. Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative * in folio_remove_rmap_pte(); * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the * decremented mapcount is visible. And the old page * cannot be reused until after the decremented * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ folio_remove_rmap_pte(old_folio, vmf->page, vma); } /* Free the old page.. */ new_folio = old_folio; page_copied = 1; pte_unmap_unlock(vmf->pte, vmf->ptl); } else if (vmf->pte) { update_mmu_tlb(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); } mmu_notifier_invalidate_range_end(&range); if (new_folio) folio_put(new_folio); if (old_folio) { if (page_copied) free_swap_cache(old_folio); folio_put(old_folio); } delayacct_wpcopy_end(); return 0; oom: ret = VM_FAULT_OOM; out: if (old_folio) folio_put(old_folio); delayacct_wpcopy_end(); return ret; } /** * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE * writeable once the page is prepared * * @vmf: structure describing the fault * @folio: the folio of vmf->page * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. * It handles locking of PTE and modifying it. * * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before * we acquired PTE lock. */ static vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf, struct folio *folio) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!vmf->pte) return VM_FAULT_NOPAGE; /* * We might have raced with another page fault while we released the * pte_offset_map_lock. */ if (!pte_same(ptep_get(vmf->pte), vmf->orig_pte)) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } wp_page_reuse(vmf, folio); return 0; } /* * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); ret = vmf_can_call_fault(vmf); if (ret) return ret; vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf, NULL); } wp_page_reuse(vmf, NULL); return 0; } static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; folio_get(folio); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = vmf_can_call_fault(vmf); if (tmp) { folio_put(folio); return tmp; } tmp = do_page_mkwrite(vmf, folio); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { folio_put(folio); return tmp; } tmp = finish_mkwrite_fault(vmf, folio); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { folio_unlock(folio); folio_put(folio); return tmp; } } else { wp_page_reuse(vmf, folio); folio_lock(folio); } ret |= fault_dirty_shared_page(vmf); folio_put(folio); return ret; } static bool wp_can_reuse_anon_folio(struct folio *folio, struct vm_area_struct *vma) { /* * We could currently only reuse a subpage of a large folio if no * other subpages of the large folios are still mapped. However, * let's just consistently not reuse subpages even if we could * reuse in that scenario, and give back a large folio a bit * sooner. */ if (folio_test_large(folio)) return false; /* * We have to verify under folio lock: these early checks are * just an optimization to avoid locking the folio and freeing * the swapcache if there is little hope that we can reuse. * * KSM doesn't necessarily raise the folio refcount. */ if (folio_test_ksm(folio) || folio_ref_count(folio) > 3) return false; if (!folio_test_lru(folio)) /* * We cannot easily detect+handle references from * remote LRU caches or references to LRU folios. */ lru_add_drain(); if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio)) return false; if (!folio_trylock(folio)) return false; if (folio_test_swapcache(folio)) folio_free_swap(folio); if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) { folio_unlock(folio); return false; } /* * Ok, we've got the only folio reference from our mapping * and the folio is locked, it's dark out, and we're wearing * sunglasses. Hit it. */ folio_move_anon_rmap(folio, vma); folio_unlock(folio); return true; } /* * This routine handles present pages, when * * users try to write to a shared page (FAULT_FLAG_WRITE) * * GUP wants to take a R/O pin on a possibly shared anonymous page * (FAULT_FLAG_UNSHARE) * * It is done by copying the page to a new address and decrementing the * shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus, with FAULT_FLAG_WRITE, we can safely just mark it writable once we've * done any necessary COW. * * In case of FAULT_FLAG_WRITE, we also mark the page dirty at this point even * though the page will change only once the write actually happens. This * avoids a few races, and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct folio *folio = NULL; pte_t pte; if (likely(!unshare)) { if (userfaultfd_pte_wp(vma, ptep_get(vmf->pte))) { if (!userfaultfd_wp_async(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_WP); } /* * Nothing needed (cache flush, TLB invalidations, * etc.) because we're only removing the uffd-wp bit, * which is completely invisible to the user. */ pte = pte_clear_uffd_wp(ptep_get(vmf->pte)); set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); /* * Update this to be prepared for following up CoW * handling */ vmf->orig_pte = pte; } /* * Userfaultfd write-protect can defer flushes. Ensure the TLB * is flushed in this case before copying. */ if (unlikely(userfaultfd_wp(vmf->vma) && mm_tlb_flush_pending(vmf->vma->vm_mm))) flush_tlb_page(vmf->vma, vmf->address); } vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (vmf->page) folio = page_folio(vmf->page); /* * Shared mapping: we are guaranteed to have VM_WRITE and * FAULT_FLAG_WRITE set at this point. */ if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. * * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if (!vmf->page) return wp_pfn_shared(vmf); return wp_page_shared(vmf, folio); } /* * Private mapping: create an exclusive anonymous page copy if reuse * is impossible. We might miss VM_WRITE for FOLL_FORCE handling. * * If we encounter a page that is marked exclusive, we must reuse * the page without further checks. */ if (folio && folio_test_anon(folio) && (PageAnonExclusive(vmf->page) || wp_can_reuse_anon_folio(folio, vma))) { if (!PageAnonExclusive(vmf->page)) SetPageAnonExclusive(vmf->page); if (unlikely(unshare)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } wp_page_reuse(vmf, folio); return 0; } /* * Ok, we need to copy. Oh, well.. */ if (folio) folio_get(folio); pte_unmap_unlock(vmf->pte, vmf->ptl); #ifdef CONFIG_KSM if (folio && folio_test_ksm(folio)) count_vm_event(COW_KSM); #endif return wp_page_copy(vmf); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, pgoff_t first_index, pgoff_t last_index, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; vma_interval_tree_foreach(vma, root, first_index, last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; zba = max(first_index, vba); zea = min(last_index, vea); unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, details); } } /** * unmap_mapping_folio() - Unmap single folio from processes. * @folio: The locked folio to be unmapped. * * Unmap this folio from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once * truncation or invalidation holds the lock on a folio, it may find that * the page has been remapped again: and then uses unmap_mapping_folio() * to unmap it finally. */ void unmap_mapping_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; struct zap_details details = { }; pgoff_t first_index; pgoff_t last_index; VM_BUG_ON(!folio_test_locked(folio)); first_index = folio->index; last_index = folio_next_index(folio) - 1; details.even_cows = false; details.single_folio = folio; details.zap_flags = ZAP_FLAG_DROP_MARKER; i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, first_index, last_index, &details); i_mmap_unlock_read(mapping); } /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. * @nr: Number of pages to be unmapped. 0 to unmap to end of file. * @even_cows: Whether to unmap even private COWed pages. * * Unmap the pages in this address space from any userspace process which * has them mmaped. Generally, you want to remove COWed pages as well when * a file is being truncated, but not when invalidating pages from the page * cache. */ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; pgoff_t first_index = start; pgoff_t last_index = start + nr - 1; details.even_cows = even_cows; if (last_index < first_index) last_index = ULONG_MAX; i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, first_index, last_index, &details); i_mmap_unlock_read(mapping); } EXPORT_SYMBOL_GPL(unmap_mapping_pages); /** * unmap_mapping_range - unmap the portion of all mmaps in the specified * address_space corresponding to the specified byte range in the underlying * file. * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded * up to a PAGE_SIZE boundary. A holelen of zero truncates to the * end of the file. * @even_cows: 1 when truncating a file, unmap even private COWed pages; * but 0 when invalidating pagecache, don't throw away private data. */ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { long long holeend = (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; if (holeend & ~(long long)ULONG_MAX) hlen = ULONG_MAX - hba + 1; } unmap_mapping_pages(mapping, hba, hlen, even_cows); } EXPORT_SYMBOL(unmap_mapping_range); /* * Restore a potential device exclusive pte to a working pte entry */ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) { struct folio *folio = page_folio(vmf->page); struct vm_area_struct *vma = vmf->vma; struct mmu_notifier_range range; vm_fault_t ret; /* * We need a reference to lock the folio because we don't hold * the PTL so a racing thread can remove the device-exclusive * entry and unmap it. If the folio is free the entry must * have been removed already. If it happens to have already * been re-allocated after being freed all we do is lock and * unlock it. */ if (!folio_try_get(folio)) return 0; ret = folio_lock_or_retry(folio, vmf); if (ret) { folio_put(folio); return ret; } mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); mmu_notifier_invalidate_range_start(&range); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) restore_exclusive_pte(vma, vmf->page, vmf->address, vmf->pte); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); folio_unlock(folio); folio_put(folio); mmu_notifier_invalidate_range_end(&range); return 0; } static inline bool should_try_to_free_swap(struct folio *folio, struct vm_area_struct *vma, unsigned int fault_flags) { if (!folio_test_swapcache(folio)) return false; if (mem_cgroup_swap_full(folio) || (vma->vm_flags & VM_LOCKED) || folio_test_mlocked(folio)) return true; /* * If we want to map a page that's in the swapcache writable, we * have to detect via the refcount if we're really the exclusive * user. Try freeing the swapcache to get rid of the swapcache * reference only in case it's likely that we'll be the exlusive user. */ return (fault_flags & FAULT_FLAG_WRITE) && !folio_test_ksm(folio) && folio_ref_count(folio) == (1 + folio_nr_pages(folio)); } static vm_fault_t pte_marker_clear(struct vm_fault *vmf) { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!vmf->pte) return 0; /* * Be careful so that we will only recover a special uffd-wp pte into a * none pte. Otherwise it means the pte could have changed, so retry. * * This should also cover the case where e.g. the pte changed * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_POISONED. * So is_pte_marker() check is not enough to safely drop the pte. */ if (pte_same(vmf->orig_pte, ptep_get(vmf->pte))) pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } static vm_fault_t do_pte_missing(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_anonymous_page(vmf); else return do_fault(vmf); } /* * This is actually a page-missing access, but with uffd-wp special pte * installed. It means this pte was wr-protected before being unmapped. */ static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf) { /* * Just in case there're leftover special ptes even after the region * got unregistered - we can simply clear them. */ if (unlikely(!userfaultfd_wp(vmf->vma))) return pte_marker_clear(vmf); return do_pte_missing(vmf); } static vm_fault_t handle_pte_marker(struct vm_fault *vmf) { swp_entry_t entry = pte_to_swp_entry(vmf->orig_pte); unsigned long marker = pte_marker_get(entry); /* * PTE markers should never be empty. If anything weird happened, * the best thing to do is to kill the process along with its mm. */ if (WARN_ON_ONCE(!marker)) return VM_FAULT_SIGBUS; /* Higher priority than uffd-wp when data corrupted */ if (marker & PTE_MARKER_POISONED) return VM_FAULT_HWPOISON; if (pte_marker_entry_uffd_wp(entry)) return pte_marker_handle_uffd_wp(vmf); /* This is an unknown pte marker */ return VM_FAULT_SIGBUS; } static struct folio *__alloc_swap_folio(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; swp_entry_t entry; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); if (!folio) return NULL; entry = pte_to_swp_entry(vmf->orig_pte); if (mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, GFP_KERNEL, entry)) { folio_put(folio); return NULL; } return folio; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) { struct swap_info_struct *si = swp_swap_info(entry); pgoff_t offset = swp_offset(entry); int i; /* * While allocating a large folio and doing swap_read_folio, which is * the case the being faulted pte doesn't have swapcache. We need to * ensure all PTEs have no cache as well, otherwise, we might go to * swap devices while the content is in swapcache. */ for (i = 0; i < max_nr; i++) { if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) return i; } return i; } /* * Check if the PTEs within a range are contiguous swap entries * and have consistent swapcache, zeromap. */ static bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages) { unsigned long addr; swp_entry_t entry; int idx; pte_t pte; addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE); idx = (vmf->address - addr) / PAGE_SIZE; pte = ptep_get(ptep); if (!pte_same(pte, pte_move_swp_offset(vmf->orig_pte, -idx))) return false; entry = pte_to_swp_entry(pte); if (swap_pte_batch(ptep, nr_pages, pte) != nr_pages) return false; /* * swap_read_folio() can't handle the case a large folio is hybridly * from different backends. And they are likely corner cases. Similar * things might be added once zswap support large folios. */ if (unlikely(swap_zeromap_batch(entry, nr_pages, NULL) != nr_pages)) return false; if (unlikely(non_swapcache_batch(entry, nr_pages) != nr_pages)) return false; return true; } static inline unsigned long thp_swap_suitable_orders(pgoff_t swp_offset, unsigned long addr, unsigned long orders) { int order, nr; order = highest_order(orders); /* * To swap in a THP with nr pages, we require that its first swap_offset * is aligned with that number, as it was when the THP was swapped out. * This helps filter out most invalid entries. */ while (orders) { nr = 1 << order; if ((addr >> PAGE_SHIFT) % nr == swp_offset % nr) break; order = next_order(&orders, order); } return orders; } static struct folio *alloc_swap_folio(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; unsigned long orders; struct folio *folio; unsigned long addr; swp_entry_t entry; spinlock_t *ptl; pte_t *pte; gfp_t gfp; int order; /* * If uffd is active for the vma we need per-page fault fidelity to * maintain the uffd semantics. */ if (unlikely(userfaultfd_armed(vma))) goto fallback; /* * A large swapped out folio could be partially or fully in zswap. We * lack handling for such cases, so fallback to swapping in order-0 * folio. */ if (!zswap_never_enabled()) goto fallback; entry = pte_to_swp_entry(vmf->orig_pte); /* * Get a list of all the (large) orders below PMD_ORDER that are enabled * and suitable for swapping THP. */ orders = thp_vma_allowable_orders(vma, vma->vm_flags, TVA_IN_PF | TVA_ENFORCE_SYSFS, BIT(PMD_ORDER) - 1); orders = thp_vma_suitable_orders(vma, vmf->address, orders); orders = thp_swap_suitable_orders(swp_offset(entry), vmf->address, orders); if (!orders) goto fallback; pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address & PMD_MASK, &ptl); if (unlikely(!pte)) goto fallback; /* * For do_swap_page, find the highest order where the aligned range is * completely swap entries with contiguous swap offsets. */ order = highest_order(orders); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); if (can_swapin_thp(vmf, pte + pte_index(addr), 1 << order)) break; order = next_order(&orders, order); } pte_unmap_unlock(pte, ptl); /* Try allocating the highest of the remaining orders. */ gfp = vma_thp_gfp_mask(vma); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); folio = vma_alloc_folio(gfp, order, vma, addr, true); if (folio) { if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, gfp, entry)) return folio; folio_put(folio); } order = next_order(&orders, order); } fallback: return __alloc_swap_folio(vmf); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ static inline bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages) { return false; } static struct folio *alloc_swap_folio(struct vm_fault *vmf) { return __alloc_swap_folio(vmf); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. * * We return with the mmap_lock locked or unlocked in the same cases * as does filemap_fault(). */ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *swapcache, *folio = NULL; struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; vm_fault_t ret = 0; void *shadow = NULL; int nr_pages; unsigned long page_idx; unsigned long address; pte_t *ptep; if (!pte_unmap_same(vmf)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (is_device_exclusive_entry(entry)) { vmf->page = pfn_swap_entry_to_page(entry); ret = remove_device_exclusive_entry(vmf); } else if (is_device_private_entry(entry)) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) { /* * migrate_to_ram is not yet ready to operate * under VMA lock. */ vma_end_read(vma); ret = VM_FAULT_RETRY; goto out; } vmf->page = pfn_swap_entry_to_page(entry); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) goto unlock; /* * Get a page reference while we know the page can't be * freed. */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else if (is_pte_marker_entry(entry)) { ret = handle_pte_marker(vmf); } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; } /* Prevent swapoff from happening to us. */ si = get_swap_device(entry); if (unlikely(!si)) goto out; folio = swap_cache_get_folio(entry, vma, vmf->address); if (folio) page = folio_file_page(folio, swp_offset(entry)); swapcache = folio; if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ folio = alloc_swap_folio(vmf); if (folio) { __folio_set_locked(folio); __folio_set_swapbacked(folio); nr_pages = folio_nr_pages(folio); if (folio_test_large(folio)) entry.val = ALIGN_DOWN(entry.val, nr_pages); /* * Prevent parallel swapin from proceeding with * the cache flag. Otherwise, another thread * may finish swapin first, free the entry, and * swapout reusing the same entry. It's * undetectable as pte_same() returns true due * to entry reuse. */ if (swapcache_prepare(entry, nr_pages)) { /* * Relax a bit to prevent rapid * repeated page faults. */ schedule_timeout_uninterruptible(1); goto out_page; } need_clear_cache = true; mem_cgroup_swapin_uncharge_swap(entry, nr_pages); shadow = get_shadow_from_swap_cache(entry); if (shadow) workingset_refault(folio, shadow); folio_add_lru(folio); /* To provide entry to swap_read_folio() */ folio->swap = entry; swap_read_folio(folio, NULL); folio->private = NULL; } } else { folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); swapcache = folio; } if (!folio) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) ret = VM_FAULT_OOM; goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); page = folio_file_page(folio, swp_offset(entry)); } else if (PageHWPoison(page)) { /* * hwpoisoned dirty swapcache pages are kept for killing * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; goto out_release; } ret |= folio_lock_or_retry(folio, vmf); if (ret & VM_FAULT_RETRY) goto out_release; if (swapcache) { /* * Make sure folio_free_swap() or swapoff did not release the * swapcache from under us. The page pin, and pte_same test * below, are not enough to exclude that. Even if it is still * swapcache, we need to check that the page's swap has not * changed. */ if (unlikely(!folio_test_swapcache(folio) || page_swap_entry(page).val != entry.val)) goto out_page; /* * KSM sometimes has to copy on read faults, for example, if * page->index of !PageKSM() pages would be nonlinear inside the * anon VMA -- PageKSM() is lost on actual swapout. */ folio = ksm_might_need_to_copy(folio, vma, vmf->address); if (unlikely(!folio)) { ret = VM_FAULT_OOM; folio = swapcache; goto out_page; } else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { ret = VM_FAULT_HWPOISON; folio = swapcache; goto out_page; } if (folio != swapcache) page = folio_page(folio, 0); /* * If we want to map a page that's in the swapcache writable, we * have to detect via the refcount if we're really the exclusive * owner. Try removing the extra reference from the local LRU * caches if required. */ if ((vmf->flags & FAULT_FLAG_WRITE) && folio == swapcache && !folio_test_ksm(folio) && !folio_test_lru(folio)) lru_add_drain(); } folio_throttle_swaprate(folio, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) goto out_nomap; if (unlikely(!folio_test_uptodate(folio))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } /* allocated large folios for SWP_SYNCHRONOUS_IO */ if (folio_test_large(folio) && !folio_test_swapcache(folio)) { unsigned long nr = folio_nr_pages(folio); unsigned long folio_start = ALIGN_DOWN(vmf->address, nr * PAGE_SIZE); unsigned long idx = (vmf->address - folio_start) / PAGE_SIZE; pte_t *folio_ptep = vmf->pte - idx; pte_t folio_pte = ptep_get(folio_ptep); if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) || swap_pte_batch(folio_ptep, nr, folio_pte) != nr) goto out_nomap; page_idx = idx; address = folio_start; ptep = folio_ptep; goto check_folio; } nr_pages = 1; page_idx = 0; address = vmf->address; ptep = vmf->pte; if (folio_test_large(folio) && folio_test_swapcache(folio)) { int nr = folio_nr_pages(folio); unsigned long idx = folio_page_idx(folio, page); unsigned long folio_start = address - idx * PAGE_SIZE; unsigned long folio_end = folio_start + nr * PAGE_SIZE; pte_t *folio_ptep; pte_t folio_pte; if (unlikely(folio_start < max(address & PMD_MASK, vma->vm_start))) goto check_folio; if (unlikely(folio_end > pmd_addr_end(address, vma->vm_end))) goto check_folio; folio_ptep = vmf->pte - idx; folio_pte = ptep_get(folio_ptep); if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) || swap_pte_batch(folio_ptep, nr, folio_pte) != nr) goto check_folio; page_idx = idx; address = folio_start; ptep = folio_ptep; nr_pages = nr; entry = folio->swap; page = &folio->page; } check_folio: /* * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte * must never point at an anonymous page in the swapcache that is * PG_anon_exclusive. Sanity check that this holds and especially, that * no filesystem set PG_mappedtodisk on a page in the swapcache. Sanity * check after taking the PT lock and making sure that nobody * concurrently faulted in this page and set PG_anon_exclusive. */ BUG_ON(!folio_test_anon(folio) && folio_test_mappedtodisk(folio)); BUG_ON(folio_test_anon(folio) && PageAnonExclusive(page)); /* * Check under PT lock (to protect against concurrent fork() sharing * the swap entry concurrently) for certainly exclusive pages. */ if (!folio_test_ksm(folio)) { exclusive = pte_swp_exclusive(vmf->orig_pte); if (folio != swapcache) { /* * We have a fresh page that is not exposed to the * swapcache -> certainly exclusive. */ exclusive = true; } else if (exclusive && folio_test_writeback(folio) && data_race(si->flags & SWP_STABLE_WRITES)) { /* * This is tricky: not all swap backends support * concurrent page modifications while under writeback. * * So if we stumble over such a page in the swapcache * we must not set the page exclusive, otherwise we can * map it writable without further checks and modify it * while still under writeback. * * For these problematic swap backends, simply drop the * exclusive marker: this is perfectly fine as we start * writeback only if we fully unmapped the page and * there are no unexpected references on the page after * unmapping succeeded. After fully unmapped, no * further GUP references (FOLL_GET and FOLL_PIN) can * appear, so dropping the exclusive marker and mapping * it only R/O is fine. */ exclusive = false; } } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); /* * Remove the swap entry and conditionally try to free up the swapcache. * We're already holding a reference on the page but haven't mapped it * yet. */ swap_free_nr(entry, nr_pages); if (should_try_to_free_swap(folio, vma, vmf->flags)) folio_free_swap(folio); add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); add_mm_counter(vma->vm_mm, MM_SWAPENTS, -nr_pages); pte = mk_pte(page, vma->vm_page_prot); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(vmf->orig_pte)) pte = pte_mkuffd_wp(pte); /* * Same logic as in do_wp_page(); however, optimize for pages that are * certainly not shared either because we just allocated them without * exposing them to the swapcache or because the swap entry indicates * exclusivity. */ if (!folio_test_ksm(folio) && (exclusive || folio_ref_count(folio) == 1)) { if ((vma->vm_flags & VM_WRITE) && !userfaultfd_pte_wp(vma, pte) && !pte_needs_soft_dirty_wp(vma, pte)) { pte = pte_mkwrite(pte, vma); if (vmf->flags & FAULT_FLAG_WRITE) { pte = pte_mkdirty(pte); vmf->flags &= ~FAULT_FLAG_WRITE; } } rmap_flags |= RMAP_EXCLUSIVE; } folio_ref_add(folio, nr_pages - 1); flush_icache_pages(vma, page, nr_pages); vmf->orig_pte = pte_advance_pfn(pte, page_idx); /* ksm created a completely new copy */ if (unlikely(folio != swapcache && swapcache)) { folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } else if (!folio_test_anon(folio)) { /* * We currently only expect small !anon folios which are either * fully exclusive or fully shared, or new allocated large * folios which are fully exclusive. If we ever get large * folios within swapcache here, we have to be careful. */ VM_WARN_ON_ONCE(folio_test_large(folio) && folio_test_swapcache(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, address, rmap_flags); } else { folio_add_anon_rmap_ptes(folio, page, nr_pages, vma, address, rmap_flags); } VM_BUG_ON(!folio_test_anon(folio) || (pte_write(pte) && !PageAnonExclusive(page))); set_ptes(vma->vm_mm, address, ptep, pte, nr_pages); arch_do_swap_page_nr(vma->vm_mm, vma, address, pte, pte, nr_pages); folio_unlock(folio); if (folio != swapcache && swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check * (to avoid false positives from pte_same). For * further safety release the lock after the swap_free * so that the swap count won't change under a * parallel locked swapcache. */ folio_unlock(swapcache); folio_put(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(vmf); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ update_mmu_cache_range(vmf, vma, address, ptep, nr_pages); unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out: /* Clear the swap cache pin for direct swapin after PTL unlock */ if (need_clear_cache) swapcache_clear(si, entry, nr_pages); if (si) put_swap_device(si); return ret; out_nomap: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: folio_unlock(folio); out_release: folio_put(folio); if (folio != swapcache && swapcache) { folio_unlock(swapcache); folio_put(swapcache); } if (need_clear_cache) swapcache_clear(si, entry, nr_pages); if (si) put_swap_device(si); return ret; } static bool pte_range_none(pte_t *pte, int nr_pages) { int i; for (i = 0; i < nr_pages; i++) { if (!pte_none(ptep_get_lockless(pte + i))) return false; } return true; } static struct folio *alloc_anon_folio(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long orders; struct folio *folio; unsigned long addr; pte_t *pte; gfp_t gfp; int order; /* * If uffd is active for the vma we need per-page fault fidelity to * maintain the uffd semantics. */ if (unlikely(userfaultfd_armed(vma))) goto fallback; /* * Get a list of all the (large) orders below PMD_ORDER that are enabled * for this vma. Then filter out the orders that can't be allocated over * the faulting address and still be fully contained in the vma. */ orders = thp_vma_allowable_orders(vma, vma->vm_flags, TVA_IN_PF | TVA_ENFORCE_SYSFS, BIT(PMD_ORDER) - 1); orders = thp_vma_suitable_orders(vma, vmf->address, orders); if (!orders) goto fallback; pte = pte_offset_map(vmf->pmd, vmf->address & PMD_MASK); if (!pte) return ERR_PTR(-EAGAIN); /* * Find the highest order where the aligned range is completely * pte_none(). Note that all remaining orders will be completely * pte_none(). */ order = highest_order(orders); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); if (pte_range_none(pte + pte_index(addr), 1 << order)) break; order = next_order(&orders, order); } pte_unmap(pte); if (!orders) goto fallback; /* Try allocating the highest of the remaining orders. */ gfp = vma_thp_gfp_mask(vma); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); folio = vma_alloc_folio(gfp, order, vma, addr, true); if (folio) { if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); folio_put(folio); goto next; } folio_throttle_swaprate(folio, gfp); folio_zero_user(folio, vmf->address); return folio; } next: count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); order = next_order(&orders, order); } fallback: #endif return folio_prealloc(vma->vm_mm, vma, vmf->address, true); } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address; struct folio *folio; vm_fault_t ret = 0; int nr_pages = 1; pte_t entry; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* * Use pte_alloc() instead of pte_alloc_map(), so that OOM can * be distinguished from a transient failure of pte_offset_map(). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; /* Use the zero-page for reads */ if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!vmf->pte) goto unlock; if (vmf_pte_changed(vmf)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } goto setpte; } /* Allocate our own private page. */ ret = vmf_anon_prepare(vmf); if (ret) return ret; /* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */ folio = alloc_anon_folio(vmf); if (IS_ERR(folio)) return 0; if (!folio) goto oom; nr_pages = folio_nr_pages(folio); addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE); /* * The memory barrier inside __folio_mark_uptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __folio_mark_uptodate(folio); entry = mk_pte(&folio->page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry), vma); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) goto release; if (nr_pages == 1 && vmf_pte_changed(vmf)) { update_mmu_tlb(vma, addr, vmf->pte); goto release; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); goto release; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); folio_put(folio); return handle_userfault(vmf, VM_UFFD_MISSING); } folio_ref_add(folio, nr_pages - 1); add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_FAULT_ALLOC); folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); setpte: if (vmf_orig_pte_uffd_wp(vmf)) entry = pte_mkuffd_wp(entry); set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages); /* No need to invalidate - it was non-present before */ update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr_pages); unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: folio_put(folio); goto unlock; oom: return VM_FAULT_OOM; } /* * The mmap_lock must have been held on entry, and may have been * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; vm_fault_t ret; /* * Preallocate pte before we take page_lock because this might lead to * deadlocks for memcg reclaim which waits for pages under writeback: * lock_page(A) * SetPageWriteback(A) * unlock_page(A) * lock_page(B) * lock_page(B) * pte_alloc_one * shrink_folio_list * wait_on_page_writeback(A) * SetPageWriteback(B) * unlock_page(B) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; } ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; folio = page_folio(vmf->page); if (unlikely(PageHWPoison(vmf->page))) { vm_fault_t poisonret = VM_FAULT_HWPOISON; if (ret & VM_FAULT_LOCKED) { if (page_mapped(vmf->page)) unmap_mapping_folio(folio); /* Retry if a clean folio was removed from the cache. */ if (mapping_evict_folio(folio->mapping, folio)) poisonret = VM_FAULT_NOPAGE; folio_unlock(folio); } folio_put(folio); vmf->page = NULL; return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) folio_lock(folio); else VM_BUG_ON_PAGE(!folio_test_locked(folio), vmf->page); return ret; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); /* * We are going to consume the prealloc table, * count that as nr_ptes. */ mm_inc_nr_ptes(vma->vm_mm); vmf->prealloc_pte = NULL; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { struct folio *folio = page_folio(page); struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; vm_fault_t ret = VM_FAULT_FALLBACK; if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret; if (folio_order(folio) != HPAGE_PMD_ORDER) return ret; page = &folio->page; /* * Just backoff if any subpage of a THP is corrupted otherwise * the corrupted page may mapped by PMD silently to escape the * check. This kind of THP just can be PTE mapped. Access to * the corrupted subpage should trigger SIGBUS as expected. */ if (unlikely(folio_test_has_hwpoisoned(folio))) return ret; /* * Archs like ppc64 need additional space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) goto out; flush_icache_pages(vma, page, HPAGE_PMD_NR); entry = mk_huge_pmd(page, vma->vm_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(folio), HPAGE_PMD_NR); folio_add_file_rmap_pmd(folio, page, vma); /* * deposit and withdraw with pmd lock held */ if (arch_needs_pgtable_deposit()) deposit_prealloc_pte(vmf); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, haddr, vmf->pmd); /* fault is handled */ ret = 0; count_vm_event(THP_FILE_MAPPED); out: spin_unlock(vmf->ptl); return ret; } #else vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { return VM_FAULT_FALLBACK; } #endif /** * set_pte_range - Set a range of PTEs to point to pages in a folio. * @vmf: Fault decription. * @folio: The folio that contains @page. * @page: The first page to create a PTE for. * @nr: The number of PTEs to create. * @addr: The first address to create a PTE for. */ void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE); pte_t entry; flush_icache_pages(vma, page, nr); entry = mk_pte(page, vma->vm_page_prot); if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); else entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (unlikely(vmf_orig_pte_uffd_wp(vmf))) entry = pte_mkuffd_wp(entry); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { VM_BUG_ON_FOLIO(nr != 1, folio); folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } else { folio_add_file_rmap_ptes(folio, page, nr, vma); } set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr); } static bool vmf_pte_changed(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID) return !pte_same(ptep_get(vmf->pte), vmf->orig_pte); return !pte_none(ptep_get(vmf->pte)); } /** * finish_fault - finish page fault once we have prepared the page to fault * * @vmf: structure describing the fault * * This function handles all that is needed to finish a page fault once the * page to fault in is prepared. It handles locking of PTEs, inserts PTE for * given page, adds reverse page mapping, handles memcg charges and LRU * addition. * * The function expects the page to be locked and on success it consumes a * reference of a page being mapped (for the PTE which maps it). * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t finish_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; struct folio *folio; vm_fault_t ret; bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED); int type, nr_pages; unsigned long addr = vmf->address; /* Did we COW the page? */ if (is_cow) page = vmf->cow_page; else page = vmf->page; /* * check even for read faults because we might have lost our CoWed * page */ if (!(vma->vm_flags & VM_SHARED)) { ret = check_stable_address_space(vma->vm_mm); if (ret) return ret; } if (pmd_none(*vmf->pmd)) { if (PageTransCompound(page)) { ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; } if (vmf->prealloc_pte) pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte); else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) return VM_FAULT_OOM; } folio = page_folio(page); nr_pages = folio_nr_pages(folio); /* * Using per-page fault to maintain the uffd semantics, and same * approach also applies to non-anonymous-shmem faults to avoid * inflating the RSS of the process. */ if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) { nr_pages = 1; } else if (nr_pages > 1) { pgoff_t idx = folio_page_idx(folio, page); /* The page offset of vmf->address within the VMA. */ pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; /* The index of the entry in the pagetable for fault page. */ pgoff_t pte_off = pte_index(vmf->address); /* * Fallback to per-page fault in case the folio size in page * cache beyond the VMA limits and PMD pagetable limits. */ if (unlikely(vma_off < idx || vma_off + (nr_pages - idx) > vma_pages(vma) || pte_off < idx || pte_off + (nr_pages - idx) > PTRS_PER_PTE)) { nr_pages = 1; } else { /* Now we can set mappings for the whole large folio. */ addr = vmf->address - idx * PAGE_SIZE; page = &folio->page; } } vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) return VM_FAULT_NOPAGE; /* Re-check under ptl */ if (nr_pages == 1 && unlikely(vmf_pte_changed(vmf))) { update_mmu_tlb(vma, addr, vmf->pte); ret = VM_FAULT_NOPAGE; goto unlock; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); ret = VM_FAULT_NOPAGE; goto unlock; } folio_ref_add(folio, nr_pages - 1); set_pte_range(vmf, folio, page, nr_pages, addr); type = is_cow ? MM_ANONPAGES : mm_counter_file(folio); add_mm_counter(vma->vm_mm, type, nr_pages); ret = 0; unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } static unsigned long fault_around_pages __read_mostly = 65536 >> PAGE_SHIFT; #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { *val = fault_around_pages << PAGE_SHIFT; return 0; } /* * fault_around_bytes must be rounded down to the nearest page order as it's * what do_fault_around() expects to see. */ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; /* * The minimum value is 1 page, however this results in no fault-around * at all. See should_fault_around(). */ val = max(val, PAGE_SIZE); fault_around_pages = rounddown_pow_of_two(val) >> PAGE_SHIFT; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, &fault_around_bytes_fops); return 0; } late_initcall(fault_around_debugfs); #endif /* * do_fault_around() tries to map few pages around the fault address. The hope * is that the pages will be needed soon and this will lower the number of * faults to handle. * * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * * This function doesn't cross VMA or page table boundaries, in order to call * map_pages() and acquire a PTE lock only once. * * fault_around_pages defines how many pages we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal * to PTRS_PER_PTE. * * The virtual address of the area that we map is naturally aligned to * fault_around_pages * PAGE_SIZE rounded down to the machine page size * (and therefore to page order). This way it's easier to guarantee * that we don't cross page table boundaries. */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { pgoff_t nr_pages = READ_ONCE(fault_around_pages); pgoff_t pte_off = pte_index(vmf->address); /* The page offset of vmf->address within the VMA. */ pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; pgoff_t from_pte, to_pte; vm_fault_t ret; /* The PTE offset of the start address, clamped to the VMA. */ from_pte = max(ALIGN_DOWN(pte_off, nr_pages), pte_off - min(pte_off, vma_off)); /* The PTE offset of the end address, clamped to the VMA and PTE. */ to_pte = min3(from_pte + nr_pages, (pgoff_t)PTRS_PER_PTE, pte_off + vma_pages(vmf->vma) - vma_off) - 1; if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; } rcu_read_lock(); ret = vmf->vma->vm_ops->map_pages(vmf, vmf->pgoff + from_pte - pte_off, vmf->pgoff + to_pte - pte_off); rcu_read_unlock(); return ret; } /* Return true if we should do read fault-around, false otherwise */ static inline bool should_fault_around(struct vm_fault *vmf) { /* No ->map_pages? No way to fault around... */ if (!vmf->vma->vm_ops->map_pages) return false; if (uffd_disable_fault_around(vmf->vma)) return false; /* A single page implies no faulting 'around' at all. */ return fault_around_pages > 1; } static vm_fault_t do_read_fault(struct vm_fault *vmf) { vm_fault_t ret = 0; struct folio *folio; /* * Let's call ->map_pages() first and use ->fault() as fallback * if page by the offset is not ready to be mapped (cold cache or * something). */ if (should_fault_around(vmf)) { ret = do_fault_around(vmf); if (ret) return ret; } ret = vmf_can_call_fault(vmf); if (ret) return ret; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; ret |= finish_fault(vmf); folio = page_folio(vmf->page); folio_unlock(folio); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) folio_put(folio); return ret; } static vm_fault_t do_cow_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; vm_fault_t ret; ret = vmf_can_call_fault(vmf); if (!ret) ret = vmf_anon_prepare(vmf); if (ret) return ret; folio = folio_prealloc(vma->vm_mm, vma, vmf->address, false); if (!folio) return VM_FAULT_OOM; vmf->cow_page = &folio->page; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; if (ret & VM_FAULT_DONE_COW) return ret; if (copy_mc_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma)) { ret = VM_FAULT_HWPOISON; goto unlock; } __folio_mark_uptodate(folio); ret |= finish_fault(vmf); unlock: unlock_page(vmf->page); put_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; return ret; uncharge_out: folio_put(folio); return ret; } static vm_fault_t do_shared_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret, tmp; struct folio *folio; ret = vmf_can_call_fault(vmf); if (ret) return ret; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; folio = page_folio(vmf->page); /* * Check if the backing address space wants to know that the page is * about to become writable */ if (vma->vm_ops->page_mkwrite) { folio_unlock(folio); tmp = do_page_mkwrite(vmf, folio); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { folio_put(folio); return tmp; } } ret |= finish_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) { folio_unlock(folio); folio_put(folio); return ret; } ret |= fault_dirty_shared_page(vmf); return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __folio_lock_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ static vm_fault_t do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *vm_mm = vma->vm_mm; vm_fault_t ret; /* * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ if (!vma->vm_ops->fault) { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte)) ret = VM_FAULT_SIGBUS; else { /* * Make sure this is not a temporary clearing of pte * by holding ptl and checking again. A R/M/W update * of pte involves: take ptl, clearing the pte so that * we don't have concurrent modification by hardware * followed by an update. */ if (unlikely(pte_none(ptep_get(vmf->pte)))) ret = VM_FAULT_SIGBUS; else ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); } } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); else if (!(vma->vm_flags & VM_SHARED)) ret = do_cow_fault(vmf); else ret = do_shared_fault(vmf); /* preallocated pagetable is unused: free it */ if (vmf->prealloc_pte) { pte_free(vm_mm, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } return ret; } int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int *flags, bool writable, int *last_cpupid) { struct vm_area_struct *vma = vmf->vma; /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses * the case where a mapping is writable but the process never writes * to it but pte_write gets cleared during protection updates and * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ if (!writable) *flags |= TNF_NO_GROUP; /* * Flag if the folio is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ if (folio_likely_mapped_shared(folio) && (vma->vm_flags & VM_SHARED)) *flags |= TNF_SHARED; /* * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. */ if (folio_use_access_time(folio)) *last_cpupid = (-1 & LAST_CPUPID_MASK); else *last_cpupid = folio_last_cpupid(folio); /* Record the current PID acceesing VMA */ vma_set_access_pid_bit(vma); count_vm_numa_event(NUMA_HINT_FAULTS); #ifdef CONFIG_NUMA_BALANCING count_memcg_folio_events(folio, NUMA_HINT_FAULTS, 1); #endif if (folio_nid(folio) == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); *flags |= TNF_FAULT_LOCAL; } return mpol_misplaced(folio, vmf, addr); } static void numa_rebuild_single_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long fault_addr, pte_t *fault_pte, bool writable) { pte_t pte, old_pte; old_pte = ptep_modify_prot_start(vma, fault_addr, fault_pte); pte = pte_modify(old_pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (writable) pte = pte_mkwrite(pte, vma); ptep_modify_prot_commit(vma, fault_addr, fault_pte, old_pte, pte); update_mmu_cache_range(vmf, vma, fault_addr, fault_pte, 1); } static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, struct folio *folio, pte_t fault_pte, bool ignore_writable, bool pte_write_upgrade) { int nr = pte_pfn(fault_pte) - folio_pfn(folio); unsigned long start, end, addr = vmf->address; unsigned long addr_start = addr - (nr << PAGE_SHIFT); unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE); pte_t *start_ptep; /* Stay within the VMA and within the page table. */ start = max3(addr_start, pt_start, vma->vm_start); end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE, vma->vm_end); start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT); /* Restore all PTEs' mapping of the large folio */ for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) { pte_t ptent = ptep_get(start_ptep); bool writable = false; if (!pte_present(ptent) || !pte_protnone(ptent)) continue; if (pfn_folio(pte_pfn(ptent)) != folio) continue; if (!ignore_writable) { ptent = pte_modify(ptent, vma->vm_page_prot); writable = pte_write(ptent); if (!writable && pte_write_upgrade && can_change_pte_writable(vma, addr, ptent)) writable = true; } numa_rebuild_single_mapping(vmf, vma, addr, start_ptep, writable); } } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio = NULL; int nid = NUMA_NO_NODE; bool writable = false, ignore_writable = false; bool pte_write_upgrade = vma_wants_manual_pte_write_upgrade(vma); int last_cpupid; int target_nid; pte_t pte, old_pte; int flags = 0, nr_pages; /* * The pte cannot be used safely until we verify, while holding the page * table lock, that its contents have not changed during fault handling. */ spin_lock(vmf->ptl); /* Read the live PTE from the page tables: */ old_pte = ptep_get(vmf->pte); if (unlikely(!pte_same(old_pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } pte = pte_modify(old_pte, vma->vm_page_prot); /* * Detect now whether the PTE could be writable; this information * is only valid while holding the PT lock. */ writable = pte_write(pte); if (!writable && pte_write_upgrade && can_change_pte_writable(vma, vmf->address, pte)) writable = true; folio = vm_normal_folio(vma, vmf->address, pte); if (!folio || folio_is_zone_device(folio)) goto out_map; nid = folio_nid(folio); nr_pages = folio_nr_pages(folio); target_nid = numa_migrate_check(folio, vmf, vmf->address, &flags, writable, &last_cpupid); if (target_nid == NUMA_NO_NODE) goto out_map; if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) { flags |= TNF_MIGRATE_FAIL; goto out_map; } /* The folio is isolated and isolation code holds a folio reference. */ pte_unmap_unlock(vmf->pte, vmf->ptl); writable = false; ignore_writable = true; /* Migrate to the requested node */ if (!migrate_misplaced_folio(folio, vma, target_nid)) { nid = target_nid; flags |= TNF_MIGRATED; task_numa_fault(last_cpupid, nid, nr_pages, flags); return 0; } flags |= TNF_MIGRATE_FAIL; vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte)) return 0; if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } out_map: /* * Make it present again, depending on how arch implements * non-accessible ptes, some can allow access by kernel mode. */ if (folio && folio_test_large(folio)) numa_rebuild_large_mapping(vmf, vma, folio, pte, ignore_writable, pte_write_upgrade); else numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, writable); pte_unmap_unlock(vmf->pte, vmf->ptl); if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, nr_pages, flags); return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma_is_anonymous(vma)) return do_huge_pmd_anonymous_page(vmf); if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PMD_ORDER); return VM_FAULT_FALLBACK; } /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; vm_fault_t ret; if (vma_is_anonymous(vma)) { if (likely(!unshare) && userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) { if (userfaultfd_wp_async(vmf->vma)) goto split; return handle_userfault(vmf, VM_UFFD_WP); } return do_huge_pmd_wp_page(vmf); } if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) return ret; } } split: /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } static vm_fault_t create_huge_pud(struct vm_fault *vmf) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) struct vm_area_struct *vma = vmf->vma; /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vma)) return VM_FAULT_FALLBACK; if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PUD_ORDER); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ return VM_FAULT_FALLBACK; } static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vma)) goto split; if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) return ret; } } split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vma, vmf->pud, vmf->address); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most * RISC architectures). The early dirtying is also good on the i386. * * There is also a hook called "update_mmu_cache()" that architectures * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. * See filemap_fault() and __folio_lock_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { pte_t entry; if (unlikely(pmd_none(*vmf->pmd))) { /* * Leave __pte_alloc() until later: because vm_ops->fault may * want to allocate huge page, and if we expose page table * for an instant, it will be difficult to retract from * concurrent faults and from rmap lookups. */ vmf->pte = NULL; vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID; } else { /* * A regular pmd is established and it can't morph into a huge * pmd by anon khugepaged, since that takes mmap_lock in write * mode; but shmem or file collapse to THP could still morph * it into a huge pmd: just retry later if so. */ vmf->pte = pte_offset_map_nolock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte)) return 0; vmf->orig_pte = ptep_get_lockless(vmf->pte); vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID; if (pte_none(vmf->orig_pte)) { pte_unmap(vmf->pte); vmf->pte = NULL; } } if (!vmf->pte) return do_pte_missing(vmf); if (!pte_present(vmf->orig_pte)) return do_swap_page(vmf); if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf); spin_lock(vmf->ptl); entry = vmf->orig_pte; if (unlikely(!pte_same(ptep_get(vmf->pte), entry))) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } if (vmf->flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!pte_write(entry)) return do_wp_page(vmf); else if (likely(vmf->flags & FAULT_FLAG_WRITE)) entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache_range(vmf, vmf->vma, vmf->address, vmf->pte, 1); } else { /* Skip spurious TLB flush for retried page fault */ if (vmf->flags & FAULT_FLAG_TRIED) goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. * This still avoids useless tlb flushes for .text page faults * with threads. */ if (vmf->flags & FAULT_FLAG_WRITE) flush_tlb_fix_spurious_fault(vmf->vma, vmf->address, vmf->pte); } unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * On entry, we hold either the VMA lock or the mmap_lock * (FAULT_FLAG_VMA_LOCK tells you which). If VM_FAULT_RETRY is set in * the result, the mmap_lock is not held on exit. See filemap_fault() * and __folio_lock_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { struct vm_fault vmf = { .vma = vma, .address = address & PAGE_MASK, .real_address = address, .flags = flags, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; struct mm_struct *mm = vma->vm_mm; unsigned long vm_flags = vma->vm_flags; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return VM_FAULT_OOM; vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && thp_vma_allowable_order(vma, vm_flags, TVA_IN_PF | TVA_ENFORCE_SYSFS, PUD_ORDER)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pud_t orig_pud = *vmf.pud; barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { /* * TODO once we support anonymous PUDs: NUMA case and * FAULT_FLAG_UNSHARE handling. */ if ((flags & FAULT_FLAG_WRITE) && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pud_set_accessed(&vmf, orig_pud); return 0; } } } vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; /* Huge pud page fault raced with pmd_alloc? */ if (pud_trans_unstable(vmf.pud)) goto retry_pud; if (pmd_none(*vmf.pmd) && thp_vma_allowable_order(vma, vm_flags, TVA_IN_PF | TVA_ENFORCE_SYSFS, PMD_ORDER)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { vmf.orig_pmd = pmdp_get_lockless(vmf.pmd); if (unlikely(is_swap_pmd(vmf.orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(vmf.orig_pmd)); if (is_pmd_migration_entry(vmf.orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) { if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf); if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !pmd_write(vmf.orig_pmd)) { ret = wp_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pmd_set_accessed(&vmf); return 0; } } } return handle_pte_fault(&vmf); } /** * mm_account_fault - Do page fault accounting * @mm: mm from which memcg should be extracted. It can be NULL. * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting * of perf event counters, but we'll still do the per-task accounting to * the task who triggered this page fault. * @address: the faulted address. * @flags: the fault flags. * @ret: the fault retcode. * * This will take care of most of the page fault accounting. Meanwhile, it * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter * updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ static inline void mm_account_fault(struct mm_struct *mm, struct pt_regs *regs, unsigned long address, unsigned int flags, vm_fault_t ret) { bool major; /* Incomplete faults will be accounted upon completion. */ if (ret & VM_FAULT_RETRY) return; /* * To preserve the behavior of older kernels, PGFAULT counters record * both successful and failed faults, as opposed to perf counters, * which ignore failed cases. */ count_vm_event(PGFAULT); count_memcg_event_mm(mm, PGFAULT); /* * Do not account for unsuccessful faults (e.g. when the address wasn't * valid). That includes arch_vma_access_permitted() failing before * reaching here. So this is not a "this many hardware page faults" * counter. We should use the hw profiling for that. */ if (ret & VM_FAULT_ERROR) return; /* * We define the fault as a major fault when the final successful fault * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't * handle it immediately previously). */ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); if (major) current->maj_flt++; else current->min_flt++; /* * If the fault is done for GUP, regs will be NULL. We only do the * accounting for the per thread fault counters who triggered the * fault, and we skip the perf event updates. */ if (!regs) return; if (major) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); else perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } #ifdef CONFIG_LRU_GEN static void lru_gen_enter_fault(struct vm_area_struct *vma) { /* the LRU algorithm only applies to accesses with recency */ current->in_lru_fault = vma_has_recency(vma); } static void lru_gen_exit_fault(void) { current->in_lru_fault = false; } #else static void lru_gen_enter_fault(struct vm_area_struct *vma) { } static void lru_gen_exit_fault(void) { } #endif /* CONFIG_LRU_GEN */ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma, unsigned int *flags) { if (unlikely(*flags & FAULT_FLAG_UNSHARE)) { if (WARN_ON_ONCE(*flags & FAULT_FLAG_WRITE)) return VM_FAULT_SIGSEGV; /* * FAULT_FLAG_UNSHARE only applies to COW mappings. Let's * just treat it like an ordinary read-fault otherwise. */ if (!is_cow_mapping(vma->vm_flags)) *flags &= ~FAULT_FLAG_UNSHARE; } else if (*flags & FAULT_FLAG_WRITE) { /* Write faults on read-only mappings are impossible ... */ if (WARN_ON_ONCE(!(vma->vm_flags & VM_MAYWRITE))) return VM_FAULT_SIGSEGV; /* ... and FOLL_FORCE only applies to COW mappings. */ if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE) && !is_cow_mapping(vma->vm_flags))) return VM_FAULT_SIGSEGV; } #ifdef CONFIG_PER_VMA_LOCK /* * Per-VMA locks can't be used with FAULT_FLAG_RETRY_NOWAIT because of * the assumption that lock is dropped on VM_FAULT_RETRY. */ if (WARN_ON_ONCE((*flags & (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)) == (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT))) return VM_FAULT_SIGSEGV; #endif return 0; } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __folio_lock_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* If the fault handler drops the mmap_lock, vma may be freed */ struct mm_struct *mm = vma->vm_mm; vm_fault_t ret; bool is_droppable; __set_current_state(TASK_RUNNING); ret = sanitize_fault_flags(vma, &flags); if (ret) goto out; if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) { ret = VM_FAULT_SIGSEGV; goto out; } is_droppable = !!(vma->vm_flags & VM_DROPPABLE); /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. */ if (flags & FAULT_FLAG_USER) mem_cgroup_enter_user_fault(); lru_gen_enter_fault(vma); if (unlikely(is_vm_hugetlb_page(vma))) ret = hugetlb_fault(vma->vm_mm, vma, address, flags); else ret = __handle_mm_fault(vma, address, flags); /* * Warning: It is no longer safe to dereference vma-> after this point, * because mmap_lock might have been dropped by __handle_mm_fault(), so * vma might be destroyed from underneath us. */ lru_gen_exit_fault(); /* If the mapping is droppable, then errors due to OOM aren't fatal. */ if (is_droppable) ret &= ~VM_FAULT_OOM; if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* * The task may have entered a memcg OOM situation but * if the allocation error was handled gracefully (no * VM_FAULT_OOM), there is no need to kill anything. * Just clean up the OOM state peacefully. */ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false); } out: mm_account_fault(mm, regs, address, flags, ret); return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); #ifdef CONFIG_LOCK_MM_AND_FIND_VMA #include <linux/extable.h> static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs) { if (likely(mmap_read_trylock(mm))) return true; if (regs && !user_mode(regs)) { unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } return !mmap_read_lock_killable(mm); } static inline bool mmap_upgrade_trylock(struct mm_struct *mm) { /* * We don't have this operation yet. * * It should be easy enough to do: it's basically a * atomic_long_try_cmpxchg_acquire() * from RWSEM_READER_BIAS -> RWSEM_WRITER_LOCKED, but * it also needs the proper lockdep magic etc. */ return false; } static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs) { mmap_read_unlock(mm); if (regs && !user_mode(regs)) { unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } return !mmap_write_lock_killable(mm); } /* * Helper for page fault handling. * * This is kind of equivalend to "mmap_read_lock()" followed * by "find_extend_vma()", except it's a lot more careful about * the locking (and will drop the lock on failure). * * For example, if we have a kernel bug that causes a page * fault, we don't want to just use mmap_read_lock() to get * the mm lock, because that would deadlock if the bug were * to happen while we're holding the mm lock for writing. * * So this checks the exception tables on kernel faults in * order to only do this all for instructions that are actually * expected to fault. * * We can also actually take the mm lock for writing if we * need to extend the vma, which helps the VM layer a lot. */ struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long addr, struct pt_regs *regs) { struct vm_area_struct *vma; if (!get_mmap_lock_carefully(mm, regs)) return NULL; vma = find_vma(mm, addr); if (likely(vma && (vma->vm_start <= addr))) return vma; /* * Well, dang. We might still be successful, but only * if we can extend a vma to do so. */ if (!vma || !(vma->vm_flags & VM_GROWSDOWN)) { mmap_read_unlock(mm); return NULL; } /* * We can try to upgrade the mmap lock atomically, * in which case we can continue to use the vma * we already looked up. * * Otherwise we'll have to drop the mmap lock and * re-take it, and also look up the vma again, * re-checking it. */ if (!mmap_upgrade_trylock(mm)) { if (!upgrade_mmap_lock_carefully(mm, regs)) return NULL; vma = find_vma(mm, addr); if (!vma) goto fail; if (vma->vm_start <= addr) goto success; if (!(vma->vm_flags & VM_GROWSDOWN)) goto fail; } if (expand_stack_locked(vma, addr)) goto fail; success: mmap_write_downgrade(mm); return vma; fail: mmap_write_unlock(mm); return NULL; } #endif #ifdef CONFIG_PER_VMA_LOCK /* * Lookup and lock a VMA under RCU protection. Returned VMA is guaranteed to be * stable and not isolated. If the VMA is not found or is being modified the * function returns NULL. */ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) { MA_STATE(mas, &mm->mm_mt, address, address); struct vm_area_struct *vma; rcu_read_lock(); retry: vma = mas_walk(&mas); if (!vma) goto inval; if (!vma_start_read(vma)) goto inval; /* Check if the VMA got isolated after we found it */ if (vma->detached) { vma_end_read(vma); count_vm_vma_lock_event(VMA_LOCK_MISS); /* The area was replaced with another one */ goto retry; } /* * At this point, we have a stable reference to a VMA: The VMA is * locked and we know it hasn't already been isolated. * From here on, we can access the VMA without worrying about which * fields are accessible for RCU readers. */ /* Check since vm_start/vm_end might change before we lock the VMA */ if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto inval_end_read; rcu_read_unlock(); return vma; inval_end_read: vma_end_read(vma); inval: rcu_read_unlock(); count_vm_vma_lock_event(VMA_LOCK_ABORT); return NULL; } #endif /* CONFIG_PER_VMA_LOCK */ #ifndef __PAGETABLE_P4D_FOLDED /* * Allocate p4d page table. * We've already handled the fast-path in-line. */ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { p4d_t *new = p4d_alloc_one(mm, address); if (!new) return -ENOMEM; spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) { /* Another has populated it */ p4d_free(mm, new); } else { smp_wmb(); /* See comment in pmd_install() */ pgd_populate(mm, pgd, new); } spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_P4D_FOLDED */ #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) return -ENOMEM; spin_lock(&mm->page_table_lock); if (!p4d_present(*p4d)) { mm_inc_nr_puds(mm); smp_wmb(); /* See comment in pmd_install() */ p4d_populate(mm, p4d, new); } else /* Another has populated it */ pud_free(mm, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED /* * Allocate page middle directory. * We've already handled the fast-path in-line. */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; ptl = pud_lock(mm, pud); if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); smp_wmb(); /* See comment in pmd_install() */ pud_populate(mm, pud, new); } else { /* Another has populated it */ pmd_free(mm, new); } spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ static inline void pfnmap_args_setup(struct follow_pfnmap_args *args, spinlock_t *lock, pte_t *ptep, pgprot_t pgprot, unsigned long pfn_base, unsigned long addr_mask, bool writable, bool special) { args->lock = lock; args->ptep = ptep; args->pfn = pfn_base + ((args->address & ~addr_mask) >> PAGE_SHIFT); args->pgprot = pgprot; args->writable = writable; args->special = special; } static inline void pfnmap_lockdep_assert(struct vm_area_struct *vma) { #ifdef CONFIG_LOCKDEP struct address_space *mapping = vma->vm_file->f_mapping; if (mapping) lockdep_assert(lockdep_is_held(&vma->vm_file->f_mapping->i_mmap_rwsem) || lockdep_is_held(&vma->vm_mm->mmap_lock)); else lockdep_assert(lockdep_is_held(&vma->vm_mm->mmap_lock)); #endif } /** * follow_pfnmap_start() - Look up a pfn mapping at a user virtual address * @args: Pointer to struct @follow_pfnmap_args * * The caller needs to setup args->vma and args->address to point to the * virtual address as the target of such lookup. On a successful return, * the results will be put into other output fields. * * After the caller finished using the fields, the caller must invoke * another follow_pfnmap_end() to proper releases the locks and resources * of such look up request. * * During the start() and end() calls, the results in @args will be valid * as proper locks will be held. After the end() is called, all the fields * in @follow_pfnmap_args will be invalid to be further accessed. Further * use of such information after end() may require proper synchronizations * by the caller with page table updates, otherwise it can create a * security bug. * * If the PTE maps a refcounted page, callers are responsible to protect * against invalidation with MMU notifiers; otherwise access to the PFN at * a later point in time can trigger use-after-free. * * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore * should be taken for read, and the mmap semaphore cannot be released * before the end() is invoked. * * This function must not be used to modify PTE content. * * Return: zero on success, negative otherwise. */ int follow_pfnmap_start(struct follow_pfnmap_args *args) { struct vm_area_struct *vma = args->vma; unsigned long address = args->address; struct mm_struct *mm = vma->vm_mm; spinlock_t *lock; pgd_t *pgdp; p4d_t *p4dp, p4d; pud_t *pudp, pud; pmd_t *pmdp, pmd; pte_t *ptep, pte; pfnmap_lockdep_assert(vma); if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto out; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) goto out; retry: pgdp = pgd_offset(mm, address); if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp))) goto out; p4dp = p4d_offset(pgdp, address); p4d = READ_ONCE(*p4dp); if (p4d_none(p4d) || unlikely(p4d_bad(p4d))) goto out; pudp = pud_offset(p4dp, address); pud = READ_ONCE(*pudp); if (pud_none(pud)) goto out; if (pud_leaf(pud)) { lock = pud_lock(mm, pudp); if (!unlikely(pud_leaf(pud))) { spin_unlock(lock); goto retry; } pfnmap_args_setup(args, lock, NULL, pud_pgprot(pud), pud_pfn(pud), PUD_MASK, pud_write(pud), pud_special(pud)); return 0; } pmdp = pmd_offset(pudp, address); pmd = pmdp_get_lockless(pmdp); if (pmd_leaf(pmd)) { lock = pmd_lock(mm, pmdp); if (!unlikely(pmd_leaf(pmd))) { spin_unlock(lock); goto retry; } pfnmap_args_setup(args, lock, NULL, pmd_pgprot(pmd), pmd_pfn(pmd), PMD_MASK, pmd_write(pmd), pmd_special(pmd)); return 0; } ptep = pte_offset_map_lock(mm, pmdp, address, &lock); if (!ptep) goto out; pte = ptep_get(ptep); if (!pte_present(pte)) goto unlock; pfnmap_args_setup(args, lock, ptep, pte_pgprot(pte), pte_pfn(pte), PAGE_MASK, pte_write(pte), pte_special(pte)); return 0; unlock: pte_unmap_unlock(ptep, lock); out: return -EINVAL; } EXPORT_SYMBOL_GPL(follow_pfnmap_start); /** * follow_pfnmap_end(): End a follow_pfnmap_start() process * @args: Pointer to struct @follow_pfnmap_args * * Must be used in pair of follow_pfnmap_start(). See the start() function * above for more information. */ void follow_pfnmap_end(struct follow_pfnmap_args *args) { if (args->lock) spin_unlock(args->lock); if (args->ptep) pte_unmap(args->ptep); } EXPORT_SYMBOL_GPL(follow_pfnmap_end); #ifdef CONFIG_HAVE_IOREMAP_PROT /** * generic_access_phys - generic implementation for iomem mmap access * @vma: the vma to access * @addr: userspace address, not relative offset within @vma * @buf: buffer to read/write * @len: length of transfer * @write: set to FOLL_WRITE when writing, otherwise reading * * This is a generic implementation for &vm_operations_struct.access for an * iomem mapping. This callback is used by access_process_vm() when the @vma is * not page based. */ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; unsigned long prot = 0; void __iomem *maddr; int offset = offset_in_page(addr); int ret = -EINVAL; bool writable; struct follow_pfnmap_args args = { .vma = vma, .address = addr }; retry: if (follow_pfnmap_start(&args)) return -EINVAL; prot = pgprot_val(args.pgprot); phys_addr = (resource_size_t)args.pfn << PAGE_SHIFT; writable = args.writable; follow_pfnmap_end(&args); if ((write & FOLL_WRITE) && !writable) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; if (follow_pfnmap_start(&args)) goto out_unmap; if ((prot != pgprot_val(args.pgprot)) || (phys_addr != (args.pfn << PAGE_SHIFT)) || (writable != args.writable)) { follow_pfnmap_end(&args); iounmap(maddr); goto retry; } if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); ret = len; follow_pfnmap_end(&args); out_unmap: iounmap(maddr); return ret; } EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* * Access another process' address space as given in mm. */ static int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { void *old_buf = buf; int write = gup_flags & FOLL_WRITE; if (mmap_read_lock_killable(mm)) return 0; /* Untag the address before looking up the VMA */ addr = untagged_addr_remote(mm, addr); /* Avoid triggering the temporary warning in __get_user_pages */ if (!vma_lookup(mm, addr) && !expand_stack(mm, addr)) return 0; /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, offset; void *maddr; struct vm_area_struct *vma = NULL; struct page *page = get_user_page_vma_remote(mm, addr, gup_flags, &vma); if (IS_ERR(page)) { /* We might need to expand the stack to access it */ vma = vma_lookup(mm, addr); if (!vma) { vma = expand_stack(mm, addr); /* mmap_lock was dropped on failure */ if (!vma) return buf - old_buf; /* Try again if stack expansion worked */ continue; } /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ bytes = 0; #ifdef CONFIG_HAVE_IOREMAP_PROT if (vma->vm_ops && vma->vm_ops->access) bytes = vma->vm_ops->access(vma, addr, buf, len, write); #endif if (bytes <= 0) break; } else { bytes = len; offset = addr & (PAGE_SIZE-1); if (bytes > PAGE_SIZE-offset) bytes = PAGE_SIZE-offset; maddr = kmap_local_page(page); if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); set_page_dirty_lock(page); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); } unmap_and_put_page(page, maddr); } len -= bytes; buf += bytes; addr += bytes; } mmap_read_unlock(mm); return buf - old_buf; } /** * access_remote_vm - access another process' address space * @mm: the mm_struct of the target address space * @addr: start address to access * @buf: source or destination buffer * @len: number of bytes to transfer * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. * * Return: number of bytes copied from source to destination. */ int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { return __access_remote_vm(mm, addr, buf, len, gup_flags); } /* * Access another process' address space. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = __access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } EXPORT_SYMBOL_GPL(access_process_vm); /* * Print the name of a VMA. */ void print_vma_addr(char *prefix, unsigned long ip) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; /* * we might be running from an atomic context so we cannot sleep */ if (!mmap_read_trylock(mm)) return; vma = vma_lookup(mm, ip); if (vma && vma->vm_file) { struct file *f = vma->vm_file; ip -= vma->vm_start; ip += vma->vm_pgoff << PAGE_SHIFT; printk("%s%pD[%lx,%lx+%lx]", prefix, f, ip, vma->vm_start, vma->vm_end - vma->vm_start); } mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void __might_fault(const char *file, int line) { if (pagefault_disabled()) return; __might_sleep(file, line); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_lock); #endif } EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) /* * Process all subpages of the specified huge page with the specified * operation. The target subpage will be processed last to keep its * cache lines hot. */ static inline int process_huge_page( unsigned long addr_hint, unsigned int nr_pages, int (*process_subpage)(unsigned long addr, int idx, void *arg), void *arg) { int i, n, base, l, ret; unsigned long addr = addr_hint & ~(((unsigned long)nr_pages << PAGE_SHIFT) - 1); /* Process target subpage last to keep its cache lines hot */ might_sleep(); n = (addr_hint - addr) / PAGE_SIZE; if (2 * n <= nr_pages) { /* If target subpage in first half of huge page */ base = 0; l = n; /* Process subpages at the end of huge page */ for (i = nr_pages - 1; i >= 2 * n; i--) { cond_resched(); ret = process_subpage(addr + i * PAGE_SIZE, i, arg); if (ret) return ret; } } else { /* If target subpage in second half of huge page */ base = nr_pages - 2 * (nr_pages - n); l = nr_pages - n; /* Process subpages at the begin of huge page */ for (i = 0; i < base; i++) { cond_resched(); ret = process_subpage(addr + i * PAGE_SIZE, i, arg); if (ret) return ret; } } /* * Process remaining subpages in left-right-left-right pattern * towards the target subpage */ for (i = 0; i < l; i++) { int left_idx = base + i; int right_idx = base + 2 * l - 1 - i; cond_resched(); ret = process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); if (ret) return ret; cond_resched(); ret = process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); if (ret) return ret; } return 0; } static void clear_gigantic_page(struct folio *folio, unsigned long addr, unsigned int nr_pages) { int i; might_sleep(); for (i = 0; i < nr_pages; i++) { cond_resched(); clear_user_highpage(folio_page(folio, i), addr + i * PAGE_SIZE); } } static int clear_subpage(unsigned long addr, int idx, void *arg) { struct folio *folio = arg; clear_user_highpage(folio_page(folio, idx), addr); return 0; } /** * folio_zero_user - Zero a folio which will be mapped to userspace. * @folio: The folio to zero. * @addr_hint: The address will be accessed or the base address if uncelar. */ void folio_zero_user(struct folio *folio, unsigned long addr_hint) { unsigned int nr_pages = folio_nr_pages(folio); if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) clear_gigantic_page(folio, addr_hint, nr_pages); else process_huge_page(addr_hint, nr_pages, clear_subpage, folio); } static int copy_user_gigantic_page(struct folio *dst, struct folio *src, unsigned long addr, struct vm_area_struct *vma, unsigned int nr_pages) { int i; struct page *dst_page; struct page *src_page; for (i = 0; i < nr_pages; i++) { dst_page = folio_page(dst, i); src_page = folio_page(src, i); cond_resched(); if (copy_mc_user_highpage(dst_page, src_page, addr + i*PAGE_SIZE, vma)) return -EHWPOISON; } return 0; } struct copy_subpage_arg { struct folio *dst; struct folio *src; struct vm_area_struct *vma; }; static int copy_subpage(unsigned long addr, int idx, void *arg) { struct copy_subpage_arg *copy_arg = arg; struct page *dst = folio_page(copy_arg->dst, idx); struct page *src = folio_page(copy_arg->src, idx); if (copy_mc_user_highpage(dst, src, addr, copy_arg->vma)) return -EHWPOISON; return 0; } int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma) { unsigned int nr_pages = folio_nr_pages(dst); struct copy_subpage_arg arg = { .dst = dst, .src = src, .vma = vma, }; if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) return copy_user_gigantic_page(dst, src, addr_hint, vma, nr_pages); return process_huge_page(addr_hint, nr_pages, copy_subpage, &arg); } long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault) { void *kaddr; unsigned long i, rc = 0; unsigned int nr_pages = folio_nr_pages(dst_folio); unsigned long ret_val = nr_pages * PAGE_SIZE; struct page *subpage; for (i = 0; i < nr_pages; i++) { subpage = folio_page(dst_folio, i); kaddr = kmap_local_page(subpage); if (!allow_pagefault) pagefault_disable(); rc = copy_from_user(kaddr, usr_src + i * PAGE_SIZE, PAGE_SIZE); if (!allow_pagefault) pagefault_enable(); kunmap_local(kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) break; flush_dcache_page(subpage); cond_resched(); } return ret_val; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if defined(CONFIG_SPLIT_PTE_PTLOCKS) && ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep; void __init ptlock_cache_init(void) { page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, SLAB_PANIC, NULL); } bool ptlock_alloc(struct ptdesc *ptdesc) { spinlock_t *ptl; ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); if (!ptl) return false; ptdesc->ptl = ptl; return true; } void ptlock_free(struct ptdesc *ptdesc) { kmem_cache_free(page_ptl_cachep, ptdesc->ptl); } #endif void vma_pgtable_walk_begin(struct vm_area_struct *vma) { if (is_vm_hugetlb_page(vma)) hugetlb_vma_lock_read(vma); } void vma_pgtable_walk_end(struct vm_area_struct *vma) { if (is_vm_hugetlb_page(vma)) hugetlb_vma_unlock_read(vma); } |
| 142 44 319 321 321 320 75 161 22 21 52 16 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/khugepaged.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include <linux/tracepoint-defs.h> /* Internal core VMA manipulation functions. */ #include "vma.h" struct folio_batch; /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* * Different from WARN_ON_ONCE(), no warning will be issued * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ __warned = true; \ WARN_ON(1); \ } \ unlikely(__ret_warn_once); \ }) void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ #define ENTIRELY_MAPPED 0x800000 #define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. * * Don't use this function outside of debugging code. */ static inline int folio_nr_pages_mapped(const struct folio *folio) { return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } /* * Retrieve the first entry of a folio based on a provided entry within the * folio. We cannot rely on folio->swap as there is no guarantee that it has * been initialized. Used for calling arch_swap_restore() */ static inline swp_entry_t folio_swap(swp_entry_t entry, const struct folio *folio) { swp_entry_t swap = { .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), }; return swap; } static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ typedef int __bitwise fpb_t; /* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */ #define FPB_IGNORE_DIRTY ((__force fpb_t)BIT(0)) /* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */ #define FPB_IGNORE_SOFT_DIRTY ((__force fpb_t)BIT(1)) static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) { if (flags & FPB_IGNORE_DIRTY) pte = pte_mkclean(pte); if (likely(flags & FPB_IGNORE_SOFT_DIRTY)) pte = pte_clear_soft_dirty(pte); return pte_wrprotect(pte_mkold(pte)); } /** * folio_pte_batch - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @addr: The user virtual address the first page is mapped at. * @start_ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @max_nr: The maximum number of table entries to consider. * @flags: Flags to modify the PTE batch semantics. * @any_writable: Optional pointer to indicate whether any entry except the * first one is writable. * @any_young: Optional pointer to indicate whether any entry except the * first one is young. * @any_dirty: Optional pointer to indicate whether any entry except the * first one is dirty. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY). * * start_ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, bool *any_writable, bool *any_young, bool *any_dirty) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; bool writable, young, dirty; int nr; if (any_writable) *any_writable = false; if (any_young) *any_young = false; if (any_dirty) *any_dirty = false; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); nr = pte_batch_hint(start_ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = start_ptep + nr; while (ptep < end_ptep) { pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); if (any_young) young = !!pte_young(pte); if (any_dirty) dirty = !!pte_dirty(pte); pte = __pte_batch_clear_ignored(pte, flags); if (!pte_same(pte, expected_pte)) break; /* * Stop immediately once we reached the end of the folio. In * corner cases the next PFN might fall into a different * folio. */ if (pte_pfn(pte) >= folio_end_pfn) break; if (any_writable) *any_writable |= writable; if (any_young) *any_young |= young; if (any_dirty) *any_dirty |= dirty; nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); ptep += nr; } return min(ptep - start_ptep, max_nr); } /** * pte_move_swp_offset - Move the swap entry offset field of a swap pte * forward or backward by delta * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * @delta: The direction and the offset we are moving; forward if delta * is positive; backward if delta is negative * * Moves the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_move_swp_offset(pte_t pte, long delta) { swp_entry_t entry = pte_to_swp_entry(pte); pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), (swp_offset(entry) + delta))); if (pte_swp_soft_dirty(pte)) new = pte_swp_mksoft_dirty(new); if (pte_swp_exclusive(pte)) new = pte_swp_mkexclusive(new); if (pte_swp_uffd_wp(pte)) new = pte_swp_mkuffd_wp(new); return new; } /** * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * * Increments the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_next_swp_offset(pte_t pte) { return pte_move_swp_offset(pte, 1); } /** * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries * @start_ptep: Page table pointer for the first entry. * @max_nr: The maximum number of table entries to consider. * @pte: Page table entry for the first entry. * * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs * containing swap entries all with consecutive offsets and targeting the same * swap type, all with matching swp pte bits. * * max_nr must be at least one and must be limited by the caller so scanning * cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) { pte_t expected_pte = pte_next_swp_offset(pte); const pte_t *end_ptep = start_ptep + max_nr; swp_entry_t entry = pte_to_swp_entry(pte); pte_t *ptep = start_ptep + 1; unsigned short cgroup_id; VM_WARN_ON(max_nr < 1); VM_WARN_ON(!is_swap_pte(pte)); VM_WARN_ON(non_swap_entry(entry)); cgroup_id = lookup_swap_cgroup_id(entry); while (ptep < end_ptep) { pte = ptep_get(ptep); if (!pte_same(pte, expected_pte)) break; if (lookup_swap_cgroup_id(pte_to_swp_entry(pte)) != cgroup_id) break; expected_pte = pte_next_swp_offset(expected_pte); ptep++; } return ptep - start_ptep; } #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) { pg_data_t *pgdat = folio_pgdat(folio); int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); if (nr_throttled) __acct_reclaim_writeback(pgdat, folio, nr_throttled); } static inline void wake_throttle_isolated(pg_data_t *pgdat) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; if (waitqueue_active(wqh)) wake_up(wqh); } vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf); static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) { vm_fault_t ret = __vmf_anon_prepare(vmf); if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vmf->vma); return ret; } vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void deactivate_file_folio(struct folio *folio); void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling, bool mm_wr_locked); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *, unsigned int order); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); /** * folio_evictable - Test whether a folio is evictable. * @folio: The folio to test. * * Test whether @folio is evictable -- i.e., should be placed on * active/inactive lists vs unevictable list. * * Reasons folio might not be evictable: * 1. folio's mapping marked unevictable * 2. One of the pages in the folio is part of an mlocked VMA */ static inline bool folio_evictable(struct folio *folio) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } /* * Return true if a folio needs ->release_folio() calling upon it. */ static inline bool folio_needs_release(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); return folio_has_private(folio) || (mapping && mapping_release_always(mapping)); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ bool folio_isolate_lru(struct folio *folio); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); /* * in mm/rmap.c: */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ #define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; /* perform sanity checks on struct pages being allocated or freed */ DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we set PageBuddy. * Setting, clearing, and testing PageBuddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline bool page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { if (!page_is_guard(buddy) && !PageBuddy(buddy)) return false; if (buddy_order(buddy) != order) return false; /* * zone check is done late to avoid uselessly calculating * zone/node ids for pages that could never merge. */ if (page_zone_id(page) != page_zone_id(buddy)) return false; VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return true; } /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } /* * Find the buddy of @page and validate it. * @page: The input page * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the * function is used in the performance-critical __free_one_page(). * @order: The order of the page * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to * page_to_pfn(). * * The found buddy can be a non PageBuddy, out of @page's zone, or its order is * not the same as @page. The validation is necessary before use it. * * Return: the found buddy page or NULL if not found. */ static inline struct page *find_buddy_page_pfn(struct page *page, unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) { unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); struct page *buddy; buddy = page + (__buddy_pfn - pfn); if (buddy_pfn) *buddy_pfn = __buddy_pfn; if (page_is_buddy(page, buddy, order)) return buddy; return NULL; } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } void set_zone_contiguous(struct zone *zone); static inline void clear_zone_contiguous(struct zone *zone) { zone->contiguous = false; } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order, enum meminit_context context); /* * This will have no effect, other than possibly generating a warning, if the * caller passes in a non-large folio. */ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; #ifdef CONFIG_64BIT folio->_folio_nr_pages = 1U << order; #endif } void __folio_undo_large_rmappable(struct folio *folio); static inline void folio_undo_large_rmappable(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) return; /* * At this point, there is no one trying to add the folio to * deferred_list. If folio is not in deferred_list, it's safe * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) return; __folio_undo_large_rmappable(folio); } static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio); return folio; } static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); if (order > 1) INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) { struct page *p = head + tail_idx; p->mapping = TAIL_MAPPING; set_compound_head(p, head); set_page_private(p, 0); } extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; void free_unref_page(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ bool finish_pageblock; /* Scan the remainder of a pageblock. Used * when there are potentially transient * isolation or migration failures to * ensure forward progress. */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long start, unsigned long end, int migratetype); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } /* mm/util.c */ struct anon_vma *folio_anon_vma(struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); /* * NOTE: This function can't tell whether the folio is "fully mapped" in the * range. * "fully mapped" means all the pages of folio is associated with the page * table of range while this function just check whether the folio range is * within the range [start, end). Function caller needs to do page table * check if it cares about the page table association. * * Typical usage (like mlock or madvise) is: * Caller knows at least 1 page of folio is associated with page table of VMA * and the range [start, end) is intersect with the VMA range. Caller wants * to know whether the folio is fully associated with the range. It calls * this function to check whether the folio is in the range first. Then checks * the page table to know whether the folio is fully mapped to the range. */ static inline bool folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) return false; if (start < vma->vm_start) start = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pgoff = folio_pgoff(folio); /* if folio start address is not in vma range */ if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) return false; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); return !(addr < start || end - addr < folio_size(folio)); } static inline bool folio_within_vma(struct folio *folio, struct vm_area_struct *vma) { return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); } /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. * 1) VM_IO check prevents migration from double-counting during mlock. * 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED * is never left set on a VM_SPECIAL vma, there is an interval while * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * munlock if the function is called. Ideally, we should only * do munlock if any page of folio is unmapped from VMA and * cause folio not fully mapped to VMA. * * But it's not easy to confirm that's the situation. So we * always munlock the folio and page reclaim will correct it * if it's wrong. */ if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } void mlock_new_folio(struct folio *folio); bool need_mlock_drain(int cpu); void mlock_drain_local(void); void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /** * vma_address - Find the virtual address a page range is mapped at * @vma: The vma which maps this object. * @pgoff: The page offset within its object. * @nr_pages: The number of pages to consider. * * If any page in this range is mapped by this VMA, return the first address * where any of these pages appear. Otherwise, return -EFAULT. */ static inline unsigned long vma_address(struct vm_area_struct *vma, pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; pgoff_t pgoff; unsigned long address; /* Common case, plus ->pgoff is invalid for KSM */ if (pvmw->nr_pages == 1) return pvmw->address + PAGE_SIZE; pgoff = pvmw->pgoff + pvmw->nr_pages; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); release_fault_lock(vmf); } return fpin; } #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } static inline void mlock_new_folio(struct folio *folio) { } static inline bool need_mlock_drain(int cpu) { return false; } static inline void mlock_drain_local(void) { } static inline void mlock_drain_remote(int cpu) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } #endif /* !CONFIG_MMU */ /* Memory initialisation debug and verification */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT DECLARE_STATIC_KEY_TRUE(deferred_pages); bool __init deferred_grow_zone(struct zone *zone, unsigned int order); #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } static inline int find_next_best_node(int node, nodemask_t *used_node_mask) { return NUMA_NO_NODE; } #endif /* * mm/memory-failure.c */ #ifdef CONFIG_MEMORY_FAILURE void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu); void shake_folio(struct folio *folio); extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; extern u32 hwpoison_filter_dev_minor; extern u64 hwpoison_filter_flags_mask; extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; #define MAGIC_HWPOISON 0x48575053U /* HWPS */ void SetPageHWPoisonTakenOff(struct page *page); void ClearPageHWPoisonTakenOff(struct page *page); bool take_page_off_buddy(struct page *page); bool put_page_back_buddy(struct page *page); struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); void add_to_kill_ksm(struct task_struct *tsk, struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long ksm_addr); unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); #else static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) { } #endif extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); struct folio *alloc_migrate_folio(struct folio *src, unsigned long private); unsigned long reclaim_pages(struct list_head *folio_list); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access * to 25% of the min watermark or * 62.5% if __GFP_HIGH is set. */ #define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50% * of the min watermark. */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */ #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ /* Flags that allow allocations below the min watermark. */ #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM) enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; static inline bool is_migrate_highatomic(enum migratetype migratetype) { return migratetype == MIGRATE_HIGHATOMIC; } void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; enum migrate_reason reason; }; /* * mm/filemap.c */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size); /* * mm/vmalloc.c */ #ifdef CONFIG_MMU void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); #else static inline void vmalloc_init(void) { } static inline int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { return -EINVAL; } #endif int __must_check __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int *flags, bool writable, int *last_cpupid); void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_folio(struct folio *folio); /* * mm/gup.c */ int __must_check try_grab_folio(struct folio *folio, int refs, unsigned int flags); /* * mm/huge_memory.c */ void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write); void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, /* a retry, previous pass started an IO */ FOLL_TRIED = 1 << 17, /* we are working on non-current tsk/mm */ FOLL_REMOTE = 1 << 18, /* pages must be released via unpin_user_page */ FOLL_PIN = 1 << 19, /* gup_fast: prevent fall-back to slow gup */ FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the * GUP pin will remain consistent with the pages mapped into the page tables * of the MM. * * Temporary unmapping of PageAnonExclusive() pages or clearing of * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. * * If the vma is NULL, we're coming from the GUP-fast path and might have * to fallback to the slow path just to lookup the vma. */ static inline bool gup_must_unshare(struct vm_area_struct *vma, unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry * has to be writable -- and if it references (part of) an anonymous * folio, that part is required to be marked exclusive. */ if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) return false; /* * Note: PageAnon(page) is stable until the page is actually getting * freed. */ if (!PageAnon(page)) { /* * We only care about R/O long-term pining: R/O short-term * pinning does not have the semantics to observe successive * changes through the process page tables. */ if (!(flags & FOLL_LONGTERM)) return false; /* We really need the vma ... */ if (!vma) return true; /* * ... because we only care about writable private ("COW") * mappings where we have to break COW early. */ return is_cow_mapping(vma->vm_flags); } /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); } extern bool mirrored_kernelcore; extern bool memblock_has_mirror(void); static __always_inline void vma_set_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; } static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) { /* * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty * enablements, because when without soft-dirty being compiled in, * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return false; /* * Soft-dirty is kind of special: its tracking is enabled when the * vma flags not set. */ return !(vma->vm_flags & VM_SOFTDIRTY); } static inline bool pmd_needs_soft_dirty_wp(struct vm_area_struct *vma, pmd_t pmd) { return vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd); } static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte) { return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte); } void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid); /* shrinker related functions */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); #ifdef CONFIG_64BIT static inline int can_do_mseal(unsigned long flags) { if (flags) return -EINVAL; return 0; } #else static inline int can_do_mseal(unsigned long flags) { return -EPERM; } #endif #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) { shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); return shrinker->name ? 0 : -ENOMEM; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { kfree_const(shrinker->name); shrinker->name = NULL; } extern int shrinker_debugfs_add(struct shrinker *shrinker); extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id); extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id); #else /* CONFIG_SHRINKER_DEBUG */ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, const char *fmt, va_list ap) { return 0; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { } static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id) { *debugfs_id = -1; return NULL; } static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) { } #endif /* CONFIG_SHRINKER_DEBUG */ /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; /* mremap.c */ unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, bool need_rmap_locks, bool for_stack); #ifdef CONFIG_UNACCEPTED_MEMORY void accept_page(struct page *page); #else /* CONFIG_UNACCEPTED_MEMORY */ static inline void accept_page(struct page *page) { } #endif /* CONFIG_UNACCEPTED_MEMORY */ #endif /* __MM_INTERNAL_H */ |
| 67 177 498 77 39 320 31 145 35 52 139 23 164 44 55 321 323 18 21 222 139 53 34 441 139 140 139 138 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Macros for manipulating and testing page->flags */ #ifndef PAGE_FLAGS_H #define PAGE_FLAGS_H #include <linux/types.h> #include <linux/bug.h> #include <linux/mmdebug.h> #ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> #include <generated/bounds.h> #endif /* !__GENERATING_BOUNDS_H */ /* * Various page->flags bits: * * PG_reserved is set for special pages. The "struct page" of such a page * should in general not be touched (e.g. set dirty) except by its owner. * Pages marked as PG_reserved include: * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS, * initrd, HW tables) * - Pages reserved or allocated early during boot (before the page allocator * was initialized). This includes (depending on the architecture) the * initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much * much more. Once (if ever) freed, PG_reserved is cleared and they will * be given to the page allocator. * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) * Some PG_reserved pages will be excluded from the hibernation image. * PG_reserved does in general not hinder anybody from dumping or swapping * and is no longer required for remap_pfn_range(). ioremap might require it. * Consequently, PG_reserved for a page mapped into user space can indicate * the zero page, the vDSO, MMIO pages or device memory. * * The PG_private bitflag is set on pagecache pages if they contain filesystem * specific data (which is normally at page->private). It can be used by * private allocations for its own usage. * * During initiation of disk I/O, PG_locked is set. This bit is set before I/O * and cleared when writeback _starts_ or when read _completes_. PG_writeback * is set before writeback starts and cleared when it finishes. * * PG_locked also pins a page in pagecache, and blocks truncation of the file * while it is held. * * page_waitqueue(page) is a wait queue of all tasks waiting for the page * to become unlocked. * * PG_swapbacked is set when a page uses swap as a backing storage. This are * usually PageAnon or shmem pages but please note that even anonymous pages * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! */ /* * Don't use the pageflags directly. Use the PageFoo macros. * * The page flags field is split into two parts, the main flags area * which extends from the low bits upwards, and the fields area which * extends from the high bits downwards. * * | FIELD | ... | FLAGS | * N-1 ^ 0 * (NR_PAGEFLAGS) * * The fields area is reserved for fields mapping zone, node (for NUMA) and * SPARSEMEM section (for variants of SPARSEMEM that require section ids like * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP). */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ PG_writeback, /* Page is under writeback */ PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_head, /* Must be in bit 6 */ PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_active, PG_workingset, PG_owner_priv_1, /* Owner use. If pagecache, fs may use */ PG_owner_2, /* Owner use. If pagecache, fs may use */ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_2 PG_arch_2, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_3 PG_arch_3, #endif __NR_PAGEFLAGS, PG_readahead = PG_reclaim, /* Anonymous memory (and shmem) */ PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ /* Some filesystems */ PG_checked = PG_owner_priv_1, /* * Depending on the way an anonymous folio can be mapped into a page * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped * THP), PG_anon_exclusive may be set only for the head page or for * tail pages of an anonymous folio. For now, we only expect it to be * set on tail pages for PTE-mapped THP. */ PG_anon_exclusive = PG_owner_2, /* * Set if all buffer heads in the folio are mapped. * Filesystems which do not use BHs can use it for their own purpose. */ PG_mappedtodisk = PG_owner_2, /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes * when those inodes are being locally cached. */ PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, /* non-lru isolated movable page */ PG_isolated = PG_reclaim, /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, #ifdef CONFIG_MEMORY_HOTPLUG /* For self-hosted memmap pages */ PG_vmemmap_self_hosted = PG_owner_priv_1, #endif /* * Flags only valid for compound pages. Stored in first tail page's * flags word. Cannot use the first 8 flags or any flag marked as * PF_ANY. */ /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */ }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) #ifndef __GENERATING_BOUNDS_H #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP DECLARE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key); /* * Return the real head page struct iff the @page is a fake head page, otherwise * return the @page itself. See Documentation/mm/vmemmap_dedup.rst. */ static __always_inline const struct page *page_fixed_fake_head(const struct page *page) { if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key)) return page; /* * Only addresses aligned with PAGE_SIZE of struct page may be fake head * struct page. The alignment check aims to avoid access the fields ( * e.g. compound_head) of the @page[1]. It can avoid touch a (possibly) * cold cacheline in some cases. */ if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) && test_bit(PG_head, &page->flags)) { /* * We can safely access the field of the @page[1] with PG_head * because the @page is a compound page composed with at least * two contiguous pages. */ unsigned long head = READ_ONCE(page[1].compound_head); if (likely(head & 1)) return (const struct page *)(head - 1); } return page; } #else static inline const struct page *page_fixed_fake_head(const struct page *page) { return page; } #endif static __always_inline int page_is_fake_head(const struct page *page) { return page_fixed_fake_head(page) != page; } static __always_inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return head - 1; return (unsigned long)page_fixed_fake_head(page); } #define compound_head(page) ((typeof(page))_compound_head(page)) /** * page_folio - Converts from page to folio. * @p: The page. * * Every page is part of a folio. This function cannot be called on a * NULL pointer. * * Context: No reference, nor lock is required on @page. If the caller * does not hold a reference, this call may race with a folio split, so * it should re-check the folio still contains this page after gaining * a reference on the folio. * Return: The folio which contains this page. */ #define page_folio(p) (_Generic((p), \ const struct page *: (const struct folio *)_compound_head(p), \ struct page *: (struct folio *)_compound_head(p))) /** * folio_page - Return a page from a folio. * @folio: The folio. * @n: The page number to return. * * @n is relative to the start of the folio. This function does not * check that the page number lies within @folio; the caller is presumed * to have a reference to the page. */ #define folio_page(folio, n) nth_page(&(folio)->page, n) static __always_inline int PageTail(const struct page *page) { return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page); } static __always_inline int PageCompound(const struct page *page) { return test_bit(PG_head, &page->flags) || READ_ONCE(page->compound_head) & 1; } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { return READ_ONCE(page->flags) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM void page_init_poison(struct page *page, size_t size); #else static inline void page_init_poison(struct page *page, size_t size) { } #endif static const unsigned long *const_folio_flags(const struct folio *folio, unsigned n) { const struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(PageTail(page), page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } static unsigned long *folio_flags(struct folio *folio, unsigned n) { struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(PageTail(page), page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } /* * Page flags policies wrt compound pages * * PF_POISONED_CHECK * check if this struct page poisoned/uninitialized * * PF_ANY: * the page flag is relevant for small, head and tail pages. * * PF_HEAD: * for compound page all operations related to the page flag applied to * head page. * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. * * PF_NO_COMPOUND: * the page flag is not relevant for compound pages. * * PF_SECOND: * the page flag is stored in the first tail page. */ #define PF_POISONED_CHECK(page) ({ \ VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \ page; }) #define PF_ANY(page, enforce) PF_POISONED_CHECK(page) #define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page)) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ PF_POISONED_CHECK(compound_head(page)); }) #define PF_NO_COMPOUND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ PF_POISONED_CHECK(page); }) #define PF_SECOND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) /* Which page is the flag stored in */ #define FOLIO_PF_ANY 0 #define FOLIO_PF_HEAD 0 #define FOLIO_PF_NO_TAIL 0 #define FOLIO_PF_NO_COMPOUND 0 #define FOLIO_PF_SECOND 1 #define FOLIO_HEAD_PAGE 0 #define FOLIO_SECOND_PAGE 1 /* * Macros to create function definitions for page flags */ #define FOLIO_TEST_FLAG(name, page) \ static __always_inline bool folio_test_##name(const struct folio *folio) \ { return test_bit(PG_##name, const_folio_flags(folio, page)); } #define FOLIO_SET_FLAG(name, page) \ static __always_inline void folio_set_##name(struct folio *folio) \ { set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void folio_clear_##name(struct folio *folio) \ { clear_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_SET_FLAG(name, page) \ static __always_inline void __folio_set_##name(struct folio *folio) \ { __set_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void __folio_clear_##name(struct folio *folio) \ { __clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_SET_FLAG(name, page) \ static __always_inline bool folio_test_set_##name(struct folio *folio) \ { return test_and_set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_CLEAR_FLAG(name, page) \ static __always_inline bool folio_test_clear_##name(struct folio *folio) \ { return test_and_clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_FLAG(name, page) \ FOLIO_TEST_FLAG(name, page) \ FOLIO_SET_FLAG(name, page) \ FOLIO_CLEAR_FLAG(name, page) #define TESTPAGEFLAG(uname, lname, policy) \ FOLIO_TEST_FLAG(lname, FOLIO_##policy) \ static __always_inline int Page##uname(const struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ __FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ __FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ FOLIO_TEST_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ FOLIO_TEST_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ SETPAGEFLAG(uname, lname, policy) \ CLEARPAGEFLAG(uname, lname, policy) #define __PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ __SETPAGEFLAG(uname, lname, policy) \ __CLEARPAGEFLAG(uname, lname, policy) #define TESTSCFLAG(uname, lname, policy) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) #define FOLIO_TEST_FLAG_FALSE(name) \ static inline bool folio_test_##name(const struct folio *folio) \ { return false; } #define FOLIO_SET_FLAG_NOOP(name) \ static inline void folio_set_##name(struct folio *folio) { } #define FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void folio_clear_##name(struct folio *folio) { } #define __FOLIO_SET_FLAG_NOOP(name) \ static inline void __folio_set_##name(struct folio *folio) { } #define __FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void __folio_clear_##name(struct folio *folio) { } #define FOLIO_TEST_SET_FLAG_FALSE(name) \ static inline bool folio_test_set_##name(struct folio *folio) \ { return false; } #define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ static inline bool folio_test_clear_##name(struct folio *folio) \ { return false; } #define FOLIO_FLAG_FALSE(name) \ FOLIO_TEST_FLAG_FALSE(name) \ FOLIO_SET_FLAG_NOOP(name) \ FOLIO_CLEAR_FLAG_NOOP(name) #define TESTPAGEFLAG_FALSE(uname, lname) \ FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ __FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname) #define TESTSCFLAG_FALSE(uname, lname) \ TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) TESTCLEARFLAG(LRU, lru, PF_HEAD) FOLIO_FLAG(active, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(swapbacked, FOLIO_HEAD_PAGE) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) /* owner_2 can be set on tail pages for anon memory */ FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE) #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not * available at this point. */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #define folio_test_highmem(__f) is_highmem_idx(folio_zonenum(__f)) #else PAGEFLAG_FALSE(HighMem, highmem) #endif #ifdef CONFIG_SWAP static __always_inline bool folio_test_swapcache(const struct folio *folio) { return folio_test_swapbacked(folio) && test_bit(PG_swapcache, const_folio_flags(folio, 0)); } FOLIO_SET_FLAG(swapcache, FOLIO_HEAD_PAGE) FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(swapcache) #endif FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) #ifdef CONFIG_MMU FOLIO_FLAG(mlocked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_SET_FLAG(mlocked, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(mlocked) __FOLIO_CLEAR_FLAG_NOOP(mlocked) FOLIO_TEST_CLEAR_FLAG_FALSE(mlocked) FOLIO_TEST_SET_FLAG_FALSE(mlocked) #endif #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif #ifdef CONFIG_PAGE_IDLE_FLAG #ifdef CONFIG_64BIT FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_FLAG(idle, FOLIO_HEAD_PAGE) #endif /* See page_idle.h for !64BIT workaround */ #else /* !CONFIG_PAGE_IDLE_FLAG */ FOLIO_FLAG_FALSE(young) FOLIO_TEST_CLEAR_FLAG_FALSE(young) FOLIO_FLAG_FALSE(idle) #endif /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set * operations as both should be shielded with the zone lock to prevent * any possible races on the setting or clearing of the bit. */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #ifdef CONFIG_MEMORY_HOTPLUG PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) #else PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) #endif /* * On an anonymous folio mapped into a user virtual memory area, * folio->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON * bit; and then folio->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable * page and then folio->mapping points to a struct movable_operations. * * Please note that, confusingly, "folio_mapping" refers to the inode * address_space which maps the folio from disk; whereas "folio_mapped" * refers to user virtual address space into which the folio is mapped. * * For slab pages, since slab reuses the bits in struct page to store its * internal states, the folio->mapping does not exist as such, nor do * these flags below. So in order to avoid testing non-existent bits, * please make sure that folio_test_slab(folio) actually evaluates to * false before calling the following functions (e.g., folio_test_anon). * See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) /* * Different with flags above, this flag is used only for fsdax mode. It * indicates that this page->mapping is now under reflink case. */ #define PAGE_MAPPING_DAX_SHARED ((void *)0x1) static __always_inline bool folio_mapping_flags(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline bool PageMappingFlags(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline bool folio_test_anon(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; } static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); } static __always_inline bool __folio_test_movable(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } static __always_inline bool __PageMovable(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } #ifdef CONFIG_KSM /* * A KSM page is one of those write-protected "shared pages" or "merged pages" * which KSM maps into multiple mms, wherever identical anonymous page content * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ static __always_inline bool folio_test_ksm(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } static __always_inline bool PageKsm(const struct page *page) { return folio_test_ksm(page_folio(page)); } #else TESTPAGEFLAG_FALSE(Ksm, ksm) #endif u64 stable_page_flags(const struct page *page); /** * folio_xor_flags_has_waiters - Change some folio flags. * @folio: The folio. * @mask: Bits set in this word will be changed. * * This must only be used for flags which are changed with the folio * lock held. For example, it is unsafe to use for PG_dirty as that * can be set without the folio lock held. It can also only be used * on flags which are in the range 0-6 as some of the implementations * only affect those bits. * * Return: Whether there are tasks waiting on the folio. */ static inline bool folio_xor_flags_has_waiters(struct folio *folio, unsigned long mask) { return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0)); } /** * folio_test_uptodate - Is this folio up to date? * @folio: The folio. * * The uptodate flag is set on a folio when every byte in the folio is * at least as new as the corresponding bytes on storage. Anonymous * and CoW folios are always uptodate. If the folio is not uptodate, * some of the bytes in it may be; see the is_partially_uptodate() * address_space operation. */ static inline bool folio_test_uptodate(const struct folio *folio) { bool ret = test_bit(PG_uptodate, const_folio_flags(folio, 0)); /* * Must ensure that the data we read out of the folio is loaded * _after_ we've loaded folio->flags to check the uptodate bit. * We can skip the barrier if the folio is not uptodate, because * we wouldn't be reading anything from it. * * See folio_mark_uptodate() for the other side of the story. */ if (ret) smp_rmb(); return ret; } static inline bool PageUptodate(const struct page *page) { return folio_test_uptodate(page_folio(page)); } static __always_inline void __folio_mark_uptodate(struct folio *folio) { smp_wmb(); __set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void folio_mark_uptodate(struct folio *folio) { /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the folio * uptodate are actually visible before folio_test_uptodate becomes true. */ smp_wmb(); set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void __SetPageUptodate(struct page *page) { __folio_mark_uptodate((struct folio *)page); } static __always_inline void SetPageUptodate(struct page *page) { folio_mark_uptodate((struct folio *)page); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) void __folio_start_writeback(struct folio *folio, bool keep_write); void set_page_writeback(struct page *page); #define folio_start_writeback(folio) \ __folio_start_writeback(folio, false) #define folio_start_writeback_keepwrite(folio) \ __folio_start_writeback(folio, true) static __always_inline bool folio_test_head(const struct folio *folio) { return test_bit(PG_head, const_folio_flags(folio, FOLIO_PF_ANY)); } static __always_inline int PageHead(const struct page *page) { PF_POISONED_CHECK(page); return test_bit(PG_head, &page->flags) && !page_is_fake_head(page); } __SETPAGEFLAG(Head, head, PF_ANY) __CLEARPAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) /** * folio_test_large() - Does this folio contain more than one page? * @folio: The folio to test. * * Return: True if the folio is larger than one page. */ static inline bool folio_test_large(const struct folio *folio) { return folio_test_head(folio); } static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); } static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_head, 0); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { BUG_ON(!PageHead(page)); ClearPageHead(page); } FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) FOLIO_TEST_FLAG(partially_mapped, FOLIO_SECOND_PAGE) /* * PG_partially_mapped is protected by deferred_split split_queue_lock, * so its safe to use non-atomic set/clear. */ __FOLIO_SET_FLAG(partially_mapped, FOLIO_SECOND_PAGE) __FOLIO_CLEAR_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(large_rmappable) FOLIO_TEST_FLAG_FALSE(partially_mapped) __FOLIO_SET_FLAG_NOOP(partially_mapped) __FOLIO_CLEAR_FLAG_NOOP(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for * normal or transparent huge pages. * * PageTransHuge() returns true for both transparent huge and * hugetlbfs pages, but not normal pages. PageTransHuge() can only be * called only in the core VM paths where hugetlbfs pages can't exist. */ static inline int PageTransHuge(const struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); return PageHead(page); } /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransCompound(const struct page *page) { return PageCompound(page); } /* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransTail(const struct page *page) { return PageTail(page); } #else TESTPAGEFLAG_FALSE(TransHuge, transhuge) TESTPAGEFLAG_FALSE(TransCompound, transcompound) TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap) TESTPAGEFLAG_FALSE(TransTail, transtail) #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE) /* * PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the * compound page. * * This flag is set by hwpoison handler. Cleared by THP split or free page. */ PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) #else PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif /* * For pages that do not use mapcount, page_type may be used. * The low 24 bits of pagetype may be used for your own purposes, as long * as you are careful to not affect the top 8 bits. The low bits of * pagetype will be overwritten when you clear the page_type from the page. */ enum pagetype { /* 0x00-0x7f are positive numbers, ie mapcount */ /* Reserve 0x80-0xef for mapcount overflow. */ PGTY_buddy = 0xf0, PGTY_offline = 0xf1, PGTY_table = 0xf2, PGTY_guard = 0xf3, PGTY_hugetlb = 0xf4, PGTY_slab = 0xf5, PGTY_zsmalloc = 0xf6, PGTY_unaccepted = 0xf7, PGTY_mapcount_underflow = 0xff }; static inline bool page_type_has_type(int page_type) { return page_type < (PGTY_mapcount_underflow << 24); } /* This takes a mapcount which is one more than page->_mapcount */ static inline bool page_mapcount_is_type(unsigned int mapcount) { return page_type_has_type(mapcount - 1); } static inline bool page_has_type(const struct page *page) { return page_mapcount_is_type(data_race(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ static __always_inline bool folio_test_##fname(const struct folio *folio) \ { \ return data_race(folio->page.page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ folio); \ folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type = UINT_MAX; \ } #define PAGE_TYPE_OPS(uname, lname, fname) \ FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return data_race(page->page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type = UINT_MAX; \ } /* * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ PAGE_TYPE_OPS(Buddy, buddy, buddy) /* * PageOffline() indicates that the page is logically offline although the * containing section is online. (e.g. inflated in a balloon driver or * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * * When a memory block gets onlined, all pages are initialized with a * refcount of 1 and PageOffline(). generic_online_page() will * take care of clearing PageOffline(). * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() * pages (now with a reference count of zero) are treated like free (unmanaged) * pages, allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will * require not giving them to the buddy via generic_online_page(). * * Memory offlining code will not adjust the managed page count for any * PageOffline() pages, treating them like they were never exposed to the * buddy using generic_online_page(). * * There are drivers that mark a page PageOffline() and expect there won't be * any further access to page content. PFN walkers that read content of random * pages should check PageOffline() and synchronize with such drivers using * page_offline_freeze()/page_offline_thaw(). */ PAGE_TYPE_OPS(Offline, offline, offline) extern void page_offline_freeze(void); extern void page_offline_thaw(void); extern void page_offline_begin(void); extern void page_offline_end(void); /* * Marks pages in use as page tables. */ PAGE_TYPE_OPS(Table, table, pgtable) /* * Marks guardpages used with debug_pagealloc. */ PAGE_TYPE_OPS(Guard, guard, guard) FOLIO_TYPE_OPS(slab, slab) /** * PageSlab - Determine if the page belongs to the slab allocator * @page: The page to test. * * Context: Any context. * Return: True for slab pages, false for any other kind of page. */ static inline bool PageSlab(const struct page *page) { return folio_test_slab(page_folio(page)); } #ifdef CONFIG_HUGETLB_PAGE FOLIO_TYPE_OPS(hugetlb, hugetlb) #else FOLIO_TEST_FLAG_FALSE(hugetlb) #endif PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) /* * Mark pages that has to be accepted before touched for the first time. * * Serialized with zone lock. */ PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted) /** * PageHuge - Determine if the page belongs to hugetlbfs * @page: The page to test. * * Context: Any context. * Return: True for hugetlbfs pages, false for anon pages or pages * belonging to other filesystems. */ static inline bool PageHuge(const struct page *page) { return folio_test_hugetlb(page_folio(page)); } /* * Check if a page is currently marked HWPoisoned. Note that this check is * best effort only and inherently racy: there is no way to synchronize with * failing hardware. */ static inline bool is_page_hwpoison(const struct page *page) { const struct folio *folio; if (PageHWPoison(page)) return true; folio = page_folio(page); return folio_test_hugetlb(folio) && PageHWPoison(&folio->page); } bool is_free_buddy_page(const struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); static __always_inline int PageAnonExclusive(const struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); /* * HugeTLB stores this information on the head page; THP keeps it per * page */ if (PageHuge(page)) page = compound_head(page); return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void SetPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void __ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else #define __PG_MLOCKED 0 #endif /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. If they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* * Flags checked when a page is prepped for return by the page allocator. * Pages being prepped should not have these flags set. If they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK) /* * Flags stored in the second page of a compound page. They may overlap * the CHECK_AT_FREE flags above, so need to be cleared. */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ 1UL << PG_large_rmappable | 1UL << PG_partially_mapped) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** * folio_has_private - Determine if folio has private stuff * @folio: The folio to be checked * * Determine if a folio has private stuff, indicating that release routines * should be invoked upon it. */ static inline int folio_has_private(const struct folio *folio) { return !!(folio->flags & PAGE_FLAGS_PRIVATE); } #undef PF_ANY #undef PF_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #undef PF_SECOND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ |
| 38 24 23 38 38 38 33 38 24 24 183 183 21 21 24 24 6 6 3 6 6 6 24 25 25 24 24 24 24 24 24 24 24 244 243 31 31 1 4 182 187 187 183 183 21 21 38 38 38 38 21 19 19 24 33 33 6 14 14 2 32 33 5 5 24 2 2 31 31 31 8 23 24 4 5 19 24 24 4 24 17 37 37 37 37 37 7 37 15 33 29 11 33 24 13 37 20 20 44 4 35 1 38 38 46 46 2 42 3 41 41 42 9 44 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/mman.h> #include <linux/kvm_host.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/sched/signal.h> #include <trace/events/kvm.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/kvm_arm.h> #include <asm/kvm_mmu.h> #include <asm/kvm_pgtable.h> #include <asm/kvm_ras.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/virt.h> #include "trace.h" static struct kvm_pgtable *hyp_pgtable; static DEFINE_MUTEX(kvm_hyp_pgd_mutex); static unsigned long __ro_after_init hyp_idmap_start; static unsigned long __ro_after_init hyp_idmap_end; static phys_addr_t __ro_after_init hyp_idmap_vector; static unsigned long __ro_after_init io_map_base; static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end, phys_addr_t size) { phys_addr_t boundary = ALIGN_DOWN(addr + size, size); return (boundary - 1 < end - 1) ? boundary : end; } static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) { phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL); return __stage2_range_addr_end(addr, end, size); } /* * Release kvm_mmu_lock periodically if the memory region is large. Otherwise, * we may see kernel panics with CONFIG_DETECT_HUNG_TASK, * CONFIG_LOCKUP_DETECTOR, CONFIG_LOCKDEP. Additionally, holding the lock too * long will also starve other vCPUs. We have to also make sure that the page * tables are not freed while we released the lock. */ static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end, int (*fn)(struct kvm_pgtable *, u64, u64), bool resched) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); int ret; u64 next; do { struct kvm_pgtable *pgt = mmu->pgt; if (!pgt) return -EINVAL; next = stage2_range_addr_end(addr, end); ret = fn(pgt, addr, next - addr); if (ret) break; if (resched && next != end) cond_resched_rwlock_write(&kvm->mmu_lock); } while (addr = next, addr != end); return ret; } #define stage2_apply_range_resched(mmu, addr, end, fn) \ stage2_apply_range(mmu, addr, end, fn, true) /* * Get the maximum number of page-tables pages needed to split a range * of blocks into PAGE_SIZE PTEs. It assumes the range is already * mapped at level 2, or at level 1 if allowed. */ static int kvm_mmu_split_nr_page_tables(u64 range) { int n = 0; if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2) n += DIV_ROUND_UP(range, PUD_SIZE); n += DIV_ROUND_UP(range, PMD_SIZE); return n; } static bool need_split_memcache_topup_or_resched(struct kvm *kvm) { struct kvm_mmu_memory_cache *cache; u64 chunk_size, min; if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) return true; chunk_size = kvm->arch.mmu.split_page_chunk_size; min = kvm_mmu_split_nr_page_tables(chunk_size); cache = &kvm->arch.mmu.split_page_cache; return kvm_mmu_memory_cache_nr_free_objects(cache) < min; } static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) { struct kvm_mmu_memory_cache *cache; struct kvm_pgtable *pgt; int ret, cache_capacity; u64 next, chunk_size; lockdep_assert_held_write(&kvm->mmu_lock); chunk_size = kvm->arch.mmu.split_page_chunk_size; cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size); if (chunk_size == 0) return 0; cache = &kvm->arch.mmu.split_page_cache; do { if (need_split_memcache_topup_or_resched(kvm)) { write_unlock(&kvm->mmu_lock); cond_resched(); /* Eager page splitting is best-effort. */ ret = __kvm_mmu_topup_memory_cache(cache, cache_capacity, cache_capacity); write_lock(&kvm->mmu_lock); if (ret) break; } pgt = kvm->arch.mmu.pgt; if (!pgt) return -EINVAL; next = __stage2_range_addr_end(addr, end, chunk_size); ret = kvm_pgtable_stage2_split(pgt, addr, next - addr, cache); if (ret) break; } while (addr = next, addr != end); return ret; } static bool memslot_is_logging(struct kvm_memory_slot *memslot) { return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY); } /** * kvm_arch_flush_remote_tlbs() - flush all VM TLB entries for v7/8 * @kvm: pointer to kvm structure. * * Interface to HYP function to flush all VM TLB entries */ int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); return 0; } int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { kvm_tlb_flush_vmid_range(&kvm->arch.mmu, gfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT); return 0; } static bool kvm_is_device_pfn(unsigned long pfn) { return !pfn_is_map_memory(pfn); } static void *stage2_memcache_zalloc_page(void *arg) { struct kvm_mmu_memory_cache *mc = arg; void *virt; /* Allocated with __GFP_ZERO, so no need to zero */ virt = kvm_mmu_memory_cache_alloc(mc); if (virt) kvm_account_pgtable_pages(virt, 1); return virt; } static void *kvm_host_zalloc_pages_exact(size_t size) { return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); } static void *kvm_s2_zalloc_pages_exact(size_t size) { void *virt = kvm_host_zalloc_pages_exact(size); if (virt) kvm_account_pgtable_pages(virt, (size >> PAGE_SHIFT)); return virt; } static void kvm_s2_free_pages_exact(void *virt, size_t size) { kvm_account_pgtable_pages(virt, -(size >> PAGE_SHIFT)); free_pages_exact(virt, size); } static struct kvm_pgtable_mm_ops kvm_s2_mm_ops; static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head) { struct page *page = container_of(head, struct page, rcu_head); void *pgtable = page_to_virt(page); s8 level = page_private(page); kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level); } static void stage2_free_unlinked_table(void *addr, s8 level) { struct page *page = virt_to_page(addr); set_page_private(page, (unsigned long)level); call_rcu(&page->rcu_head, stage2_free_unlinked_table_rcu_cb); } static void kvm_host_get_page(void *addr) { get_page(virt_to_page(addr)); } static void kvm_host_put_page(void *addr) { put_page(virt_to_page(addr)); } static void kvm_s2_put_page(void *addr) { struct page *p = virt_to_page(addr); /* Dropping last refcount, the page will be freed */ if (page_count(p) == 1) kvm_account_pgtable_pages(addr, -1); put_page(p); } static int kvm_host_page_count(void *addr) { return page_count(virt_to_page(addr)); } static phys_addr_t kvm_host_pa(void *addr) { return __pa(addr); } static void *kvm_host_va(phys_addr_t phys) { return __va(phys); } static void clean_dcache_guest_page(void *va, size_t size) { __clean_dcache_guest_page(va, size); } static void invalidate_icache_guest_page(void *va, size_t size) { __invalidate_icache_guest_page(va, size); } /* * Unmapping vs dcache management: * * If a guest maps certain memory pages as uncached, all writes will * bypass the data cache and go directly to RAM. However, the CPUs * can still speculate reads (not writes) and fill cache lines with * data. * * Those cache lines will be *clean* cache lines though, so a * clean+invalidate operation is equivalent to an invalidate * operation, because no cache lines are marked dirty. * * Those clean cache lines could be filled prior to an uncached write * by the guest, and the cache coherent IO subsystem would therefore * end up writing old data to disk. * * This is why right after unmapping a page/section and invalidating * the corresponding TLBs, we flush to make sure the IO subsystem will * never hit in the cache. * * This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as * we then fully enforce cacheability of RAM, no matter what the guest * does. */ /** * __unmap_stage2_range -- Clear stage2 page table entries to unmap a range * @mmu: The KVM stage-2 MMU pointer * @start: The intermediate physical base address of the range to unmap * @size: The size of the area to unmap * @may_block: Whether or not we are permitted to block * * Clear a range of stage-2 mappings, lowering the various ref-counts. Must * be called while holding mmu_lock (unless for freeing the stage2 pgd before * destroying the VM), otherwise another faulting VCPU may come in and mess * with things behind our backs. */ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, bool may_block) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); phys_addr_t end = start + size; lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON(size & ~PAGE_MASK); WARN_ON(stage2_apply_range(mmu, start, end, kvm_pgtable_stage2_unmap, may_block)); } void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, bool may_block) { __unmap_stage2_range(mmu, start, size, may_block); } void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_flush); } static void stage2_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) { phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t end = addr + PAGE_SIZE * memslot->npages; kvm_stage2_flush_range(&kvm->arch.mmu, addr, end); } /** * stage2_flush_vm - Invalidate cache for pages mapped in stage 2 * @kvm: The struct kvm pointer * * Go through the stage 2 page tables and invalidate any cache lines * backing memory already mapped to the VM. */ static void stage2_flush_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int idx, bkt; idx = srcu_read_lock(&kvm->srcu); write_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, bkt, slots) stage2_flush_memslot(kvm, memslot); kvm_nested_s2_flush(kvm); write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); } /** * free_hyp_pgds - free Hyp-mode page tables */ void __init free_hyp_pgds(void) { mutex_lock(&kvm_hyp_pgd_mutex); if (hyp_pgtable) { kvm_pgtable_hyp_destroy(hyp_pgtable); kfree(hyp_pgtable); hyp_pgtable = NULL; } mutex_unlock(&kvm_hyp_pgd_mutex); } static bool kvm_host_owns_hyp_mappings(void) { if (is_kernel_in_hyp_mode()) return false; if (static_branch_likely(&kvm_protected_mode_initialized)) return false; /* * This can happen at boot time when __create_hyp_mappings() is called * after the hyp protection has been enabled, but the static key has * not been flipped yet. */ if (!hyp_pgtable && is_protected_kvm_enabled()) return false; WARN_ON(!hyp_pgtable); return true; } int __create_hyp_mappings(unsigned long start, unsigned long size, unsigned long phys, enum kvm_pgtable_prot prot) { int err; if (WARN_ON(!kvm_host_owns_hyp_mappings())) return -EINVAL; mutex_lock(&kvm_hyp_pgd_mutex); err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot); mutex_unlock(&kvm_hyp_pgd_mutex); return err; } static phys_addr_t kvm_kaddr_to_phys(void *kaddr) { if (!is_vmalloc_addr(kaddr)) { BUG_ON(!virt_addr_valid(kaddr)); return __pa(kaddr); } else { return page_to_phys(vmalloc_to_page(kaddr)) + offset_in_page(kaddr); } } struct hyp_shared_pfn { u64 pfn; int count; struct rb_node node; }; static DEFINE_MUTEX(hyp_shared_pfns_lock); static struct rb_root hyp_shared_pfns = RB_ROOT; static struct hyp_shared_pfn *find_shared_pfn(u64 pfn, struct rb_node ***node, struct rb_node **parent) { struct hyp_shared_pfn *this; *node = &hyp_shared_pfns.rb_node; *parent = NULL; while (**node) { this = container_of(**node, struct hyp_shared_pfn, node); *parent = **node; if (this->pfn < pfn) *node = &((**node)->rb_left); else if (this->pfn > pfn) *node = &((**node)->rb_right); else return this; } return NULL; } static int share_pfn_hyp(u64 pfn) { struct rb_node **node, *parent; struct hyp_shared_pfn *this; int ret = 0; mutex_lock(&hyp_shared_pfns_lock); this = find_shared_pfn(pfn, &node, &parent); if (this) { this->count++; goto unlock; } this = kzalloc(sizeof(*this), GFP_KERNEL); if (!this) { ret = -ENOMEM; goto unlock; } this->pfn = pfn; this->count = 1; rb_link_node(&this->node, parent, node); rb_insert_color(&this->node, &hyp_shared_pfns); ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn, 1); unlock: mutex_unlock(&hyp_shared_pfns_lock); return ret; } static int unshare_pfn_hyp(u64 pfn) { struct rb_node **node, *parent; struct hyp_shared_pfn *this; int ret = 0; mutex_lock(&hyp_shared_pfns_lock); this = find_shared_pfn(pfn, &node, &parent); if (WARN_ON(!this)) { ret = -ENOENT; goto unlock; } this->count--; if (this->count) goto unlock; rb_erase(&this->node, &hyp_shared_pfns); kfree(this); ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn, 1); unlock: mutex_unlock(&hyp_shared_pfns_lock); return ret; } int kvm_share_hyp(void *from, void *to) { phys_addr_t start, end, cur; u64 pfn; int ret; if (is_kernel_in_hyp_mode()) return 0; /* * The share hcall maps things in the 'fixed-offset' region of the hyp * VA space, so we can only share physically contiguous data-structures * for now. */ if (is_vmalloc_or_module_addr(from) || is_vmalloc_or_module_addr(to)) return -EINVAL; if (kvm_host_owns_hyp_mappings()) return create_hyp_mappings(from, to, PAGE_HYP); start = ALIGN_DOWN(__pa(from), PAGE_SIZE); end = PAGE_ALIGN(__pa(to)); for (cur = start; cur < end; cur += PAGE_SIZE) { pfn = __phys_to_pfn(cur); ret = share_pfn_hyp(pfn); if (ret) return ret; } return 0; } void kvm_unshare_hyp(void *from, void *to) { phys_addr_t start, end, cur; u64 pfn; if (is_kernel_in_hyp_mode() || kvm_host_owns_hyp_mappings() || !from) return; start = ALIGN_DOWN(__pa(from), PAGE_SIZE); end = PAGE_ALIGN(__pa(to)); for (cur = start; cur < end; cur += PAGE_SIZE) { pfn = __phys_to_pfn(cur); WARN_ON(unshare_pfn_hyp(pfn)); } } /** * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode * @from: The virtual kernel start address of the range * @to: The virtual kernel end address of the range (exclusive) * @prot: The protection to be applied to this range * * The same virtual address as the kernel virtual address is also used * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying * physical pages. */ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot) { phys_addr_t phys_addr; unsigned long virt_addr; unsigned long start = kern_hyp_va((unsigned long)from); unsigned long end = kern_hyp_va((unsigned long)to); if (is_kernel_in_hyp_mode()) return 0; if (!kvm_host_owns_hyp_mappings()) return -EPERM; start = start & PAGE_MASK; end = PAGE_ALIGN(end); for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) { int err; phys_addr = kvm_kaddr_to_phys(from + virt_addr - start); err = __create_hyp_mappings(virt_addr, PAGE_SIZE, phys_addr, prot); if (err) return err; } return 0; } static int __hyp_alloc_private_va_range(unsigned long base) { lockdep_assert_held(&kvm_hyp_pgd_mutex); if (!PAGE_ALIGNED(base)) return -EINVAL; /* * Verify that BIT(VA_BITS - 1) hasn't been flipped by * allocating the new area, as it would indicate we've * overflowed the idmap/IO address range. */ if ((base ^ io_map_base) & BIT(VA_BITS - 1)) return -ENOMEM; io_map_base = base; return 0; } /** * hyp_alloc_private_va_range - Allocates a private VA range. * @size: The size of the VA range to reserve. * @haddr: The hypervisor virtual start address of the allocation. * * The private virtual address (VA) range is allocated below io_map_base * and aligned based on the order of @size. * * Return: 0 on success or negative error code on failure. */ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr) { unsigned long base; int ret = 0; mutex_lock(&kvm_hyp_pgd_mutex); /* * This assumes that we have enough space below the idmap * page to allocate our VAs. If not, the check in * __hyp_alloc_private_va_range() will kick. A potential * alternative would be to detect that overflow and switch * to an allocation above the idmap. * * The allocated size is always a multiple of PAGE_SIZE. */ size = PAGE_ALIGN(size); base = io_map_base - size; ret = __hyp_alloc_private_va_range(base); mutex_unlock(&kvm_hyp_pgd_mutex); if (!ret) *haddr = base; return ret; } static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, unsigned long *haddr, enum kvm_pgtable_prot prot) { unsigned long addr; int ret = 0; if (!kvm_host_owns_hyp_mappings()) { addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping, phys_addr, size, prot); if (IS_ERR_VALUE(addr)) return addr; *haddr = addr; return 0; } size = PAGE_ALIGN(size + offset_in_page(phys_addr)); ret = hyp_alloc_private_va_range(size, &addr); if (ret) return ret; ret = __create_hyp_mappings(addr, size, phys_addr, prot); if (ret) return ret; *haddr = addr + offset_in_page(phys_addr); return ret; } int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr) { unsigned long base; size_t size; int ret; mutex_lock(&kvm_hyp_pgd_mutex); /* * Efficient stack verification using the PAGE_SHIFT bit implies * an alignment of our allocation on the order of the size. */ size = PAGE_SIZE * 2; base = ALIGN_DOWN(io_map_base - size, size); ret = __hyp_alloc_private_va_range(base); mutex_unlock(&kvm_hyp_pgd_mutex); if (ret) { kvm_err("Cannot allocate hyp stack guard page\n"); return ret; } /* * Since the stack grows downwards, map the stack to the page * at the higher address and leave the lower guard page * unbacked. * * Any valid stack address now has the PAGE_SHIFT bit as 1 * and addresses corresponding to the guard page have the * PAGE_SHIFT bit as 0 - this is used for overflow detection. */ ret = __create_hyp_mappings(base + PAGE_SIZE, PAGE_SIZE, phys_addr, PAGE_HYP); if (ret) kvm_err("Cannot map hyp stack\n"); *haddr = base + size; return ret; } /** * create_hyp_io_mappings - Map IO into both kernel and HYP * @phys_addr: The physical start address which gets mapped * @size: Size of the region being mapped * @kaddr: Kernel VA for this mapping * @haddr: HYP VA for this mapping */ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **kaddr, void __iomem **haddr) { unsigned long addr; int ret; if (is_protected_kvm_enabled()) return -EPERM; *kaddr = ioremap(phys_addr, size); if (!*kaddr) return -ENOMEM; if (is_kernel_in_hyp_mode()) { *haddr = *kaddr; return 0; } ret = __create_hyp_private_mapping(phys_addr, size, &addr, PAGE_HYP_DEVICE); if (ret) { iounmap(*kaddr); *kaddr = NULL; *haddr = NULL; return ret; } *haddr = (void __iomem *)addr; return 0; } /** * create_hyp_exec_mappings - Map an executable range into HYP * @phys_addr: The physical start address which gets mapped * @size: Size of the region being mapped * @haddr: HYP VA for this mapping */ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, void **haddr) { unsigned long addr; int ret; BUG_ON(is_kernel_in_hyp_mode()); ret = __create_hyp_private_mapping(phys_addr, size, &addr, PAGE_HYP_EXEC); if (ret) { *haddr = NULL; return ret; } *haddr = (void *)addr; return 0; } static struct kvm_pgtable_mm_ops kvm_user_mm_ops = { /* We shouldn't need any other callback to walk the PT */ .phys_to_virt = kvm_host_va, }; static int get_user_mapping_size(struct kvm *kvm, u64 addr) { struct kvm_pgtable pgt = { .pgd = (kvm_pteref_t)kvm->mm->pgd, .ia_bits = vabits_actual, .start_level = (KVM_PGTABLE_LAST_LEVEL - ARM64_HW_PGTABLE_LEVELS(pgt.ia_bits) + 1), .mm_ops = &kvm_user_mm_ops, }; unsigned long flags; kvm_pte_t pte = 0; /* Keep GCC quiet... */ s8 level = S8_MAX; int ret; /* * Disable IRQs so that we hazard against a concurrent * teardown of the userspace page tables (which relies on * IPI-ing threads). */ local_irq_save(flags); ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level); local_irq_restore(flags); if (ret) return ret; /* * Not seeing an error, but not updating level? Something went * deeply wrong... */ if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL)) return -EFAULT; if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL)) return -EFAULT; /* Oops, the userspace PTs are gone... Replay the fault */ if (!kvm_pte_valid(pte)) return -EAGAIN; return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level)); } static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .zalloc_page = stage2_memcache_zalloc_page, .zalloc_pages_exact = kvm_s2_zalloc_pages_exact, .free_pages_exact = kvm_s2_free_pages_exact, .free_unlinked_table = stage2_free_unlinked_table, .get_page = kvm_host_get_page, .put_page = kvm_s2_put_page, .page_count = kvm_host_page_count, .phys_to_virt = kvm_host_va, .virt_to_phys = kvm_host_pa, .dcache_clean_inval_poc = clean_dcache_guest_page, .icache_inval_pou = invalidate_icache_guest_page, }; static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type) { u32 kvm_ipa_limit = get_kvm_ipa_limit(); u64 mmfr0, mmfr1; u32 phys_shift; if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK) return -EINVAL; phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type); if (is_protected_kvm_enabled()) { phys_shift = kvm_ipa_limit; } else if (phys_shift) { if (phys_shift > kvm_ipa_limit || phys_shift < ARM64_MIN_PARANGE_BITS) return -EINVAL; } else { phys_shift = KVM_PHYS_SHIFT; if (phys_shift > kvm_ipa_limit) { pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n", current->comm); return -EINVAL; } } mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift); return 0; } /** * kvm_init_stage2_mmu - Initialise a S2 MMU structure * @kvm: The pointer to the KVM structure * @mmu: The pointer to the s2 MMU structure * @type: The machine type of the virtual machine * * Allocates only the stage-2 HW PGD level table(s). * Note we don't need locking here as this is only called in two cases: * * - when the VM is created, which can't race against anything * * - when secondary kvm_s2_mmu structures are initialised for NV * guests, and the caller must hold kvm->lock as this is called on a * per-vcpu basis. */ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type) { int cpu, err; struct kvm_pgtable *pgt; /* * If we already have our page tables in place, and that the * MMU context is the canonical one, we have a bug somewhere, * as this is only supposed to ever happen once per VM. * * Otherwise, we're building nested page tables, and that's * probably because userspace called KVM_ARM_VCPU_INIT more * than once on the same vcpu. Since that's actually legal, * don't kick a fuss and leave gracefully. */ if (mmu->pgt != NULL) { if (kvm_is_nested_s2_mmu(kvm, mmu)) return 0; kvm_err("kvm_arch already initialized?\n"); return -EINVAL; } err = kvm_init_ipa_range(mmu, type); if (err) return err; pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT); if (!pgt) return -ENOMEM; mmu->arch = &kvm->arch; err = kvm_pgtable_stage2_init(pgt, mmu, &kvm_s2_mm_ops); if (err) goto out_free_pgtable; mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran)); if (!mmu->last_vcpu_ran) { err = -ENOMEM; goto out_destroy_pgtable; } for_each_possible_cpu(cpu) *per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1; /* The eager page splitting is disabled by default */ mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT; mmu->split_page_cache.gfp_zero = __GFP_ZERO; mmu->pgt = pgt; mmu->pgd_phys = __pa(pgt->pgd); if (kvm_is_nested_s2_mmu(kvm, mmu)) kvm_init_nested_s2_mmu(mmu); return 0; out_destroy_pgtable: kvm_pgtable_stage2_destroy(pgt); out_free_pgtable: kfree(pgt); return err; } void kvm_uninit_stage2_mmu(struct kvm *kvm) { kvm_free_stage2_pgd(&kvm->arch.mmu); kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache); } static void stage2_unmap_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) { hva_t hva = memslot->userspace_addr; phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t size = PAGE_SIZE * memslot->npages; hva_t reg_end = hva + size; /* * A memory region could potentially cover multiple VMAs, and any holes * between them, so iterate over all of them to find out if we should * unmap any of them. * * +--------------------------------------------+ * +---------------+----------------+ +----------------+ * | : VMA 1 | VMA 2 | | VMA 3 : | * +---------------+----------------+ +----------------+ * | memory region | * +--------------------------------------------+ */ do { struct vm_area_struct *vma; hva_t vm_start, vm_end; vma = find_vma_intersection(current->mm, hva, reg_end); if (!vma) break; /* * Take the intersection of this VMA with the memory region */ vm_start = max(hva, vma->vm_start); vm_end = min(reg_end, vma->vm_end); if (!(vma->vm_flags & VM_PFNMAP)) { gpa_t gpa = addr + (vm_start - memslot->userspace_addr); kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true); } hva = vm_end; } while (hva < reg_end); } /** * stage2_unmap_vm - Unmap Stage-2 RAM mappings * @kvm: The struct kvm pointer * * Go through the memregions and unmap any regular RAM * backing memory already mapped to the VM. */ void stage2_unmap_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int idx, bkt; idx = srcu_read_lock(&kvm->srcu); mmap_read_lock(current->mm); write_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, bkt, slots) stage2_unmap_memslot(kvm, memslot); kvm_nested_s2_unmap(kvm, true); write_unlock(&kvm->mmu_lock); mmap_read_unlock(current->mm); srcu_read_unlock(&kvm->srcu, idx); } void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); struct kvm_pgtable *pgt = NULL; write_lock(&kvm->mmu_lock); pgt = mmu->pgt; if (pgt) { mmu->pgd_phys = 0; mmu->pgt = NULL; free_percpu(mmu->last_vcpu_ran); } write_unlock(&kvm->mmu_lock); if (pgt) { kvm_pgtable_stage2_destroy(pgt); kfree(pgt); } } static void hyp_mc_free_fn(void *addr, void *unused) { free_page((unsigned long)addr); } static void *hyp_mc_alloc_fn(void *unused) { return (void *)__get_free_page(GFP_KERNEL_ACCOUNT); } void free_hyp_memcache(struct kvm_hyp_memcache *mc) { if (is_protected_kvm_enabled()) __free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, NULL); } int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) { if (!is_protected_kvm_enabled()) return 0; return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn, kvm_host_pa, NULL); } /** * kvm_phys_addr_ioremap - map a device range to guest IPA * * @kvm: The KVM pointer * @guest_ipa: The IPA at which to insert the mapping * @pa: The physical address of the device * @size: The size of the mapping * @writable: Whether or not to create a writable mapping */ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, phys_addr_t pa, unsigned long size, bool writable) { phys_addr_t addr; int ret = 0; struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO }; struct kvm_s2_mmu *mmu = &kvm->arch.mmu; struct kvm_pgtable *pgt = mmu->pgt; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_R | (writable ? KVM_PGTABLE_PROT_W : 0); if (is_protected_kvm_enabled()) return -EPERM; size += offset_in_page(guest_ipa); guest_ipa &= PAGE_MASK; for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) { ret = kvm_mmu_topup_memory_cache(&cache, kvm_mmu_cache_min_pages(mmu)); if (ret) break; write_lock(&kvm->mmu_lock); ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot, &cache, 0); write_unlock(&kvm->mmu_lock); if (ret) break; pa += PAGE_SIZE; } kvm_mmu_free_memory_cache(&cache); return ret; } /** * kvm_stage2_wp_range() - write protect stage2 memory region range * @mmu: The KVM stage-2 MMU pointer * @addr: Start address of range * @end: End address of range */ void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect); } /** * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot * @kvm: The KVM pointer * @slot: The memory slot to write protect * * Called to start logging dirty pages after memory region * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns * all present PUD, PMD and PTEs are write protected in the memory region. * Afterwards read of dirty page log can be called. * * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired, * serializing operations for VM memory regions. */ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot) { struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); phys_addr_t start, end; if (WARN_ON_ONCE(!memslot)) return; start = memslot->base_gfn << PAGE_SHIFT; end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; write_lock(&kvm->mmu_lock); kvm_stage2_wp_range(&kvm->arch.mmu, start, end); kvm_nested_s2_wp(kvm); write_unlock(&kvm->mmu_lock); kvm_flush_remote_tlbs_memslot(kvm, memslot); } /** * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE * pages for memory slot * @kvm: The KVM pointer * @slot: The memory slot to split * * Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired, * serializing operations for VM memory regions. */ static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; phys_addr_t start, end; lockdep_assert_held(&kvm->slots_lock); slots = kvm_memslots(kvm); memslot = id_to_memslot(slots, slot); start = memslot->base_gfn << PAGE_SHIFT; end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; write_lock(&kvm->mmu_lock); kvm_mmu_split_huge_pages(kvm, start, end); write_unlock(&kvm->mmu_lock); } /* * kvm_arch_mmu_enable_log_dirty_pt_masked() - enable dirty logging for selected pages. * @kvm: The KVM pointer * @slot: The memory slot associated with mask * @gfn_offset: The gfn offset in memory slot * @mask: The mask of pages at offset 'gfn_offset' in this memory * slot to enable dirty logging on * * Writes protect selected pages to enable dirty logging, and then * splits them to PAGE_SIZE. Caller must acquire kvm->mmu_lock. */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { phys_addr_t base_gfn = slot->base_gfn + gfn_offset; phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; lockdep_assert_held_write(&kvm->mmu_lock); kvm_stage2_wp_range(&kvm->arch.mmu, start, end); /* * Eager-splitting is done when manual-protect is set. We * also check for initially-all-set because we can avoid * eager-splitting if initially-all-set is false. * Initially-all-set equal false implies that huge-pages were * already split when enabling dirty logging: no need to do it * again. */ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) kvm_mmu_split_huge_pages(kvm, start, end); kvm_nested_s2_wp(kvm); } static void kvm_send_hwpoison_signal(unsigned long address, short lsb) { send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current); } static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, unsigned long hva, unsigned long map_size) { gpa_t gpa_start; hva_t uaddr_start, uaddr_end; size_t size; /* The memslot and the VMA are guaranteed to be aligned to PAGE_SIZE */ if (map_size == PAGE_SIZE) return true; size = memslot->npages * PAGE_SIZE; gpa_start = memslot->base_gfn << PAGE_SHIFT; uaddr_start = memslot->userspace_addr; uaddr_end = uaddr_start + size; /* * Pages belonging to memslots that don't have the same alignment * within a PMD/PUD for userspace and IPA cannot be mapped with stage-2 * PMD/PUD entries, because we'll end up mapping the wrong pages. * * Consider a layout like the following: * * memslot->userspace_addr: * +-----+--------------------+--------------------+---+ * |abcde|fgh Stage-1 block | Stage-1 block tv|xyz| * +-----+--------------------+--------------------+---+ * * memslot->base_gfn << PAGE_SHIFT: * +---+--------------------+--------------------+-----+ * |abc|def Stage-2 block | Stage-2 block |tvxyz| * +---+--------------------+--------------------+-----+ * * If we create those stage-2 blocks, we'll end up with this incorrect * mapping: * d -> f * e -> g * f -> h */ if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1))) return false; /* * Next, let's make sure we're not trying to map anything not covered * by the memslot. This means we have to prohibit block size mappings * for the beginning and end of a non-block aligned and non-block sized * memory slot (illustrated by the head and tail parts of the * userspace view above containing pages 'abcde' and 'xyz', * respectively). * * Note that it doesn't matter if we do the check using the * userspace_addr or the base_gfn, as both are equally aligned (per * the check above) and equally sized. */ return (hva & ~(map_size - 1)) >= uaddr_start && (hva & ~(map_size - 1)) + map_size <= uaddr_end; } /* * Check if the given hva is backed by a transparent huge page (THP) and * whether it can be mapped using block mapping in stage2. If so, adjust * the stage2 PFN and IPA accordingly. Only PMD_SIZE THPs are currently * supported. This will need to be updated to support other THP sizes. * * Returns the size of the mapping. */ static long transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long hva, kvm_pfn_t *pfnp, phys_addr_t *ipap) { kvm_pfn_t pfn = *pfnp; /* * Make sure the adjustment is done only for THP pages. Also make * sure that the HVA and IPA are sufficiently aligned and that the * block map is contained within the memslot. */ if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { int sz = get_user_mapping_size(kvm, hva); if (sz < 0) return sz; if (sz < PMD_SIZE) return PAGE_SIZE; *ipap &= PMD_MASK; pfn &= ~(PTRS_PER_PMD - 1); *pfnp = pfn; return PMD_SIZE; } /* Use page mapping if we cannot use block mapping. */ return PAGE_SIZE; } static int get_vma_page_shift(struct vm_area_struct *vma, unsigned long hva) { unsigned long pa; if (is_vm_hugetlb_page(vma) && !(vma->vm_flags & VM_PFNMAP)) return huge_page_shift(hstate_vma(vma)); if (!(vma->vm_flags & VM_PFNMAP)) return PAGE_SHIFT; VM_BUG_ON(is_vm_hugetlb_page(vma)); pa = (vma->vm_pgoff << PAGE_SHIFT) + (hva - vma->vm_start); #ifndef __PAGETABLE_PMD_FOLDED if ((hva & (PUD_SIZE - 1)) == (pa & (PUD_SIZE - 1)) && ALIGN_DOWN(hva, PUD_SIZE) >= vma->vm_start && ALIGN(hva, PUD_SIZE) <= vma->vm_end) return PUD_SHIFT; #endif if ((hva & (PMD_SIZE - 1)) == (pa & (PMD_SIZE - 1)) && ALIGN_DOWN(hva, PMD_SIZE) >= vma->vm_start && ALIGN(hva, PMD_SIZE) <= vma->vm_end) return PMD_SHIFT; return PAGE_SHIFT; } /* * The page will be mapped in stage 2 as Normal Cacheable, so the VM will be * able to see the page's tags and therefore they must be initialised first. If * PG_mte_tagged is set, tags have already been initialised. * * The race in the test/set of the PG_mte_tagged flag is handled by: * - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs * racing to santise the same page * - mmap_lock protects between a VM faulting a page in and the VMM performing * an mprotect() to add VM_MTE */ static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, unsigned long size) { unsigned long i, nr_pages = size >> PAGE_SHIFT; struct page *page = pfn_to_page(pfn); if (!kvm_has_mte(kvm)) return; for (i = 0; i < nr_pages; i++, page++) { if (try_page_mte_tagging(page)) { mte_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } } } static bool kvm_vma_mte_allowed(struct vm_area_struct *vma) { return vma->vm_flags & VM_MTE_ALLOWED; } static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_s2_trans *nested, struct kvm_memory_slot *memslot, unsigned long hva, bool fault_is_perm) { int ret = 0; bool write_fault, writable, force_pte = false; bool exec_fault, mte_allowed; bool device = false, vfio_allow_any_uc = false; unsigned long mmu_seq; phys_addr_t ipa = fault_ipa; struct kvm *kvm = vcpu->kvm; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; struct vm_area_struct *vma; short vma_shift; gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt; if (fault_is_perm) fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu); write_fault = kvm_is_write_fault(vcpu); exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); if (fault_is_perm && !write_fault && !exec_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; } /* * Permission faults just need to update the existing leaf entry, * and so normally don't require allocations from the memcache. The * only exception to this is when dirty logging is enabled at runtime * and a write fault needs to collapse a block entry into a table. */ if (!fault_is_perm || (logging_active && write_fault)) { ret = kvm_mmu_topup_memory_cache(memcache, kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu)); if (ret) return ret; } /* * Let's check if we will get back a huge page backed by hugetlbfs, or * get block mapping for device MMIO region. */ mmap_read_lock(current->mm); vma = vma_lookup(current->mm, hva); if (unlikely(!vma)) { kvm_err("Failed to find VMA for hva 0x%lx\n", hva); mmap_read_unlock(current->mm); return -EFAULT; } /* * logging_active is guaranteed to never be true for VM_PFNMAP * memslots. */ if (logging_active) { force_pte = true; vma_shift = PAGE_SHIFT; } else { vma_shift = get_vma_page_shift(vma, hva); } switch (vma_shift) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE)) break; fallthrough; #endif case CONT_PMD_SHIFT: vma_shift = PMD_SHIFT; fallthrough; case PMD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) break; fallthrough; case CONT_PTE_SHIFT: vma_shift = PAGE_SHIFT; force_pte = true; fallthrough; case PAGE_SHIFT: break; default: WARN_ONCE(1, "Unknown vma_shift %d", vma_shift); } vma_pagesize = 1UL << vma_shift; if (nested) { unsigned long max_map_size; max_map_size = force_pte ? PAGE_SIZE : PUD_SIZE; ipa = kvm_s2_trans_output(nested); /* * If we're about to create a shadow stage 2 entry, then we * can only create a block mapping if the guest stage 2 page * table uses at least as big a mapping. */ max_map_size = min(kvm_s2_trans_size(nested), max_map_size); /* * Be careful that if the mapping size falls between * two host sizes, take the smallest of the two. */ if (max_map_size >= PMD_SIZE && max_map_size < PUD_SIZE) max_map_size = PMD_SIZE; else if (max_map_size >= PAGE_SIZE && max_map_size < PMD_SIZE) max_map_size = PAGE_SIZE; force_pte = (max_map_size == PAGE_SIZE); vma_pagesize = min(vma_pagesize, (long)max_map_size); } /* * Both the canonical IPA and fault IPA must be hugepage-aligned to * ensure we find the right PFN and lay down the mapping in the right * place. */ if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) { fault_ipa &= ~(vma_pagesize - 1); ipa &= ~(vma_pagesize - 1); } gfn = ipa >> PAGE_SHIFT; mte_allowed = kvm_vma_mte_allowed(vma); vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED; /* Don't use the VMA after the unlock -- it may have vanished */ vma = NULL; /* * Read mmu_invalidate_seq so that KVM can detect if the results of * vma_lookup() or __gfn_to_pfn_memslot() become stale prior to * acquiring kvm->mmu_lock. * * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs * with the smp_wmb() in kvm_mmu_invalidate_end(). */ mmu_seq = vcpu->kvm->mmu_invalidate_seq; mmap_read_unlock(current->mm); pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL, write_fault, &writable, NULL); if (pfn == KVM_PFN_ERR_HWPOISON) { kvm_send_hwpoison_signal(hva, vma_shift); return 0; } if (is_error_noslot_pfn(pfn)) return -EFAULT; if (kvm_is_device_pfn(pfn)) { /* * If the page was identified as device early by looking at * the VMA flags, vma_pagesize is already representing the * largest quantity we can map. If instead it was mapped * via gfn_to_pfn_prot(), vma_pagesize is set to PAGE_SIZE * and must not be upgraded. * * In both cases, we don't let transparent_hugepage_adjust() * change things at the last minute. */ device = true; } else if (logging_active && !write_fault) { /* * Only actually map the page as writable if this was a write * fault. */ writable = false; } if (exec_fault && device) return -ENOEXEC; /* * Potentially reduce shadow S2 permissions to match the guest's own * S2. For exec faults, we'd only reach this point if the guest * actually allowed it (see kvm_s2_handle_perm_fault). * * Also encode the level of the original translation in the SW bits * of the leaf entry as a proxy for the span of that translation. * This will be retrieved on TLB invalidation from the guest and * used to limit the invalidation scope if a TTL hint or a range * isn't provided. */ if (nested) { writable &= kvm_s2_trans_writable(nested); if (!kvm_s2_trans_readable(nested)) prot &= ~KVM_PGTABLE_PROT_R; prot |= kvm_encode_nested_level(nested); } read_lock(&kvm->mmu_lock); pgt = vcpu->arch.hw_mmu->pgt; if (mmu_invalidate_retry(kvm, mmu_seq)) { ret = -EAGAIN; goto out_unlock; } /* * If we are not forced to use page mapping, check if we are * backed by a THP and thus use block mapping if possible. */ if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) { if (fault_is_perm && fault_granule > PAGE_SIZE) vma_pagesize = fault_granule; else vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &pfn, &fault_ipa); if (vma_pagesize < 0) { ret = vma_pagesize; goto out_unlock; } } if (!fault_is_perm && !device && kvm_has_mte(kvm)) { /* Check the VMM hasn't introduced a new disallowed VMA */ if (mte_allowed) { sanitise_mte_tags(kvm, pfn, vma_pagesize); } else { ret = -EFAULT; goto out_unlock; } } if (writable) prot |= KVM_PGTABLE_PROT_W; if (exec_fault) prot |= KVM_PGTABLE_PROT_X; if (device) { if (vfio_allow_any_uc) prot |= KVM_PGTABLE_PROT_NORMAL_NC; else prot |= KVM_PGTABLE_PROT_DEVICE; } else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC) && (!nested || kvm_s2_trans_executable(nested))) { prot |= KVM_PGTABLE_PROT_X; } /* * Under the premise of getting a FSC_PERM fault, we just need to relax * permissions only if vma_pagesize equals fault_granule. Otherwise, * kvm_pgtable_stage2_map() should be called to change block size. */ if (fault_is_perm && vma_pagesize == fault_granule) { /* * Drop the SW bits in favour of those stored in the * PTE, which will be preserved. */ prot &= ~KVM_NV_GUEST_MAP_SZ; ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); } else { ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, memcache, KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED); } out_unlock: read_unlock(&kvm->mmu_lock); /* Mark the page dirty only if the fault is handled successfully */ if (writable && !ret) { kvm_set_pfn_dirty(pfn); mark_page_dirty_in_slot(kvm, memslot, gfn); } kvm_release_pfn_clean(pfn); return ret != -EAGAIN ? ret : 0; } /* Resolve the access fault by making the page young again. */ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { kvm_pte_t pte; struct kvm_s2_mmu *mmu; trace_kvm_access_fault(fault_ipa); read_lock(&vcpu->kvm->mmu_lock); mmu = vcpu->arch.hw_mmu; pte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa); read_unlock(&vcpu->kvm->mmu_lock); if (kvm_pte_valid(pte)) kvm_set_pfn_accessed(kvm_pte_to_pfn(pte)); } /** * kvm_handle_guest_abort - handles all 2nd stage aborts * @vcpu: the VCPU pointer * * Any abort that gets to the host is almost guaranteed to be caused by a * missing second stage translation table entry, which can mean that either the * guest simply needs more memory and we must allocate an appropriate page or it * can mean that the guest tried to access I/O memory, which is emulated by user * space. The distinction is based on the IPA causing the fault and whether this * memory region has been registered as standard RAM by user space. */ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) { struct kvm_s2_trans nested_trans, *nested = NULL; unsigned long esr; phys_addr_t fault_ipa; /* The address we faulted on */ phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */ struct kvm_memory_slot *memslot; unsigned long hva; bool is_iabt, write_fault, writable; gfn_t gfn; int ret, idx; esr = kvm_vcpu_get_esr(vcpu); ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); if (esr_fsc_is_translation_fault(esr)) { /* Beyond sanitised PARange (which is the IPA limit) */ if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { kvm_inject_size_fault(vcpu); return 1; } /* Falls between the IPA range and the PARange? */ if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) { fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); if (is_iabt) kvm_inject_pabt(vcpu, fault_ipa); else kvm_inject_dabt(vcpu, fault_ipa); return 1; } } /* Synchronous External Abort? */ if (kvm_vcpu_abt_issea(vcpu)) { /* * For RAS the host kernel may handle this abort. * There is no need to pass the error into the guest. */ if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu))) kvm_inject_vabt(vcpu); return 1; } trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu), kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ if (!esr_fsc_is_translation_fault(esr) && !esr_fsc_is_permission_fault(esr) && !esr_fsc_is_access_flag_fault(esr)) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), (unsigned long)kvm_vcpu_get_esr(vcpu)); return -EFAULT; } idx = srcu_read_lock(&vcpu->kvm->srcu); /* * We may have faulted on a shadow stage 2 page table if we are * running a nested guest. In this case, we have to resolve the L2 * IPA to the L1 IPA first, before knowing what kind of memory should * back the L1 IPA. * * If the shadow stage 2 page table walk faults, then we simply inject * this to the guest and carry on. * * If there are no shadow S2 PTs because S2 is disabled, there is * nothing to walk and we treat it as a 1:1 before going through the * canonical translation. */ if (kvm_is_nested_s2_mmu(vcpu->kvm,vcpu->arch.hw_mmu) && vcpu->arch.hw_mmu->nested_stage2_enabled) { u32 esr; ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans); if (ret) { esr = kvm_s2_trans_esr(&nested_trans); kvm_inject_s2_fault(vcpu, esr); goto out_unlock; } ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans); if (ret) { esr = kvm_s2_trans_esr(&nested_trans); kvm_inject_s2_fault(vcpu, esr); goto out_unlock; } ipa = kvm_s2_trans_output(&nested_trans); nested = &nested_trans; } gfn = ipa >> PAGE_SHIFT; memslot = gfn_to_memslot(vcpu->kvm, gfn); hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable); write_fault = kvm_is_write_fault(vcpu); if (kvm_is_error_hva(hva) || (write_fault && !writable)) { /* * The guest has put either its instructions or its page-tables * somewhere it shouldn't have. Userspace won't be able to do * anything about this (there's no syndrome for a start), so * re-inject the abort back into the guest. */ if (is_iabt) { ret = -ENOEXEC; goto out; } if (kvm_vcpu_abt_iss1tw(vcpu)) { kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); ret = 1; goto out_unlock; } /* * Check for a cache maintenance operation. Since we * ended-up here, we know it is outside of any memory * slot. But we can't find out if that is for a device, * or if the guest is just being stupid. The only thing * we know for sure is that this range cannot be cached. * * So let's assume that the guest is just being * cautious, and skip the instruction. */ if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) { kvm_incr_pc(vcpu); ret = 1; goto out_unlock; } /* * The IPA is reported as [MAX:12], so we need to * complement it with the bottom 12 bits from the * faulting VA. This is always 12 bits, irrespective * of the page size. */ ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); ret = io_mem_abort(vcpu, ipa); goto out_unlock; } /* Userspace should not be able to register out-of-bounds IPAs */ VM_BUG_ON(ipa >= kvm_phys_size(vcpu->arch.hw_mmu)); if (esr_fsc_is_access_flag_fault(esr)) { handle_access_fault(vcpu, fault_ipa); ret = 1; goto out_unlock; } ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva, esr_fsc_is_permission_fault(esr)); if (ret == 0) ret = 1; out: if (ret == -ENOEXEC) { kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); ret = 1; } out_unlock: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) return false; __unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); kvm_nested_s2_unmap(kvm, range->may_block); return false; } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { u64 size = (range->end - range->start) << PAGE_SHIFT; if (!kvm->arch.mmu.pgt) return false; return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, size, true); /* * TODO: Handle nested_mmu structures here using the reverse mapping in * a later version of patch series. */ } bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { u64 size = (range->end - range->start) << PAGE_SHIFT; if (!kvm->arch.mmu.pgt) return false; return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, size, false); } phys_addr_t kvm_mmu_get_httbr(void) { return __pa(hyp_pgtable->pgd); } phys_addr_t kvm_get_idmap_vector(void) { return hyp_idmap_vector; } static int kvm_map_idmap_text(void) { unsigned long size = hyp_idmap_end - hyp_idmap_start; int err = __create_hyp_mappings(hyp_idmap_start, size, hyp_idmap_start, PAGE_HYP_EXEC); if (err) kvm_err("Failed to idmap %lx-%lx\n", hyp_idmap_start, hyp_idmap_end); return err; } static void *kvm_hyp_zalloc_page(void *arg) { return (void *)get_zeroed_page(GFP_KERNEL); } static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = { .zalloc_page = kvm_hyp_zalloc_page, .get_page = kvm_host_get_page, .put_page = kvm_host_put_page, .phys_to_virt = kvm_host_va, .virt_to_phys = kvm_host_pa, }; int __init kvm_mmu_init(u32 *hyp_va_bits) { int err; u32 idmap_bits; u32 kernel_bits; hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start); hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE); hyp_idmap_end = __pa_symbol(__hyp_idmap_text_end); hyp_idmap_end = ALIGN(hyp_idmap_end, PAGE_SIZE); hyp_idmap_vector = __pa_symbol(__kvm_hyp_init); /* * We rely on the linker script to ensure at build time that the HYP * init code does not cross a page boundary. */ BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); /* * The ID map is always configured for 48 bits of translation, which * may be fewer than the number of VA bits used by the regular kernel * stage 1, when VA_BITS=52. * * At EL2, there is only one TTBR register, and we can't switch between * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom * line: we need to use the extended range with *both* our translation * tables. * * So use the maximum of the idmap VA bits and the regular kernel stage * 1 VA bits to assure that the hypervisor can both ID map its code page * and map any kernel memory. */ idmap_bits = IDMAP_VA_BITS; kernel_bits = vabits_actual; *hyp_va_bits = max(idmap_bits, kernel_bits); kvm_debug("Using %u-bit virtual addresses at EL2\n", *hyp_va_bits); kvm_debug("IDMAP page: %lx\n", hyp_idmap_start); kvm_debug("HYP VA range: %lx:%lx\n", kern_hyp_va(PAGE_OFFSET), kern_hyp_va((unsigned long)high_memory - 1)); if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) && hyp_idmap_start < kern_hyp_va((unsigned long)high_memory - 1) && hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) { /* * The idmap page is intersecting with the VA space, * it is not safe to continue further. */ kvm_err("IDMAP intersecting with HYP VA, unable to continue\n"); err = -EINVAL; goto out; } hyp_pgtable = kzalloc(sizeof(*hyp_pgtable), GFP_KERNEL); if (!hyp_pgtable) { kvm_err("Hyp mode page-table not allocated\n"); err = -ENOMEM; goto out; } err = kvm_pgtable_hyp_init(hyp_pgtable, *hyp_va_bits, &kvm_hyp_mm_ops); if (err) goto out_free_pgtable; err = kvm_map_idmap_text(); if (err) goto out_destroy_pgtable; io_map_base = hyp_idmap_start; return 0; out_destroy_pgtable: kvm_pgtable_hyp_destroy(hyp_pgtable); out_free_pgtable: kfree(hyp_pgtable); hyp_pgtable = NULL; out: return err; } void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { bool log_dirty_pages = new && new->flags & KVM_MEM_LOG_DIRTY_PAGES; /* * At this point memslot has been committed and there is an * allocated dirty_bitmap[], dirty pages will be tracked while the * memory slot is write protected. */ if (log_dirty_pages) { if (change == KVM_MR_DELETE) return; /* * Huge and normal pages are write-protected and split * on either of these two cases: * * 1. with initial-all-set: gradually with CLEAR ioctls, */ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) return; /* * or * 2. without initial-all-set: all in one shot when * enabling dirty logging. */ kvm_mmu_wp_memory_region(kvm, new->id); kvm_mmu_split_memory_region(kvm, new->id); } else { /* * Free any leftovers from the eager page splitting cache. Do * this when deleting, moving, disabling dirty logging, or * creating the memslot (a nop). Doing it for deletes makes * sure we don't leak memory, and there's no need to keep the * cache around for any of the other cases. */ kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache); } } int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { hva_t hva, reg_end; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && change != KVM_MR_FLAGS_ONLY) return 0; /* * Prevent userspace from creating a memory region outside of the IPA * space addressable by the KVM guest IPA space. */ if ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT)) return -EFAULT; hva = new->userspace_addr; reg_end = hva + (new->npages << PAGE_SHIFT); mmap_read_lock(current->mm); /* * A memory region could potentially cover multiple VMAs, and any holes * between them, so iterate over all of them. * * +--------------------------------------------+ * +---------------+----------------+ +----------------+ * | : VMA 1 | VMA 2 | | VMA 3 : | * +---------------+----------------+ +----------------+ * | memory region | * +--------------------------------------------+ */ do { struct vm_area_struct *vma; vma = find_vma_intersection(current->mm, hva, reg_end); if (!vma) break; if (kvm_has_mte(kvm) && !kvm_vma_mte_allowed(vma)) { ret = -EINVAL; break; } if (vma->vm_flags & VM_PFNMAP) { /* IO region dirty page logging not allowed */ if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; break; } } hva = min(reg_end, vma->vm_end); } while (hva < reg_end); mmap_read_unlock(current->mm); return ret; } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { } void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { gpa_t gpa = slot->base_gfn << PAGE_SHIFT; phys_addr_t size = slot->npages << PAGE_SHIFT; write_lock(&kvm->mmu_lock); kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true); kvm_nested_s2_unmap(kvm, true); write_unlock(&kvm->mmu_lock); } /* * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). * * Main problems: * - S/W ops are local to a CPU (not broadcast) * - We have line migration behind our back (speculation) * - System caches don't support S/W at all (damn!) * * In the face of the above, the best we can do is to try and convert * S/W ops to VA ops. Because the guest is not allowed to infer the * S/W to PA mapping, it can only use S/W to nuke the whole cache, * which is a rather good thing for us. * * Also, it is only used when turning caches on/off ("The expected * usage of the cache maintenance instructions that operate by set/way * is associated with the cache maintenance instructions associated * with the powerdown and powerup of caches, if this is required by * the implementation."). * * We use the following policy: * * - If we trap a S/W operation, we enable VM trapping to detect * caches being turned on/off, and do a full clean. * * - We flush the caches on both caches being turned on and off. * * - Once the caches are enabled, we stop trapping VM ops. */ void kvm_set_way_flush(struct kvm_vcpu *vcpu) { unsigned long hcr = *vcpu_hcr(vcpu); /* * If this is the first time we do a S/W operation * (i.e. HCR_TVM not set) flush the whole memory, and set the * VM trapping. * * Otherwise, rely on the VM trapping to wait for the MMU + * Caches to be turned off. At that point, we'll be able to * clean the caches again. */ if (!(hcr & HCR_TVM)) { trace_kvm_set_way_flush(*vcpu_pc(vcpu), vcpu_has_cache_enabled(vcpu)); stage2_flush_vm(vcpu->kvm); *vcpu_hcr(vcpu) = hcr | HCR_TVM; } } void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled) { bool now_enabled = vcpu_has_cache_enabled(vcpu); /* * If switching the MMU+caches on, need to invalidate the caches. * If switching it off, need to clean the caches. * Clean + invalidate does the trick always. */ if (now_enabled != was_enabled) stage2_flush_vm(vcpu->kvm); /* Caches are now on, stop trapping VM ops (until a S/W op) */ if (now_enabled) *vcpu_hcr(vcpu) &= ~HCR_TVM; trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds); struct file *needs_masking; /* * 'mask' is zero for an out-of-bounds fd, all ones for ok. * 'fd&mask' is 'fd' for ok, or 0 for out of bounds. * * Accessing fdt->fd[0] is ok, but needs masking of the result. */ needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]); return (struct file *)(mask & (unsigned long)needs_masking); } static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } struct file *lookup_fdget_rcu(unsigned int fd); struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd); struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *fd); static inline bool close_on_exec(unsigned int fd, const struct files_struct *files) { return test_bit(fd, files_fdtable(files)->close_on_exec); } struct task_struct; void put_files_struct(struct files_struct *fs); int unshare_files(void); struct fd_range { unsigned int from, to; }; struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern struct file *file_close_fd(unsigned int fd); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include "ipvlan.h" #include <linux/if_vlan.h> #include <linux/if_tap.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static dev_t ipvtap_major; static struct cdev ipvtap_cdev; static const void *ipvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class ipvtap_class = { .name = "ipvtap", .ns_type = &net_ns_type_operations, .namespace = ipvtap_net_namespace, }; struct ipvtap_dev { struct ipvl_dev vlan; struct tap_dev tap; }; static void ipvtap_count_tx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_drps); } static void ipvtap_count_rx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; ipvlan_count_rx(vlan, 0, 0, 0); } static void ipvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; vlan->sfeatures = features; netdev_update_features(vlan->dev); } static int ipvtap_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; vlantap->tap.count_tx_dropped = ipvtap_count_tx_dropped; vlantap->tap.update_features = ipvtap_update_features; vlantap->tap.count_rx_dropped = ipvtap_count_rx_dropped; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = ipvlan_link_new(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return err; } static void ipvtap_dellink(struct net_device *dev, struct list_head *head) { struct ipvtap_dev *vlan = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlan->tap); ipvlan_link_delete(dev, head); } static void ipvtap_setup(struct net_device *dev) { ipvlan_link_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; dev->priv_flags &= ~IFF_NO_QUEUE; } static struct rtnl_link_ops ipvtap_link_ops __read_mostly = { .kind = "ipvtap", .setup = ipvtap_setup, .newlink = ipvtap_newlink, .dellink = ipvtap_dellink, .priv_size = sizeof(struct ipvtap_dev), }; static int ipvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &ipvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(ipvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); classdev = device_create(&ipvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(ipvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); device_destroy(&ipvtap_class, devt); tap_free_minor(ipvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block ipvtap_notifier_block __read_mostly = { .notifier_call = ipvtap_device_event, }; static int __init ipvtap_init(void) { int err; err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap", THIS_MODULE); if (err) goto out1; err = class_register(&ipvtap_class); if (err) goto out2; err = register_netdevice_notifier(&ipvtap_notifier_block); if (err) goto out3; err = ipvlan_link_register(&ipvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&ipvtap_notifier_block); out3: class_unregister(&ipvtap_class); out2: tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); out1: return err; } module_init(ipvtap_init); static void __exit ipvtap_exit(void) { rtnl_link_unregister(&ipvtap_link_ops); unregister_netdevice_notifier(&ipvtap_notifier_block); class_unregister(&ipvtap_class); tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); } module_exit(ipvtap_exit); MODULE_ALIAS_RTNL_LINK("ipvtap"); MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>"); MODULE_DESCRIPTION("IP-VLAN based tap driver"); MODULE_LICENSE("GPL"); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* Generic nexthop implementation * * Copyright (c) 2017-19 Cumulus Networks * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> */ #include <linux/nexthop.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/arp.h> #include <net/ipv6_stubs.h> #include <net/lwtunnel.h> #include <net/ndisc.h> #include <net/nexthop.h> #include <net/route.h> #include <net/sock.h> #define NH_RES_DEFAULT_IDLE_TIMER (120 * HZ) #define NH_RES_DEFAULT_UNBALANCED_TIMER 0 /* No forced rebalancing. */ static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo); #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) #define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS | \ NHA_OP_FLAG_DUMP_HW_STATS) static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, [NHA_GROUP_TYPE] = { .type = NLA_U16 }, [NHA_BLACKHOLE] = { .type = NLA_FLAG }, [NHA_OIF] = { .type = NLA_U32 }, [NHA_GATEWAY] = { .type = NLA_BINARY }, [NHA_ENCAP_TYPE] = { .type = NLA_U16 }, [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_RES_GROUP] = { .type = NLA_NESTED }, [NHA_HW_STATS_ENABLE] = NLA_POLICY_MAX(NLA_U32, true), }; static const struct nla_policy rtm_nh_policy_get[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_policy_del[] = { [NHA_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_OIF] = { .type = NLA_U32 }, [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_res_policy_new[] = { [NHA_RES_GROUP_BUCKETS] = { .type = NLA_U16 }, [NHA_RES_GROUP_IDLE_TIMER] = { .type = NLA_U32 }, [NHA_RES_GROUP_UNBALANCED_TIMER] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump_bucket[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_OIF] = { .type = NLA_U32 }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_RES_BUCKET] = { .type = NLA_NESTED }, }; static const struct nla_policy rtm_nh_res_bucket_policy_dump[] = { [NHA_RES_BUCKET_NH_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_get_bucket[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_RES_BUCKET] = { .type = NLA_NESTED }, }; static const struct nla_policy rtm_nh_res_bucket_policy_get[] = { [NHA_RES_BUCKET_INDEX] = { .type = NLA_U16 }, }; static bool nexthop_notifiers_is_empty(struct net *net) { return !net->nexthop.notifier_chain.head; } static void __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, const struct nh_info *nhi) { nh_info->dev = nhi->fib_nhc.nhc_dev; nh_info->gw_family = nhi->fib_nhc.nhc_gw_family; if (nh_info->gw_family == AF_INET) nh_info->ipv4 = nhi->fib_nhc.nhc_gw.ipv4; else if (nh_info->gw_family == AF_INET6) nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6; nh_info->id = nhi->nh_parent->id; nh_info->is_reject = nhi->reject_nh; nh_info->is_fdb = nhi->fdb_nh; nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate; } static int nh_notifier_single_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_info *nhi = rtnl_dereference(nh->nh_info); info->type = NH_NOTIFIER_INFO_TYPE_SINGLE; info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL); if (!info->nh) return -ENOMEM; __nh_notifier_single_info_init(info->nh, nhi); return 0; } static void nh_notifier_single_info_fini(struct nh_notifier_info *info) { kfree(info->nh); } static int nh_notifier_mpath_info_init(struct nh_notifier_info *info, struct nh_group *nhg) { u16 num_nh = nhg->num_nh; int i; info->type = NH_NOTIFIER_INFO_TYPE_GRP; info->nh_grp = kzalloc(struct_size(info->nh_grp, nh_entries, num_nh), GFP_KERNEL); if (!info->nh_grp) return -ENOMEM; info->nh_grp->num_nh = num_nh; info->nh_grp->is_fdb = nhg->fdb_nh; info->nh_grp->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi; nhi = rtnl_dereference(nhge->nh->nh_info); info->nh_grp->nh_entries[i].weight = nhge->weight; __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh, nhi); } return 0; } static int nh_notifier_res_table_info_init(struct nh_notifier_info *info, struct nh_group *nhg) { struct nh_res_table *res_table = rtnl_dereference(nhg->res_table); u16 num_nh_buckets = res_table->num_nh_buckets; unsigned long size; u16 i; info->type = NH_NOTIFIER_INFO_TYPE_RES_TABLE; size = struct_size(info->nh_res_table, nhs, num_nh_buckets); info->nh_res_table = __vmalloc(size, GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN); if (!info->nh_res_table) return -ENOMEM; info->nh_res_table->num_nh_buckets = num_nh_buckets; info->nh_res_table->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; struct nh_grp_entry *nhge; struct nh_info *nhi; nhge = rtnl_dereference(bucket->nh_entry); nhi = rtnl_dereference(nhge->nh->nh_info); __nh_notifier_single_info_init(&info->nh_res_table->nhs[i], nhi); } return 0; } static int nh_notifier_grp_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); if (nhg->hash_threshold) return nh_notifier_mpath_info_init(info, nhg); else if (nhg->resilient) return nh_notifier_res_table_info_init(info, nhg); return -EINVAL; } static void nh_notifier_grp_info_fini(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); if (nhg->hash_threshold) kfree(info->nh_grp); else if (nhg->resilient) vfree(info->nh_res_table); } static int nh_notifier_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { info->id = nh->id; if (nh->is_group) return nh_notifier_grp_info_init(info, nh); else return nh_notifier_single_info_init(info, nh); } static void nh_notifier_info_fini(struct nh_notifier_info *info, const struct nexthop *nh) { if (nh->is_group) nh_notifier_grp_info_fini(info, nh); else nh_notifier_single_info_fini(info); } static int call_nexthop_notifiers(struct net *net, enum nexthop_event_type event_type, struct nexthop *nh, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, }; int err; ASSERT_RTNL(); if (nexthop_notifiers_is_empty(net)) return 0; err = nh_notifier_info_init(&info, nh); if (err) { NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info"); return err; } err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, event_type, &info); nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } static int nh_notifier_res_bucket_idle_timer_get(const struct nh_notifier_info *info, bool force, unsigned int *p_idle_timer_ms) { struct nh_res_table *res_table; struct nh_group *nhg; struct nexthop *nh; int err = 0; /* When 'force' is false, nexthop bucket replacement is performed * because the bucket was deemed to be idle. In this case, capable * listeners can choose to perform an atomic replacement: The bucket is * only replaced if it is inactive. However, if the idle timer interval * is smaller than the interval in which a listener is querying * buckets' activity from the device, then atomic replacement should * not be tried. Pass the idle timer value to listeners, so that they * could determine which type of replacement to perform. */ if (force) { *p_idle_timer_ms = 0; return 0; } rcu_read_lock(); nh = nexthop_find_by_id(info->net, info->id); if (!nh) { err = -EINVAL; goto out; } nhg = rcu_dereference(nh->nh_grp); res_table = rcu_dereference(nhg->res_table); *p_idle_timer_ms = jiffies_to_msecs(res_table->idle_timer); out: rcu_read_unlock(); return err; } static int nh_notifier_res_bucket_info_init(struct nh_notifier_info *info, u16 bucket_index, bool force, struct nh_info *oldi, struct nh_info *newi) { unsigned int idle_timer_ms; int err; err = nh_notifier_res_bucket_idle_timer_get(info, force, &idle_timer_ms); if (err) return err; info->type = NH_NOTIFIER_INFO_TYPE_RES_BUCKET; info->nh_res_bucket = kzalloc(sizeof(*info->nh_res_bucket), GFP_KERNEL); if (!info->nh_res_bucket) return -ENOMEM; info->nh_res_bucket->bucket_index = bucket_index; info->nh_res_bucket->idle_timer_ms = idle_timer_ms; info->nh_res_bucket->force = force; __nh_notifier_single_info_init(&info->nh_res_bucket->old_nh, oldi); __nh_notifier_single_info_init(&info->nh_res_bucket->new_nh, newi); return 0; } static void nh_notifier_res_bucket_info_fini(struct nh_notifier_info *info) { kfree(info->nh_res_bucket); } static int __call_nexthop_res_bucket_notifiers(struct net *net, u32 nhg_id, u16 bucket_index, bool force, struct nh_info *oldi, struct nh_info *newi, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, .id = nhg_id, }; int err; if (nexthop_notifiers_is_empty(net)) return 0; err = nh_notifier_res_bucket_info_init(&info, bucket_index, force, oldi, newi); if (err) return err; err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, NEXTHOP_EVENT_BUCKET_REPLACE, &info); nh_notifier_res_bucket_info_fini(&info); return notifier_to_errno(err); } /* There are three users of RES_TABLE, and NHs etc. referenced from there: * * 1) a collection of callbacks for NH maintenance. This operates under * RTNL, * 2) the delayed work that gradually balances the resilient table, * 3) and nexthop_select_path(), operating under RCU. * * Both the delayed work and the RTNL block are writers, and need to * maintain mutual exclusion. Since there are only two and well-known * writers for each table, the RTNL code can make sure it has exclusive * access thus: * * - Have the DW operate without locking; * - synchronously cancel the DW; * - do the writing; * - if the write was not actually a delete, call upkeep, which schedules * DW again if necessary. * * The functions that are always called from the RTNL context use * rtnl_dereference(). The functions that can also be called from the DW do * a raw dereference and rely on the above mutual exclusion scheme. */ #define nh_res_dereference(p) (rcu_dereference_raw(p)) static int call_nexthop_res_bucket_notifiers(struct net *net, u32 nhg_id, u16 bucket_index, bool force, struct nexthop *old_nh, struct nexthop *new_nh, struct netlink_ext_ack *extack) { struct nh_info *oldi = nh_res_dereference(old_nh->nh_info); struct nh_info *newi = nh_res_dereference(new_nh->nh_info); return __call_nexthop_res_bucket_notifiers(net, nhg_id, bucket_index, force, oldi, newi, extack); } static int call_nexthop_res_table_notifiers(struct net *net, struct nexthop *nh, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, .id = nh->id, }; struct nh_group *nhg; int err; ASSERT_RTNL(); if (nexthop_notifiers_is_empty(net)) return 0; /* At this point, the nexthop buckets are still not populated. Only * emit a notification with the logical nexthops, so that a listener * could potentially veto it in case of unsupported configuration. */ nhg = rtnl_dereference(nh->nh_grp); err = nh_notifier_mpath_info_init(&info, nhg); if (err) { NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info"); return err; } err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, &info); kfree(info.nh_grp); return notifier_to_errno(err); } static int call_nexthop_notifier(struct notifier_block *nb, struct net *net, enum nexthop_event_type event_type, struct nexthop *nh, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, }; int err; err = nh_notifier_info_init(&info, nh); if (err) return err; err = nb->notifier_call(nb, event_type, &info); nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } static unsigned int nh_dev_hashfn(unsigned int val) { unsigned int mask = NH_DEV_HASHSIZE - 1; return (val ^ (val >> NH_DEV_HASHBITS) ^ (val >> (NH_DEV_HASHBITS * 2))) & mask; } static void nexthop_devhash_add(struct net *net, struct nh_info *nhi) { struct net_device *dev = nhi->fib_nhc.nhc_dev; struct hlist_head *head; unsigned int hash; WARN_ON(!dev); hash = nh_dev_hashfn(dev->ifindex); head = &net->nexthop.devhash[hash]; hlist_add_head(&nhi->dev_hash, head); } static void nexthop_free_group(struct nexthop *nh) { struct nh_group *nhg; int i; nhg = rcu_dereference_raw(nh->nh_grp); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; WARN_ON(!list_empty(&nhge->nh_list)); free_percpu(nhge->stats); nexthop_put(nhge->nh); } WARN_ON(nhg->spare == nhg); if (nhg->resilient) vfree(rcu_dereference_raw(nhg->res_table)); kfree(nhg->spare); kfree(nhg); } static void nexthop_free_single(struct nexthop *nh) { struct nh_info *nhi; nhi = rcu_dereference_raw(nh->nh_info); switch (nhi->family) { case AF_INET: fib_nh_release(nh->net, &nhi->fib_nh); break; case AF_INET6: ipv6_stub->fib6_nh_release(&nhi->fib6_nh); break; } kfree(nhi); } void nexthop_free_rcu(struct rcu_head *head) { struct nexthop *nh = container_of(head, struct nexthop, rcu); if (nh->is_group) nexthop_free_group(nh); else nexthop_free_single(nh); kfree(nh); } EXPORT_SYMBOL_GPL(nexthop_free_rcu); static struct nexthop *nexthop_alloc(void) { struct nexthop *nh; nh = kzalloc(sizeof(struct nexthop), GFP_KERNEL); if (nh) { INIT_LIST_HEAD(&nh->fi_list); INIT_LIST_HEAD(&nh->f6i_list); INIT_LIST_HEAD(&nh->grp_list); INIT_LIST_HEAD(&nh->fdb_list); } return nh; } static struct nh_group *nexthop_grp_alloc(u16 num_nh) { struct nh_group *nhg; nhg = kzalloc(struct_size(nhg, nh_entries, num_nh), GFP_KERNEL); if (nhg) nhg->num_nh = num_nh; return nhg; } static void nh_res_table_upkeep_dw(struct work_struct *work); static struct nh_res_table * nexthop_res_table_alloc(struct net *net, u32 nhg_id, struct nh_config *cfg) { const u16 num_nh_buckets = cfg->nh_grp_res_num_buckets; struct nh_res_table *res_table; unsigned long size; size = struct_size(res_table, nh_buckets, num_nh_buckets); res_table = __vmalloc(size, GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN); if (!res_table) return NULL; res_table->net = net; res_table->nhg_id = nhg_id; INIT_DELAYED_WORK(&res_table->upkeep_dw, &nh_res_table_upkeep_dw); INIT_LIST_HEAD(&res_table->uw_nh_entries); res_table->idle_timer = cfg->nh_grp_res_idle_timer; res_table->unbalanced_timer = cfg->nh_grp_res_unbalanced_timer; res_table->num_nh_buckets = num_nh_buckets; return res_table; } static void nh_base_seq_inc(struct net *net) { while (++net->nexthop.seq == 0) ; } /* no reference taken; rcu lock or rtnl must be held */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id) { struct rb_node **pp, *parent = NULL, *next; pp = &net->nexthop.rb_root.rb_node; while (1) { struct nexthop *nh; next = rcu_dereference_raw(*pp); if (!next) break; parent = next; nh = rb_entry(parent, struct nexthop, rb_node); if (id < nh->id) pp = &next->rb_left; else if (id > nh->id) pp = &next->rb_right; else return nh; } return NULL; } EXPORT_SYMBOL_GPL(nexthop_find_by_id); /* used for auto id allocation; called with rtnl held */ static u32 nh_find_unused_id(struct net *net) { u32 id_start = net->nexthop.last_id_allocated; while (1) { net->nexthop.last_id_allocated++; if (net->nexthop.last_id_allocated == id_start) break; if (!nexthop_find_by_id(net, net->nexthop.last_id_allocated)) return net->nexthop.last_id_allocated; } return 0; } static void nh_res_time_set_deadline(unsigned long next_time, unsigned long *deadline) { if (time_before(next_time, *deadline)) *deadline = next_time; } static clock_t nh_res_table_unbalanced_time(struct nh_res_table *res_table) { if (list_empty(&res_table->uw_nh_entries)) return 0; return jiffies_delta_to_clock_t(jiffies - res_table->unbalanced_since); } static int nla_put_nh_group_res(struct sk_buff *skb, struct nh_group *nhg) { struct nh_res_table *res_table = rtnl_dereference(nhg->res_table); struct nlattr *nest; nest = nla_nest_start(skb, NHA_RES_GROUP); if (!nest) return -EMSGSIZE; if (nla_put_u16(skb, NHA_RES_GROUP_BUCKETS, res_table->num_nh_buckets) || nla_put_u32(skb, NHA_RES_GROUP_IDLE_TIMER, jiffies_to_clock_t(res_table->idle_timer)) || nla_put_u32(skb, NHA_RES_GROUP_UNBALANCED_TIMER, jiffies_to_clock_t(res_table->unbalanced_timer)) || nla_put_u64_64bit(skb, NHA_RES_GROUP_UNBALANCED_TIME, nh_res_table_unbalanced_time(res_table), NHA_RES_GROUP_PAD)) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static void nh_grp_entry_stats_inc(struct nh_grp_entry *nhge) { struct nh_grp_entry_stats *cpu_stats; cpu_stats = get_cpu_ptr(nhge->stats); u64_stats_update_begin(&cpu_stats->syncp); u64_stats_inc(&cpu_stats->packets); u64_stats_update_end(&cpu_stats->syncp); put_cpu_ptr(cpu_stats); } static void nh_grp_entry_stats_read(struct nh_grp_entry *nhge, u64 *ret_packets) { int i; *ret_packets = 0; for_each_possible_cpu(i) { struct nh_grp_entry_stats *cpu_stats; unsigned int start; u64 packets; cpu_stats = per_cpu_ptr(nhge->stats, i); do { start = u64_stats_fetch_begin(&cpu_stats->syncp); packets = u64_stats_read(&cpu_stats->packets); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); *ret_packets += packets; } } static int nh_notifier_grp_hw_stats_init(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_group *nhg; int i; ASSERT_RTNL(); nhg = rtnl_dereference(nh->nh_grp); info->id = nh->id; info->type = NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS; info->nh_grp_hw_stats = kzalloc(struct_size(info->nh_grp_hw_stats, stats, nhg->num_nh), GFP_KERNEL); if (!info->nh_grp_hw_stats) return -ENOMEM; info->nh_grp_hw_stats->num_nh = nhg->num_nh; for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; info->nh_grp_hw_stats->stats[i].id = nhge->nh->id; } return 0; } static void nh_notifier_grp_hw_stats_fini(struct nh_notifier_info *info) { kfree(info->nh_grp_hw_stats); } void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, unsigned int nh_idx, u64 delta_packets) { info->hw_stats_used = true; info->stats[nh_idx].packets += delta_packets; } EXPORT_SYMBOL(nh_grp_hw_stats_report_delta); static void nh_grp_hw_stats_apply_update(struct nexthop *nh, struct nh_notifier_info *info) { struct nh_group *nhg; int i; ASSERT_RTNL(); nhg = rtnl_dereference(nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; nhge->packets_hw += info->nh_grp_hw_stats->stats[i].packets; } } static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) { struct nh_notifier_info info = { .net = nh->net, }; struct net *net = nh->net; int err; if (nexthop_notifiers_is_empty(net)) { *hw_stats_used = false; return 0; } err = nh_notifier_grp_hw_stats_init(&info, nh); if (err) return err; err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, &info); /* Cache whatever we got, even if there was an error, otherwise the * successful stats retrievals would get lost. */ nh_grp_hw_stats_apply_update(nh, &info); *hw_stats_used = info.nh_grp_hw_stats->hw_stats_used; nh_notifier_grp_hw_stats_fini(&info); return notifier_to_errno(err); } static int nla_put_nh_group_stats_entry(struct sk_buff *skb, struct nh_grp_entry *nhge, u32 op_flags) { struct nlattr *nest; u64 packets; nh_grp_entry_stats_read(nhge, &packets); nest = nla_nest_start(skb, NHA_GROUP_STATS_ENTRY); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, NHA_GROUP_STATS_ENTRY_ID, nhge->nh->id) || nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, packets + nhge->packets_hw)) goto nla_put_failure; if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS_HW, nhge->packets_hw)) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh, u32 op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nlattr *nest; bool hw_stats_used; int err; int i; if (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats)) goto err_out; if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && nhg->hw_stats) { err = nh_grp_hw_stats_update(nh, &hw_stats_used); if (err) goto out; if (nla_put_u32(skb, NHA_HW_STATS_USED, hw_stats_used)) goto err_out; } nest = nla_nest_start(skb, NHA_GROUP_STATS); if (!nest) goto err_out; for (i = 0; i < nhg->num_nh; i++) if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i], op_flags)) goto cancel_out; nla_nest_end(skb, nest); return 0; cancel_out: nla_nest_cancel(skb, nest); err_out: err = -EMSGSIZE; out: return err; } static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, u32 op_flags, u32 *resp_op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; u16 group_type = 0; u16 weight; int i; *resp_op_flags |= NHA_OP_FLAG_RESP_GRP_RESVD_0; if (nhg->hash_threshold) group_type = NEXTHOP_GRP_TYPE_MPATH; else if (nhg->resilient) group_type = NEXTHOP_GRP_TYPE_RES; if (nla_put_u16(skb, NHA_GROUP_TYPE, group_type)) goto nla_put_failure; nla = nla_reserve(skb, NHA_GROUP, len); if (!nla) goto nla_put_failure; p = nla_data(nla); for (i = 0; i < nhg->num_nh; ++i) { weight = nhg->nh_entries[i].weight - 1; *p++ = (struct nexthop_grp) { .id = nhg->nh_entries[i].nh->id, .weight = weight, .weight_high = weight >> 8, }; } if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) goto nla_put_failure; if (op_flags & NHA_OP_FLAG_DUMP_STATS && (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) || nla_put_nh_group_stats(skb, nh, op_flags))) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, int event, u32 portid, u32 seq, unsigned int nlflags, u32 op_flags) { struct fib6_nh *fib6_nh; struct fib_nh *fib_nh; struct nlmsghdr *nlh; struct nh_info *nhi; struct nhmsg *nhm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags); if (!nlh) return -EMSGSIZE; nhm = nlmsg_data(nlh); nhm->nh_family = AF_UNSPEC; nhm->nh_flags = nh->nh_flags; nhm->nh_protocol = nh->protocol; nhm->nh_scope = 0; nhm->resvd = 0; if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); u32 resp_op_flags = 0; if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; if (nla_put_nh_group(skb, nh, op_flags, &resp_op_flags) || nla_put_u32(skb, NHA_OP_FLAGS, resp_op_flags)) goto nla_put_failure; goto out; } nhi = rtnl_dereference(nh->nh_info); nhm->nh_family = nhi->family; if (nhi->reject_nh) { if (nla_put_flag(skb, NHA_BLACKHOLE)) goto nla_put_failure; goto out; } else if (nhi->fdb_nh) { if (nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; } else { const struct net_device *dev; dev = nhi->fib_nhc.nhc_dev; if (dev && nla_put_u32(skb, NHA_OIF, dev->ifindex)) goto nla_put_failure; } nhm->nh_scope = nhi->fib_nhc.nhc_scope; switch (nhi->family) { case AF_INET: fib_nh = &nhi->fib_nh; if (fib_nh->fib_nh_gw_family && nla_put_be32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) goto nla_put_failure; break; case AF_INET6: fib6_nh = &nhi->fib6_nh; if (fib6_nh->fib_nh_gw_family && nla_put_in6_addr(skb, NHA_GATEWAY, &fib6_nh->fib_nh_gw6)) goto nla_put_failure; break; } if (nhi->fib_nhc.nhc_lwtstate && lwtunnel_fill_encap(skb, nhi->fib_nhc.nhc_lwtstate, NHA_ENCAP, NHA_ENCAP_TYPE) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static size_t nh_nlmsg_size_grp_res(struct nh_group *nhg) { return nla_total_size(0) + /* NHA_RES_GROUP */ nla_total_size(2) + /* NHA_RES_GROUP_BUCKETS */ nla_total_size(4) + /* NHA_RES_GROUP_IDLE_TIMER */ nla_total_size(4) + /* NHA_RES_GROUP_UNBALANCED_TIMER */ nla_total_size_64bit(8);/* NHA_RES_GROUP_UNBALANCED_TIME */ } static size_t nh_nlmsg_size_grp(struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); size_t sz = sizeof(struct nexthop_grp) * nhg->num_nh; size_t tot = nla_total_size(sz) + nla_total_size(2); /* NHA_GROUP_TYPE */ if (nhg->resilient) tot += nh_nlmsg_size_grp_res(nhg); return tot; } static size_t nh_nlmsg_size_single(struct nexthop *nh) { struct nh_info *nhi = rtnl_dereference(nh->nh_info); size_t sz; /* covers NHA_BLACKHOLE since NHA_OIF and BLACKHOLE * are mutually exclusive */ sz = nla_total_size(4); /* NHA_OIF */ switch (nhi->family) { case AF_INET: if (nhi->fib_nh.fib_nh_gw_family) sz += nla_total_size(4); /* NHA_GATEWAY */ break; case AF_INET6: /* NHA_GATEWAY */ if (nhi->fib6_nh.fib_nh_gw_family) sz += nla_total_size(sizeof(const struct in6_addr)); break; } if (nhi->fib_nhc.nhc_lwtstate) { sz += lwtunnel_get_encap_size(nhi->fib_nhc.nhc_lwtstate); sz += nla_total_size(2); /* NHA_ENCAP_TYPE */ } return sz; } static size_t nh_nlmsg_size(struct nexthop *nh) { size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg)); sz += nla_total_size(4); /* NHA_ID */ if (nh->is_group) sz += nh_nlmsg_size_grp(nh) + nla_total_size(4) + /* NHA_OP_FLAGS */ 0; else sz += nh_nlmsg_size_single(nh); return sz; } static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) { unsigned int nlflags = info->nlh ? info->nlh->nlmsg_flags : 0; u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(nh_nlmsg_size(nh), gfp_any()); if (!skb) goto errout; err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags, 0); if (err < 0) { /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_NEXTHOP, info->nlh, gfp_any()); return; errout: rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); } static unsigned long nh_res_bucket_used_time(const struct nh_res_bucket *bucket) { return (unsigned long)atomic_long_read(&bucket->used_time); } static unsigned long nh_res_bucket_idle_point(const struct nh_res_table *res_table, const struct nh_res_bucket *bucket, unsigned long now) { unsigned long time = nh_res_bucket_used_time(bucket); /* Bucket was not used since it was migrated. The idle time is now. */ if (time == bucket->migrated_time) return now; return time + res_table->idle_timer; } static unsigned long nh_res_table_unb_point(const struct nh_res_table *res_table) { return res_table->unbalanced_since + res_table->unbalanced_timer; } static void nh_res_bucket_set_idle(const struct nh_res_table *res_table, struct nh_res_bucket *bucket) { unsigned long now = jiffies; atomic_long_set(&bucket->used_time, (long)now); bucket->migrated_time = now; } static void nh_res_bucket_set_busy(struct nh_res_bucket *bucket) { atomic_long_set(&bucket->used_time, (long)jiffies); } static clock_t nh_res_bucket_idle_time(const struct nh_res_bucket *bucket) { unsigned long used_time = nh_res_bucket_used_time(bucket); return jiffies_delta_to_clock_t(jiffies - used_time); } static int nh_fill_res_bucket(struct sk_buff *skb, struct nexthop *nh, struct nh_res_bucket *bucket, u16 bucket_index, int event, u32 portid, u32 seq, unsigned int nlflags, struct netlink_ext_ack *extack) { struct nh_grp_entry *nhge = nh_res_dereference(bucket->nh_entry); struct nlmsghdr *nlh; struct nlattr *nest; struct nhmsg *nhm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags); if (!nlh) return -EMSGSIZE; nhm = nlmsg_data(nlh); nhm->nh_family = AF_UNSPEC; nhm->nh_flags = bucket->nh_flags; nhm->nh_protocol = nh->protocol; nhm->nh_scope = 0; nhm->resvd = 0; if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; nest = nla_nest_start(skb, NHA_RES_BUCKET); if (!nest) goto nla_put_failure; if (nla_put_u16(skb, NHA_RES_BUCKET_INDEX, bucket_index) || nla_put_u32(skb, NHA_RES_BUCKET_NH_ID, nhge->nh->id) || nla_put_u64_64bit(skb, NHA_RES_BUCKET_IDLE_TIME, nh_res_bucket_idle_time(bucket), NHA_RES_BUCKET_PAD)) goto nla_put_failure_nest; nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; nla_put_failure_nest: nla_nest_cancel(skb, nest); nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static void nexthop_bucket_notify(struct nh_res_table *res_table, u16 bucket_index) { struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index]; struct nh_grp_entry *nhge = nh_res_dereference(bucket->nh_entry); struct nexthop *nh = nhge->nh_parent; struct sk_buff *skb; int err = -ENOBUFS; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) goto errout; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, 0, 0, NLM_F_REPLACE, NULL); if (err < 0) { kfree_skb(skb); goto errout; } rtnl_notify(skb, nh->net, 0, RTNLGRP_NEXTHOP, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); } static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, bool *is_fdb, struct netlink_ext_ack *extack) { if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); /* Nesting groups within groups is not supported. */ if (nhg->hash_threshold) { NL_SET_ERR_MSG(extack, "Hash-threshold group can not be a nexthop within a group"); return false; } if (nhg->resilient) { NL_SET_ERR_MSG(extack, "Resilient group can not be a nexthop within a group"); return false; } *is_fdb = nhg->fdb_nh; } else { struct nh_info *nhi = rtnl_dereference(nh->nh_info); if (nhi->reject_nh && npaths > 1) { NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be used in a group with more than 1 path"); return false; } *is_fdb = nhi->fdb_nh; } return true; } static int nh_check_attr_fdb_group(struct nexthop *nh, u8 *nh_family, struct netlink_ext_ack *extack) { struct nh_info *nhi; nhi = rtnl_dereference(nh->nh_info); if (!nhi->fdb_nh) { NL_SET_ERR_MSG(extack, "FDB nexthop group can only have fdb nexthops"); return -EINVAL; } if (*nh_family == AF_UNSPEC) { *nh_family = nhi->family; } else if (*nh_family != nhi->family) { NL_SET_ERR_MSG(extack, "FDB nexthop group cannot have mixed family nexthops"); return -EINVAL; } return 0; } static int nh_check_attr_group(struct net *net, struct nlattr *tb[], size_t tb_size, u16 nh_grp_type, struct netlink_ext_ack *extack) { unsigned int len = nla_len(tb[NHA_GROUP]); u8 nh_family = AF_UNSPEC; struct nexthop_grp *nhg; unsigned int i, j; u8 nhg_fdb = 0; if (!len || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, "Invalid length for nexthop group attribute"); return -EINVAL; } /* convert len to number of nexthop ids */ len /= sizeof(*nhg); nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { if (nhg[i].resvd2) { NL_SET_ERR_MSG(extack, "Reserved field in nexthop_grp must be 0"); return -EINVAL; } if (nexthop_grp_weight(&nhg[i]) == 0) { /* 0xffff got passed in, representing weight of 0x10000, * which is too heavy. */ NL_SET_ERR_MSG(extack, "Invalid value for weight"); return -EINVAL; } for (j = i + 1; j < len; ++j) { if (nhg[i].id == nhg[j].id) { NL_SET_ERR_MSG(extack, "Nexthop id can not be used twice in a group"); return -EINVAL; } } } if (tb[NHA_FDB]) nhg_fdb = 1; nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { struct nexthop *nh; bool is_fdb_nh; nh = nexthop_find_by_id(net, nhg[i].id); if (!nh) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } if (!valid_group_nh(nh, len, &is_fdb_nh, extack)) return -EINVAL; if (nhg_fdb && nh_check_attr_fdb_group(nh, &nh_family, extack)) return -EINVAL; if (!nhg_fdb && is_fdb_nh) { NL_SET_ERR_MSG(extack, "Non FDB nexthop group cannot have fdb nexthops"); return -EINVAL; } } for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) { if (!tb[i]) continue; switch (i) { case NHA_HW_STATS_ENABLE: case NHA_FDB: continue; case NHA_RES_GROUP: if (nh_grp_type == NEXTHOP_GRP_TYPE_RES) continue; break; } NL_SET_ERR_MSG(extack, "No other attributes can be set in nexthop groups"); return -EINVAL; } return 0; } static bool ipv6_good_nh(const struct fib6_nh *nh) { int state = NUD_REACHABLE; struct neighbour *n; rcu_read_lock(); n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6); if (n) state = READ_ONCE(n->nud_state); rcu_read_unlock(); return !!(state & NUD_VALID); } static bool ipv4_good_nh(const struct fib_nh *nh) { int state = NUD_REACHABLE; struct neighbour *n; rcu_read_lock(); n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, (__force u32)nh->fib_nh_gw4); if (n) state = READ_ONCE(n->nud_state); rcu_read_unlock(); return !!(state & NUD_VALID); } static bool nexthop_is_good_nh(const struct nexthop *nh) { struct nh_info *nhi = rcu_dereference(nh->nh_info); switch (nhi->family) { case AF_INET: return ipv4_good_nh(&nhi->fib_nh); case AF_INET6: return ipv6_good_nh(&nhi->fib6_nh); } return false; } static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) { int i; for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; nh_grp_entry_stats_inc(nhge); return nhge->nh; } WARN_ON_ONCE(1); return NULL; } static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) { struct nh_grp_entry *nhge0 = NULL; int i; if (nhg->fdb_nh) return nexthop_select_path_fdb(nhg, hash); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; /* nexthops always check if it is good and does * not rely on a sysctl for this behavior */ if (!nexthop_is_good_nh(nhge->nh)) continue; if (!nhge0) nhge0 = nhge; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; nh_grp_entry_stats_inc(nhge); return nhge->nh; } if (!nhge0) nhge0 = &nhg->nh_entries[0]; nh_grp_entry_stats_inc(nhge0); return nhge0->nh; } static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) { struct nh_res_table *res_table = rcu_dereference(nhg->res_table); u16 bucket_index = hash % res_table->num_nh_buckets; struct nh_res_bucket *bucket; struct nh_grp_entry *nhge; /* nexthop_select_path() is expected to return a non-NULL value, so * skip protocol validation and just hand out whatever there is. */ bucket = &res_table->nh_buckets[bucket_index]; nh_res_bucket_set_busy(bucket); nhge = rcu_dereference(bucket->nh_entry); nh_grp_entry_stats_inc(nhge); return nhge->nh; } struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) { struct nh_group *nhg; if (!nh->is_group) return nh; nhg = rcu_dereference(nh->nh_grp); if (nhg->hash_threshold) return nexthop_select_path_hthr(nhg, hash); else if (nhg->resilient) return nexthop_select_path_res(nhg, hash); /* Unreachable. */ return NULL; } EXPORT_SYMBOL_GPL(nexthop_select_path); int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg) { struct nh_info *nhi; int err; if (nh->is_group) { struct nh_group *nhg; int i; nhg = rcu_dereference_rtnl(nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; nhi = rcu_dereference_rtnl(nhge->nh->nh_info); err = cb(&nhi->fib6_nh, arg); if (err) return err; } } else { nhi = rcu_dereference_rtnl(nh->nh_info); err = cb(&nhi->fib6_nh, arg); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(nexthop_for_each_fib6_nh); static int check_src_addr(const struct in6_addr *saddr, struct netlink_ext_ack *extack) { if (!ipv6_addr_any(saddr)) { NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects"); return -EINVAL; } return 0; } int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct nh_info *nhi; bool is_fdb_nh; /* fib6_src is unique to a fib6_info and limits the ability to cache * routes in fib6_nh within a nexthop that is potentially shared * across multiple fib entries. If the config wants to use source * routing it can not use nexthop objects. mlxsw also does not allow * fib6_src on routes. */ if (cfg && check_src_addr(&cfg->fc_src, extack) < 0) return -EINVAL; if (nh->is_group) { struct nh_group *nhg; nhg = rtnl_dereference(nh->nh_grp); if (nhg->has_v4) goto no_v4_nh; is_fdb_nh = nhg->fdb_nh; } else { nhi = rtnl_dereference(nh->nh_info); if (nhi->family == AF_INET) goto no_v4_nh; is_fdb_nh = nhi->fdb_nh; } if (is_fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); return -EINVAL; } return 0; no_v4_nh: NL_SET_ERR_MSG(extack, "IPv6 routes can not use an IPv4 nexthop"); return -EINVAL; } EXPORT_SYMBOL_GPL(fib6_check_nexthop); /* if existing nexthop has ipv6 routes linked to it, need * to verify this new spec works with ipv6 */ static int fib6_check_nh_list(struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct fib6_info *f6i; if (list_empty(&old->f6i_list)) return 0; list_for_each_entry(f6i, &old->f6i_list, nh_list) { if (check_src_addr(&f6i->fib6_src.addr, extack) < 0) return -EINVAL; } return fib6_check_nexthop(new, NULL, extack); } static int nexthop_check_scope(struct nh_info *nhi, u8 scope, struct netlink_ext_ack *extack) { if (scope == RT_SCOPE_HOST && nhi->fib_nhc.nhc_gw_family) { NL_SET_ERR_MSG(extack, "Route with host scope can not have a gateway"); return -EINVAL; } if (nhi->fib_nhc.nhc_flags & RTNH_F_ONLINK && scope >= RT_SCOPE_LINK) { NL_SET_ERR_MSG(extack, "Scope mismatch with nexthop"); return -EINVAL; } return 0; } /* Invoked by fib add code to verify nexthop by id is ok with * config for prefix; parts of fib_check_nh not done when nexthop * object is used. */ int fib_check_nexthop(struct nexthop *nh, u8 scope, struct netlink_ext_ack *extack) { struct nh_info *nhi; int err = 0; if (nh->is_group) { struct nh_group *nhg; nhg = rtnl_dereference(nh->nh_grp); if (nhg->fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); err = -EINVAL; goto out; } if (scope == RT_SCOPE_HOST) { NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops"); err = -EINVAL; goto out; } /* all nexthops in a group have the same scope */ nhi = rtnl_dereference(nhg->nh_entries[0].nh->nh_info); err = nexthop_check_scope(nhi, scope, extack); } else { nhi = rtnl_dereference(nh->nh_info); if (nhi->fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); err = -EINVAL; goto out; } err = nexthop_check_scope(nhi, scope, extack); } out: return err; } static int fib_check_nh_list(struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct fib_info *fi; list_for_each_entry(fi, &old->fi_list, nh_list) { int err; err = fib_check_nexthop(new, fi->fib_scope, extack); if (err) return err; } return 0; } static bool nh_res_nhge_is_balanced(const struct nh_grp_entry *nhge) { return nhge->res.count_buckets == nhge->res.wants_buckets; } static bool nh_res_nhge_is_ow(const struct nh_grp_entry *nhge) { return nhge->res.count_buckets > nhge->res.wants_buckets; } static bool nh_res_nhge_is_uw(const struct nh_grp_entry *nhge) { return nhge->res.count_buckets < nhge->res.wants_buckets; } static bool nh_res_table_is_balanced(const struct nh_res_table *res_table) { return list_empty(&res_table->uw_nh_entries); } static void nh_res_bucket_unset_nh(struct nh_res_bucket *bucket) { struct nh_grp_entry *nhge; if (bucket->occupied) { nhge = nh_res_dereference(bucket->nh_entry); nhge->res.count_buckets--; bucket->occupied = false; } } static void nh_res_bucket_set_nh(struct nh_res_bucket *bucket, struct nh_grp_entry *nhge) { nh_res_bucket_unset_nh(bucket); bucket->occupied = true; rcu_assign_pointer(bucket->nh_entry, nhge); nhge->res.count_buckets++; } static bool nh_res_bucket_should_migrate(struct nh_res_table *res_table, struct nh_res_bucket *bucket, unsigned long *deadline, bool *force) { unsigned long now = jiffies; struct nh_grp_entry *nhge; unsigned long idle_point; if (!bucket->occupied) { /* The bucket is not occupied, its NHGE pointer is either * NULL or obsolete. We _have to_ migrate: set force. */ *force = true; return true; } nhge = nh_res_dereference(bucket->nh_entry); /* If the bucket is populated by an underweight or balanced * nexthop, do not migrate. */ if (!nh_res_nhge_is_ow(nhge)) return false; /* At this point we know that the bucket is populated with an * overweight nexthop. It needs to be migrated to a new nexthop if * the idle timer of unbalanced timer expired. */ idle_point = nh_res_bucket_idle_point(res_table, bucket, now); if (time_after_eq(now, idle_point)) { /* The bucket is idle. We _can_ migrate: unset force. */ *force = false; return true; } /* Unbalanced timer of 0 means "never force". */ if (res_table->unbalanced_timer) { unsigned long unb_point; unb_point = nh_res_table_unb_point(res_table); if (time_after(now, unb_point)) { /* The bucket is not idle, but the unbalanced timer * expired. We _can_ migrate, but set force anyway, * so that drivers know to ignore activity reports * from the HW. */ *force = true; return true; } nh_res_time_set_deadline(unb_point, deadline); } nh_res_time_set_deadline(idle_point, deadline); return false; } static bool nh_res_bucket_migrate(struct nh_res_table *res_table, u16 bucket_index, bool notify, bool notify_nl, bool force) { struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index]; struct nh_grp_entry *new_nhge; struct netlink_ext_ack extack; int err; new_nhge = list_first_entry_or_null(&res_table->uw_nh_entries, struct nh_grp_entry, res.uw_nh_entry); if (WARN_ON_ONCE(!new_nhge)) /* If this function is called, "bucket" is either not * occupied, or it belongs to a next hop that is * overweight. In either case, there ought to be a * corresponding underweight next hop. */ return false; if (notify) { struct nh_grp_entry *old_nhge; old_nhge = nh_res_dereference(bucket->nh_entry); err = call_nexthop_res_bucket_notifiers(res_table->net, res_table->nhg_id, bucket_index, force, old_nhge->nh, new_nhge->nh, &extack); if (err) { pr_err_ratelimited("%s\n", extack._msg); if (!force) return false; /* It is not possible to veto a forced replacement, so * just clear the hardware flags from the nexthop * bucket to indicate to user space that this bucket is * not correctly populated in hardware. */ bucket->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); } } nh_res_bucket_set_nh(bucket, new_nhge); nh_res_bucket_set_idle(res_table, bucket); if (notify_nl) nexthop_bucket_notify(res_table, bucket_index); if (nh_res_nhge_is_balanced(new_nhge)) list_del(&new_nhge->res.uw_nh_entry); return true; } #define NH_RES_UPKEEP_DW_MINIMUM_INTERVAL (HZ / 2) static void nh_res_table_upkeep(struct nh_res_table *res_table, bool notify, bool notify_nl) { unsigned long now = jiffies; unsigned long deadline; u16 i; /* Deadline is the next time that upkeep should be run. It is the * earliest time at which one of the buckets might be migrated. * Start at the most pessimistic estimate: either unbalanced_timer * from now, or if there is none, idle_timer from now. For each * encountered time point, call nh_res_time_set_deadline() to * refine the estimate. */ if (res_table->unbalanced_timer) deadline = now + res_table->unbalanced_timer; else deadline = now + res_table->idle_timer; for (i = 0; i < res_table->num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; bool force; if (nh_res_bucket_should_migrate(res_table, bucket, &deadline, &force)) { if (!nh_res_bucket_migrate(res_table, i, notify, notify_nl, force)) { unsigned long idle_point; /* A driver can override the migration * decision if the HW reports that the * bucket is actually not idle. Therefore * remark the bucket as busy again and * update the deadline. */ nh_res_bucket_set_busy(bucket); idle_point = nh_res_bucket_idle_point(res_table, bucket, now); nh_res_time_set_deadline(idle_point, &deadline); } } } /* If the group is still unbalanced, schedule the next upkeep to * either the deadline computed above, or the minimum deadline, * whichever comes later. */ if (!nh_res_table_is_balanced(res_table)) { unsigned long now = jiffies; unsigned long min_deadline; min_deadline = now + NH_RES_UPKEEP_DW_MINIMUM_INTERVAL; if (time_before(deadline, min_deadline)) deadline = min_deadline; queue_delayed_work(system_power_efficient_wq, &res_table->upkeep_dw, deadline - now); } } static void nh_res_table_upkeep_dw(struct work_struct *work) { struct delayed_work *dw = to_delayed_work(work); struct nh_res_table *res_table; res_table = container_of(dw, struct nh_res_table, upkeep_dw); nh_res_table_upkeep(res_table, true, true); } static void nh_res_table_cancel_upkeep(struct nh_res_table *res_table) { cancel_delayed_work_sync(&res_table->upkeep_dw); } static void nh_res_group_rebalance(struct nh_group *nhg, struct nh_res_table *res_table) { u16 prev_upper_bound = 0; u32 total = 0; u32 w = 0; int i; INIT_LIST_HEAD(&res_table->uw_nh_entries); for (i = 0; i < nhg->num_nh; ++i) total += nhg->nh_entries[i].weight; for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; u16 upper_bound; u64 btw; w += nhge->weight; btw = ((u64)res_table->num_nh_buckets) * w; upper_bound = DIV_ROUND_CLOSEST_ULL(btw, total); nhge->res.wants_buckets = upper_bound - prev_upper_bound; prev_upper_bound = upper_bound; if (nh_res_nhge_is_uw(nhge)) { if (list_empty(&res_table->uw_nh_entries)) res_table->unbalanced_since = jiffies; list_add(&nhge->res.uw_nh_entry, &res_table->uw_nh_entries); } } } /* Migrate buckets in res_table so that they reference NHGE's from NHG with * the right NH ID. Set those buckets that do not have a corresponding NHGE * entry in NHG as not occupied. */ static void nh_res_table_migrate_buckets(struct nh_res_table *res_table, struct nh_group *nhg) { u16 i; for (i = 0; i < res_table->num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; u32 id = rtnl_dereference(bucket->nh_entry)->nh->id; bool found = false; int j; for (j = 0; j < nhg->num_nh; j++) { struct nh_grp_entry *nhge = &nhg->nh_entries[j]; if (nhge->nh->id == id) { nh_res_bucket_set_nh(bucket, nhge); found = true; break; } } if (!found) nh_res_bucket_unset_nh(bucket); } } static void replace_nexthop_grp_res(struct nh_group *oldg, struct nh_group *newg) { /* For NH group replacement, the new NHG might only have a stub * hash table with 0 buckets, because the number of buckets was not * specified. For NH removal, oldg and newg both reference the same * res_table. So in any case, in the following, we want to work * with oldg->res_table. */ struct nh_res_table *old_res_table = rtnl_dereference(oldg->res_table); unsigned long prev_unbalanced_since = old_res_table->unbalanced_since; bool prev_has_uw = !list_empty(&old_res_table->uw_nh_entries); nh_res_table_cancel_upkeep(old_res_table); nh_res_table_migrate_buckets(old_res_table, newg); nh_res_group_rebalance(newg, old_res_table); if (prev_has_uw && !list_empty(&old_res_table->uw_nh_entries)) old_res_table->unbalanced_since = prev_unbalanced_since; nh_res_table_upkeep(old_res_table, true, false); } static void nh_hthr_group_rebalance(struct nh_group *nhg) { u32 total = 0; u32 w = 0; int i; for (i = 0; i < nhg->num_nh; ++i) total += nhg->nh_entries[i].weight; for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; u32 upper_bound; w += nhge->weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; atomic_set(&nhge->hthr.upper_bound, upper_bound); } } static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, struct nl_info *nlinfo) { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; struct netlink_ext_ack extack; struct nexthop *nh = nhge->nh; struct nh_group *nhg, *newg; int i, j, err; WARN_ON(!nh); nhg = rtnl_dereference(nhp->nh_grp); newg = nhg->spare; /* last entry, keep it visible and remove the parent */ if (nhg->num_nh == 1) { remove_nexthop(net, nhp, nlinfo); return; } newg->has_v4 = false; newg->is_multipath = nhg->is_multipath; newg->hash_threshold = nhg->hash_threshold; newg->resilient = nhg->resilient; newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; /* copy old entries to new except the one getting removed */ nhges = nhg->nh_entries; new_nhges = newg->nh_entries; for (i = 0, j = 0; i < nhg->num_nh; ++i) { struct nh_info *nhi; /* current nexthop getting removed */ if (nhg->nh_entries[i].nh == nh) { newg->num_nh--; continue; } nhi = rtnl_dereference(nhges[i].nh->nh_info); if (nhi->family == AF_INET) newg->has_v4 = true; list_del(&nhges[i].nh_list); new_nhges[j].stats = nhges[i].stats; new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; new_nhges[j].weight = nhges[i].weight; list_add(&new_nhges[j].nh_list, &new_nhges[j].nh->grp_list); j++; } if (newg->hash_threshold) nh_hthr_group_rebalance(newg); else if (newg->resilient) replace_nexthop_grp_res(nhg, newg); rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); free_percpu(nhge->stats); nexthop_put(nhge->nh); /* Removal of a NH from a resilient group is notified through * bucket notifications. */ if (newg->hash_threshold) { err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, &extack); if (err) pr_err("%s\n", extack._msg); } if (nlinfo) nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo); } static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { struct nh_grp_entry *nhge, *tmp; list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) remove_nh_grp_entry(net, nhge, nlinfo); /* make sure all see the newly published array before releasing rtnl */ synchronize_net(); } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) { struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); struct nh_res_table *res_table; int i, num_nh = nhg->num_nh; for (i = 0; i < num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; if (WARN_ON(!nhge->nh)) continue; list_del_init(&nhge->nh_list); } if (nhg->resilient) { res_table = rtnl_dereference(nhg->res_table); nh_res_table_cancel_upkeep(res_table); } } /* not called for nexthop replace */ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) { struct fib6_info *f6i, *tmp; bool do_flush = false; struct fib_info *fi; list_for_each_entry(fi, &nh->fi_list, nh_list) { fi->fib_flags |= RTNH_F_DEAD; do_flush = true; } if (do_flush) fib_flush(net); /* ip6_del_rt removes the entry from this list hence the _safe */ list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) { /* __ip6_del_rt does a release, so do a hold here */ fib6_info_hold(f6i); ipv6_stub->ip6_del_rt(net, f6i, !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)); } } static void __remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { __remove_nexthop_fib(net, nh); if (nh->is_group) { remove_nexthop_group(nh, nlinfo); } else { struct nh_info *nhi; nhi = rtnl_dereference(nh->nh_info); if (nhi->fib_nhc.nhc_dev) hlist_del(&nhi->dev_hash); remove_nexthop_from_groups(net, nh, nlinfo); } } static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh, NULL); /* remove from the tree */ rb_erase(&nh->rb_node, &net->nexthop.rb_root); if (nlinfo) nexthop_notify(RTM_DELNEXTHOP, nh, nlinfo); __remove_nexthop(net, nh, nlinfo); nh_base_seq_inc(net); nexthop_put(nh); } /* if any FIB entries reference this nexthop, any dst entries * need to be regenerated */ static void nh_rt_cache_flush(struct net *net, struct nexthop *nh, struct nexthop *replaced_nh) { struct fib6_info *f6i; struct nh_group *nhg; int i; if (!list_empty(&nh->fi_list)) rt_cache_flush(net); list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_update_sernum(net, f6i); /* if an IPv6 group was replaced, we have to release all old * dsts to make sure all refcounts are released */ if (!replaced_nh->is_group) return; nhg = rtnl_dereference(replaced_nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info); if (nhi->family == AF_INET6) ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh); } } static int replace_nexthop_grp(struct net *net, struct nexthop *old, struct nexthop *new, const struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nh_res_table *tmp_table = NULL; struct nh_res_table *new_res_table; struct nh_res_table *old_res_table; struct nh_group *oldg, *newg; int i, err; if (!new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop."); return -EINVAL; } oldg = rtnl_dereference(old->nh_grp); newg = rtnl_dereference(new->nh_grp); if (newg->hash_threshold != oldg->hash_threshold) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with one of a different type."); return -EINVAL; } if (newg->hash_threshold) { err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); if (err) return err; } else if (newg->resilient) { new_res_table = rtnl_dereference(newg->res_table); old_res_table = rtnl_dereference(oldg->res_table); /* Accept if num_nh_buckets was not given, but if it was * given, demand that the value be correct. */ if (cfg->nh_grp_res_has_num_buckets && cfg->nh_grp_res_num_buckets != old_res_table->num_nh_buckets) { NL_SET_ERR_MSG(extack, "Can not change number of buckets of a resilient nexthop group."); return -EINVAL; } /* Emit a pre-replace notification so that listeners could veto * a potentially unsupported configuration. Otherwise, * individual bucket replacement notifications would need to be * vetoed, which is something that should only happen if the * bucket is currently active. */ err = call_nexthop_res_table_notifiers(net, new, extack); if (err) return err; if (cfg->nh_grp_res_has_idle_timer) old_res_table->idle_timer = cfg->nh_grp_res_idle_timer; if (cfg->nh_grp_res_has_unbalanced_timer) old_res_table->unbalanced_timer = cfg->nh_grp_res_unbalanced_timer; replace_nexthop_grp_res(oldg, newg); tmp_table = new_res_table; rcu_assign_pointer(newg->res_table, old_res_table); rcu_assign_pointer(newg->spare->res_table, old_res_table); } /* update parents - used by nexthop code for cleanup */ for (i = 0; i < newg->num_nh; i++) newg->nh_entries[i].nh_parent = old; rcu_assign_pointer(old->nh_grp, newg); /* Make sure concurrent readers are not using 'oldg' anymore. */ synchronize_net(); if (newg->resilient) { rcu_assign_pointer(oldg->res_table, tmp_table); rcu_assign_pointer(oldg->spare->res_table, tmp_table); } for (i = 0; i < oldg->num_nh; i++) oldg->nh_entries[i].nh_parent = new; rcu_assign_pointer(new->nh_grp, oldg); return 0; } static void nh_group_v4_update(struct nh_group *nhg) { struct nh_grp_entry *nhges; bool has_v4 = false; int i; nhges = nhg->nh_entries; for (i = 0; i < nhg->num_nh; i++) { struct nh_info *nhi; nhi = rtnl_dereference(nhges[i].nh->nh_info); if (nhi->family == AF_INET) has_v4 = true; } nhg->has_v4 = has_v4; } static int replace_nexthop_single_notify_res(struct net *net, struct nh_res_table *res_table, struct nexthop *old, struct nh_info *oldi, struct nh_info *newi, struct netlink_ext_ack *extack) { u32 nhg_id = res_table->nhg_id; int err; u16 i; for (i = 0; i < res_table->num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; struct nh_grp_entry *nhge; nhge = rtnl_dereference(bucket->nh_entry); if (nhge->nh == old) { err = __call_nexthop_res_bucket_notifiers(net, nhg_id, i, true, oldi, newi, extack); if (err) goto err_notify; } } return 0; err_notify: while (i-- > 0) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; struct nh_grp_entry *nhge; nhge = rtnl_dereference(bucket->nh_entry); if (nhge->nh == old) __call_nexthop_res_bucket_notifiers(net, nhg_id, i, true, newi, oldi, extack); } return err; } static int replace_nexthop_single_notify(struct net *net, struct nexthop *group_nh, struct nexthop *old, struct nh_info *oldi, struct nh_info *newi, struct netlink_ext_ack *extack) { struct nh_group *nhg = rtnl_dereference(group_nh->nh_grp); struct nh_res_table *res_table; if (nhg->hash_threshold) { return call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, group_nh, extack); } else if (nhg->resilient) { res_table = rtnl_dereference(nhg->res_table); return replace_nexthop_single_notify_res(net, res_table, old, oldi, newi, extack); } return -EINVAL; } static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { u8 old_protocol, old_nh_flags; struct nh_info *oldi, *newi; struct nh_grp_entry *nhge; int err; if (new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group."); return -EINVAL; } err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); if (err) return err; /* Hardware flags were set on 'old' as 'new' is not in the red-black * tree. Therefore, inherit the flags from 'old' to 'new'. */ new->nh_flags |= old->nh_flags & (RTNH_F_OFFLOAD | RTNH_F_TRAP); oldi = rtnl_dereference(old->nh_info); newi = rtnl_dereference(new->nh_info); newi->nh_parent = old; oldi->nh_parent = new; old_protocol = old->protocol; old_nh_flags = old->nh_flags; old->protocol = new->protocol; old->nh_flags = new->nh_flags; rcu_assign_pointer(old->nh_info, newi); rcu_assign_pointer(new->nh_info, oldi); /* Send a replace notification for all the groups using the nexthop. */ list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; err = replace_nexthop_single_notify(net, nhp, old, oldi, newi, extack); if (err) goto err_notify; } /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially * update IPv4 indication in all the groups using the nexthop. */ if (oldi->family == AF_INET && newi->family == AF_INET6) { list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; struct nh_group *nhg; nhg = rtnl_dereference(nhp->nh_grp); nh_group_v4_update(nhg); } } return 0; err_notify: rcu_assign_pointer(new->nh_info, newi); rcu_assign_pointer(old->nh_info, oldi); old->nh_flags = old_nh_flags; old->protocol = old_protocol; oldi->nh_parent = old; newi->nh_parent = new; list_for_each_entry_continue_reverse(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; replace_nexthop_single_notify(net, nhp, old, newi, oldi, NULL); } call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, old, extack); return err; } static void __nexthop_replace_notify(struct net *net, struct nexthop *nh, struct nl_info *info) { struct fib6_info *f6i; if (!list_empty(&nh->fi_list)) { struct fib_info *fi; /* expectation is a few fib_info per nexthop and then * a lot of routes per fib_info. So mark the fib_info * and then walk the fib tables once */ list_for_each_entry(fi, &nh->fi_list, nh_list) fi->nh_updated = true; fib_info_notify_update(net, info); list_for_each_entry(fi, &nh->fi_list, nh_list) fi->nh_updated = false; } list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_rt_update(net, f6i, info); } /* send RTM_NEWROUTE with REPLACE flag set for all FIB entries * linked to this nexthop and for all groups that the nexthop * is a member of */ static void nexthop_replace_notify(struct net *net, struct nexthop *nh, struct nl_info *info) { struct nh_grp_entry *nhge; __nexthop_replace_notify(net, nh, info); list_for_each_entry(nhge, &nh->grp_list, nh_list) __nexthop_replace_notify(net, nhge->nh_parent, info); } static int replace_nexthop(struct net *net, struct nexthop *old, struct nexthop *new, const struct nh_config *cfg, struct netlink_ext_ack *extack) { bool new_is_reject = false; struct nh_grp_entry *nhge; int err; /* check that existing FIB entries are ok with the * new nexthop definition */ err = fib_check_nh_list(old, new, extack); if (err) return err; err = fib6_check_nh_list(old, new, extack); if (err) return err; if (!new->is_group) { struct nh_info *nhi = rtnl_dereference(new->nh_info); new_is_reject = nhi->reject_nh; } list_for_each_entry(nhge, &old->grp_list, nh_list) { /* if new nexthop is a blackhole, any groups using this * nexthop cannot have more than 1 path */ if (new_is_reject && nexthop_num_path(nhge->nh_parent) > 1) { NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be a member of a group with more than one path"); return -EINVAL; } err = fib_check_nh_list(nhge->nh_parent, new, extack); if (err) return err; err = fib6_check_nh_list(nhge->nh_parent, new, extack); if (err) return err; } if (old->is_group) err = replace_nexthop_grp(net, old, new, cfg, extack); else err = replace_nexthop_single(net, old, new, extack); if (!err) { nh_rt_cache_flush(net, old, new); __remove_nexthop(net, new, NULL); nexthop_put(new); } return err; } /* called with rtnl_lock held */ static int insert_nexthop(struct net *net, struct nexthop *new_nh, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct rb_node **pp, *parent = NULL, *next; struct rb_root *root = &net->nexthop.rb_root; bool replace = !!(cfg->nlflags & NLM_F_REPLACE); bool create = !!(cfg->nlflags & NLM_F_CREATE); u32 new_id = new_nh->id; int replace_notify = 0; int rc = -EEXIST; pp = &root->rb_node; while (1) { struct nexthop *nh; next = *pp; if (!next) break; parent = next; nh = rb_entry(parent, struct nexthop, rb_node); if (new_id < nh->id) { pp = &next->rb_left; } else if (new_id > nh->id) { pp = &next->rb_right; } else if (replace) { rc = replace_nexthop(net, nh, new_nh, cfg, extack); if (!rc) { new_nh = nh; /* send notification with old nh */ replace_notify = 1; } goto out; } else { /* id already exists and not a replace */ goto out; } } if (replace && !create) { NL_SET_ERR_MSG(extack, "Replace specified without create and no entry exists"); rc = -ENOENT; goto out; } if (new_nh->is_group) { struct nh_group *nhg = rtnl_dereference(new_nh->nh_grp); struct nh_res_table *res_table; if (nhg->resilient) { res_table = rtnl_dereference(nhg->res_table); /* Not passing the number of buckets is OK when * replacing, but not when creating a new group. */ if (!cfg->nh_grp_res_has_num_buckets) { NL_SET_ERR_MSG(extack, "Number of buckets not specified for nexthop group insertion"); rc = -EINVAL; goto out; } nh_res_group_rebalance(nhg, res_table); /* Do not send bucket notifications, we do full * notification below. */ nh_res_table_upkeep(res_table, false, false); } } rb_link_node_rcu(&new_nh->rb_node, parent, pp); rb_insert_color(&new_nh->rb_node, root); /* The initial insertion is a full notification for hash-threshold as * well as resilient groups. */ rc = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new_nh, extack); if (rc) rb_erase(&new_nh->rb_node, &net->nexthop.rb_root); out: if (!rc) { nh_base_seq_inc(net); nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo); if (replace_notify && READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)) nexthop_replace_notify(net, new_nh, &cfg->nlinfo); } return rc; } /* rtnl */ /* remove all nexthops tied to a device being deleted */ static void nexthop_flush_dev(struct net_device *dev, unsigned long event) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); struct hlist_head *head = &net->nexthop.devhash[hash]; struct hlist_node *n; struct nh_info *nhi; hlist_for_each_entry_safe(nhi, n, head, dev_hash) { if (nhi->fib_nhc.nhc_dev != dev) continue; if (nhi->reject_nh && (event == NETDEV_DOWN || event == NETDEV_CHANGE)) continue; remove_nexthop(net, nhi->nh_parent, NULL); } } /* rtnl; called when net namespace is deleted */ static void flush_all_nexthops(struct net *net) { struct rb_root *root = &net->nexthop.rb_root; struct rb_node *node; struct nexthop *nh; while ((node = rb_first(root))) { nh = rb_entry(node, struct nexthop, rb_node); remove_nexthop(net, nh, NULL); cond_resched(); } } static struct nexthop *nexthop_create_group(struct net *net, struct nh_config *cfg) { struct nlattr *grps_attr = cfg->nh_grp; struct nexthop_grp *entry = nla_data(grps_attr); u16 num_nh = nla_len(grps_attr) / sizeof(*entry); struct nh_group *nhg; struct nexthop *nh; int err; int i; if (WARN_ON(!num_nh)) return ERR_PTR(-EINVAL); nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); nh->is_group = 1; nhg = nexthop_grp_alloc(num_nh); if (!nhg) { kfree(nh); return ERR_PTR(-ENOMEM); } /* spare group used for removals */ nhg->spare = nexthop_grp_alloc(num_nh); if (!nhg->spare) { kfree(nhg); kfree(nh); return ERR_PTR(-ENOMEM); } nhg->spare->spare = nhg; for (i = 0; i < nhg->num_nh; ++i) { struct nexthop *nhe; struct nh_info *nhi; nhe = nexthop_find_by_id(net, entry[i].id); if (!nexthop_get(nhe)) { err = -ENOENT; goto out_no_nh; } nhi = rtnl_dereference(nhe->nh_info); if (nhi->family == AF_INET) nhg->has_v4 = true; nhg->nh_entries[i].stats = netdev_alloc_pcpu_stats(struct nh_grp_entry_stats); if (!nhg->nh_entries[i].stats) { err = -ENOMEM; nexthop_put(nhe); goto out_no_nh; } nhg->nh_entries[i].nh = nhe; nhg->nh_entries[i].weight = nexthop_grp_weight(&entry[i]); list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); nhg->nh_entries[i].nh_parent = nh; } if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) { nhg->hash_threshold = 1; nhg->is_multipath = true; } else if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) { struct nh_res_table *res_table; res_table = nexthop_res_table_alloc(net, cfg->nh_id, cfg); if (!res_table) { err = -ENOMEM; goto out_no_nh; } rcu_assign_pointer(nhg->spare->res_table, res_table); rcu_assign_pointer(nhg->res_table, res_table); nhg->resilient = true; nhg->is_multipath = true; } WARN_ON_ONCE(nhg->hash_threshold + nhg->resilient != 1); if (nhg->hash_threshold) nh_hthr_group_rebalance(nhg); if (cfg->nh_fdb) nhg->fdb_nh = 1; if (cfg->nh_hw_stats) nhg->hw_stats = true; rcu_assign_pointer(nh->nh_grp, nhg); return nh; out_no_nh: for (i--; i >= 0; --i) { list_del(&nhg->nh_entries[i].nh_list); free_percpu(nhg->nh_entries[i].stats); nexthop_put(nhg->nh_entries[i].nh); } kfree(nhg->spare); kfree(nhg); kfree(nh); return ERR_PTR(err); } static int nh_create_ipv4(struct net *net, struct nexthop *nh, struct nh_info *nhi, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct fib_nh *fib_nh = &nhi->fib_nh; struct fib_config fib_cfg = { .fc_oif = cfg->nh_ifindex, .fc_gw4 = cfg->gw.ipv4, .fc_gw_family = cfg->gw.ipv4 ? AF_INET : 0, .fc_flags = cfg->nh_flags, .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, }; u32 tb_id = (cfg->dev ? l3mdev_fib_table(cfg->dev) : RT_TABLE_MAIN); int err; err = fib_nh_init(net, fib_nh, &fib_cfg, 1, extack); if (err) { fib_nh_release(net, fib_nh); goto out; } if (nhi->fdb_nh) goto out; /* sets nh_dev if successful */ err = fib_check_nh(net, fib_nh, tb_id, 0, extack); if (!err) { nh->nh_flags = fib_nh->fib_nh_flags; fib_info_update_nhc_saddr(net, &fib_nh->nh_common, !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1); } else { fib_nh_release(net, fib_nh); } out: return err; } static int nh_create_ipv6(struct net *net, struct nexthop *nh, struct nh_info *nhi, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct fib6_nh *fib6_nh = &nhi->fib6_nh; struct fib6_config fib6_cfg = { .fc_table = l3mdev_fib_table(cfg->dev), .fc_ifindex = cfg->nh_ifindex, .fc_gateway = cfg->gw.ipv6, .fc_flags = cfg->nh_flags, .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, .fc_is_fdb = cfg->nh_fdb, }; int err; if (!ipv6_addr_any(&cfg->gw.ipv6)) fib6_cfg.fc_flags |= RTF_GATEWAY; /* sets nh_dev if successful */ err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL, extack); if (err) { /* IPv6 is not enabled, don't call fib6_nh_release */ if (err == -EAFNOSUPPORT) goto out; ipv6_stub->fib6_nh_release(fib6_nh); } else { nh->nh_flags = fib6_nh->fib_nh_flags; } out: return err; } static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nh_info *nhi; struct nexthop *nh; int err = 0; nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); nhi = kzalloc(sizeof(*nhi), GFP_KERNEL); if (!nhi) { kfree(nh); return ERR_PTR(-ENOMEM); } nh->nh_flags = cfg->nh_flags; nh->net = net; nhi->nh_parent = nh; nhi->family = cfg->nh_family; nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK; if (cfg->nh_fdb) nhi->fdb_nh = 1; if (cfg->nh_blackhole) { nhi->reject_nh = 1; cfg->nh_ifindex = net->loopback_dev->ifindex; } switch (cfg->nh_family) { case AF_INET: err = nh_create_ipv4(net, nh, nhi, cfg, extack); break; case AF_INET6: err = nh_create_ipv6(net, nh, nhi, cfg, extack); break; } if (err) { kfree(nhi); kfree(nh); return ERR_PTR(err); } /* add the entry to the device based hash */ if (!nhi->fdb_nh) nexthop_devhash_add(net, nhi); rcu_assign_pointer(nh->nh_info, nhi); return nh; } /* called with rtnl lock held */ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nexthop *nh; int err; if (cfg->nlflags & NLM_F_REPLACE && !cfg->nh_id) { NL_SET_ERR_MSG(extack, "Replace requires nexthop id"); return ERR_PTR(-EINVAL); } if (!cfg->nh_id) { cfg->nh_id = nh_find_unused_id(net); if (!cfg->nh_id) { NL_SET_ERR_MSG(extack, "No unused id"); return ERR_PTR(-EINVAL); } } if (cfg->nh_grp) nh = nexthop_create_group(net, cfg); else nh = nexthop_create(net, cfg, extack); if (IS_ERR(nh)) return nh; refcount_set(&nh->refcnt, 1); nh->id = cfg->nh_id; nh->protocol = cfg->nh_protocol; nh->net = net; err = insert_nexthop(net, nh, cfg, extack); if (err) { __remove_nexthop(net, nh, NULL); nexthop_put(nh); nh = ERR_PTR(err); } return nh; } static int rtm_nh_get_timer(struct nlattr *attr, unsigned long fallback, unsigned long *timer_p, bool *has_p, struct netlink_ext_ack *extack) { unsigned long timer; u32 value; if (!attr) { *timer_p = fallback; *has_p = false; return 0; } value = nla_get_u32(attr); timer = clock_t_to_jiffies(value); if (timer == ~0UL) { NL_SET_ERR_MSG(extack, "Timer value too large"); return -EINVAL; } *timer_p = timer; *has_p = true; return 0; } static int rtm_to_nh_config_grp_res(struct nlattr *res, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_res_policy_new)] = {}; int err; if (res) { err = nla_parse_nested(tb, ARRAY_SIZE(rtm_nh_res_policy_new) - 1, res, rtm_nh_res_policy_new, extack); if (err < 0) return err; } if (tb[NHA_RES_GROUP_BUCKETS]) { cfg->nh_grp_res_num_buckets = nla_get_u16(tb[NHA_RES_GROUP_BUCKETS]); cfg->nh_grp_res_has_num_buckets = true; if (!cfg->nh_grp_res_num_buckets) { NL_SET_ERR_MSG(extack, "Number of buckets needs to be non-0"); return -EINVAL; } } err = rtm_nh_get_timer(tb[NHA_RES_GROUP_IDLE_TIMER], NH_RES_DEFAULT_IDLE_TIMER, &cfg->nh_grp_res_idle_timer, &cfg->nh_grp_res_has_idle_timer, extack); if (err) return err; return rtm_nh_get_timer(tb[NHA_RES_GROUP_UNBALANCED_TIMER], NH_RES_DEFAULT_UNBALANCED_TIMER, &cfg->nh_grp_res_unbalanced_timer, &cfg->nh_grp_res_has_unbalanced_timer, extack); } static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)]; int err; err = nlmsg_parse(nlh, sizeof(*nhm), tb, ARRAY_SIZE(rtm_nh_policy_new) - 1, rtm_nh_policy_new, extack); if (err < 0) return err; err = -EINVAL; if (nhm->resvd || nhm->nh_scope) { NL_SET_ERR_MSG(extack, "Invalid values in ancillary header"); goto out; } if (nhm->nh_flags & ~NEXTHOP_VALID_USER_FLAGS) { NL_SET_ERR_MSG(extack, "Invalid nexthop flags in ancillary header"); goto out; } switch (nhm->nh_family) { case AF_INET: case AF_INET6: break; case AF_UNSPEC: if (tb[NHA_GROUP]) break; fallthrough; default: NL_SET_ERR_MSG(extack, "Invalid address family"); goto out; } memset(cfg, 0, sizeof(*cfg)); cfg->nlflags = nlh->nlmsg_flags; cfg->nlinfo.portid = NETLINK_CB(skb).portid; cfg->nlinfo.nlh = nlh; cfg->nlinfo.nl_net = net; cfg->nh_family = nhm->nh_family; cfg->nh_protocol = nhm->nh_protocol; cfg->nh_flags = nhm->nh_flags; if (tb[NHA_ID]) cfg->nh_id = nla_get_u32(tb[NHA_ID]); if (tb[NHA_FDB]) { if (tb[NHA_OIF] || tb[NHA_BLACKHOLE] || tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "Fdb attribute can not be used with encap, oif or blackhole"); goto out; } if (nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Unsupported nexthop flags in ancillary header"); goto out; } cfg->nh_fdb = nla_get_flag(tb[NHA_FDB]); } if (tb[NHA_GROUP]) { if (nhm->nh_family != AF_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid family for group"); goto out; } cfg->nh_grp = tb[NHA_GROUP]; cfg->nh_grp_type = NEXTHOP_GRP_TYPE_MPATH; if (tb[NHA_GROUP_TYPE]) cfg->nh_grp_type = nla_get_u16(tb[NHA_GROUP_TYPE]); if (cfg->nh_grp_type > NEXTHOP_GRP_TYPE_MAX) { NL_SET_ERR_MSG(extack, "Invalid group type"); goto out; } err = nh_check_attr_group(net, tb, ARRAY_SIZE(tb), cfg->nh_grp_type, extack); if (err) goto out; if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) err = rtm_to_nh_config_grp_res(tb[NHA_RES_GROUP], cfg, extack); if (tb[NHA_HW_STATS_ENABLE]) cfg->nh_hw_stats = nla_get_u32(tb[NHA_HW_STATS_ENABLE]); /* no other attributes should be set */ goto out; } if (tb[NHA_BLACKHOLE]) { if (tb[NHA_GATEWAY] || tb[NHA_OIF] || tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE] || tb[NHA_FDB]) { NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway, oif, encap or fdb"); goto out; } cfg->nh_blackhole = 1; err = 0; goto out; } if (!cfg->nh_fdb && !tb[NHA_OIF]) { NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole and non-fdb nexthops"); goto out; } if (!cfg->nh_fdb && tb[NHA_OIF]) { cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); if (cfg->nh_ifindex) cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); if (!cfg->dev) { NL_SET_ERR_MSG(extack, "Invalid device index"); goto out; } else if (!(cfg->dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } else if (!netif_carrier_ok(cfg->dev)) { NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); err = -ENETDOWN; goto out; } } err = -EINVAL; if (tb[NHA_GATEWAY]) { struct nlattr *gwa = tb[NHA_GATEWAY]; switch (cfg->nh_family) { case AF_INET: if (nla_len(gwa) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid gateway"); goto out; } cfg->gw.ipv4 = nla_get_be32(gwa); break; case AF_INET6: if (nla_len(gwa) != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid gateway"); goto out; } cfg->gw.ipv6 = nla_get_in6_addr(gwa); break; default: NL_SET_ERR_MSG(extack, "Unknown address family for gateway"); goto out; } } else { /* device only nexthop (no gateway) */ if (cfg->nh_flags & RTNH_F_ONLINK) { NL_SET_ERR_MSG(extack, "ONLINK flag can not be set for nexthop without a gateway"); goto out; } } if (tb[NHA_ENCAP]) { cfg->nh_encap = tb[NHA_ENCAP]; if (!tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "LWT encapsulation type is missing"); goto out; } cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->nh_encap_type, extack); if (err < 0) goto out; } else if (tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "LWT encapsulation attribute is missing"); goto out; } if (tb[NHA_HW_STATS_ENABLE]) { NL_SET_ERR_MSG(extack, "Cannot enable nexthop hardware statistics for non-group nexthops"); goto out; } err = 0; out: return err; } /* rtnl */ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nh_config cfg; struct nexthop *nh; int err; err = rtm_to_nh_config(net, skb, nlh, &cfg, extack); if (!err) { nh = nexthop_add(net, &cfg, extack); if (IS_ERR(nh)) err = PTR_ERR(nh); } return err; } static int nh_valid_get_del_req(const struct nlmsghdr *nlh, struct nlattr **tb, u32 *id, u32 *op_flags, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header"); return -EINVAL; } if (!tb[NHA_ID]) { NL_SET_ERR_MSG(extack, "Nexthop id is missing"); return -EINVAL; } *id = nla_get_u32(tb[NHA_ID]); if (!(*id)) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } if (op_flags) { if (tb[NHA_OP_FLAGS]) *op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); else *op_flags = 0; } return 0; } /* rtnl */ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_del)]; struct net *net = sock_net(skb->sk); struct nl_info nlinfo = { .nlh = nlh, .nl_net = net, .portid = NETLINK_CB(skb).portid, }; struct nexthop *nh; int err; u32 id; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_del) - 1, rtm_nh_policy_del, extack); if (err < 0) return err; err = nh_valid_get_del_req(nlh, tb, &id, NULL, extack); if (err) return err; nh = nexthop_find_by_id(net, id); if (!nh) return -ENOENT; remove_nexthop(net, nh, &nlinfo); return 0; } /* rtnl */ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; struct net *net = sock_net(in_skb->sk); struct sk_buff *skb = NULL; struct nexthop *nh; u32 op_flags; int err; u32 id; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_get) - 1, rtm_nh_policy_get, extack); if (err < 0) return err; err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; err = -ENOBUFS; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) goto out; err = -ENOENT; nh = nexthop_find_by_id(net, id); if (!nh) goto errout_free; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, op_flags); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); out: return err; errout_free: kfree_skb(skb); goto out; } struct nh_dump_filter { u32 nh_id; int dev_idx; int master_idx; bool group_filter; bool fdb_filter; u32 res_bucket_nh_id; u32 op_flags; }; static bool nh_dump_filtered(struct nexthop *nh, struct nh_dump_filter *filter, u8 family) { const struct net_device *dev; const struct nh_info *nhi; if (filter->group_filter && !nh->is_group) return true; if (!filter->dev_idx && !filter->master_idx && !family) return false; if (nh->is_group) return true; nhi = rtnl_dereference(nh->nh_info); if (family && nhi->family != family) return true; dev = nhi->fib_nhc.nhc_dev; if (filter->dev_idx && (!dev || dev->ifindex != filter->dev_idx)) return true; if (filter->master_idx) { struct net_device *master; if (!dev) return true; master = netdev_master_upper_dev_get((struct net_device *)dev); if (!master || master->ifindex != filter->master_idx) return true; } return false; } static int __nh_valid_dump_req(const struct nlmsghdr *nlh, struct nlattr **tb, struct nh_dump_filter *filter, struct netlink_ext_ack *extack) { struct nhmsg *nhm; u32 idx; if (tb[NHA_OIF]) { idx = nla_get_u32(tb[NHA_OIF]); if (idx > INT_MAX) { NL_SET_ERR_MSG(extack, "Invalid device index"); return -EINVAL; } filter->dev_idx = idx; } if (tb[NHA_MASTER]) { idx = nla_get_u32(tb[NHA_MASTER]); if (idx > INT_MAX) { NL_SET_ERR_MSG(extack, "Invalid master device index"); return -EINVAL; } filter->master_idx = idx; } filter->group_filter = nla_get_flag(tb[NHA_GROUPS]); filter->fdb_filter = nla_get_flag(tb[NHA_FDB]); nhm = nlmsg_data(nlh); if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header for nexthop dump request"); return -EINVAL; } return 0; } static int nh_valid_dump_req(const struct nlmsghdr *nlh, struct nh_dump_filter *filter, struct netlink_callback *cb) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump)]; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_dump) - 1, rtm_nh_policy_dump, cb->extack); if (err < 0) return err; if (tb[NHA_OP_FLAGS]) filter->op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); else filter->op_flags = 0; return __nh_valid_dump_req(nlh, tb, filter, cb->extack); } struct rtm_dump_nh_ctx { u32 idx; }; static struct rtm_dump_nh_ctx * rtm_dump_nh_ctx(struct netlink_callback *cb) { struct rtm_dump_nh_ctx *ctx = (void *)cb->ctx; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); return ctx; } static int rtm_dump_walk_nexthops(struct sk_buff *skb, struct netlink_callback *cb, struct rb_root *root, struct rtm_dump_nh_ctx *ctx, int (*nh_cb)(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, void *data), void *data) { struct rb_node *node; int s_idx; int err; s_idx = ctx->idx; for (node = rb_first(root); node; node = rb_next(node)) { struct nexthop *nh; nh = rb_entry(node, struct nexthop, rb_node); if (nh->id < s_idx) continue; ctx->idx = nh->id; err = nh_cb(skb, cb, nh, data); if (err) return err; } return 0; } static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, void *data) { struct nhmsg *nhm = nlmsg_data(cb->nlh); struct nh_dump_filter *filter = data; if (nh_dump_filtered(nh, filter, nhm->nh_family)) return 0; return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, filter->op_flags); } /* rtnl */ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) { struct rtm_dump_nh_ctx *ctx = rtm_dump_nh_ctx(cb); struct net *net = sock_net(skb->sk); struct rb_root *root = &net->nexthop.rb_root; struct nh_dump_filter filter = {}; int err; err = nh_valid_dump_req(cb->nlh, &filter, cb); if (err < 0) return err; err = rtm_dump_walk_nexthops(skb, cb, root, ctx, &rtm_dump_nexthop_cb, &filter); cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; } static struct nexthop * nexthop_find_group_resilient(struct net *net, u32 id, struct netlink_ext_ack *extack) { struct nh_group *nhg; struct nexthop *nh; nh = nexthop_find_by_id(net, id); if (!nh) return ERR_PTR(-ENOENT); if (!nh->is_group) { NL_SET_ERR_MSG(extack, "Not a nexthop group"); return ERR_PTR(-EINVAL); } nhg = rtnl_dereference(nh->nh_grp); if (!nhg->resilient) { NL_SET_ERR_MSG(extack, "Nexthop group not of type resilient"); return ERR_PTR(-EINVAL); } return nh; } static int nh_valid_dump_nhid(struct nlattr *attr, u32 *nh_id_p, struct netlink_ext_ack *extack) { u32 idx; if (attr) { idx = nla_get_u32(attr); if (!idx) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } *nh_id_p = idx; } else { *nh_id_p = 0; } return 0; } static int nh_valid_dump_bucket_req(const struct nlmsghdr *nlh, struct nh_dump_filter *filter, struct netlink_callback *cb) { struct nlattr *res_tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_dump)]; struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump_bucket)]; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_dump_bucket) - 1, rtm_nh_policy_dump_bucket, NULL); if (err < 0) return err; err = nh_valid_dump_nhid(tb[NHA_ID], &filter->nh_id, cb->extack); if (err) return err; if (tb[NHA_RES_BUCKET]) { size_t max = ARRAY_SIZE(rtm_nh_res_bucket_policy_dump) - 1; err = nla_parse_nested(res_tb, max, tb[NHA_RES_BUCKET], rtm_nh_res_bucket_policy_dump, cb->extack); if (err < 0) return err; err = nh_valid_dump_nhid(res_tb[NHA_RES_BUCKET_NH_ID], &filter->res_bucket_nh_id, cb->extack); if (err) return err; } return __nh_valid_dump_req(nlh, tb, filter, cb->extack); } struct rtm_dump_res_bucket_ctx { struct rtm_dump_nh_ctx nh; u16 bucket_index; }; static struct rtm_dump_res_bucket_ctx * rtm_dump_res_bucket_ctx(struct netlink_callback *cb) { struct rtm_dump_res_bucket_ctx *ctx = (void *)cb->ctx; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); return ctx; } struct rtm_dump_nexthop_bucket_data { struct rtm_dump_res_bucket_ctx *ctx; struct nh_dump_filter filter; }; static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, struct rtm_dump_nexthop_bucket_data *dd) { u32 portid = NETLINK_CB(cb->skb).portid; struct nhmsg *nhm = nlmsg_data(cb->nlh); struct nh_res_table *res_table; struct nh_group *nhg; u16 bucket_index; int err; nhg = rtnl_dereference(nh->nh_grp); res_table = rtnl_dereference(nhg->res_table); for (bucket_index = dd->ctx->bucket_index; bucket_index < res_table->num_nh_buckets; bucket_index++) { struct nh_res_bucket *bucket; struct nh_grp_entry *nhge; bucket = &res_table->nh_buckets[bucket_index]; nhge = rtnl_dereference(bucket->nh_entry); if (nh_dump_filtered(nhge->nh, &dd->filter, nhm->nh_family)) continue; if (dd->filter.res_bucket_nh_id && dd->filter.res_bucket_nh_id != nhge->nh->id) continue; dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); if (err) return err; } dd->ctx->bucket_index = 0; return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, void *data) { struct rtm_dump_nexthop_bucket_data *dd = data; struct nh_group *nhg; if (!nh->is_group) return 0; nhg = rtnl_dereference(nh->nh_grp); if (!nhg->resilient) return 0; return rtm_dump_nexthop_bucket_nh(skb, cb, nh, dd); } /* rtnl */ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, struct netlink_callback *cb) { struct rtm_dump_res_bucket_ctx *ctx = rtm_dump_res_bucket_ctx(cb); struct rtm_dump_nexthop_bucket_data dd = { .ctx = ctx }; struct net *net = sock_net(skb->sk); struct nexthop *nh; int err; err = nh_valid_dump_bucket_req(cb->nlh, &dd.filter, cb); if (err) return err; if (dd.filter.nh_id) { nh = nexthop_find_group_resilient(net, dd.filter.nh_id, cb->extack); if (IS_ERR(nh)) return PTR_ERR(nh); err = rtm_dump_nexthop_bucket_nh(skb, cb, nh, &dd); } else { struct rb_root *root = &net->nexthop.rb_root; err = rtm_dump_walk_nexthops(skb, cb, root, &ctx->nh, &rtm_dump_nexthop_bucket_cb, &dd); } cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; } static int nh_valid_get_bucket_req_res_bucket(struct nlattr *res, u16 *bucket_index, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_get)]; int err; err = nla_parse_nested(tb, ARRAY_SIZE(rtm_nh_res_bucket_policy_get) - 1, res, rtm_nh_res_bucket_policy_get, extack); if (err < 0) return err; if (!tb[NHA_RES_BUCKET_INDEX]) { NL_SET_ERR_MSG(extack, "Bucket index is missing"); return -EINVAL; } *bucket_index = nla_get_u16(tb[NHA_RES_BUCKET_INDEX]); return 0; } static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, u32 *id, u16 *bucket_index, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get_bucket)]; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_get_bucket) - 1, rtm_nh_policy_get_bucket, extack); if (err < 0) return err; err = nh_valid_get_del_req(nlh, tb, id, NULL, extack); if (err) return err; if (!tb[NHA_RES_BUCKET]) { NL_SET_ERR_MSG(extack, "Bucket information is missing"); return -EINVAL; } err = nh_valid_get_bucket_req_res_bucket(tb[NHA_RES_BUCKET], bucket_index, extack); if (err) return err; return 0; } /* rtnl */ static int rtm_get_nexthop_bucket(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nh_res_table *res_table; struct sk_buff *skb = NULL; struct nh_group *nhg; struct nexthop *nh; u16 bucket_index; int err; u32 id; err = nh_valid_get_bucket_req(nlh, &id, &bucket_index, extack); if (err) return err; nh = nexthop_find_group_resilient(net, id, extack); if (IS_ERR(nh)) return PTR_ERR(nh); nhg = rtnl_dereference(nh->nh_grp); res_table = rtnl_dereference(nhg->res_table); if (bucket_index >= res_table->num_nh_buckets) { NL_SET_ERR_MSG(extack, "Bucket index out of bounds"); return -ENOENT; } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; err = nh_fill_res_bucket(skb, nh, &res_table->nh_buckets[bucket_index], bucket_index, RTM_NEWNEXTHOPBUCKET, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, extack); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; } return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_free: kfree_skb(skb); return err; } static void nexthop_sync_mtu(struct net_device *dev, u32 orig_mtu) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); struct hlist_head *head = &net->nexthop.devhash[hash]; struct hlist_node *n; struct nh_info *nhi; hlist_for_each_entry_safe(nhi, n, head, dev_hash) { if (nhi->fib_nhc.nhc_dev == dev) { if (nhi->family == AF_INET) fib_nhc_update_mtu(&nhi->fib_nhc, dev->mtu, orig_mtu); } } } /* rtnl */ static int nh_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_info_ext *info_ext; switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: nexthop_flush_dev(dev, event); break; case NETDEV_CHANGE: if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) nexthop_flush_dev(dev, event); break; case NETDEV_CHANGEMTU: info_ext = ptr; nexthop_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(dev_net(dev)); break; } return NOTIFY_DONE; } static struct notifier_block nh_netdev_notifier = { .notifier_call = nh_netdev_event, }; static int nexthops_dump(struct net *net, struct notifier_block *nb, enum nexthop_event_type event_type, struct netlink_ext_ack *extack) { struct rb_root *root = &net->nexthop.rb_root; struct rb_node *node; int err = 0; for (node = rb_first(root); node; node = rb_next(node)) { struct nexthop *nh; nh = rb_entry(node, struct nexthop, rb_node); err = call_nexthop_notifier(nb, net, event_type, nh, extack); if (err) break; } return err; } int register_nexthop_notifier(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { int err; rtnl_lock(); err = nexthops_dump(net, nb, NEXTHOP_EVENT_REPLACE, extack); if (err) goto unlock; err = blocking_notifier_chain_register(&net->nexthop.notifier_chain, nb); unlock: rtnl_unlock(); return err; } EXPORT_SYMBOL(register_nexthop_notifier); int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { int err; err = blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, nb); if (!err) nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); return err; } EXPORT_SYMBOL(__unregister_nexthop_notifier); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { int err; rtnl_lock(); err = __unregister_nexthop_notifier(net, nb); rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_nexthop_notifier); void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap) { struct nexthop *nexthop; rcu_read_lock(); nexthop = nexthop_find_by_id(net, id); if (!nexthop) goto out; nexthop->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); if (offload) nexthop->nh_flags |= RTNH_F_OFFLOAD; if (trap) nexthop->nh_flags |= RTNH_F_TRAP; out: rcu_read_unlock(); } EXPORT_SYMBOL(nexthop_set_hw_flags); void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap) { struct nh_res_table *res_table; struct nh_res_bucket *bucket; struct nexthop *nexthop; struct nh_group *nhg; rcu_read_lock(); nexthop = nexthop_find_by_id(net, id); if (!nexthop || !nexthop->is_group) goto out; nhg = rcu_dereference(nexthop->nh_grp); if (!nhg->resilient) goto out; if (bucket_index >= nhg->res_table->num_nh_buckets) goto out; res_table = rcu_dereference(nhg->res_table); bucket = &res_table->nh_buckets[bucket_index]; bucket->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); if (offload) bucket->nh_flags |= RTNH_F_OFFLOAD; if (trap) bucket->nh_flags |= RTNH_F_TRAP; out: rcu_read_unlock(); } EXPORT_SYMBOL(nexthop_bucket_set_hw_flags); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity) { struct nh_res_table *res_table; struct nexthop *nexthop; struct nh_group *nhg; u16 i; rcu_read_lock(); nexthop = nexthop_find_by_id(net, id); if (!nexthop || !nexthop->is_group) goto out; nhg = rcu_dereference(nexthop->nh_grp); if (!nhg->resilient) goto out; /* Instead of silently ignoring some buckets, demand that the sizes * be the same. */ res_table = rcu_dereference(nhg->res_table); if (num_buckets != res_table->num_nh_buckets) goto out; for (i = 0; i < num_buckets; i++) { if (test_bit(i, activity)) nh_res_bucket_set_busy(&res_table->nh_buckets[i]); } out: rcu_read_unlock(); } EXPORT_SYMBOL(nexthop_res_grp_activity_update); static void __net_exit nexthop_net_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) flush_all_nexthops(net); } static void __net_exit nexthop_net_exit(struct net *net) { kfree(net->nexthop.devhash); net->nexthop.devhash = NULL; } static int __net_init nexthop_net_init(struct net *net) { size_t sz = sizeof(struct hlist_head) * NH_DEV_HASHSIZE; net->nexthop.rb_root = RB_ROOT; net->nexthop.devhash = kzalloc(sz, GFP_KERNEL); if (!net->nexthop.devhash) return -ENOMEM; BLOCKING_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain); return 0; } static struct pernet_operations nexthop_net_ops = { .init = nexthop_net_init, .exit = nexthop_net_exit, .exit_batch_rtnl = nexthop_net_exit_batch_rtnl, }; static int __init nexthop_init(void) { register_pernet_subsys(&nexthop_net_ops); register_netdevice_notifier(&nh_netdev_notifier); rtnl_register(PF_UNSPEC, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELNEXTHOP, rtm_del_nexthop, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETNEXTHOP, rtm_get_nexthop, rtm_dump_nexthop, 0); rtnl_register(PF_INET, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); rtnl_register(PF_INET, RTM_GETNEXTHOP, NULL, rtm_dump_nexthop, 0); rtnl_register(PF_INET6, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); rtnl_register(PF_INET6, RTM_GETNEXTHOP, NULL, rtm_dump_nexthop, 0); rtnl_register(PF_UNSPEC, RTM_GETNEXTHOPBUCKET, rtm_get_nexthop_bucket, rtm_dump_nexthop_bucket, 0); return 0; } subsys_initcall(nexthop_init); |
| 358 360 322 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_MAPLE_TREE_H #define _LINUX_MAPLE_TREE_H /* * Maple Tree - An RCU-safe adaptive tree for storing ranges * Copyright (c) 2018-2022 Oracle * Authors: Liam R. Howlett <Liam.Howlett@Oracle.com> * Matthew Wilcox <willy@infradead.org> */ #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> /* #define CONFIG_MAPLE_RCU_DISABLED */ /* * Allocated nodes are mutable until they have been inserted into the tree, * at which time they cannot change their type until they have been removed * from the tree and an RCU grace period has passed. * * Removed nodes have their ->parent set to point to themselves. RCU readers * check ->parent before relying on the value that they loaded from the * slots array. This lets us reuse the slots array for the RCU head. * * Nodes in the tree point to their parent unless bit 0 is set. */ #if defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) /* 64bit sizes */ #define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1) #else /* 32bit sizes */ #define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2) #endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */ #define MAPLE_NODE_MASK 255UL /* * The node->parent of the root node has bit 0 set and the rest of the pointer * is a pointer to the tree itself. No more bits are available in this pointer * (on m68k, the data structure may only be 2-byte aligned). * * Internal non-root nodes can only have maple_range_* nodes as parents. The * parent pointer is 256B aligned like all other tree nodes. When storing a 32 * or 64 bit values, the offset can fit into 4 bits. The 16 bit values need an * extra bit to store the offset. This extra bit comes from a reuse of the last * bit in the node type. This is possible by using bit 1 to indicate if bit 2 * is part of the type or the slot. * * Once the type is decided, the decision of an allocation range type or a * range type is done by examining the immutable tree flag for the * MT_FLAGS_ALLOC_RANGE flag. * * Node types: * 0x??1 = Root * 0x?00 = 16 bit nodes * 0x010 = 32 bit nodes * 0x110 = 64 bit nodes * * Slot size and location in the parent pointer: * type : slot location * 0x??1 : Root * 0x?00 : 16 bit values, type in 0-1, slot in 2-6 * 0x010 : 32 bit values, type in 0-2, slot in 3-6 * 0x110 : 64 bit values, type in 0-2, slot in 3-6 */ /* * This metadata is used to optimize the gap updating code and in reverse * searching for gaps or any other code that needs to find the end of the data. */ struct maple_metadata { unsigned char end; unsigned char gap; }; /* * Leaf nodes do not store pointers to nodes, they store user data. Users may * store almost any bit pattern. As noted above, the optimisation of storing an * entry at 0 in the root pointer cannot be done for data which have the bottom * two bits set to '10'. We also reserve values with the bottom two bits set to * '10' which are below 4096 (ie 2, 6, 10 .. 4094) for internal use. Some APIs * return errnos as a negative errno shifted right by two bits and the bottom * two bits set to '10', and while choosing to store these values in the array * is not an error, it may lead to confusion if you're testing for an error with * mas_is_err(). * * Non-leaf nodes store the type of the node pointed to (enum maple_type in bits * 3-6), bit 2 is reserved. That leaves bits 0-1 unused for now. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges, Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. */ struct maple_range_64 { struct maple_pnode *parent; unsigned long pivot[MAPLE_RANGE64_SLOTS - 1]; union { void __rcu *slot[MAPLE_RANGE64_SLOTS]; struct { void __rcu *pad[MAPLE_RANGE64_SLOTS - 1]; struct maple_metadata meta; }; }; }; /* * At tree creation time, the user can specify that they're willing to trade off * storing fewer entries in a tree in return for storing more information in * each node. * * The maple tree supports recording the largest range of NULL entries available * in this node, also called gaps. This optimises the tree for allocating a * range. */ struct maple_arange_64 { struct maple_pnode *parent; unsigned long pivot[MAPLE_ARANGE64_SLOTS - 1]; void __rcu *slot[MAPLE_ARANGE64_SLOTS]; unsigned long gap[MAPLE_ARANGE64_SLOTS]; struct maple_metadata meta; }; struct maple_alloc { unsigned long total; unsigned char node_count; unsigned int request_count; struct maple_alloc *slot[MAPLE_ALLOC_SLOTS]; }; struct maple_topiary { struct maple_pnode *parent; struct maple_enode *next; /* Overlaps the pivot */ }; enum maple_type { maple_dense, maple_leaf_64, maple_range_64, maple_arange_64, }; enum store_type { wr_invalid, wr_new_root, wr_store_root, wr_exact_fit, wr_spanning_store, wr_split_store, wr_rebalance, wr_append, wr_node_store, wr_slot_store, }; /** * DOC: Maple tree flags * * * MT_FLAGS_ALLOC_RANGE - Track gaps in this tree * * MT_FLAGS_USE_RCU - Operate in RCU mode * * MT_FLAGS_HEIGHT_OFFSET - The position of the tree height in the flags * * MT_FLAGS_HEIGHT_MASK - The mask for the maple tree height value * * MT_FLAGS_LOCK_MASK - How the mt_lock is used * * MT_FLAGS_LOCK_IRQ - Acquired irq-safe * * MT_FLAGS_LOCK_BH - Acquired bh-safe * * MT_FLAGS_LOCK_EXTERN - mt_lock is not used * * MAPLE_HEIGHT_MAX The largest height that can be stored */ #define MT_FLAGS_ALLOC_RANGE 0x01 #define MT_FLAGS_USE_RCU 0x02 #define MT_FLAGS_HEIGHT_OFFSET 0x02 #define MT_FLAGS_HEIGHT_MASK 0x7C #define MT_FLAGS_LOCK_MASK 0x300 #define MT_FLAGS_LOCK_IRQ 0x100 #define MT_FLAGS_LOCK_BH 0x200 #define MT_FLAGS_LOCK_EXTERN 0x300 #define MT_FLAGS_ALLOC_WRAPPED 0x0800 #define MAPLE_HEIGHT_MAX 31 #define MAPLE_NODE_TYPE_MASK 0x0F #define MAPLE_NODE_TYPE_SHIFT 0x03 #define MAPLE_RESERVED_RANGE 4096 #ifdef CONFIG_LOCKDEP typedef struct lockdep_map *lockdep_map_p; #define mt_lock_is_held(mt) \ (!(mt)->ma_external_lock || lock_is_held((mt)->ma_external_lock)) #define mt_write_lock_is_held(mt) \ (!(mt)->ma_external_lock || \ lock_is_held_type((mt)->ma_external_lock, 0)) #define mt_set_external_lock(mt, lock) \ (mt)->ma_external_lock = &(lock)->dep_map #define mt_on_stack(mt) (mt).ma_external_lock = NULL #else typedef struct { /* nothing */ } lockdep_map_p; #define mt_lock_is_held(mt) 1 #define mt_write_lock_is_held(mt) 1 #define mt_set_external_lock(mt, lock) do { } while (0) #define mt_on_stack(mt) do { } while (0) #endif /* * If the tree contains a single entry at index 0, it is usually stored in * tree->ma_root. To optimise for the page cache, an entry which ends in '00', * '01' or '11' is stored in the root, but an entry which ends in '10' will be * stored in a node. Bits 3-6 are used to store enum maple_type. * * The flags are used both to store some immutable information about this tree * (set at tree creation time) and dynamic information set under the spinlock. * * Another use of flags are to indicate global states of the tree. This is the * case with the MAPLE_USE_RCU flag, which indicates the tree is currently in * RCU mode. This mode was added to allow the tree to reuse nodes instead of * re-allocating and RCU freeing nodes when there is a single user. */ struct maple_tree { union { spinlock_t ma_lock; lockdep_map_p ma_external_lock; }; unsigned int ma_flags; void __rcu *ma_root; }; /** * MTREE_INIT() - Initialize a maple tree * @name: The maple tree name * @__flags: The maple tree flags * */ #define MTREE_INIT(name, __flags) { \ .ma_lock = __SPIN_LOCK_UNLOCKED((name).ma_lock), \ .ma_flags = __flags, \ .ma_root = NULL, \ } /** * MTREE_INIT_EXT() - Initialize a maple tree with an external lock. * @name: The tree name * @__flags: The maple tree flags * @__lock: The external lock */ #ifdef CONFIG_LOCKDEP #define MTREE_INIT_EXT(name, __flags, __lock) { \ .ma_external_lock = &(__lock).dep_map, \ .ma_flags = (__flags), \ .ma_root = NULL, \ } #else #define MTREE_INIT_EXT(name, __flags, __lock) MTREE_INIT(name, __flags) #endif #define DEFINE_MTREE(name) \ struct maple_tree name = MTREE_INIT(name, 0) #define mtree_lock(mt) spin_lock((&(mt)->ma_lock)) #define mtree_lock_nested(mas, subclass) \ spin_lock_nested((&(mt)->ma_lock), subclass) #define mtree_unlock(mt) spin_unlock((&(mt)->ma_lock)) /* * The Maple Tree squeezes various bits in at various points which aren't * necessarily obvious. Usually, this is done by observing that pointers are * N-byte aligned and thus the bottom log_2(N) bits are available for use. We * don't use the high bits of pointers to store additional information because * we don't know what bits are unused on any given architecture. * * Nodes are 256 bytes in size and are also aligned to 256 bytes, giving us 8 * low bits for our own purposes. Nodes are currently of 4 types: * 1. Single pointer (Range is 0-0) * 2. Non-leaf Allocation Range nodes * 3. Non-leaf Range nodes * 4. Leaf Range nodes All nodes consist of a number of node slots, * pivots, and a parent pointer. */ struct maple_node { union { struct { struct maple_pnode *parent; void __rcu *slot[MAPLE_NODE_SLOTS]; }; struct { void *pad; struct rcu_head rcu; struct maple_enode *piv_parent; unsigned char parent_slot; enum maple_type type; unsigned char slot_len; unsigned int ma_flags; }; struct maple_range_64 mr64; struct maple_arange_64 ma64; struct maple_alloc alloc; }; }; /* * More complicated stores can cause two nodes to become one or three and * potentially alter the height of the tree. Either half of the tree may need * to be rebalanced against the other. The ma_topiary struct is used to track * which nodes have been 'cut' from the tree so that the change can be done * safely at a later date. This is done to support RCU. */ struct ma_topiary { struct maple_enode *head; struct maple_enode *tail; struct maple_tree *mtree; }; void *mtree_load(struct maple_tree *mt, unsigned long index); int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp); int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); int mtree_store_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp); int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp); void *mtree_erase(struct maple_tree *mt, unsigned long index); int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); void mtree_destroy(struct maple_tree *mt); void __mt_destroy(struct maple_tree *mt); /** * mtree_empty() - Determine if a tree has any present entries. * @mt: Maple Tree. * * Context: Any context. * Return: %true if the tree contains only NULL pointers. */ static inline bool mtree_empty(const struct maple_tree *mt) { return mt->ma_root == NULL; } /* Advanced API */ /* * Maple State Status * ma_active means the maple state is pointing to a node and offset and can * continue operating on the tree. * ma_start means we have not searched the tree. * ma_root means we have searched the tree and the entry we found lives in * the root of the tree (ie it has index 0, length 1 and is the only entry in * the tree). * ma_none means we have searched the tree and there is no node in the * tree for this entry. For example, we searched for index 1 in an empty * tree. Or we have a tree which points to a full leaf node and we * searched for an entry which is larger than can be contained in that * leaf node. * ma_pause means the data within the maple state may be stale, restart the * operation * ma_overflow means the search has reached the upper limit of the search * ma_underflow means the search has reached the lower limit of the search * ma_error means there was an error, check the node for the error number. */ enum maple_status { ma_active, ma_start, ma_root, ma_none, ma_pause, ma_overflow, ma_underflow, ma_error, }; /* * The maple state is defined in the struct ma_state and is used to keep track * of information during operations, and even between operations when using the * advanced API. * * If state->node has bit 0 set then it references a tree location which is not * a node (eg the root). If bit 1 is set, the rest of the bits are a negative * errno. Bit 2 (the 'unallocated slots' bit) is clear. Bits 3-6 indicate the * node type. * * state->alloc either has a request number of nodes or an allocated node. If * stat->alloc has a requested number of nodes, the first bit will be set (0x1) * and the remaining bits are the value. If state->alloc is a node, then the * node will be of type maple_alloc. maple_alloc has MAPLE_NODE_SLOTS - 1 for * storing more allocated nodes, a total number of nodes allocated, and the * node_count in this node. node_count is the number of allocated nodes in this * node. The scaling beyond MAPLE_NODE_SLOTS - 1 is handled by storing further * nodes into state->alloc->slot[0]'s node. Nodes are taken from state->alloc * by removing a node from the state->alloc node until state->alloc->node_count * is 1, when state->alloc is returned and the state->alloc->slot[0] is promoted * to state->alloc. Nodes are pushed onto state->alloc by putting the current * state->alloc into the pushed node's slot[0]. * * The state also contains the implied min/max of the state->node, the depth of * this search, and the offset. The implied min/max are either from the parent * node or are 0-oo for the root node. The depth is incremented or decremented * every time a node is walked down or up. The offset is the slot/pivot of * interest in the node - either for reading or writing. * * When returning a value the maple state index and last respectively contain * the start and end of the range for the entry. Ranges are inclusive in the * Maple Tree. * * The status of the state is used to determine how the next action should treat * the state. For instance, if the status is ma_start then the next action * should start at the root of the tree and walk down. If the status is * ma_pause then the node may be stale data and should be discarded. If the * status is ma_overflow, then the last action hit the upper limit. * */ struct ma_state { struct maple_tree *tree; /* The tree we're operating in */ unsigned long index; /* The index we're operating on - range start */ unsigned long last; /* The last index we're operating on - range end */ struct maple_enode *node; /* The node containing this entry */ unsigned long min; /* The minimum index of this node - implied pivot min */ unsigned long max; /* The maximum index of this node - implied pivot max */ struct maple_alloc *alloc; /* Allocated nodes for this operation */ enum maple_status status; /* The status of the state (active, start, none, etc) */ unsigned char depth; /* depth of tree descent during write */ unsigned char offset; unsigned char mas_flags; unsigned char end; /* The end of the node */ enum store_type store_type; /* The type of store needed for this operation */ }; struct ma_wr_state { struct ma_state *mas; struct maple_node *node; /* Decoded mas->node */ unsigned long r_min; /* range min */ unsigned long r_max; /* range max */ enum maple_type type; /* mas->node type */ unsigned char offset_end; /* The offset where the write ends */ unsigned long *pivots; /* mas->node->pivots pointer */ unsigned long end_piv; /* The pivot at the offset end */ void __rcu **slots; /* mas->node->slots pointer */ void *entry; /* The entry to write */ void *content; /* The existing entry that is being overwritten */ }; #define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock)) #define mas_lock_nested(mas, subclass) \ spin_lock_nested(&((mas)->tree->ma_lock), subclass) #define mas_unlock(mas) spin_unlock(&((mas)->tree->ma_lock)) /* * Special values for ma_state.node. * MA_ERROR represents an errno. After dropping the lock and attempting * to resolve the error, the walk would have to be restarted from the * top of the tree as the tree may have been modified. */ #define MA_ERROR(err) \ ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) #define MA_STATE(name, mt, first, end) \ struct ma_state name = { \ .tree = mt, \ .index = first, \ .last = end, \ .node = NULL, \ .status = ma_start, \ .min = 0, \ .max = ULONG_MAX, \ .alloc = NULL, \ .mas_flags = 0, \ .store_type = wr_invalid, \ } #define MA_WR_STATE(name, ma_state, wr_entry) \ struct ma_wr_state name = { \ .mas = ma_state, \ .content = NULL, \ .entry = wr_entry, \ } #define MA_TOPIARY(name, tree) \ struct ma_topiary name = { \ .head = NULL, \ .tail = NULL, \ .mtree = tree, \ } void *mas_walk(struct ma_state *mas); void *mas_store(struct ma_state *mas, void *entry); void *mas_erase(struct ma_state *mas); int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp); void mas_store_prealloc(struct ma_state *mas, void *entry); void *mas_find(struct ma_state *mas, unsigned long max); void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); void *mas_find_range_rev(struct ma_state *mas, unsigned long max); int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp); bool mas_nomem(struct ma_state *mas, gfp_t gfp); void mas_pause(struct ma_state *mas); void maple_tree_init(void); void mas_destroy(struct ma_state *mas); int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries); void *mas_prev(struct ma_state *mas, unsigned long min); void *mas_prev_range(struct ma_state *mas, unsigned long max); void *mas_next(struct ma_state *mas, unsigned long max); void *mas_next_range(struct ma_state *mas, unsigned long max); int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); /* * This finds an empty area from the highest address to the lowest. * AKA "Topdown" version, */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); static inline void mas_init(struct ma_state *mas, struct maple_tree *tree, unsigned long addr) { memset(mas, 0, sizeof(struct ma_state)); mas->tree = tree; mas->index = mas->last = addr; mas->max = ULONG_MAX; mas->status = ma_start; mas->node = NULL; } static inline bool mas_is_active(struct ma_state *mas) { return mas->status == ma_active; } static inline bool mas_is_err(struct ma_state *mas) { return mas->status == ma_error; } /** * mas_reset() - Reset a Maple Tree operation state. * @mas: Maple Tree operation state. * * Resets the error or walk state of the @mas so future walks of the * array will start from the root. Use this if you have dropped the * lock and want to reuse the ma_state. * * Context: Any context. */ static __always_inline void mas_reset(struct ma_state *mas) { mas->status = ma_start; mas->node = NULL; } /** * mas_for_each() - Iterate over a range of the maple tree. * @__mas: Maple Tree operation state (maple_state) * @__entry: Entry retrieved from the tree * @__max: maximum index to retrieve from the tree * * When returned, mas->index and mas->last will hold the entire range for the * entry. * * Note: may return the zero entry. */ #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) #ifdef CONFIG_DEBUG_MAPLE_TREE enum mt_dump_format { mt_dump_dec, mt_dump_hex, }; extern atomic_t maple_tree_tests_run; extern atomic_t maple_tree_tests_passed; void mt_dump(const struct maple_tree *mt, enum mt_dump_format format); void mas_dump(const struct ma_state *mas); void mas_wr_dump(const struct ma_wr_state *wr_mas); void mt_validate(struct maple_tree *mt); void mt_cache_shrink(void); #define MT_BUG_ON(__tree, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mt_dump(__tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MAS_BUG_ON(__mas, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_dump(__mas); \ mt_dump((__mas)->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MAS_WR_BUG_ON(__wrmas, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_wr_dump(__wrmas); \ mas_dump((__wrmas)->mas); \ mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MT_WARN_ON(__tree, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mt_dump(__tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #define MAS_WARN_ON(__mas, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_dump(__mas); \ mt_dump((__mas)->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #define MAS_WR_WARN_ON(__wrmas, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_wr_dump(__wrmas); \ mas_dump((__wrmas)->mas); \ mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #else #define MT_BUG_ON(__tree, __x) BUG_ON(__x) #define MAS_BUG_ON(__mas, __x) BUG_ON(__x) #define MAS_WR_BUG_ON(__mas, __x) BUG_ON(__x) #define MT_WARN_ON(__tree, __x) WARN_ON(__x) #define MAS_WARN_ON(__mas, __x) WARN_ON(__x) #define MAS_WR_WARN_ON(__mas, __x) WARN_ON(__x) #endif /* CONFIG_DEBUG_MAPLE_TREE */ /** * __mas_set_range() - Set up Maple Tree operation state to a sub-range of the * current location. * @mas: Maple Tree operation state. * @start: New start of range in the Maple Tree. * @last: New end of range in the Maple Tree. * * set the internal maple state values to a sub-range. * Please use mas_set_range() if you do not know where you are in the tree. */ static inline void __mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { /* Ensure the range starts within the current slot */ MAS_WARN_ON(mas, mas_is_active(mas) && (mas->index > start || mas->last < start)); mas->index = start; mas->last = last; } /** * mas_set_range() - Set up Maple Tree operation state for a different index. * @mas: Maple Tree operation state. * @start: New start of range in the Maple Tree. * @last: New end of range in the Maple Tree. * * Move the operation state to refer to a different range. This will * have the effect of starting a walk from the top; see mas_next() * to move to an adjacent index. */ static inline void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { mas_reset(mas); __mas_set_range(mas, start, last); } /** * mas_set() - Set up Maple Tree operation state for a different index. * @mas: Maple Tree operation state. * @index: New index into the Maple Tree. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see mas_next() * to move to an adjacent index. */ static inline void mas_set(struct ma_state *mas, unsigned long index) { mas_set_range(mas, index, index); } static inline bool mt_external_lock(const struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_LOCK_MASK) == MT_FLAGS_LOCK_EXTERN; } /** * mt_init_flags() - Initialise an empty maple tree with flags. * @mt: Maple Tree * @flags: maple tree flags. * * If you need to initialise a Maple Tree with special flags (eg, an * allocation tree), use this function. * * Context: Any context. */ static inline void mt_init_flags(struct maple_tree *mt, unsigned int flags) { mt->ma_flags = flags; if (!mt_external_lock(mt)) spin_lock_init(&mt->ma_lock); rcu_assign_pointer(mt->ma_root, NULL); } /** * mt_init() - Initialise an empty maple tree. * @mt: Maple Tree * * An empty Maple Tree. * * Context: Any context. */ static inline void mt_init(struct maple_tree *mt) { mt_init_flags(mt, 0); } static inline bool mt_in_rcu(struct maple_tree *mt) { #ifdef CONFIG_MAPLE_RCU_DISABLED return false; #endif return mt->ma_flags & MT_FLAGS_USE_RCU; } /** * mt_clear_in_rcu() - Switch the tree to non-RCU mode. * @mt: The Maple Tree */ static inline void mt_clear_in_rcu(struct maple_tree *mt) { if (!mt_in_rcu(mt)) return; if (mt_external_lock(mt)) { WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags &= ~MT_FLAGS_USE_RCU; } else { mtree_lock(mt); mt->ma_flags &= ~MT_FLAGS_USE_RCU; mtree_unlock(mt); } } /** * mt_set_in_rcu() - Switch the tree to RCU safe mode. * @mt: The Maple Tree */ static inline void mt_set_in_rcu(struct maple_tree *mt) { if (mt_in_rcu(mt)) return; if (mt_external_lock(mt)) { WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags |= MT_FLAGS_USE_RCU; } else { mtree_lock(mt); mt->ma_flags |= MT_FLAGS_USE_RCU; mtree_unlock(mt); } } static inline unsigned int mt_height(const struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET; } void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max); void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max); void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min); void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); /** * mt_for_each - Iterate over each entry starting at index until max. * @__tree: The Maple Tree * @__entry: The current entry * @__index: The index to start the search from. Subsequently used as iterator. * @__max: The maximum limit for @index * * This iterator skips all entries, which resolve to a NULL pointer, * e.g. entries which has been reserved with XA_ZERO_ENTRY. */ #define mt_for_each(__tree, __entry, __index, __max) \ for (__entry = mt_find(__tree, &(__index), __max); \ __entry; __entry = mt_find_after(__tree, &(__index), __max)) #endif /*_LINUX_MAPLE_TREE_H */ |
| 98 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef LINUX_RESUME_USER_MODE_H #define LINUX_RESUME_USER_MODE_H #include <linux/sched.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/rseq.h> #include <linux/blk-cgroup.h> /** * set_notify_resume - cause resume_user_mode_work() to be called * @task: task that will call resume_user_mode_work() * * Calling this arranges that @task will call resume_user_mode_work() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call resume_user_mode_work() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); } /** * resume_user_mode_work - Perform work before returning to user mode * @regs: user-mode registers of @current task * * This is called when %TIF_NOTIFY_RESUME has been set. Now we are * about to return to user mode, and the user state in @regs can be * inspected or adjusted. The caller in arch code has cleared * %TIF_NOTIFY_RESUME before the call. If the flag gets set again * asynchronously, this will be called again before we return to * user mode. * * Called without locks. */ static inline void resume_user_mode_work(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); /* * This barrier pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); if (unlikely(task_work_pending(current))) task_work_run(); #ifdef CONFIG_KEYS_REQUEST_CACHE if (unlikely(current->cached_requested_key)) { key_put(current->cached_requested_key); current->cached_requested_key = NULL; } #endif mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_notify_resume(NULL, regs); } #endif /* LINUX_RESUME_USER_MODE_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 6 6 6 6 6 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 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 | // 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/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/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_rx_queue.h> #include <net/page_pool/types.h> #include <net/page_pool/helpers.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 DECLARE_RWSEM(devnet_rename_sem); 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). */ static DEFINE_PER_CPU(struct page_pool *, system_page_pool); #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)) return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all; else return pt->dev ? &pt->dev->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); 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; 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); /** * __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 < MIN_NAPI_ID) return NULL; napi = napi_by_id(napi_id); return napi ? napi->dev : NULL; } EXPORT_SYMBOL(dev_get_by_napi_id); 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; } /** * 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 or RTNL. * 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->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); 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); /** * __dev_get_by_flags - find any device with given flags * @net: the applicable net namespace * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. Returns NULL if a device * is not found or a pointer to the device. Must be called inside * rtnl_lock(), and result refcount is unchanged. */ struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags, unsigned short mask) { struct net_device *dev, *ret; ASSERT_RTNL(); ret = NULL; for_each_netdev(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { ret = dev; break; } } return ret; } EXPORT_SYMBOL(__dev_get_by_flags); /** * 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; } /** * dev_change_name - change name of a device * @dev: device * @newname: name (or format string) must be at least IFNAMSIZ * * Change name of a device, can pass format strings "eth%d". * for wildcarding. */ int dev_change_name(struct net_device *dev, const char *newname) { unsigned char old_assign_type; char oldname[IFNAMSIZ]; int err = 0; int ret; struct net *net; ASSERT_RTNL(); BUG_ON(!dev_net(dev)); net = dev_net(dev); down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { up_write(&devnet_rename_sem); 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) { up_write(&devnet_rename_sem); 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) { memcpy(dev->name, oldname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); up_write(&devnet_rename_sem); return ret; } up_write(&devnet_rename_sem); 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; down_write(&devnet_rename_sem); 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; } /** * dev_set_alias - change ifalias of a device * @dev: device * @alias: name up to IFALIASZ * @len: limit of bytes to copy from info * * Set ifalias for a device, */ int dev_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; } EXPORT_SYMBOL(dev_set_alias); /** * 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); /** * netdev_state_change - device changes state * @dev: device to cause notification * * Called to indicate a device has changed state. This function calls * the notifier chains for netdev_chain and sends a NEWLINK message * to the routing socket. */ void netdev_state_change(struct net_device *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); } } EXPORT_SYMBOL(netdev_state_change); /** * __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); 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 { dev->flags |= IFF_UP; dev_set_rx_mode(dev); dev_activate(dev); add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; } /** * dev_open - prepare an interface for use. * @dev: device to open * @extack: netlink extended ack * * Takes a device from down to up state. The device's private open * function is invoked and then the multicast lists are loaded. Finally * the device is moved into the up state and a %NETDEV_UP message is * sent to the netdev notifier chain. * * Calling this function on an active interface is a nop. On a failure * a negative errno code is returned. */ int dev_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; } EXPORT_SYMBOL(dev_open); 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. */ if (ops->ndo_stop) ops->ndo_stop(dev); dev->flags &= ~IFF_UP; 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 dev_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(dev_close_many); /** * dev_close - shutdown an interface. * @dev: device to shutdown * * This function moves an active device into down state. A * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier * chain. */ void dev_close(struct net_device *dev) { if (dev->flags & IFF_UP) { LIST_HEAD(single); list_add(&dev->close_list, &single); dev_close_many(&single, true); list_del(&single); } } EXPORT_SYMBOL(dev_close); /** * dev_disable_lro - disable Large Receive Offload on a device * @dev: device * * Disable Large Receive Offload (LRO) on a net device. Must be * called under RTNL. This is needed if received packets may be * forwarded to another interface. */ void dev_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) dev_disable_lro(lower_dev); } EXPORT_SYMBOL(dev_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) { err = call_netdevice_register_notifiers(nb, 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); rtnl_lock(); err = raw_notifier_chain_register(&netdev_chain, nb); if (err) goto unlock; if (dev_boot_phase) goto unlock; for_each_net(net) { err = call_netdevice_register_net_notifiers(nb, net); if (err) goto rollback; } unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; rollback: for_each_net_continue_reverse(net) call_netdevice_unregister_net_notifiers(nb, 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) call_netdevice_unregister_net_notifiers(nb, 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_lock(); err = __register_netdevice_notifier_net(net, nb, false); rtnl_unlock(); 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_lock(); err = __unregister_netdevice_notifier_net(net, nb); rtnl_unlock(); 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); } int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_lock(); err = __register_netdevice_notifier_net(dev_net(dev), nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } rtnl_unlock(); 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_lock(); list_del(&nn->list); err = __unregister_netdevice_notifier_net(dev_net(dev), nb); rtnl_unlock(); 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_bypass_check_needed_key); EXPORT_SYMBOL(tcf_bypass_check_needed_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 - return true if any network interface taps are in use * * @dev: network device to check for the presence of taps */ bool dev_nit_active(struct net_device *dev) { return !list_empty(&net_hotdata.ptype_all) || !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active); /* * 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 list_head *ptype_list = &net_hotdata.ptype_all; struct packet_type *ptype, *pt_prev = NULL; struct sk_buff *skb2 = NULL; rcu_read_lock(); 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 == &net_hotdata.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) { ASSERT_RTNL(); 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); 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); #ifdef CONFIG_SYSFS /** * 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) { ASSERT_RTNL(); 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); #endif /** * 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); int skb_crc32c_csum_help(struct sk_buff *skb) { __le32 crc32c_csum; 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; crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start, skb->len - start, ~(__u32)0, crc32c_csum_stub)); *(__le32 *)(skb->data + offset) = crc32c_csum; skb_reset_csum_not_inet(skb); out: return ret; } EXPORT_SYMBOL(skb_crc32c_csum_help); __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; } 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(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)) { switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): return 0; } } return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again) { netdev_features_t features; 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 */ hdr_len = skb_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; if (static_branch_unlikely(&tcf_bypass_check_needed_key)) { 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)) __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()/dev_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: 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 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 = skb_get_hash(skb) & flow_table->mask; 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[hash & flow_table->mask]; 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 <= flow_table->mask) { 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->mask))) 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); sd->received_rps++; } #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 = skb_get_hash(skb) & (fl->num_buckets - 1); 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)) { fl->count++; 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, 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, struct bpf_prog *prog) { struct sk_buff *skb = *pskb; int err, hroom, troom; if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog)) 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, 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, 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(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) { 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 (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); 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, &net_hotdata.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)) 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]); } 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) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; *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, SKB_DROP_REASON_UNHANDLED_PROTO); /* 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); dev_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); static DEFINE_PER_CPU(struct work_struct, flush_works); /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) { struct sk_buff *skb, *tmp; struct softnet_data *sd; 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 (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); dev_kfree_skb_irq(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 (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); kfree_skb(skb); rps_input_queue_head_incr(sd); } } local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); local_bh_enable(); } 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; } static void flush_all_backlogs(void) { static cpumask_t flush_cpus; unsigned int cpu; /* since we are under rtnl lock protection we can use static data * for the cpumask and avoid allocating on stack the possibly * large mask */ ASSERT_RTNL(); cpus_read_lock(); cpumask_clear(&flush_cpus); for_each_online_cpu(cpu) { if (flush_required(cpu)) { queue_work_on(cpu, system_highpri_wq, per_cpu_ptr(&flush_works, cpu)); cpumask_set_cpu(cpu, &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, &flush_cpus) flush_work(per_cpu_ptr(&flush_works, cpu)); cpus_read_unlock(); } 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 = READ_ONCE(n->dev->gro_flush_timeout); n->defer_hard_irqs_count = READ_ONCE(n->dev->napi_defer_hard_irqs); } if (n->defer_hard_irqs_count > 0) { n->defer_hard_irqs_count--; timeout = READ_ONCE(n->dev->gro_flush_timeout); if (timeout) ret = false; } if (n->gro_bitmask) { /* 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 */ napi_gro_flush(n, !!timeout); } gro_normal_list(n); 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); /* must be called under rcu_read_lock(), as we dont take a reference */ 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; } 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); __napi_schedule(napi); return; } if (napi->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ napi_gro_flush(napi, HZ >= 1000); } gro_normal_list(napi); 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 = READ_ONCE(napi->dev->napi_defer_hard_irqs); timeout = READ_ONCE(napi->dev->gro_flush_timeout); 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); 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); #endif /* CONFIG_NET_RX_BUSY_POLL */ static void napi_hash_add(struct napi_struct *napi) { if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock(&napi_hash_lock); /* 0..NR_CPUS range is reserved for sender_cpu use */ do { if (unlikely(++napi_gen_id < MIN_NAPI_ID)) napi_gen_id = MIN_NAPI_ID; } while (napi_by_id(napi_gen_id)); napi->napi_id = napi_gen_id; hlist_add_head_rcu(&napi->napi_hash_node, &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); spin_unlock(&napi_hash_lock); } /* 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) { spin_lock(&napi_hash_lock); hlist_del_init_rcu(&napi->napi_hash_node); spin_unlock(&napi_hash_lock); } 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 init_gro_hash(struct napi_struct *napi) { int i; for (i = 0; i < GRO_HASH_BUCKETS; i++) { INIT_LIST_HEAD(&napi->gro_hash[i].list); napi->gro_hash[i].count = 0; } napi->gro_bitmask = 0; } int dev_set_threaded(struct net_device *dev, bool threaded) { struct napi_struct *napi; int err = 0; if (dev->threaded == threaded) return 0; if (threaded) { list_for_each_entry(napi, &dev->napi_list, dev_list) { if (!napi->thread) { err = napi_kthread_create(napi); if (err) { threaded = false; break; } } } } WRITE_ONCE(dev->threaded, threaded); /* Make sure kthread is created before THREADED bit * is set. */ smp_mb__before_atomic(); /* 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. */ list_for_each_entry(napi, &dev->napi_list, dev_list) assign_bit(NAPI_STATE_THREADED, &napi->state, threaded); return err; } EXPORT_SYMBOL(dev_set_threaded); /** * 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; if (dev->reg_state >= NETREG_REGISTERED) ASSERT_RTNL(); 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); void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { 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_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; init_gro_hash(napi); napi->skb = NULL; INIT_LIST_HEAD(&napi->rx_list); napi->rx_count = 0; 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); list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); 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 (dev->threaded && napi_kthread_create(napi)) dev->threaded = false; netif_napi_set_irq(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight); void napi_disable(struct napi_struct *n) { unsigned long val, new; might_sleep(); 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); clear_bit(NAPI_STATE_DISABLE, &n->state); } EXPORT_SYMBOL(napi_disable); /** * napi_enable - enable NAPI scheduling * @n: NAPI context * * Resume NAPI from being scheduled on this context. * Must be paired with napi_disable. */ void napi_enable(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); 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); static void flush_gro_hash(struct napi_struct *napi) { int i; for (i = 0; i < GRO_HASH_BUCKETS; i++) { struct sk_buff *skb, *n; list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list) kfree_skb(skb); napi->gro_hash[i].count = 0; } } /* Must be called in process context */ void __netif_napi_del(struct napi_struct *napi) { if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) return; napi_hash_del(napi); list_del_rcu(&napi->dev_list); napi_free_frags(napi); flush_gro_hash(napi); napi->gro_bitmask = 0; if (napi->thread) { kthread_stop(napi->thread); napi->thread = NULL; } } EXPORT_SYMBOL(__netif_napi_del); 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; } if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ napi_gro_flush(n, HZ >= 1000); } gro_normal_list(n); /* 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) 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))) { sd->time_squeeze++; 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) __dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL); return 0; } /** * dev_set_promiscuity - update promiscuity count on a device * @dev: device * @inc: modifier * * Add or remove promiscuity from a device. While the count in the device * remains above zero the interface remains promiscuous. Once it hits zero * the device reverts back to normal filtering operation. A negative inc * value is used to drop promiscuity on the device. * Return 0 if successful or a negative errno code on error. */ int dev_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; } EXPORT_SYMBOL(dev_set_promiscuity); static int __dev_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; } /** * dev_set_allmulti - update allmulti count on a device * @dev: device * @inc: modifier * * Add or remove reception of all multicast frames to a device. While the * count in the device remains above zero the interface remains listening * to all interfaces. Once it hits zero the device reverts back to normal * filtering operation. A negative @inc value is used to drop the counter * when releasing a resource needing all multicasts. * Return 0 if successful or a negative errno code on error. */ int dev_set_allmulti(struct net_device *dev, int inc) { return __dev_set_allmulti(dev, inc, true); } EXPORT_SYMBOL(dev_set_allmulti); /* * 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); } /** * dev_get_flags - get flags reported to userspace * @dev: device * * Get the combination of flag bits exported through APIs to userspace. */ unsigned int dev_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(dev_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; unsigned int 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; __dev_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); } } /** * dev_change_flags - change device settings * @dev: device * @flags: device state flags * @extack: netlink extended ack * * Change settings on device based state flags. The flags are * in the userspace exported format. */ int dev_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; } EXPORT_SYMBOL(dev_change_flags); int __dev_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(__dev_set_mtu); 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; } /** * dev_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. */ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { int err, orig_mtu; 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 = __dev_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. */ __dev_set_mtu(dev, orig_mtu); call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, new_mtu); } } return err; } int dev_set_mtu(struct net_device *dev, int new_mtu) { struct netlink_ext_ack extack; int err; memset(&extack, 0, sizeof(extack)); err = dev_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(dev_set_mtu); /** * dev_change_tx_queue_len - Change TX queue length of a netdevice * @dev: device * @new_len: new tx queue length */ int dev_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; } /** * dev_set_group - Change group this device belongs to * @dev: device * @new_group: group this device should belong to */ void dev_set_group(struct net_device *dev, int new_group) { dev->group = new_group; } /** * dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR. * @dev: device * @addr: new address * @extack: netlink extended ack */ int dev_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(dev_pre_changeaddr_notify); /** * dev_set_mac_address - Change Media Access Control Address * @dev: device * @sa: new address * @extack: netlink extended ack * * Change the hardware (MAC) address of the device */ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, 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 (sa->sa_family != dev->type) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack); if (err) return err; if (memcmp(dev->dev_addr, sa->sa_data, dev->addr_len)) { err = ops->ndo_set_mac_address(dev, sa); 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; } EXPORT_SYMBOL(dev_set_mac_address); DECLARE_RWSEM(dev_addr_sem); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack) { int ret; down_write(&dev_addr_sem); ret = dev_set_mac_address(dev, sa, extack); up_write(&dev_addr_sem); return ret; } EXPORT_SYMBOL(dev_set_mac_address_user); int dev_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(dev_get_mac_address); /** * dev_change_carrier - Change device carrier * @dev: device * @new_carrier: new value * * Change device carrier */ int dev_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); } /** * dev_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 */ int dev_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 = dev_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(dev_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 (dev_get_port_parent_id(a, &a_id, true) || dev_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); /** * dev_change_proto_down - set carrier according to proto_down. * * @dev: device * @proto_down: new value */ int dev_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; } /** * dev_change_proto_down_reason - proto down reason * * @dev: device * @mask: proto down mask * @value: proto down value */ void dev_change_proto_down_reason(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); int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) { if (!dev->netdev_ops->ndo_bpf) return -EOPNOTSUPP; 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(dev_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; 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 (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) { WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link)); 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; } 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); 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); link->dev = dev; link->flags = attr->link_create.flags; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto unlock; } err = dev_xdp_attach_link(dev, &extack, link); 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; ASSERT_RTNL(); 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)); } /* 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); 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); } } } 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(); 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. */ if (features & NETIF_F_RX_UDP_TUNNEL_PORT) { dev->features = features; udp_tunnel_get_rx_info(dev); } else { udp_tunnel_drop_rx_info(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); WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED); if (ret) goto err_uninit_notify; __netdev_update_features(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. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, 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_state == RTNL_LINK_INITIALIZED) 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. * This is useful if you are calling this function after alloc_netdev(), * since it does not memset the net_device fields. */ static void init_dummy_netdev_core(struct net_device *dev) { /* make sure we BUG if trying to hit standard * register/unregister code path */ dev->reg_state = NETREG_DUMMY; /* NAPI wants this */ INIT_LIST_HEAD(&dev->napi_list); /* a dummy interface is started by default */ set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); /* napi_busy_loop stats accounting wants this */ dev_net_set(dev, &init_net); /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. */ } /** * init_dummy_netdev - init a dummy network device for NAPI * @dev: device to init * * This takes a network device structure and initializes the minimum * amount of fields so it can be used to schedule NAPI polls without * registering a full blown interface. This is to be used by drivers * that need to tie several hardware interfaces to a single NAPI * poll scheduler due to HW limitations. */ void init_dummy_netdev(struct net_device *dev) { /* Clear everything. Note we don't initialize spinlocks * as they aren't supposed to be taken by any of the * NAPI code and this dummy netdev is supposed to be * only ever used for NAPI polls */ memset(dev, 0, sizeof(struct net_device)); init_dummy_netdev_core(dev); } EXPORT_SYMBOL_GPL(init_dummy_netdev); /** * 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) { int err; if (rtnl_lock_killable()) return -EINTR; err = register_netdevice(dev); rtnl_unlock(); 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)) { struct net_device *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; } WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED); 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; 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)) { dev->gro_flush_timeout = 20000; dev->napi_defer_hard_irqs = 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; 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; } 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, name); #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 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; 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); /** * 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) { struct napi_struct *p, *n; 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; } 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); list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); 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); /* 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_core); } 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 (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) { struct ethtool_rxfh_param rxfh; rxfh.indir = ethtool_rxfh_context_indir(ctx); rxfh.key = ethtool_rxfh_context_key(ctx); rxfh.hfunc = ctx->hfunc; rxfh.input_xfrm = ctx->input_xfrm; rxfh.rss_context = context; rxfh.rss_delete = true; xa_erase(&dev->ethtool->rss_ctx, context); if (dev->ethtool_ops->create_rxfh_context) dev->ethtool_ops->remove_rxfh_context(dev, ctx, context, NULL); else dev->ethtool_ops->set_rxfh(dev, &rxfh, 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); 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. */ list_for_each_entry(dev, head, unreg_list) list_add_tail(&dev->close_list, &close_head); dev_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); } flush_all_backlogs(); synchronize_net(); list_for_each_entry(dev, head, unreg_list) { struct sk_buff *skb = NULL; /* Shutdown queueing discipline. */ dev_shutdown(dev); dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); bpf_dev_bound_netdev_unregister(dev); dev_dmabuf_uninstall(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_state == RTNL_LINK_INITIALIZED) 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); 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_lock(); unregister_netdevice(dev); rtnl_unlock(); } EXPORT_SYMBOL(unregister_netdev); /** * __dev_change_net_namespace - move device to different nethost namespace * @dev: device * @net: network namespace * @pat: If not NULL name pattern to try if the current device name * is already taken in the destination network namespace. * @new_ifindex: If not zero, specifies device index in the target * namespace. * * This function shuts down a device interface and moves it * to a new network namespace. On success 0 is returned, on * a failure a netagive errno code is returned. * * Callers must hold the rtnl semaphore. */ int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex) { 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_local) goto out; /* Ensure the device has been registered */ if (dev->reg_state != NETREG_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) goto out; err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST); if (err < 0) 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)) goto out; /* Check that new_ifindex isn't used yet. */ if (new_ifindex) { err = dev_index_reserve(net, new_ifindex); if (err < 0) 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) goto out; new_ifindex = err; } /* * And now a mini version of register_netdevice unregister_netdevice. */ /* If device is running close it first. */ dev_close(dev); /* And unlink it from device chain */ unlist_netdevice(dev); synchronize_net(); /* Shutdown queueing discipline. */ dev_shutdown(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 */ dev_net_set(dev, net); 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); /* Add the device back in the hashes */ list_netdevice(dev); /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, 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; } EXPORT_SYMBOL_GPL(__dev_change_net_namespace); 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 > 8 * sizeof_field(struct napi_struct, gro_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_local) 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_flush_timeout); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, napi_defer_hard_irqs); 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, 104); } /* * 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; pp_ptr = page_pool_create_percpu(&page_pool_params, cpuid); if (IS_ERR(pp_ptr)) return -ENOMEM; per_cpu(system_page_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. */ for_each_possible_cpu(i) { struct work_struct *flush = per_cpu_ptr(&flush_works, i); struct softnet_data *sd = &per_cpu(softnet_data, i); INIT_WORK(flush, flush_backlog); 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); init_gro_hash(&sd->backlog); 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, i); if (!pp_ptr) continue; page_pool_destroy(pp_ptr); per_cpu(system_page_pool, i) = NULL; } } return rc; } subsys_initcall(net_dev_init); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* gw.c - CAN frame Gateway/Router/Bridge with netlink interface * * Copyright (c) 2019 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/gw.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #define CAN_GW_NAME "can-gw" MODULE_DESCRIPTION("PF_CAN netlink gateway"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); MODULE_ALIAS(CAN_GW_NAME); #define CGW_MIN_HOPS 1 #define CGW_MAX_HOPS 6 #define CGW_DEFAULT_HOPS 1 static unsigned int max_hops __read_mostly = CGW_DEFAULT_HOPS; module_param(max_hops, uint, 0444); MODULE_PARM_DESC(max_hops, "maximum " CAN_GW_NAME " routing hops for CAN frames " "(valid values: " __stringify(CGW_MIN_HOPS) "-" __stringify(CGW_MAX_HOPS) " hops, " "default: " __stringify(CGW_DEFAULT_HOPS) ")"); static struct notifier_block notifier; static struct kmem_cache *cgw_cache __read_mostly; /* structure that contains the (on-the-fly) CAN frame modifications */ struct cf_mod { struct { struct canfd_frame and; struct canfd_frame or; struct canfd_frame xor; struct canfd_frame set; } modframe; struct { u8 and; u8 or; u8 xor; u8 set; } modtype; void (*modfunc[MAX_MODFUNCTIONS])(struct canfd_frame *cf, struct cf_mod *mod); /* CAN frame checksum calculation after CAN frame modifications */ struct { struct cgw_csum_xor xor; struct cgw_csum_crc8 crc8; } csum; struct { void (*xor)(struct canfd_frame *cf, struct cgw_csum_xor *xor); void (*crc8)(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8); } csumfunc; u32 uid; }; /* So far we just support CAN -> CAN routing and frame modifications. * * The internal can_can_gw structure contains data and attributes for * a CAN -> CAN gateway job. */ struct can_can_gw { struct can_filter filter; int src_idx; int dst_idx; }; /* list entry for CAN gateways jobs */ struct cgw_job { struct hlist_node list; struct rcu_head rcu; u32 handled_frames; u32 dropped_frames; u32 deleted_frames; struct cf_mod mod; union { /* CAN frame data source */ struct net_device *dev; } src; union { /* CAN frame data destination */ struct net_device *dev; } dst; union { struct can_can_gw ccgw; /* tbc */ }; u8 gwtype; u8 limit_hops; u16 flags; }; /* modification functions that are invoked in the hot path in can_can_gw_rcv */ #define MODFUNC(func, op) static void func(struct canfd_frame *cf, \ struct cf_mod *mod) { op ; } MODFUNC(mod_and_id, cf->can_id &= mod->modframe.and.can_id) MODFUNC(mod_and_len, cf->len &= mod->modframe.and.len) MODFUNC(mod_and_flags, cf->flags &= mod->modframe.and.flags) MODFUNC(mod_and_data, *(u64 *)cf->data &= *(u64 *)mod->modframe.and.data) MODFUNC(mod_or_id, cf->can_id |= mod->modframe.or.can_id) MODFUNC(mod_or_len, cf->len |= mod->modframe.or.len) MODFUNC(mod_or_flags, cf->flags |= mod->modframe.or.flags) MODFUNC(mod_or_data, *(u64 *)cf->data |= *(u64 *)mod->modframe.or.data) MODFUNC(mod_xor_id, cf->can_id ^= mod->modframe.xor.can_id) MODFUNC(mod_xor_len, cf->len ^= mod->modframe.xor.len) MODFUNC(mod_xor_flags, cf->flags ^= mod->modframe.xor.flags) MODFUNC(mod_xor_data, *(u64 *)cf->data ^= *(u64 *)mod->modframe.xor.data) MODFUNC(mod_set_id, cf->can_id = mod->modframe.set.can_id) MODFUNC(mod_set_len, cf->len = mod->modframe.set.len) MODFUNC(mod_set_flags, cf->flags = mod->modframe.set.flags) MODFUNC(mod_set_data, *(u64 *)cf->data = *(u64 *)mod->modframe.set.data) static void mod_and_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) &= *(u64 *)(mod->modframe.and.data + i); } static void mod_or_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) |= *(u64 *)(mod->modframe.or.data + i); } static void mod_xor_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) ^= *(u64 *)(mod->modframe.xor.data + i); } static void mod_set_fddata(struct canfd_frame *cf, struct cf_mod *mod) { memcpy(cf->data, mod->modframe.set.data, CANFD_MAX_DLEN); } /* retrieve valid CC DLC value and store it into 'len' */ static void mod_retrieve_ccdlc(struct canfd_frame *cf) { struct can_frame *ccf = (struct can_frame *)cf; /* len8_dlc is only valid if len == CAN_MAX_DLEN */ if (ccf->len != CAN_MAX_DLEN) return; /* do we have a valid len8_dlc value from 9 .. 15 ? */ if (ccf->len8_dlc > CAN_MAX_DLEN && ccf->len8_dlc <= CAN_MAX_RAW_DLC) ccf->len = ccf->len8_dlc; } /* convert valid CC DLC value in 'len' into struct can_frame elements */ static void mod_store_ccdlc(struct canfd_frame *cf) { struct can_frame *ccf = (struct can_frame *)cf; /* clear potential leftovers */ ccf->len8_dlc = 0; /* plain data length 0 .. 8 - that was easy */ if (ccf->len <= CAN_MAX_DLEN) return; /* potentially broken values are caught in can_can_gw_rcv() */ if (ccf->len > CAN_MAX_RAW_DLC) return; /* we have a valid dlc value from 9 .. 15 in ccf->len */ ccf->len8_dlc = ccf->len; ccf->len = CAN_MAX_DLEN; } static void mod_and_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_and_len(cf, mod); mod_store_ccdlc(cf); } static void mod_or_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_or_len(cf, mod); mod_store_ccdlc(cf); } static void mod_xor_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_xor_len(cf, mod); mod_store_ccdlc(cf); } static void mod_set_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_set_len(cf, mod); mod_store_ccdlc(cf); } static void canframecpy(struct canfd_frame *dst, struct can_frame *src) { /* Copy the struct members separately to ensure that no uninitialized * data are copied in the 3 bytes hole of the struct. This is needed * to make easy compares of the data in the struct cf_mod. */ dst->can_id = src->can_id; dst->len = src->len; *(u64 *)dst->data = *(u64 *)src->data; } static void canfdframecpy(struct canfd_frame *dst, struct canfd_frame *src) { /* Copy the struct members separately to ensure that no uninitialized * data are copied in the 2 bytes hole of the struct. This is needed * to make easy compares of the data in the struct cf_mod. */ dst->can_id = src->can_id; dst->flags = src->flags; dst->len = src->len; memcpy(dst->data, src->data, CANFD_MAX_DLEN); } static int cgw_chk_csum_parms(s8 fr, s8 to, s8 re, struct rtcanmsg *r) { s8 dlen = CAN_MAX_DLEN; if (r->flags & CGW_FLAGS_CAN_FD) dlen = CANFD_MAX_DLEN; /* absolute dlc values 0 .. 7 => 0 .. 7, e.g. data [0] * relative to received dlc -1 .. -8 : * e.g. for received dlc = 8 * -1 => index = 7 (data[7]) * -3 => index = 5 (data[5]) * -8 => index = 0 (data[0]) */ if (fr >= -dlen && fr < dlen && to >= -dlen && to < dlen && re >= -dlen && re < dlen) return 0; else return -EINVAL; } static inline int calc_idx(int idx, int rx_len) { if (idx < 0) return rx_len + idx; else return idx; } static void cgw_csum_xor_rel(struct canfd_frame *cf, struct cgw_csum_xor *xor) { int from = calc_idx(xor->from_idx, cf->len); int to = calc_idx(xor->to_idx, cf->len); int res = calc_idx(xor->result_idx, cf->len); u8 val = xor->init_xor_val; int i; if (from < 0 || to < 0 || res < 0) return; if (from <= to) { for (i = from; i <= to; i++) val ^= cf->data[i]; } else { for (i = from; i >= to; i--) val ^= cf->data[i]; } cf->data[res] = val; } static void cgw_csum_xor_pos(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; for (i = xor->from_idx; i <= xor->to_idx; i++) val ^= cf->data[i]; cf->data[xor->result_idx] = val; } static void cgw_csum_xor_neg(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; for (i = xor->from_idx; i >= xor->to_idx; i--) val ^= cf->data[i]; cf->data[xor->result_idx] = val; } static void cgw_csum_crc8_rel(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { int from = calc_idx(crc8->from_idx, cf->len); int to = calc_idx(crc8->to_idx, cf->len); int res = calc_idx(crc8->result_idx, cf->len); u8 crc = crc8->init_crc_val; int i; if (from < 0 || to < 0 || res < 0) return; if (from <= to) { for (i = crc8->from_idx; i <= crc8->to_idx; i++) crc = crc8->crctab[crc ^ cf->data[i]]; } else { for (i = crc8->from_idx; i >= crc8->to_idx; i--) crc = crc8->crctab[crc ^ cf->data[i]]; } switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_pos(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i <= crc8->to_idx; i++) crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_neg(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i >= crc8->to_idx; i--) crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } /* the receive & process & send function */ static void can_can_gw_rcv(struct sk_buff *skb, void *data) { struct cgw_job *gwj = (struct cgw_job *)data; struct canfd_frame *cf; struct sk_buff *nskb; int modidx = 0; /* process strictly Classic CAN or CAN FD frames */ if (gwj->flags & CGW_FLAGS_CAN_FD) { if (!can_is_canfd_skb(skb)) return; } else { if (!can_is_can_skb(skb)) return; } /* Do not handle CAN frames routed more than 'max_hops' times. * In general we should never catch this delimiter which is intended * to cover a misconfiguration protection (e.g. circular CAN routes). * * The Controller Area Network controllers only accept CAN frames with * correct CRCs - which are not visible in the controller registers. * According to skbuff.h documentation the csum_start element for IP * checksums is undefined/unused when ip_summed == CHECKSUM_UNNECESSARY. * Only CAN skbs can be processed here which already have this property. */ #define cgw_hops(skb) ((skb)->csum_start) BUG_ON(skb->ip_summed != CHECKSUM_UNNECESSARY); if (cgw_hops(skb) >= max_hops) { /* indicate deleted frames due to misconfiguration */ gwj->deleted_frames++; return; } if (!(gwj->dst.dev->flags & IFF_UP)) { gwj->dropped_frames++; return; } /* is sending the skb back to the incoming interface not allowed? */ if (!(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK) && can_skb_prv(skb)->ifindex == gwj->dst.dev->ifindex) return; /* clone the given skb, which has not been done in can_rcv() * * When there is at least one modification function activated, * we need to copy the skb as we want to modify skb->data. */ if (gwj->mod.modfunc[0]) nskb = skb_copy(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) { gwj->dropped_frames++; return; } /* put the incremented hop counter in the cloned skb */ cgw_hops(nskb) = cgw_hops(skb) + 1; /* first processing of this CAN frame -> adjust to private hop limit */ if (gwj->limit_hops && cgw_hops(nskb) == 1) cgw_hops(nskb) = max_hops - gwj->limit_hops + 1; nskb->dev = gwj->dst.dev; /* pointer to modifiable CAN frame */ cf = (struct canfd_frame *)nskb->data; /* perform preprocessed modification functions if there are any */ while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); /* Has the CAN frame been modified? */ if (modidx) { /* get available space for the processed CAN frame type */ int max_len = nskb->len - offsetof(struct canfd_frame, data); /* dlc may have changed, make sure it fits to the CAN frame */ if (cf->len > max_len) { /* delete frame due to misconfiguration */ gwj->deleted_frames++; kfree_skb(nskb); return; } /* check for checksum updates */ if (gwj->mod.csumfunc.crc8) (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); if (gwj->mod.csumfunc.xor) (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); } /* clear the skb timestamp if not configured the other way */ if (!(gwj->flags & CGW_FLAGS_CAN_SRC_TSTAMP)) nskb->tstamp = 0; /* send to netdevice */ if (can_send(nskb, gwj->flags & CGW_FLAGS_CAN_ECHO)) gwj->dropped_frames++; else gwj->handled_frames++; } static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj) { return can_rx_register(net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj, "gw", NULL); } static inline void cgw_unregister_filter(struct net *net, struct cgw_job *gwj) { can_rx_unregister(net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj); } static void cgw_job_free_rcu(struct rcu_head *rcu_head) { struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu); kmem_cache_free(cgw_cache, gwj); } static int cgw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg == NETDEV_UNREGISTER) { struct cgw_job *gwj = NULL; struct hlist_node *nx; ASSERT_RTNL(); hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); } } } return NOTIFY_DONE; } static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, u32 pid, u32 seq, int flags) { struct rtcanmsg *rtcan; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags); if (!nlh) return -EMSGSIZE; rtcan = nlmsg_data(nlh); rtcan->can_family = AF_CAN; rtcan->gwtype = gwj->gwtype; rtcan->flags = gwj->flags; /* add statistics if available */ if (gwj->handled_frames) { if (nla_put_u32(skb, CGW_HANDLED, gwj->handled_frames) < 0) goto cancel; } if (gwj->dropped_frames) { if (nla_put_u32(skb, CGW_DROPPED, gwj->dropped_frames) < 0) goto cancel; } if (gwj->deleted_frames) { if (nla_put_u32(skb, CGW_DELETED, gwj->deleted_frames) < 0) goto cancel; } /* check non default settings of attributes */ if (gwj->limit_hops) { if (nla_put_u8(skb, CGW_LIM_HOPS, gwj->limit_hops) < 0) goto cancel; } if (gwj->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; if (gwj->mod.modtype.and) { memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.and; if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.or) { memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.or; if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.xor) { memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.xor; if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.set) { memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.set; if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } else { struct cgw_frame_mod mb; if (gwj->mod.modtype.and) { memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.and; if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.or) { memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.or; if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.xor) { memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.xor; if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.set) { memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.set; if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } if (gwj->mod.uid) { if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0) goto cancel; } if (gwj->mod.csumfunc.crc8) { if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN, &gwj->mod.csum.crc8) < 0) goto cancel; } if (gwj->mod.csumfunc.xor) { if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN, &gwj->mod.csum.xor) < 0) goto cancel; } if (gwj->gwtype == CGW_TYPE_CAN_CAN) { if (gwj->ccgw.filter.can_id || gwj->ccgw.filter.can_mask) { if (nla_put(skb, CGW_FILTER, sizeof(struct can_filter), &gwj->ccgw.filter) < 0) goto cancel; } if (nla_put_u32(skb, CGW_SRC_IF, gwj->ccgw.src_idx) < 0) goto cancel; if (nla_put_u32(skb, CGW_DST_IF, gwj->ccgw.dst_idx) < 0) goto cancel; } nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } /* Dump information about all CAN gateway jobs, in response to RTM_GETROUTE */ static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct cgw_job *gwj = NULL; int idx = 0; int s_idx = cb->args[0]; rcu_read_lock(); hlist_for_each_entry_rcu(gwj, &net->can.cgw_list, list) { if (idx < s_idx) goto cont; if (cgw_put_job(skb, gwj, RTM_NEWROUTE, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) break; cont: idx++; } rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static const struct nla_policy cgw_policy[CGW_MAX + 1] = { [CGW_MOD_AND] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_OR] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_XOR] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_SET] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_CS_XOR] = { .len = sizeof(struct cgw_csum_xor) }, [CGW_CS_CRC8] = { .len = sizeof(struct cgw_csum_crc8) }, [CGW_SRC_IF] = { .type = NLA_U32 }, [CGW_DST_IF] = { .type = NLA_U32 }, [CGW_FILTER] = { .len = sizeof(struct can_filter) }, [CGW_LIM_HOPS] = { .type = NLA_U8 }, [CGW_MOD_UID] = { .type = NLA_U32 }, [CGW_FDMOD_AND] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_OR] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_XOR] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_SET] = { .len = sizeof(struct cgw_fdframe_mod) }, }; /* check for common and gwtype specific attributes */ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, u8 gwtype, void *gwtypeattr, u8 *limhops) { struct nlattr *tb[CGW_MAX + 1]; struct rtcanmsg *r = nlmsg_data(nlh); int modidx = 0; int err = 0; /* initialize modification & checksum data space */ memset(mod, 0, sizeof(*mod)); err = nlmsg_parse_deprecated(nlh, sizeof(struct rtcanmsg), tb, CGW_MAX, cgw_policy, NULL); if (err < 0) return err; if (tb[CGW_LIM_HOPS]) { *limhops = nla_get_u8(tb[CGW_LIM_HOPS]); if (*limhops < 1 || *limhops > max_hops) return -EINVAL; } /* check for AND/OR/XOR/SET modifications */ if (r->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; if (tb[CGW_FDMOD_AND]) { nla_memcpy(&mb, tb[CGW_FDMOD_AND], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.and, &mb.cf); mod->modtype.and = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_and_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_and_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_and_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_and_fddata; } if (tb[CGW_FDMOD_OR]) { nla_memcpy(&mb, tb[CGW_FDMOD_OR], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.or, &mb.cf); mod->modtype.or = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_or_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_or_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_or_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_or_fddata; } if (tb[CGW_FDMOD_XOR]) { nla_memcpy(&mb, tb[CGW_FDMOD_XOR], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.xor, &mb.cf); mod->modtype.xor = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_xor_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_xor_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_xor_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_xor_fddata; } if (tb[CGW_FDMOD_SET]) { nla_memcpy(&mb, tb[CGW_FDMOD_SET], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.set, &mb.cf); mod->modtype.set = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_set_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_set_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_set_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_set_fddata; } } else { struct cgw_frame_mod mb; if (tb[CGW_MOD_AND]) { nla_memcpy(&mb, tb[CGW_MOD_AND], CGW_MODATTR_LEN); canframecpy(&mod->modframe.and, &mb.cf); mod->modtype.and = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_and_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_and_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_and_data; } if (tb[CGW_MOD_OR]) { nla_memcpy(&mb, tb[CGW_MOD_OR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.or, &mb.cf); mod->modtype.or = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_or_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_or_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_or_data; } if (tb[CGW_MOD_XOR]) { nla_memcpy(&mb, tb[CGW_MOD_XOR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.xor, &mb.cf); mod->modtype.xor = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_xor_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_xor_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_xor_data; } if (tb[CGW_MOD_SET]) { nla_memcpy(&mb, tb[CGW_MOD_SET], CGW_MODATTR_LEN); canframecpy(&mod->modframe.set, &mb.cf); mod->modtype.set = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_set_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_set_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_set_data; } } /* check for checksum operations after CAN frame modifications */ if (modidx) { if (tb[CGW_CS_CRC8]) { struct cgw_csum_crc8 *c = nla_data(tb[CGW_CS_CRC8]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.crc8, tb[CGW_CS_CRC8], CGW_CS_CRC8_LEN); /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || c->result_idx < 0) mod->csumfunc.crc8 = cgw_csum_crc8_rel; else if (c->from_idx <= c->to_idx) mod->csumfunc.crc8 = cgw_csum_crc8_pos; else mod->csumfunc.crc8 = cgw_csum_crc8_neg; } if (tb[CGW_CS_XOR]) { struct cgw_csum_xor *c = nla_data(tb[CGW_CS_XOR]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.xor, tb[CGW_CS_XOR], CGW_CS_XOR_LEN); /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || c->result_idx < 0) mod->csumfunc.xor = cgw_csum_xor_rel; else if (c->from_idx <= c->to_idx) mod->csumfunc.xor = cgw_csum_xor_pos; else mod->csumfunc.xor = cgw_csum_xor_neg; } if (tb[CGW_MOD_UID]) nla_memcpy(&mod->uid, tb[CGW_MOD_UID], sizeof(u32)); } if (gwtype == CGW_TYPE_CAN_CAN) { /* check CGW_TYPE_CAN_CAN specific attributes */ struct can_can_gw *ccgw = (struct can_can_gw *)gwtypeattr; memset(ccgw, 0, sizeof(*ccgw)); /* check for can_filter in attributes */ if (tb[CGW_FILTER]) nla_memcpy(&ccgw->filter, tb[CGW_FILTER], sizeof(struct can_filter)); err = -ENODEV; /* specifying two interfaces is mandatory */ if (!tb[CGW_SRC_IF] || !tb[CGW_DST_IF]) return err; ccgw->src_idx = nla_get_u32(tb[CGW_SRC_IF]); ccgw->dst_idx = nla_get_u32(tb[CGW_DST_IF]); /* both indices set to 0 for flushing all routing entries */ if (!ccgw->src_idx && !ccgw->dst_idx) return 0; /* only one index set to 0 is an error */ if (!ccgw->src_idx || !ccgw->dst_idx) return err; } /* add the checks for other gwtypes here */ return 0; } static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct rtcanmsg *r; struct cgw_job *gwj; struct cf_mod mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; r = nlmsg_data(nlh); if (r->can_family != AF_CAN) return -EPFNOSUPPORT; /* so far we only support CAN -> CAN routings */ if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) return err; if (mod.uid) { ASSERT_RTNL(); /* check for updating an existing job with identical uid */ hlist_for_each_entry(gwj, &net->can.cgw_list, list) { if (gwj->mod.uid != mod.uid) continue; /* interfaces & filters must be identical */ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) return -EINVAL; /* update modifications with disabled softirq & quit */ local_bh_disable(); memcpy(&gwj->mod, &mod, sizeof(mod)); local_bh_enable(); return 0; } } /* ifindex == 0 is not allowed for job creation */ if (!ccgw.src_idx || !ccgw.dst_idx) return -ENODEV; gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL); if (!gwj) return -ENOMEM; gwj->handled_frames = 0; gwj->dropped_frames = 0; gwj->deleted_frames = 0; gwj->flags = r->flags; gwj->gwtype = r->gwtype; gwj->limit_hops = limhops; /* insert already parsed information */ memcpy(&gwj->mod, &mod, sizeof(mod)); memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw)); err = -ENODEV; gwj->src.dev = __dev_get_by_index(net, gwj->ccgw.src_idx); if (!gwj->src.dev) goto out; if (gwj->src.dev->type != ARPHRD_CAN) goto out; gwj->dst.dev = __dev_get_by_index(net, gwj->ccgw.dst_idx); if (!gwj->dst.dev) goto out; if (gwj->dst.dev->type != ARPHRD_CAN) goto out; /* is sending the skb back to the incoming interface intended? */ if (gwj->src.dev == gwj->dst.dev && !(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK)) { err = -EINVAL; goto out; } ASSERT_RTNL(); err = cgw_register_filter(net, gwj); if (!err) hlist_add_head_rcu(&gwj->list, &net->can.cgw_list); out: if (err) kmem_cache_free(cgw_cache, gwj); return err; } static void cgw_remove_all_jobs(struct net *net) { struct cgw_job *gwj = NULL; struct hlist_node *nx; ASSERT_RTNL(); hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); } } static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct cgw_job *gwj = NULL; struct hlist_node *nx; struct rtcanmsg *r; struct cf_mod mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; r = nlmsg_data(nlh); if (r->can_family != AF_CAN) return -EPFNOSUPPORT; /* so far we only support CAN -> CAN routings */ if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) return err; /* two interface indices both set to 0 => remove all entries */ if (!ccgw.src_idx && !ccgw.dst_idx) { cgw_remove_all_jobs(net); return 0; } err = -EINVAL; ASSERT_RTNL(); /* remove only the first matching entry */ hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { if (gwj->flags != r->flags) continue; if (gwj->limit_hops != limhops) continue; /* we have a match when uid is enabled and identical */ if (gwj->mod.uid || mod.uid) { if (gwj->mod.uid != mod.uid) continue; } else { /* no uid => check for identical modifications */ if (memcmp(&gwj->mod, &mod, sizeof(mod))) continue; } /* if (r->gwtype == CGW_TYPE_CAN_CAN) - is made sure here */ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) continue; hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); err = 0; break; } return err; } static int __net_init cangw_pernet_init(struct net *net) { INIT_HLIST_HEAD(&net->can.cgw_list); return 0; } static void __net_exit cangw_pernet_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) cgw_remove_all_jobs(net); rtnl_unlock(); } static struct pernet_operations cangw_pernet_ops = { .init = cangw_pernet_init, .exit_batch = cangw_pernet_exit_batch, }; static __init int cgw_module_init(void) { int ret; /* sanitize given module parameter */ max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS); pr_info("can: netlink gateway - max_hops=%d\n", max_hops); ret = register_pernet_subsys(&cangw_pernet_ops); if (ret) return ret; ret = -ENOMEM; cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); if (!cgw_cache) goto out_cache_create; /* set notifier */ notifier.notifier_call = cgw_notifier; ret = register_netdevice_notifier(¬ifier); if (ret) goto out_register_notifier; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, 0); if (ret) goto out_rtnl_register1; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, cgw_create_job, NULL, 0); if (ret) goto out_rtnl_register2; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, cgw_remove_job, NULL, 0); if (ret) goto out_rtnl_register3; return 0; out_rtnl_register3: rtnl_unregister(PF_CAN, RTM_NEWROUTE); out_rtnl_register2: rtnl_unregister(PF_CAN, RTM_GETROUTE); out_rtnl_register1: unregister_netdevice_notifier(¬ifier); out_register_notifier: kmem_cache_destroy(cgw_cache); out_cache_create: unregister_pernet_subsys(&cangw_pernet_ops); return ret; } static __exit void cgw_module_exit(void) { rtnl_unregister_all(PF_CAN); unregister_netdevice_notifier(¬ifier); unregister_pernet_subsys(&cangw_pernet_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ kmem_cache_destroy(cgw_cache); } module_init(cgw_module_init); module_exit(cgw_module_exit); |
| 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2010-2011 EIA Electronics, // Pieter Beyens <pieter.beyens@eia.be> // Copyright (c) 2010-2011 EIA Electronics, // Kurt Van Dijck <kurt.van.dijck@eia.be> // Copyright (c) 2018 Protonic, // Robin van der Gracht <robin@protonic.nl> // Copyright (c) 2017-2019 Pengutronix, // Marc Kleine-Budde <kernel@pengutronix.de> // Copyright (c) 2017-2019 Pengutronix, // Oleksij Rempel <kernel@pengutronix.de> /* Core of can-j1939 that links j1939 to CAN. */ #include <linux/can/can-ml.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/if_arp.h> #include <linux/module.h> #include "j1939-priv.h" MODULE_DESCRIPTION("PF_CAN SAE J1939"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("EIA Electronics (Kurt Van Dijck & Pieter Beyens)"); MODULE_ALIAS("can-proto-" __stringify(CAN_J1939)); /* LOWLEVEL CAN interface */ /* CAN_HDR: #bytes before can_frame data part */ #define J1939_CAN_HDR (offsetof(struct can_frame, data)) /* lowest layer */ static void j1939_can_recv(struct sk_buff *iskb, void *data) { struct j1939_priv *priv = data; struct sk_buff *skb; struct j1939_sk_buff_cb *skcb, *iskcb; struct can_frame *cf; /* make sure we only get Classical CAN frames */ if (!can_is_can_skb(iskb)) return; /* create a copy of the skb * j1939 only delivers the real data bytes, * the header goes into sockaddr. * j1939 may not touch the incoming skb in such way */ skb = skb_clone(iskb, GFP_ATOMIC); if (!skb) return; j1939_priv_get(priv); can_skb_set_owner(skb, iskb->sk); /* get a pointer to the header of the skb * the skb payload (pointer) is moved, so that the next skb_data * returns the actual payload */ cf = (void *)skb->data; skb_pull(skb, J1939_CAN_HDR); /* fix length, set to dlc, with 8 maximum */ skb_trim(skb, min_t(uint8_t, cf->len, 8)); /* set addr */ skcb = j1939_skb_to_cb(skb); memset(skcb, 0, sizeof(*skcb)); iskcb = j1939_skb_to_cb(iskb); skcb->tskey = iskcb->tskey; skcb->priority = (cf->can_id >> 26) & 0x7; skcb->addr.sa = cf->can_id; skcb->addr.pgn = (cf->can_id >> 8) & J1939_PGN_MAX; /* set default message type */ skcb->addr.type = J1939_TP; if (!j1939_address_is_valid(skcb->addr.sa)) { netdev_err_once(priv->ndev, "%s: sa is broadcast address, ignoring!\n", __func__); goto done; } if (j1939_pgn_is_pdu1(skcb->addr.pgn)) { /* Type 1: with destination address */ skcb->addr.da = skcb->addr.pgn; /* normalize pgn: strip dst address */ skcb->addr.pgn &= 0x3ff00; } else { /* set broadcast address */ skcb->addr.da = J1939_NO_ADDR; } /* update localflags */ read_lock_bh(&priv->lock); if (j1939_address_is_unicast(skcb->addr.sa) && priv->ents[skcb->addr.sa].nusers) skcb->flags |= J1939_ECU_LOCAL_SRC; if (j1939_address_is_unicast(skcb->addr.da) && priv->ents[skcb->addr.da].nusers) skcb->flags |= J1939_ECU_LOCAL_DST; read_unlock_bh(&priv->lock); /* deliver into the j1939 stack ... */ j1939_ac_recv(priv, skb); if (j1939_tp_recv(priv, skb)) /* this means the transport layer processed the message */ goto done; j1939_simple_recv(priv, skb); j1939_sk_recv(priv, skb); done: j1939_priv_put(priv); kfree_skb(skb); } /* NETDEV MANAGEMENT */ /* values for can_rx_(un)register */ #define J1939_CAN_ID CAN_EFF_FLAG #define J1939_CAN_MASK (CAN_EFF_FLAG | CAN_RTR_FLAG) static DEFINE_MUTEX(j1939_netdev_lock); static struct j1939_priv *j1939_priv_create(struct net_device *ndev) { struct j1939_priv *priv; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return NULL; rwlock_init(&priv->lock); INIT_LIST_HEAD(&priv->ecus); priv->ndev = ndev; kref_init(&priv->kref); kref_init(&priv->rx_kref); dev_hold(ndev); netdev_dbg(priv->ndev, "%s : 0x%p\n", __func__, priv); return priv; } static inline void j1939_priv_set(struct net_device *ndev, struct j1939_priv *priv) { struct can_ml_priv *can_ml = can_get_ml_priv(ndev); can_ml->j1939_priv = priv; } static void __j1939_priv_release(struct kref *kref) { struct j1939_priv *priv = container_of(kref, struct j1939_priv, kref); struct net_device *ndev = priv->ndev; netdev_dbg(priv->ndev, "%s: 0x%p\n", __func__, priv); WARN_ON_ONCE(!list_empty(&priv->active_session_list)); WARN_ON_ONCE(!list_empty(&priv->ecus)); WARN_ON_ONCE(!list_empty(&priv->j1939_socks)); dev_put(ndev); kfree(priv); } void j1939_priv_put(struct j1939_priv *priv) { kref_put(&priv->kref, __j1939_priv_release); } void j1939_priv_get(struct j1939_priv *priv) { kref_get(&priv->kref); } static int j1939_can_rx_register(struct j1939_priv *priv) { struct net_device *ndev = priv->ndev; int ret; j1939_priv_get(priv); ret = can_rx_register(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, j1939_can_recv, priv, "j1939", NULL); if (ret < 0) { j1939_priv_put(priv); return ret; } return 0; } static void j1939_can_rx_unregister(struct j1939_priv *priv) { struct net_device *ndev = priv->ndev; can_rx_unregister(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, j1939_can_recv, priv); /* The last reference of priv is dropped by the RCU deferred * j1939_sk_sock_destruct() of the last socket, so we can * safely drop this reference here. */ j1939_priv_put(priv); } static void __j1939_rx_release(struct kref *kref) __releases(&j1939_netdev_lock) { struct j1939_priv *priv = container_of(kref, struct j1939_priv, rx_kref); j1939_can_rx_unregister(priv); j1939_ecu_unmap_all(priv); j1939_priv_set(priv->ndev, NULL); mutex_unlock(&j1939_netdev_lock); } /* get pointer to priv without increasing ref counter */ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) { struct can_ml_priv *can_ml = can_get_ml_priv(ndev); return can_ml->j1939_priv; } static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) { struct j1939_priv *priv; lockdep_assert_held(&j1939_netdev_lock); priv = j1939_ndev_to_priv(ndev); if (priv) j1939_priv_get(priv); return priv; } static struct j1939_priv *j1939_priv_get_by_ndev(struct net_device *ndev) { struct j1939_priv *priv; mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); mutex_unlock(&j1939_netdev_lock); return priv; } struct j1939_priv *j1939_netdev_start(struct net_device *ndev) { struct j1939_priv *priv, *priv_new; int ret; mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); if (priv) { kref_get(&priv->rx_kref); mutex_unlock(&j1939_netdev_lock); return priv; } mutex_unlock(&j1939_netdev_lock); priv = j1939_priv_create(ndev); if (!priv) return ERR_PTR(-ENOMEM); j1939_tp_init(priv); rwlock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); mutex_lock(&j1939_netdev_lock); priv_new = j1939_priv_get_by_ndev_locked(ndev); if (priv_new) { /* Someone was faster than us, use their priv and roll * back our's. */ kref_get(&priv_new->rx_kref); mutex_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); return priv_new; } j1939_priv_set(ndev, priv); ret = j1939_can_rx_register(priv); if (ret < 0) goto out_priv_put; mutex_unlock(&j1939_netdev_lock); return priv; out_priv_put: j1939_priv_set(ndev, NULL); mutex_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); return ERR_PTR(ret); } void j1939_netdev_stop(struct j1939_priv *priv) { kref_put_mutex(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); j1939_priv_put(priv); } int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) { int ret, dlc; canid_t canid; struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); struct can_frame *cf; /* apply sanity checks */ if (j1939_pgn_is_pdu1(skcb->addr.pgn)) skcb->addr.pgn &= J1939_PGN_PDU1_MAX; else skcb->addr.pgn &= J1939_PGN_MAX; if (skcb->priority > 7) skcb->priority = 6; ret = j1939_ac_fixup(priv, skb); if (unlikely(ret)) goto failed; dlc = skb->len; /* re-claim the CAN_HDR from the SKB */ cf = skb_push(skb, J1939_CAN_HDR); /* initialize header structure */ memset(cf, 0, J1939_CAN_HDR); /* make it a full can frame again */ skb_put_zero(skb, 8 - dlc); canid = CAN_EFF_FLAG | (skcb->priority << 26) | (skcb->addr.pgn << 8) | skcb->addr.sa; if (j1939_pgn_is_pdu1(skcb->addr.pgn)) canid |= skcb->addr.da << 8; cf->can_id = canid; cf->len = dlc; return can_send(skb, 1); failed: kfree_skb(skb); return ret; } static int j1939_netdev_notify(struct notifier_block *nb, unsigned long msg, void *data) { struct net_device *ndev = netdev_notifier_info_to_dev(data); struct can_ml_priv *can_ml = can_get_ml_priv(ndev); struct j1939_priv *priv; if (!can_ml) goto notify_done; priv = j1939_priv_get_by_ndev(ndev); if (!priv) goto notify_done; switch (msg) { case NETDEV_DOWN: j1939_cancel_active_session(priv, NULL); j1939_sk_netdev_event_netdown(priv); j1939_ecu_unmap_all(priv); break; } j1939_priv_put(priv); notify_done: return NOTIFY_DONE; } static struct notifier_block j1939_netdev_notifier = { .notifier_call = j1939_netdev_notify, }; /* MODULE interface */ static __init int j1939_module_init(void) { int ret; pr_info("can: SAE J1939\n"); ret = register_netdevice_notifier(&j1939_netdev_notifier); if (ret) goto fail_notifier; ret = can_proto_register(&j1939_can_proto); if (ret < 0) { pr_err("can: registration of j1939 protocol failed\n"); goto fail_sk; } return 0; fail_sk: unregister_netdevice_notifier(&j1939_netdev_notifier); fail_notifier: return ret; } static __exit void j1939_module_exit(void) { can_proto_unregister(&j1939_can_proto); unregister_netdevice_notifier(&j1939_netdev_notifier); } module_init(j1939_module_init); module_exit(j1939_module_exit); |
| 143 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* 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; #define MNT_NOSUID 0x01 #define MNT_NODEV 0x02 #define MNT_NOEXEC 0x04 #define MNT_NOATIME 0x08 #define MNT_NODIRATIME 0x10 #define MNT_RELATIME 0x20 #define MNT_READONLY 0x40 /* does the user want this to be r/o? */ #define MNT_NOSYMFOLLOW 0x80 #define MNT_SHRINKABLE 0x100 #define MNT_WRITE_HOLD 0x200 #define MNT_SHARED 0x1000 /* if the vfsmount is a shared mount */ #define MNT_UNBINDABLE 0x2000 /* if the vfsmount is a unbindable mount */ /* * MNT_SHARED_MASK is the set of flags that should be cleared when a * mount becomes shared. Currently, this is only the flag that says a * mount cannot be bind mounted, since this is how we create a mount * that shares events with another mount. If you add a new MNT_* * flag, consider how it interacts with shared mounts. */ #define MNT_SHARED_MASK (MNT_UNBINDABLE) #define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \ | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \ | MNT_READONLY | MNT_NOSYMFOLLOW) #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB) #define MNT_INTERNAL 0x4000 #define MNT_LOCK_ATIME 0x040000 #define MNT_LOCK_NOEXEC 0x080000 #define MNT_LOCK_NOSUID 0x100000 #define MNT_LOCK_NODEV 0x200000 #define MNT_LOCK_READONLY 0x400000 #define MNT_LOCKED 0x800000 #define MNT_DOOMED 0x1000000 #define MNT_SYNC_UMOUNT 0x2000000 #define MNT_MARKED 0x4000000 #define MNT_UMOUNT 0x8000000 #define MNT_ONRB 0x10000000 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 smp_load_acquire(&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 *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 struct vfsmount *vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, 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 *); extern long do_mount(const char *, const char __user *, const char *, unsigned long, void *); extern struct vfsmount *collect_mounts(const struct path *); extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, struct vfsmount *); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); extern int cifs_root_data(char **dev, char **opts); #endif /* _LINUX_MOUNT_H */ |
| 139 669 139 139 137 725 730 669 716 2 139 726 729 722 725 139 5 134 127 11 138 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/file.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/slab.h> /* * Mapping table from "enum tomoyo_path_acl_index" to "enum tomoyo_mac_index". */ static const u8 tomoyo_p2mac[TOMOYO_MAX_PATH_OPERATION] = { [TOMOYO_TYPE_EXECUTE] = TOMOYO_MAC_FILE_EXECUTE, [TOMOYO_TYPE_READ] = TOMOYO_MAC_FILE_OPEN, [TOMOYO_TYPE_WRITE] = TOMOYO_MAC_FILE_OPEN, [TOMOYO_TYPE_APPEND] = TOMOYO_MAC_FILE_OPEN, [TOMOYO_TYPE_UNLINK] = TOMOYO_MAC_FILE_UNLINK, [TOMOYO_TYPE_GETATTR] = TOMOYO_MAC_FILE_GETATTR, [TOMOYO_TYPE_RMDIR] = TOMOYO_MAC_FILE_RMDIR, [TOMOYO_TYPE_TRUNCATE] = TOMOYO_MAC_FILE_TRUNCATE, [TOMOYO_TYPE_SYMLINK] = TOMOYO_MAC_FILE_SYMLINK, [TOMOYO_TYPE_CHROOT] = TOMOYO_MAC_FILE_CHROOT, [TOMOYO_TYPE_UMOUNT] = TOMOYO_MAC_FILE_UMOUNT, }; /* * Mapping table from "enum tomoyo_mkdev_acl_index" to "enum tomoyo_mac_index". */ const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION] = { [TOMOYO_TYPE_MKBLOCK] = TOMOYO_MAC_FILE_MKBLOCK, [TOMOYO_TYPE_MKCHAR] = TOMOYO_MAC_FILE_MKCHAR, }; /* * Mapping table from "enum tomoyo_path2_acl_index" to "enum tomoyo_mac_index". */ const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION] = { [TOMOYO_TYPE_LINK] = TOMOYO_MAC_FILE_LINK, [TOMOYO_TYPE_RENAME] = TOMOYO_MAC_FILE_RENAME, [TOMOYO_TYPE_PIVOT_ROOT] = TOMOYO_MAC_FILE_PIVOT_ROOT, }; /* * Mapping table from "enum tomoyo_path_number_acl_index" to * "enum tomoyo_mac_index". */ const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION] = { [TOMOYO_TYPE_CREATE] = TOMOYO_MAC_FILE_CREATE, [TOMOYO_TYPE_MKDIR] = TOMOYO_MAC_FILE_MKDIR, [TOMOYO_TYPE_MKFIFO] = TOMOYO_MAC_FILE_MKFIFO, [TOMOYO_TYPE_MKSOCK] = TOMOYO_MAC_FILE_MKSOCK, [TOMOYO_TYPE_IOCTL] = TOMOYO_MAC_FILE_IOCTL, [TOMOYO_TYPE_CHMOD] = TOMOYO_MAC_FILE_CHMOD, [TOMOYO_TYPE_CHOWN] = TOMOYO_MAC_FILE_CHOWN, [TOMOYO_TYPE_CHGRP] = TOMOYO_MAC_FILE_CHGRP, }; /** * tomoyo_put_name_union - Drop reference on "struct tomoyo_name_union". * * @ptr: Pointer to "struct tomoyo_name_union". * * Returns nothing. */ void tomoyo_put_name_union(struct tomoyo_name_union *ptr) { tomoyo_put_group(ptr->group); tomoyo_put_name(ptr->filename); } /** * tomoyo_compare_name_union - Check whether a name matches "struct tomoyo_name_union" or not. * * @name: Pointer to "struct tomoyo_path_info". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns "struct tomoyo_path_info" if @name matches @ptr, NULL otherwise. */ const struct tomoyo_path_info * tomoyo_compare_name_union(const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr) { if (ptr->group) return tomoyo_path_matches_group(name, ptr->group); if (tomoyo_path_matches_pattern(name, ptr->filename)) return ptr->filename; return NULL; } /** * tomoyo_put_number_union - Drop reference on "struct tomoyo_number_union". * * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ void tomoyo_put_number_union(struct tomoyo_number_union *ptr) { tomoyo_put_group(ptr->group); } /** * tomoyo_compare_number_union - Check whether a value matches "struct tomoyo_number_union" or not. * * @value: Number to check. * @ptr: Pointer to "struct tomoyo_number_union". * * Returns true if @value matches @ptr, false otherwise. */ bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr) { if (ptr->group) return tomoyo_number_matches_group(value, value, ptr->group); return value >= ptr->values[0] && value <= ptr->values[1]; } /** * tomoyo_add_slash - Add trailing '/' if needed. * * @buf: Pointer to "struct tomoyo_path_info". * * Returns nothing. * * @buf must be generated by tomoyo_encode() because this function does not * allocate memory for adding '/'. */ static void tomoyo_add_slash(struct tomoyo_path_info *buf) { if (buf->is_dir) return; /* * This is OK because tomoyo_encode() reserves space for appending "/". */ strcat((char *) buf->name, "/"); tomoyo_fill_path_info(buf); } /** * tomoyo_get_realpath - Get realpath. * * @buf: Pointer to "struct tomoyo_path_info". * @path: Pointer to "struct path". * * Returns true on success, false otherwise. */ static bool tomoyo_get_realpath(struct tomoyo_path_info *buf, const struct path *path) { buf->name = tomoyo_realpath_from_path(path); if (buf->name) { tomoyo_fill_path_info(buf); return true; } return false; } /** * tomoyo_audit_path_log - Audit path request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_path_log(struct tomoyo_request_info *r) { return tomoyo_supervisor(r, "file %s %s\n", tomoyo_path_keyword [r->param.path.operation], r->param.path.filename->name); } /** * tomoyo_audit_path2_log - Audit path/path request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_path2_log(struct tomoyo_request_info *r) { return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords [tomoyo_pp2mac[r->param.path2.operation]], r->param.path2.filename1->name, r->param.path2.filename2->name); } /** * tomoyo_audit_mkdev_log - Audit path/number/number/number request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_mkdev_log(struct tomoyo_request_info *r) { return tomoyo_supervisor(r, "file %s %s 0%o %u %u\n", tomoyo_mac_keywords [tomoyo_pnnn2mac[r->param.mkdev.operation]], r->param.mkdev.filename->name, r->param.mkdev.mode, r->param.mkdev.major, r->param.mkdev.minor); } /** * tomoyo_audit_path_number_log - Audit path/number request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_path_number_log(struct tomoyo_request_info *r) { const u8 type = r->param.path_number.operation; u8 radix; char buffer[64]; switch (type) { case TOMOYO_TYPE_CREATE: case TOMOYO_TYPE_MKDIR: case TOMOYO_TYPE_MKFIFO: case TOMOYO_TYPE_MKSOCK: case TOMOYO_TYPE_CHMOD: radix = TOMOYO_VALUE_TYPE_OCTAL; break; case TOMOYO_TYPE_IOCTL: radix = TOMOYO_VALUE_TYPE_HEXADECIMAL; break; default: radix = TOMOYO_VALUE_TYPE_DECIMAL; break; } tomoyo_print_ulong(buffer, sizeof(buffer), r->param.path_number.number, radix); return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords [tomoyo_pn2mac[type]], r->param.path_number.filename->name, buffer); } /** * tomoyo_check_path_acl - Check permission for path operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. * * To be able to use wildcard for domain transition, this function sets * matching entry on success. Since the caller holds tomoyo_read_lock(), * it is safe to set matching entry. */ static bool tomoyo_check_path_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_path_acl *acl = container_of(ptr, typeof(*acl), head); if (acl->perm & (1 << r->param.path.operation)) { r->param.path.matched_path = tomoyo_compare_name_union(r->param.path.filename, &acl->name); return r->param.path.matched_path != NULL; } return false; } /** * tomoyo_check_path_number_acl - Check permission for path number operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_path_number_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_path_number_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.path_number.operation)) && tomoyo_compare_number_union(r->param.path_number.number, &acl->number) && tomoyo_compare_name_union(r->param.path_number.filename, &acl->name); } /** * tomoyo_check_path2_acl - Check permission for path path operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_path2_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_path2_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.path2.operation)) && tomoyo_compare_name_union(r->param.path2.filename1, &acl->name1) && tomoyo_compare_name_union(r->param.path2.filename2, &acl->name2); } /** * tomoyo_check_mkdev_acl - Check permission for path number number number operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_mkdev_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_mkdev_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.mkdev.operation)) && tomoyo_compare_number_union(r->param.mkdev.mode, &acl->mode) && tomoyo_compare_number_union(r->param.mkdev.major, &acl->major) && tomoyo_compare_number_union(r->param.mkdev.minor, &acl->minor) && tomoyo_compare_name_union(r->param.mkdev.filename, &acl->name); } /** * tomoyo_same_path_acl - Check for duplicated "struct tomoyo_path_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_path_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_path_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_path_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name, &p2->name); } /** * tomoyo_merge_path_acl - Merge duplicated "struct tomoyo_path_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_path_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u16 * const a_perm = &container_of(a, struct tomoyo_path_acl, head) ->perm; u16 perm = READ_ONCE(*a_perm); const u16 b_perm = container_of(b, struct tomoyo_path_acl, head)->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_path_acl - Update "struct tomoyo_path_acl" list. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_path_acl(const u16 perm, struct tomoyo_acl_param *param) { struct tomoyo_path_acl e = { .head.type = TOMOYO_TYPE_PATH_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_path_acl, tomoyo_merge_path_acl); tomoyo_put_name_union(&e.name); return error; } /** * tomoyo_same_mkdev_acl - Check for duplicated "struct tomoyo_mkdev_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_mkdev_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_mkdev_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_mkdev_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name, &p2->name) && tomoyo_same_number_union(&p1->mode, &p2->mode) && tomoyo_same_number_union(&p1->major, &p2->major) && tomoyo_same_number_union(&p1->minor, &p2->minor); } /** * tomoyo_merge_mkdev_acl - Merge duplicated "struct tomoyo_mkdev_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_mkdev_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 *const a_perm = &container_of(a, struct tomoyo_mkdev_acl, head)->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_mkdev_acl, head) ->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_mkdev_acl - Update "struct tomoyo_mkdev_acl" list. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_mkdev_acl(const u8 perm, struct tomoyo_acl_param *param) { struct tomoyo_mkdev_acl e = { .head.type = TOMOYO_TYPE_MKDEV_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name) || !tomoyo_parse_number_union(param, &e.mode) || !tomoyo_parse_number_union(param, &e.major) || !tomoyo_parse_number_union(param, &e.minor)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_mkdev_acl, tomoyo_merge_mkdev_acl); tomoyo_put_name_union(&e.name); tomoyo_put_number_union(&e.mode); tomoyo_put_number_union(&e.major); tomoyo_put_number_union(&e.minor); return error; } /** * tomoyo_same_path2_acl - Check for duplicated "struct tomoyo_path2_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_path2_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_path2_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_path2_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name1, &p2->name1) && tomoyo_same_name_union(&p1->name2, &p2->name2); } /** * tomoyo_merge_path2_acl - Merge duplicated "struct tomoyo_path2_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_path2_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 * const a_perm = &container_of(a, struct tomoyo_path2_acl, head) ->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_path2_acl, head)->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_path2_acl - Update "struct tomoyo_path2_acl" list. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_path2_acl(const u8 perm, struct tomoyo_acl_param *param) { struct tomoyo_path2_acl e = { .head.type = TOMOYO_TYPE_PATH2_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name1) || !tomoyo_parse_name_union(param, &e.name2)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_path2_acl, tomoyo_merge_path2_acl); tomoyo_put_name_union(&e.name1); tomoyo_put_name_union(&e.name2); return error; } /** * tomoyo_path_permission - Check permission for single path operation. * * @r: Pointer to "struct tomoyo_request_info". * @operation: Type of operation. * @filename: Filename to check. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_path_permission(struct tomoyo_request_info *r, u8 operation, const struct tomoyo_path_info *filename) { int error; r->type = tomoyo_p2mac[operation]; r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type); if (r->mode == TOMOYO_CONFIG_DISABLED) return 0; r->param_type = TOMOYO_TYPE_PATH_ACL; r->param.path.filename = filename; r->param.path.operation = operation; do { tomoyo_check_acl(r, tomoyo_check_path_acl); error = tomoyo_audit_path_log(r); } while (error == TOMOYO_RETRY_REQUEST); return error; } /** * tomoyo_execute_permission - Check permission for execute operation. * * @r: Pointer to "struct tomoyo_request_info". * @filename: Filename to check. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_execute_permission(struct tomoyo_request_info *r, const struct tomoyo_path_info *filename) { /* * Unlike other permission checks, this check is done regardless of * profile mode settings in order to check for domain transition * preference. */ r->type = TOMOYO_MAC_FILE_EXECUTE; r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type); r->param_type = TOMOYO_TYPE_PATH_ACL; r->param.path.filename = filename; r->param.path.operation = TOMOYO_TYPE_EXECUTE; tomoyo_check_acl(r, tomoyo_check_path_acl); r->ee->transition = r->matched_acl && r->matched_acl->cond ? r->matched_acl->cond->transit : NULL; if (r->mode != TOMOYO_CONFIG_DISABLED) return tomoyo_audit_path_log(r); return 0; } /** * tomoyo_same_path_number_acl - Check for duplicated "struct tomoyo_path_number_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_path_number_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_path_number_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_path_number_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name, &p2->name) && tomoyo_same_number_union(&p1->number, &p2->number); } /** * tomoyo_merge_path_number_acl - Merge duplicated "struct tomoyo_path_number_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_path_number_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 * const a_perm = &container_of(a, struct tomoyo_path_number_acl, head)->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_path_number_acl, head) ->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_path_number_acl - Update ioctl/chmod/chown/chgrp ACL. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_update_path_number_acl(const u8 perm, struct tomoyo_acl_param *param) { struct tomoyo_path_number_acl e = { .head.type = TOMOYO_TYPE_PATH_NUMBER_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name) || !tomoyo_parse_number_union(param, &e.number)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_path_number_acl, tomoyo_merge_path_number_acl); tomoyo_put_name_union(&e.name); tomoyo_put_number_union(&e.number); return error; } /** * tomoyo_path_number_perm - Check permission for "create", "mkdir", "mkfifo", "mksock", "ioctl", "chmod", "chown", "chgrp". * * @type: Type of operation. * @path: Pointer to "struct path". * @number: Number. * * Returns 0 on success, negative value otherwise. */ int tomoyo_path_number_perm(const u8 type, const struct path *path, unsigned long number) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int error = -ENOMEM; struct tomoyo_path_info buf; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_pn2mac[type]) == TOMOYO_CONFIG_DISABLED) return 0; idx = tomoyo_read_lock(); if (!tomoyo_get_realpath(&buf, path)) goto out; r.obj = &obj; if (type == TOMOYO_TYPE_MKDIR) tomoyo_add_slash(&buf); r.param_type = TOMOYO_TYPE_PATH_NUMBER_ACL; r.param.path_number.operation = type; r.param.path_number.filename = &buf; r.param.path_number.number = number; do { tomoyo_check_acl(&r, tomoyo_check_path_number_acl); error = tomoyo_audit_path_number_log(&r); } while (error == TOMOYO_RETRY_REQUEST); kfree(buf.name); out: tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_check_open_permission - Check permission for "read" and "write". * * @domain: Pointer to "struct tomoyo_domain_info". * @path: Pointer to "struct path". * @flag: Flags for open(). * * Returns 0 on success, negative value otherwise. */ int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, const struct path *path, const int flag) { const u8 acc_mode = ACC_MODE(flag); int error = 0; struct tomoyo_path_info buf; struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int idx; buf.name = NULL; r.mode = TOMOYO_CONFIG_DISABLED; idx = tomoyo_read_lock(); if (acc_mode && tomoyo_init_request_info(&r, domain, TOMOYO_MAC_FILE_OPEN) != TOMOYO_CONFIG_DISABLED) { if (!tomoyo_get_realpath(&buf, path)) { error = -ENOMEM; goto out; } r.obj = &obj; if (acc_mode & MAY_READ) error = tomoyo_path_permission(&r, TOMOYO_TYPE_READ, &buf); if (!error && (acc_mode & MAY_WRITE)) error = tomoyo_path_permission(&r, (flag & O_APPEND) ? TOMOYO_TYPE_APPEND : TOMOYO_TYPE_WRITE, &buf); } out: kfree(buf.name); tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_path_perm - Check permission for "unlink", "rmdir", "truncate", "symlink", "append", "chroot" and "unmount". * * @operation: Type of operation. * @path: Pointer to "struct path". * @target: Symlink's target if @operation is TOMOYO_TYPE_SYMLINK, * NULL otherwise. * * Returns 0 on success, negative value otherwise. */ int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int error; struct tomoyo_path_info buf; bool is_enforce; struct tomoyo_path_info symlink_target; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_p2mac[operation]) == TOMOYO_CONFIG_DISABLED) return 0; is_enforce = (r.mode == TOMOYO_CONFIG_ENFORCING); error = -ENOMEM; buf.name = NULL; idx = tomoyo_read_lock(); if (!tomoyo_get_realpath(&buf, path)) goto out; r.obj = &obj; switch (operation) { case TOMOYO_TYPE_RMDIR: case TOMOYO_TYPE_CHROOT: tomoyo_add_slash(&buf); break; case TOMOYO_TYPE_SYMLINK: symlink_target.name = tomoyo_encode(target); if (!symlink_target.name) goto out; tomoyo_fill_path_info(&symlink_target); obj.symlink_target = &symlink_target; break; } error = tomoyo_path_permission(&r, operation, &buf); if (operation == TOMOYO_TYPE_SYMLINK) kfree(symlink_target.name); out: kfree(buf.name); tomoyo_read_unlock(idx); if (!is_enforce) error = 0; return error; } /** * tomoyo_mkdev_perm - Check permission for "mkblock" and "mkchar". * * @operation: Type of operation. (TOMOYO_TYPE_MKCHAR or TOMOYO_TYPE_MKBLOCK) * @path: Pointer to "struct path". * @mode: Create mode. * @dev: Device number. * * Returns 0 on success, negative value otherwise. */ int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int error = -ENOMEM; struct tomoyo_path_info buf; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_pnnn2mac[operation]) == TOMOYO_CONFIG_DISABLED) return 0; idx = tomoyo_read_lock(); error = -ENOMEM; if (tomoyo_get_realpath(&buf, path)) { r.obj = &obj; dev = new_decode_dev(dev); r.param_type = TOMOYO_TYPE_MKDEV_ACL; r.param.mkdev.filename = &buf; r.param.mkdev.operation = operation; r.param.mkdev.mode = mode; r.param.mkdev.major = MAJOR(dev); r.param.mkdev.minor = MINOR(dev); tomoyo_check_acl(&r, tomoyo_check_mkdev_acl); error = tomoyo_audit_mkdev_log(&r); kfree(buf.name); } tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_path2_perm - Check permission for "rename", "link" and "pivot_root". * * @operation: Type of operation. * @path1: Pointer to "struct path". * @path2: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ int tomoyo_path2_perm(const u8 operation, const struct path *path1, const struct path *path2) { int error = -ENOMEM; struct tomoyo_path_info buf1; struct tomoyo_path_info buf2; struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path1->mnt, .dentry = path1->dentry }, .path2 = { .mnt = path2->mnt, .dentry = path2->dentry } }; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_pp2mac[operation]) == TOMOYO_CONFIG_DISABLED) return 0; buf1.name = NULL; buf2.name = NULL; idx = tomoyo_read_lock(); if (!tomoyo_get_realpath(&buf1, path1) || !tomoyo_get_realpath(&buf2, path2)) goto out; switch (operation) { case TOMOYO_TYPE_RENAME: case TOMOYO_TYPE_LINK: if (!d_is_dir(path1->dentry)) break; fallthrough; case TOMOYO_TYPE_PIVOT_ROOT: tomoyo_add_slash(&buf1); tomoyo_add_slash(&buf2); break; } r.obj = &obj; r.param_type = TOMOYO_TYPE_PATH2_ACL; r.param.path2.operation = operation; r.param.path2.filename1 = &buf1; r.param.path2.filename2 = &buf2; do { tomoyo_check_acl(&r, tomoyo_check_path2_acl); error = tomoyo_audit_path2_log(&r); } while (error == TOMOYO_RETRY_REQUEST); out: kfree(buf1.name); kfree(buf2.name); tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_same_mount_acl - Check for duplicated "struct tomoyo_mount_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_mount_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_mount_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_mount_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->dev_name, &p2->dev_name) && tomoyo_same_name_union(&p1->dir_name, &p2->dir_name) && tomoyo_same_name_union(&p1->fs_type, &p2->fs_type) && tomoyo_same_number_union(&p1->flags, &p2->flags); } /** * tomoyo_update_mount_acl - Write "struct tomoyo_mount_acl" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_mount_acl(struct tomoyo_acl_param *param) { struct tomoyo_mount_acl e = { .head.type = TOMOYO_TYPE_MOUNT_ACL }; int error; if (!tomoyo_parse_name_union(param, &e.dev_name) || !tomoyo_parse_name_union(param, &e.dir_name) || !tomoyo_parse_name_union(param, &e.fs_type) || !tomoyo_parse_number_union(param, &e.flags)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_mount_acl, NULL); tomoyo_put_name_union(&e.dev_name); tomoyo_put_name_union(&e.dir_name); tomoyo_put_name_union(&e.fs_type); tomoyo_put_number_union(&e.flags); return error; } /** * tomoyo_write_file - Update file related list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_file(struct tomoyo_acl_param *param) { u16 perm = 0; u8 type; const char *operation = tomoyo_read_token(param); for (type = 0; type < TOMOYO_MAX_PATH_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_path_keyword[type])) perm |= 1 << type; if (perm) return tomoyo_update_path_acl(perm, param); for (type = 0; type < TOMOYO_MAX_PATH2_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_mac_keywords[tomoyo_pp2mac[type]])) perm |= 1 << type; if (perm) return tomoyo_update_path2_acl(perm, param); for (type = 0; type < TOMOYO_MAX_PATH_NUMBER_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_mac_keywords[tomoyo_pn2mac[type]])) perm |= 1 << type; if (perm) return tomoyo_update_path_number_acl(perm, param); for (type = 0; type < TOMOYO_MAX_MKDEV_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_mac_keywords[tomoyo_pnnn2mac[type]])) perm |= 1 << type; if (perm) return tomoyo_update_mkdev_acl(perm, param); if (tomoyo_permstr(operation, tomoyo_mac_keywords[TOMOYO_MAC_FILE_MOUNT])) return tomoyo_update_mount_acl(param); return -EINVAL; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * An extensible bitmap is a bitmap that supports an * arbitrary number of bits. Extensible bitmaps are * used to represent sets of values, such as types, * roles, categories, and classes. * * Each extensible bitmap is implemented as a linked * list of bitmap nodes, where each bitmap node has * an explicitly specified starting bit position within * the total bitmap. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_EBITMAP_H_ #define _SS_EBITMAP_H_ #include <net/netlabel.h> #ifdef CONFIG_64BIT #define EBITMAP_NODE_SIZE 64 #else #define EBITMAP_NODE_SIZE 32 #endif #define EBITMAP_UNIT_NUMS \ ((EBITMAP_NODE_SIZE - sizeof(void *) - sizeof(u32)) / \ sizeof(unsigned long)) #define EBITMAP_UNIT_SIZE BITS_PER_LONG #define EBITMAP_SIZE (EBITMAP_UNIT_NUMS * EBITMAP_UNIT_SIZE) #define EBITMAP_BIT 1UL #define EBITMAP_SHIFT_UNIT_SIZE(x) \ (((x) >> EBITMAP_UNIT_SIZE / 2) >> EBITMAP_UNIT_SIZE / 2) struct ebitmap_node { struct ebitmap_node *next; unsigned long maps[EBITMAP_UNIT_NUMS]; u32 startbit; }; struct ebitmap { struct ebitmap_node *node; /* first node in the bitmap */ u32 highbit; /* highest position in the total bitmap */ }; #define ebitmap_length(e) ((e)->highbit) static inline u32 ebitmap_start_positive(const struct ebitmap *e, struct ebitmap_node **n) { u32 ofs; for (*n = e->node; *n; *n = (*n)->next) { ofs = find_first_bit((*n)->maps, EBITMAP_SIZE); if (ofs < EBITMAP_SIZE) return (*n)->startbit + ofs; } return ebitmap_length(e); } static inline void ebitmap_init(struct ebitmap *e) { memset(e, 0, sizeof(*e)); } static inline u32 ebitmap_next_positive(const struct ebitmap *e, struct ebitmap_node **n, u32 bit) { u32 ofs; ofs = find_next_bit((*n)->maps, EBITMAP_SIZE, bit - (*n)->startbit + 1); if (ofs < EBITMAP_SIZE) return ofs + (*n)->startbit; for (*n = (*n)->next; *n; *n = (*n)->next) { ofs = find_first_bit((*n)->maps, EBITMAP_SIZE); if (ofs < EBITMAP_SIZE) return ofs + (*n)->startbit; } return ebitmap_length(e); } #define EBITMAP_NODE_INDEX(node, bit) \ (((bit) - (node)->startbit) / EBITMAP_UNIT_SIZE) #define EBITMAP_NODE_OFFSET(node, bit) \ (((bit) - (node)->startbit) % EBITMAP_UNIT_SIZE) static inline int ebitmap_node_get_bit(const struct ebitmap_node *n, u32 bit) { u32 index = EBITMAP_NODE_INDEX(n, bit); u32 ofs = EBITMAP_NODE_OFFSET(n, bit); BUG_ON(index >= EBITMAP_UNIT_NUMS); if ((n->maps[index] & (EBITMAP_BIT << ofs))) return 1; return 0; } static inline void ebitmap_node_set_bit(struct ebitmap_node *n, u32 bit) { u32 index = EBITMAP_NODE_INDEX(n, bit); u32 ofs = EBITMAP_NODE_OFFSET(n, bit); BUG_ON(index >= EBITMAP_UNIT_NUMS); n->maps[index] |= (EBITMAP_BIT << ofs); } static inline void ebitmap_node_clr_bit(struct ebitmap_node *n, u32 bit) { u32 index = EBITMAP_NODE_INDEX(n, bit); u32 ofs = EBITMAP_NODE_OFFSET(n, bit); BUG_ON(index >= EBITMAP_UNIT_NUMS); n->maps[index] &= ~(EBITMAP_BIT << ofs); } #define ebitmap_for_each_positive_bit(e, n, bit) \ for ((bit) = ebitmap_start_positive(e, &(n)); \ (bit) < ebitmap_length(e); \ (bit) = ebitmap_next_positive(e, &(n), bit)) int ebitmap_cmp(const struct ebitmap *e1, const struct ebitmap *e2); int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src); int ebitmap_and(struct ebitmap *dst, const struct ebitmap *e1, const struct ebitmap *e2); int ebitmap_contains(const struct ebitmap *e1, const struct ebitmap *e2, u32 last_e2bit); int ebitmap_get_bit(const struct ebitmap *e, u32 bit); int ebitmap_set_bit(struct ebitmap *e, u32 bit, int value); void ebitmap_destroy(struct ebitmap *e); int ebitmap_read(struct ebitmap *e, void *fp); int ebitmap_write(const struct ebitmap *e, void *fp); u32 ebitmap_hash(const struct ebitmap *e, u32 hash); #ifdef CONFIG_NETLABEL int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap); int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap); #else static inline int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap) { return -ENOMEM; } static inline int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap) { return -ENOMEM; } #endif #endif /* _SS_EBITMAP_H_ */ |
| 76 76 76 58 57 43 43 43 3 3 3 37 37 3 3 27 27 27 7 1 17 2 27 1 23 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 | // SPDX-License-Identifier: GPL-2.0-only /* * arch/arm64/mm/hugetlbpage.c * * Copyright (C) 2013 Linaro Ltd. * * Based on arch/x86/mm/hugetlbpage.c. */ #include <linux/init.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> #include <linux/err.h> #include <linux/sysctl.h> #include <asm/mman.h> #include <asm/tlb.h> #include <asm/tlbflush.h> /* * HugeTLB Support Matrix * * --------------------------------------------------- * | Page Size | CONT PTE | PMD | CONT PMD | PUD | * --------------------------------------------------- * | 4K | 64K | 2M | 32M | 1G | * | 16K | 2M | 32M | 1G | | * | 64K | 2M | 512M | 16G | | * --------------------------------------------------- */ /* * Reserve CMA areas for the largest supported gigantic * huge page when requested. Any other smaller gigantic * huge pages could still be served from those areas. */ #ifdef CONFIG_CMA void __init arm64_hugetlb_cma_reserve(void) { int order; if (pud_sect_supported()) order = PUD_SHIFT - PAGE_SHIFT; else order = CONT_PMD_SHIFT - PAGE_SHIFT; hugetlb_cma_reserve(order); } #endif /* CONFIG_CMA */ static bool __hugetlb_valid_size(unsigned long size) { switch (size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: return pud_sect_supported(); #endif case CONT_PMD_SIZE: case PMD_SIZE: case CONT_PTE_SIZE: return true; } return false; } #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h) { size_t pagesize = huge_page_size(h); if (!__hugetlb_valid_size(pagesize)) { pr_warn("%s: unrecognized huge page size 0x%lx\n", __func__, pagesize); return false; } return true; } #endif static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { pgd_t *pgdp = pgd_offset(mm, addr); p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; *pgsize = PAGE_SIZE; p4dp = p4d_offset(pgdp, addr); pudp = pud_offset(p4dp, addr); pmdp = pmd_offset(pudp, addr); if ((pte_t *)pmdp == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; } return CONT_PTES; } static inline int num_contig_ptes(unsigned long size, size_t *pgsize) { int contig_ptes = 0; *pgsize = size; switch (size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: if (pud_sect_supported()) contig_ptes = 1; break; #endif case PMD_SIZE: contig_ptes = 1; break; case CONT_PMD_SIZE: *pgsize = PMD_SIZE; contig_ptes = CONT_PMDS; break; case CONT_PTE_SIZE: *pgsize = PAGE_SIZE; contig_ptes = CONT_PTES; break; } return contig_ptes; } pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { int ncontig, i; size_t pgsize; pte_t orig_pte = __ptep_get(ptep); if (!pte_present(orig_pte) || !pte_cont(orig_pte)) return orig_pte; ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize); for (i = 0; i < ncontig; i++, ptep++) { pte_t pte = __ptep_get(ptep); if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } /* * Changing some bits of contiguous entries requires us to follow a * Break-Before-Make approach, breaking the whole contiguous set * before we can change any entries. See ARM DDI 0487A.k_iss10775, * "Misprogramming of the Contiguous bit", page D4-1762. * * This helper performs the break step. */ static pte_t get_clear_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { pte_t orig_pte = __ptep_get(ptep); unsigned long i; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) { pte_t pte = __ptep_get_and_clear(mm, addr, ptep); /* * If HW_AFDBM is enabled, then the HW could turn on * the dirty or accessed bit for any page in the set, * so check them all. */ if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } static pte_t get_clear_contig_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { pte_t orig_pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig); struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); flush_tlb_range(&vma, addr, addr + (pgsize * ncontig)); return orig_pte; } /* * Changing some bits of contiguous entries requires us to follow a * Break-Before-Make approach, breaking the whole contiguous set * before we can change any entries. See ARM DDI 0487A.k_iss10775, * "Misprogramming of the Contiguous bit", page D4-1762. * * This helper performs the break step for use cases where the * original pte is not needed. */ static void clear_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) __ptep_get_and_clear(mm, addr, ptep); flush_tlb_range(&vma, saddr, addr); } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { size_t pgsize; int i; int ncontig; unsigned long pfn, dpfn; pgprot_t hugeprot; ncontig = num_contig_ptes(sz, &pgsize); if (!pte_present(pte)) { for (i = 0; i < ncontig; i++, ptep++, addr += pgsize) __set_ptes(mm, addr, ptep, pte, 1); return; } if (!pte_cont(pte)) { __set_ptes(mm, addr, ptep, pte, 1); return; } pfn = pte_pfn(pte); dpfn = pgsize >> PAGE_SHIFT; hugeprot = pte_pgprot(pte); clear_flush(mm, addr, ptep, pgsize, ncontig); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); } pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgdp; p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep = NULL; pgdp = pgd_offset(mm, addr); p4dp = p4d_alloc(mm, pgdp, addr); if (!p4dp) return NULL; pudp = pud_alloc(mm, p4dp, addr); if (!pudp) return NULL; if (sz == PUD_SIZE) { ptep = (pte_t *)pudp; } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); if (!pmdp) return NULL; WARN_ON(addr & (sz - 1)); ptep = pte_alloc_huge(mm, pmdp, addr); } else if (sz == PMD_SIZE) { if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp))) ptep = huge_pmd_share(mm, vma, addr, pudp); else ptep = (pte_t *)pmd_alloc(mm, pudp, addr); } else if (sz == (CONT_PMD_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); return (pte_t *)pmdp; } return ptep; } pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgdp; p4d_t *p4dp; pud_t *pudp, pud; pmd_t *pmdp, pmd; pgdp = pgd_offset(mm, addr); if (!pgd_present(READ_ONCE(*pgdp))) return NULL; p4dp = p4d_offset(pgdp, addr); if (!p4d_present(READ_ONCE(*p4dp))) return NULL; pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ if (pud_leaf(pud) || !pud_present(pud)) return (pte_t *)pudp; /* table; check the next level */ if (sz == CONT_PMD_SIZE) addr &= CONT_PMD_MASK; pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && pmd_none(pmd)) return NULL; if (pmd_leaf(pmd) || !pmd_present(pmd)) return (pte_t *)pmdp; if (sz == CONT_PTE_SIZE) return pte_offset_huge(pmdp, (addr & CONT_PTE_MASK)); return NULL; } unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); switch (hp_size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: return PGDIR_SIZE - PUD_SIZE; #endif case CONT_PMD_SIZE: return PUD_SIZE - CONT_PMD_SIZE; case PMD_SIZE: return PUD_SIZE - PMD_SIZE; case CONT_PTE_SIZE: return PMD_SIZE - CONT_PTE_SIZE; default: break; } return 0UL; } pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { size_t pagesize = 1UL << shift; entry = pte_mkhuge(entry); if (pagesize == CONT_PTE_SIZE) { entry = pte_mkcont(entry); } else if (pagesize == CONT_PMD_SIZE) { entry = pmd_pte(pmd_mkcont(pte_pmd(entry))); } else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) { pr_warn("%s: unrecognized huge page size 0x%lx\n", __func__, pagesize); } return entry; } void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) { int i, ncontig; size_t pgsize; ncontig = num_contig_ptes(sz, &pgsize); for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) __pte_clear(mm, addr, ptep); } pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { int ncontig; size_t pgsize; pte_t orig_pte = __ptep_get(ptep); if (!pte_cont(orig_pte)) return __ptep_get_and_clear(mm, addr, ptep); ncontig = find_num_contig(mm, addr, ptep, &pgsize); return get_clear_contig(mm, addr, ptep, pgsize, ncontig); } /* * huge_ptep_set_access_flags will update access flags (dirty, accesssed) * and write permission. * * For a contiguous huge pte range we need to check whether or not write * permission has to change only on the first pte in the set. Then for * all the contiguous ptes we need to check whether or not there is a * discrepancy between dirty or young. */ static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig) { int i; if (pte_write(pte) != pte_write(__ptep_get(ptep))) return 1; for (i = 0; i < ncontig; i++) { pte_t orig_pte = __ptep_get(ptep + i); if (pte_dirty(pte) != pte_dirty(orig_pte)) return 1; if (pte_young(pte) != pte_young(orig_pte)) return 1; } return 0; } int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { int ncontig, i; size_t pgsize = 0; unsigned long pfn = pte_pfn(pte), dpfn; struct mm_struct *mm = vma->vm_mm; pgprot_t hugeprot; pte_t orig_pte; if (!pte_cont(pte)) return __ptep_set_access_flags(vma, addr, ptep, pte, dirty); ncontig = find_num_contig(mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; if (!__cont_access_flags_changed(ptep, pte, ncontig)) return 0; orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); /* Make sure we don't lose the dirty or young state */ if (pte_dirty(orig_pte)) pte = pte_mkdirty(pte); if (pte_young(orig_pte)) pte = pte_mkyoung(pte); hugeprot = pte_pgprot(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); return 1; } void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long pfn, dpfn; pgprot_t hugeprot; int ncontig, i; size_t pgsize; pte_t pte; if (!pte_cont(__ptep_get(ptep))) { __ptep_set_wrprotect(mm, addr, ptep); return; } ncontig = find_num_contig(mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); pte = pte_wrprotect(pte); hugeprot = pte_pgprot(pte); pfn = pte_pfn(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); } pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { struct mm_struct *mm = vma->vm_mm; size_t pgsize; int ncontig; if (!pte_cont(__ptep_get(ptep))) return ptep_clear_flush(vma, addr, ptep); ncontig = find_num_contig(mm, addr, ptep, &pgsize); return get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); } static int __init hugetlbpage_init(void) { if (pud_sect_supported()) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT); return 0; } arch_initcall(hugetlbpage_init); bool __init arch_hugetlb_valid_size(unsigned long size) { return __hugetlb_valid_size(size); } pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) { /* * Break-before-make (BBM) is required for all user space mappings * when the permission changes from executable to non-executable * in cases where cpu is affected with errata #2645198. */ if (pte_user_exec(__ptep_get(ptep))) return huge_ptep_clear_flush(vma, addr, ptep); } return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); } void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } |
| 464 498 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* rwsem.h: R/W semaphores, public interface * * Written by David Howells (dhowells@redhat.com). * Derived from asm-i386/semaphore.h */ #ifndef _LINUX_RWSEM_H #define _LINUX_RWSEM_H #include <linux/linkage.h> #include <linux/types.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/err.h> #include <linux/cleanup.h> #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __RWSEM_DEP_MAP_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_SLEEP, \ }, #else # define __RWSEM_DEP_MAP_INIT(lockname) #endif #ifndef CONFIG_PREEMPT_RT #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #include <linux/osq_lock.h> #endif /* * For an uncontended rwsem, count and owner are the only fields a task * needs to touch when acquiring the rwsem. So they are put next to each * other to increase the chance that they will share the same cacheline. * * In a contended rwsem, the owner is likely the most frequently accessed * field in the structure as the optimistic waiter that holds the osq lock * will spin on owner. For an embedded rwsem, other hot fields in the * containing structure should be moved further away from the rwsem to * reduce the chance that they will share the same cacheline causing * cacheline bouncing problem. */ struct rw_semaphore { atomic_long_t count; /* * Write owner or one of the read owners as well flags regarding * the current state of the rwsem. Can be used as a speculative * check to see if the write owner is running on the cpu. */ atomic_long_t owner; #ifdef CONFIG_RWSEM_SPIN_ON_OWNER struct optimistic_spin_queue osq; /* spinner MCS lock */ #endif raw_spinlock_t wait_lock; struct list_head wait_list; #ifdef CONFIG_DEBUG_RWSEMS void *magic; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #define RWSEM_UNLOCKED_VALUE 0UL #define RWSEM_WRITER_LOCKED (1UL << 0) #define __RWSEM_COUNT_INIT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) static inline int rwsem_is_locked(struct rw_semaphore *sem) { return atomic_long_read(&sem->count) != RWSEM_UNLOCKED_VALUE; } static inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) { WARN_ON(atomic_long_read(&sem->count) == RWSEM_UNLOCKED_VALUE); } static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!(atomic_long_read(&sem->count) & RWSEM_WRITER_LOCKED)); } /* Common initializer macros and functions */ #ifdef CONFIG_DEBUG_RWSEMS # define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname, #else # define __RWSEM_DEBUG_INIT(lockname) #endif #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #define __RWSEM_OPT_INIT(lockname) .osq = OSQ_LOCK_UNLOCKED, #else #define __RWSEM_OPT_INIT(lockname) #endif #define __RWSEM_INITIALIZER(name) \ { __RWSEM_COUNT_INIT(name), \ .owner = ATOMIC_LONG_INIT(0), \ __RWSEM_OPT_INIT(name) \ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),\ .wait_list = LIST_HEAD_INIT((name).wait_list), \ __RWSEM_DEBUG_INIT(name) \ __RWSEM_DEP_MAP_INIT(name) } #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) extern void __init_rwsem(struct rw_semaphore *sem, const char *name, struct lock_class_key *key); #define init_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ __init_rwsem((sem), #sem, &__key); \ } while (0) /* * This is the same regardless of which rwsem implementation that is being used. * It is just a heuristic meant to be called by somebody already holding the * rwsem to see if somebody from an incompatible type is wanting access to the * lock. */ static inline int rwsem_is_contended(struct rw_semaphore *sem) { return !list_empty(&sem->wait_list); } #else /* !CONFIG_PREEMPT_RT */ #include <linux/rwbase_rt.h> struct rw_semaphore { struct rwbase_rt rwbase; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #define __RWSEM_INITIALIZER(name) \ { \ .rwbase = __RWBASE_INITIALIZER(name), \ __RWSEM_DEP_MAP_INIT(name) \ } #define DECLARE_RWSEM(lockname) \ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) extern void __init_rwsem(struct rw_semaphore *rwsem, const char *name, struct lock_class_key *key); #define init_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ __init_rwsem((sem), #sem, &__key); \ } while (0) static __always_inline int rwsem_is_locked(const struct rw_semaphore *sem) { return rw_base_is_locked(&sem->rwbase); } static __always_inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!rwsem_is_locked(sem)); } static __always_inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!rw_base_is_write_locked(&sem->rwbase)); } static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) { return rw_base_is_contended(&sem->rwbase); } #endif /* CONFIG_PREEMPT_RT */ /* * The functions below are the same for all rwsem implementations including * the RT specific variant. */ static inline void rwsem_assert_held(const struct rw_semaphore *sem) { if (IS_ENABLED(CONFIG_LOCKDEP)) lockdep_assert_held(sem); else rwsem_assert_held_nolockdep(sem); } static inline void rwsem_assert_held_write(const struct rw_semaphore *sem) { if (IS_ENABLED(CONFIG_LOCKDEP)) lockdep_assert_held_write(sem); else rwsem_assert_held_write_nolockdep(sem); } /* * lock for reading */ extern void down_read(struct rw_semaphore *sem); extern int __must_check down_read_interruptible(struct rw_semaphore *sem); extern int __must_check down_read_killable(struct rw_semaphore *sem); /* * trylock for reading -- returns 1 if successful, 0 if contention */ extern int down_read_trylock(struct rw_semaphore *sem); /* * lock for writing */ extern void down_write(struct rw_semaphore *sem); extern int __must_check down_write_killable(struct rw_semaphore *sem); /* * trylock for writing -- returns 1 if successful, 0 if contention */ extern int down_write_trylock(struct rw_semaphore *sem); /* * release a read lock */ extern void up_read(struct rw_semaphore *sem); /* * release a write lock */ extern void up_write(struct rw_semaphore *sem); DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T)) DEFINE_GUARD_COND(rwsem_read, _try, down_read_trylock(_T)) DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T) == 0) DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T)) DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T)) /* * downgrade write lock to read lock */ extern void downgrade_write(struct rw_semaphore *sem); #ifdef CONFIG_DEBUG_LOCK_ALLOC /* * nested locking. NOTE: rwsems are not allowed to recurse * (which occurs if the same task tries to acquire the same * lock instance multiple times), but multiple locks of the * same lock class might be taken, if the order of the locks * is always the same. This ordering rule can be expressed * to lockdep via the _nested() APIs, but enumerating the * subclasses that are used. (If the nesting relationship is * static then another method for expressing nested locking is * the explicit definition of lock class keys and the use of * lockdep_set_class() at lock initialization time. * See Documentation/locking/lockdep-design.rst for more details.) */ extern void down_read_nested(struct rw_semaphore *sem, int subclass); extern int __must_check down_read_killable_nested(struct rw_semaphore *sem, int subclass); extern void down_write_nested(struct rw_semaphore *sem, int subclass); extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass); extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock); # define down_write_nest_lock(sem, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ } while (0) /* * Take/release a lock when not the owner will release it. * * [ This API should be avoided as much as possible - the * proper abstraction for this case is completions. ] */ extern void down_read_non_owner(struct rw_semaphore *sem); extern void up_read_non_owner(struct rw_semaphore *sem); #else # define down_read_nested(sem, subclass) down_read(sem) # define down_read_killable_nested(sem, subclass) down_read_killable(sem) # define down_write_nest_lock(sem, nest_lock) down_write(sem) # define down_write_nested(sem, subclass) down_write(sem) # define down_write_killable_nested(sem, subclass) down_write_killable(sem) # define down_read_non_owner(sem) down_read(sem) # define up_read_non_owner(sem) up_read(sem) #endif #endif /* _LINUX_RWSEM_H */ |
| 25 2 18 6 4 1 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015, 2016 ARM Ltd. */ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <trace/events/kvm.h> #include <kvm/arm_vgic.h> #include "vgic.h" /* * vgic_irqfd_set_irq: inject the IRQ corresponding to the * irqchip routing entry * * This is the entry point for irqfd IRQ injection */ static int vgic_irqfd_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { unsigned int spi_id = e->irqchip.pin + VGIC_NR_PRIVATE_IRQS; if (!vgic_valid_spi(kvm, spi_id)) return -EINVAL; return kvm_vgic_inject_irq(kvm, NULL, spi_id, level, NULL); } /** * kvm_set_routing_entry: populate a kvm routing entry * from a user routing entry * * @kvm: the VM this entry is applied to * @e: kvm kernel routing entry handle * @ue: user api routing entry handle * return 0 on success, -EINVAL on errors. */ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; switch (ue->type) { case KVM_IRQ_ROUTING_IRQCHIP: e->set = vgic_irqfd_set_irq; e->irqchip.irqchip = ue->u.irqchip.irqchip; e->irqchip.pin = ue->u.irqchip.pin; if ((e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) || (e->irqchip.irqchip >= KVM_NR_IRQCHIPS)) goto out; break; case KVM_IRQ_ROUTING_MSI: e->set = kvm_set_msi; e->msi.address_lo = ue->u.msi.address_lo; e->msi.address_hi = ue->u.msi.address_hi; e->msi.data = ue->u.msi.data; e->msi.flags = ue->flags; e->msi.devid = ue->u.msi.devid; break; default: goto out; } r = 0; out: return r; } static void kvm_populate_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm_msi *msi) { msi->address_lo = e->msi.address_lo; msi->address_hi = e->msi.address_hi; msi->data = e->msi.data; msi->flags = e->msi.flags; msi->devid = e->msi.devid; } /* * kvm_set_msi: inject the MSI corresponding to the * MSI routing entry * * This is the entry point for irqfd MSI injection * and userspace MSI injection. */ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { struct kvm_msi msi; if (!vgic_has_its(kvm)) return -ENODEV; if (!level) return -1; kvm_populate_msi(e, &msi); return vgic_its_inject_msi(kvm, &msi); } /* * kvm_arch_set_irq_inatomic: fast-path for irqfd injection */ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { if (!level) return -EWOULDBLOCK; switch (e->type) { case KVM_IRQ_ROUTING_MSI: { struct kvm_msi msi; if (!vgic_has_its(kvm)) break; kvm_populate_msi(e, &msi); return vgic_its_inject_cached_translation(kvm, &msi); } case KVM_IRQ_ROUTING_IRQCHIP: /* * Injecting SPIs is always possible in atomic context * as long as the damn vgic is initialized. */ if (unlikely(!vgic_initialized(kvm))) break; return vgic_irqfd_set_irq(e, kvm, irq_source_id, 1, line_status); } return -EWOULDBLOCK; } int kvm_vgic_setup_default_irq_routing(struct kvm *kvm) { struct kvm_irq_routing_entry *entries; struct vgic_dist *dist = &kvm->arch.vgic; u32 nr = dist->nr_spis; int i, ret; entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL_ACCOUNT); if (!entries) return -ENOMEM; for (i = 0; i < nr; i++) { entries[i].gsi = i; entries[i].type = KVM_IRQ_ROUTING_IRQCHIP; entries[i].u.irqchip.irqchip = 0; entries[i].u.irqchip.pin = i; } ret = kvm_set_irq_routing(kvm, entries, nr, 0); kfree(entries); return ret; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Skb ref helpers. * */ #ifndef _LINUX_SKBUFF_REF_H #define _LINUX_SKBUFF_REF_H #include <linux/skbuff.h> /** * __skb_frag_ref - take an addition reference on a paged fragment. * @frag: the paged fragment * * Takes an additional reference on the paged fragment @frag. */ static inline void __skb_frag_ref(skb_frag_t *frag) { get_page(skb_frag_page(frag)); } /** * skb_frag_ref - take an addition reference on a paged fragment of an skb. * @skb: the buffer * @f: the fragment offset. * * Takes an additional reference on the @f'th paged fragment of @skb. */ static inline void skb_frag_ref(struct sk_buff *skb, int f) { __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } bool napi_pp_put_page(netmem_ref netmem); static inline void skb_page_unref(netmem_ref netmem, bool recycle) { #ifdef CONFIG_PAGE_POOL if (recycle && napi_pp_put_page(netmem)) return; #endif put_page(netmem_to_page(netmem)); } /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment * @recycle: recycle the page if allocated via page_pool * * Releases a reference on the paged fragment @frag * or recycles the page via the page_pool API. */ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { skb_page_unref(skb_frag_netmem(frag), recycle); } /** * skb_frag_unref - release a reference on a paged fragment of an skb. * @skb: the buffer * @f: the fragment offset * * Releases a reference on the @f'th paged fragment of @skb. */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { struct skb_shared_info *shinfo = skb_shinfo(skb); if (!skb_zcopy_managed(skb)) __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); } #endif /* _LINUX_SKBUFF_REF_H */ |
| 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mmap #if !defined(_TRACE_MMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MMAP_H #include <linux/tracepoint.h> TRACE_EVENT(vm_unmapped_area, TP_PROTO(unsigned long addr, struct vm_unmapped_area_info *info), TP_ARGS(addr, info), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, total_vm) __field(unsigned long, flags) __field(unsigned long, length) __field(unsigned long, low_limit) __field(unsigned long, high_limit) __field(unsigned long, align_mask) __field(unsigned long, align_offset) ), TP_fast_assign( __entry->addr = addr; __entry->total_vm = current->mm->total_vm; __entry->flags = info->flags; __entry->length = info->length; __entry->low_limit = info->low_limit; __entry->high_limit = info->high_limit; __entry->align_mask = info->align_mask; __entry->align_offset = info->align_offset; ), TP_printk("addr=0x%lx err=%ld total_vm=0x%lx flags=0x%lx len=0x%lx lo=0x%lx hi=0x%lx mask=0x%lx ofs=0x%lx", IS_ERR_VALUE(__entry->addr) ? 0 : __entry->addr, IS_ERR_VALUE(__entry->addr) ? __entry->addr : 0, __entry->total_vm, __entry->flags, __entry->length, __entry->low_limit, __entry->high_limit, __entry->align_mask, __entry->align_offset) ); TRACE_EVENT(vma_mas_szero, TP_PROTO(struct maple_tree *mt, unsigned long start, unsigned long end), TP_ARGS(mt, start, end), TP_STRUCT__entry( __field(struct maple_tree *, mt) __field(unsigned long, start) __field(unsigned long, end) ), TP_fast_assign( __entry->mt = mt; __entry->start = start; __entry->end = end; ), TP_printk("mt_mod %p, (NULL), SNULL, %lu, %lu,", __entry->mt, (unsigned long) __entry->start, (unsigned long) __entry->end ) ); TRACE_EVENT(vma_store, TP_PROTO(struct maple_tree *mt, struct vm_area_struct *vma), TP_ARGS(mt, vma), TP_STRUCT__entry( __field(struct maple_tree *, mt) __field(struct vm_area_struct *, vma) __field(unsigned long, vm_start) __field(unsigned long, vm_end) ), TP_fast_assign( __entry->mt = mt; __entry->vma = vma; __entry->vm_start = vma->vm_start; __entry->vm_end = vma->vm_end - 1; ), TP_printk("mt_mod %p, (%p), STORE, %lu, %lu,", __entry->mt, __entry->vma, (unsigned long) __entry->vm_start, (unsigned long) __entry->vm_end ) ); TRACE_EVENT(exit_mmap, TP_PROTO(struct mm_struct *mm), TP_ARGS(mm), TP_STRUCT__entry( __field(struct mm_struct *, mm) __field(struct maple_tree *, mt) ), TP_fast_assign( __entry->mm = mm; __entry->mt = &mm->mm_mt; ), TP_printk("mt_mod %p, DESTROY", __entry->mt ) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h> |
| 421 418 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fault-inject.h> #include <linux/debugfs.h> #include <linux/error-injection.h> #include <linux/mm.h> static struct { struct fault_attr attr; bool ignore_gfp_highmem; bool ignore_gfp_reclaim; u32 min_order; } fail_page_alloc = { .attr = FAULT_ATTR_INITIALIZER, .ignore_gfp_reclaim = true, .ignore_gfp_highmem = true, .min_order = 1, }; static int __init setup_fail_page_alloc(char *str) { return setup_fault_attr(&fail_page_alloc.attr, str); } __setup("fail_page_alloc=", setup_fail_page_alloc); bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { int flags = 0; if (order < fail_page_alloc.min_order) return false; if (gfp_mask & __GFP_NOFAIL) return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) return false; if (fail_page_alloc.ignore_gfp_reclaim && (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; /* See comment in __should_failslab() */ if (gfp_mask & __GFP_NOWARN) flags |= FAULT_NOWARN; return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags); } ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_page_alloc_debugfs(void) { umode_t mode = S_IFREG | 0600; struct dentry *dir; dir = fault_create_debugfs_attr("fail_page_alloc", NULL, &fail_page_alloc.attr); debugfs_create_bool("ignore-gfp-wait", mode, dir, &fail_page_alloc.ignore_gfp_reclaim); debugfs_create_bool("ignore-gfp-highmem", mode, dir, &fail_page_alloc.ignore_gfp_highmem); debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order); return 0; } late_initcall(fail_page_alloc_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Frame handler other utility functions for HSR and PRP. */ #include "hsr_slave.h" #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include "hsr_main.h" #include "hsr_device.h" #include "hsr_forward.h" #include "hsr_framereg.h" bool hsr_invalid_dan_ingress_frame(__be16 protocol) { return (protocol != htons(ETH_P_PRP) && protocol != htons(ETH_P_HSR)); } static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct hsr_port *port; struct hsr_priv *hsr; __be16 protocol; /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: skb invalid", __func__); return RX_HANDLER_PASS; } port = hsr_port_get_rcu(skb->dev); if (!port) goto finish_pass; hsr = port->hsr; if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) { /* Directly kill frames sent by ourselves */ kfree_skb(skb); goto finish_consume; } /* For HSR, only tagged frames are expected (unless the device offloads * HSR tag removal), but for PRP there could be non tagged frames as * well from Single attached nodes (SANs). */ protocol = eth_hdr(skb)->h_proto; if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && port->type != HSR_PT_INTERLINK && hsr->proto_ops->invalid_dan_ingress_frame && hsr->proto_ops->invalid_dan_ingress_frame(protocol)) goto finish_pass; skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || protocol == htons(ETH_P_HSR)) skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); skb_reset_mac_len(skb); /* Only the frames received over the interlink port will assign a * sequence number and require synchronisation vs other sender. */ if (port->type == HSR_PT_INTERLINK) { spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); } else { hsr_forward_skb(skb, port); } finish_consume: return RX_HANDLER_CONSUMED; finish_pass: return RX_HANDLER_PASS; } bool hsr_port_exists(const struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == hsr_handle_frame; } static int hsr_check_dev_ok(struct net_device *dev, struct netlink_ext_ack *extack) { /* Don't allow HSR on non-ethernet like devices */ if ((dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN) { NL_SET_ERR_MSG_MOD(extack, "Cannot use loopback or non-ethernet device as HSR slave."); return -EINVAL; } /* Don't allow enslaving hsr devices */ if (is_hsr_master(dev)) { NL_SET_ERR_MSG_MOD(extack, "Cannot create trees of HSR devices."); return -EINVAL; } if (hsr_port_exists(dev)) { NL_SET_ERR_MSG_MOD(extack, "This device is already a HSR slave."); return -EINVAL; } if (is_vlan_dev(dev)) { NL_SET_ERR_MSG_MOD(extack, "HSR on top of VLAN is not yet supported in this driver."); return -EINVAL; } if (dev->priv_flags & IFF_DONT_BRIDGE) { NL_SET_ERR_MSG_MOD(extack, "This device does not support bridging."); return -EOPNOTSUPP; } /* HSR over bonded devices has not been tested, but I'm not sure it * won't work... */ return 0; } /* Setup device to be added to the HSR bridge. */ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, struct hsr_port *port, struct netlink_ext_ack *extack) { struct net_device *hsr_dev; struct hsr_port *master; int res; /* Don't use promiscuous mode for offload since L2 frame forward * happens at the offloaded hardware. */ if (!port->hsr->fwd_offloaded) { res = dev_set_promiscuity(dev, 1); if (res) return res; } master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr_dev = master->dev; res = netdev_upper_dev_link(dev, hsr_dev, extack); if (res) goto fail_upper_dev_link; res = netdev_rx_handler_register(dev, hsr_handle_frame, port); if (res) goto fail_rx_handler; dev_disable_lro(dev); return 0; fail_rx_handler: netdev_upper_dev_unlink(dev, hsr_dev); fail_upper_dev_link: if (!port->hsr->fwd_offloaded) dev_set_promiscuity(dev, -1); return res; } int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, enum hsr_port_type type, struct netlink_ext_ack *extack) { struct hsr_port *port, *master; int res; if (type != HSR_PT_MASTER) { res = hsr_check_dev_ok(dev, extack); if (res) return res; } port = hsr_port_get_hsr(hsr, type); if (port) return -EBUSY; /* This port already exists */ port = kzalloc(sizeof(*port), GFP_KERNEL); if (!port) return -ENOMEM; port->hsr = hsr; port->dev = dev; port->type = type; if (type != HSR_PT_MASTER) { res = hsr_portdev_setup(hsr, dev, port, extack); if (res) goto fail_dev_setup; } list_add_tail_rcu(&port->port_list, &hsr->ports); synchronize_rcu(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); return 0; fail_dev_setup: kfree(port); return res; } void hsr_del_port(struct hsr_port *port) { struct hsr_priv *hsr; struct hsr_port *master; hsr = port->hsr; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); list_del_rcu(&port->port_list); if (port != master) { netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); if (!port->hsr->fwd_offloaded) dev_set_promiscuity(port->dev, -1); netdev_upper_dev_unlink(port->dev, master->dev); } synchronize_rcu(); kfree(port); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0 /* * device.h - generic, centralized driver model * * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2009 Novell Inc. * * See Documentation/driver-api/driver-model/ for more information. */ #ifndef _DEVICE_H_ #define _DEVICE_H_ #include <linux/dev_printk.h> #include <linux/energy_model.h> #include <linux/ioport.h> #include <linux/kobject.h> #include <linux/klist.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/compiler.h> #include <linux/types.h> #include <linux/mutex.h> #include <linux/pm.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/device/bus.h> #include <linux/device/class.h> #include <linux/device/driver.h> #include <linux/cleanup.h> #include <asm/device.h> struct device; struct device_private; struct device_driver; struct driver_private; struct module; struct class; struct subsys_private; struct device_node; struct fwnode_handle; struct iommu_group; struct dev_pin_info; struct dev_iommu; struct msi_device_data; /** * struct subsys_interface - interfaces to device functions * @name: name of the device function * @subsys: subsystem of the devices to attach to * @node: the list of functions registered at the subsystem * @add_dev: device hookup to device function handler * @remove_dev: device hookup to device function handler * * Simple interfaces attached to a subsystem. Multiple interfaces can * attach to a subsystem and its devices. Unlike drivers, they do not * exclusively claim or control devices. Interfaces usually represent * a specific functionality of a subsystem/class of devices. */ struct subsys_interface { const char *name; const struct bus_type *subsys; struct list_head node; int (*add_dev)(struct device *dev, struct subsys_interface *sif); void (*remove_dev)(struct device *dev, struct subsys_interface *sif); }; int subsys_interface_register(struct subsys_interface *sif); void subsys_interface_unregister(struct subsys_interface *sif); int subsys_system_register(const struct bus_type *subsys, const struct attribute_group **groups); int subsys_virtual_register(const struct bus_type *subsys, const struct attribute_group **groups); /* * The type of device, "struct device" is embedded in. A class * or bus can contain devices of different types * like "partitions" and "disks", "mouse" and "event". * This identifies the device type and carries type-specific * information, equivalent to the kobj_type of a kobject. * If "name" is specified, the uevent will contain it in * the DEVTYPE variable. */ struct device_type { const char *name; const struct attribute_group **groups; int (*uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); const struct dev_pm_ops *pm; }; /** * struct device_attribute - Interface for exporting device attributes. * @attr: sysfs attribute definition. * @show: Show handler. * @store: Store handler. */ struct device_attribute { struct attribute attr; ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf); ssize_t (*store)(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); }; /** * struct dev_ext_attribute - Exported device attribute with extra context. * @attr: Exported device attribute. * @var: Pointer to context. */ struct dev_ext_attribute { struct device_attribute attr; void *var; }; ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_int(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_int(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_string(struct device *dev, struct device_attribute *attr, char *buf); /** * DEVICE_ATTR - Define a device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Convenience macro for defining a struct device_attribute. * * For example, ``DEVICE_ATTR(foo, 0644, foo_show, foo_store);`` expands to: * * .. code-block:: c * * struct device_attribute dev_attr_foo = { * .attr = { .name = "foo", .mode = 0644 }, * .show = foo_show, * .store = foo_store, * }; */ #define DEVICE_ATTR(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store) /** * DEVICE_ATTR_PREALLOC - Define a preallocated device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Like DEVICE_ATTR(), but ``SYSFS_PREALLOC`` is set on @_mode. */ #define DEVICE_ATTR_PREALLOC(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_PREALLOC(_name, _mode, _show, _store) /** * DEVICE_ATTR_RW - Define a read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0644, @_show is <_name>_show, * and @_store is <_name>_store. */ #define DEVICE_ATTR_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW(_name) /** * DEVICE_ATTR_ADMIN_RW - Define an admin-only read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RW(), but @_mode is 0600. */ #define DEVICE_ATTR_ADMIN_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600) /** * DEVICE_ATTR_RO - Define a readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0444 and @_show is <_name>_show. */ #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) /** * DEVICE_ATTR_ADMIN_RO - Define an admin-only readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RO(), but @_mode is 0400. */ #define DEVICE_ATTR_ADMIN_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400) /** * DEVICE_ATTR_WO - Define an admin-only writable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0200 and @_store is <_name>_store. */ #define DEVICE_ATTR_WO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_WO(_name) /** * DEVICE_ULONG_ATTR - Define a device attribute backed by an unsigned long. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of unsigned long. * * Like DEVICE_ATTR(), but @_show and @_store are automatically provided * such that reads and writes to the attribute from userspace affect @_var. */ #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } /** * DEVICE_INT_ATTR - Define a device attribute backed by an int. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of int. * * Like DEVICE_ULONG_ATTR(), but @_var is an int. */ #define DEVICE_INT_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) } /** * DEVICE_BOOL_ATTR - Define a device attribute backed by a bool. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of bool. * * Like DEVICE_ULONG_ATTR(), but @_var is a bool. */ #define DEVICE_BOOL_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) } /** * DEVICE_STRING_ATTR_RO - Define a device attribute backed by a r/o string. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of string. * * Like DEVICE_ULONG_ATTR(), but @_var is a string. Because the length of the * string allocation is unknown, the attribute must be read-only. */ #define DEVICE_STRING_ATTR_RO(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, (_mode) & ~0222, device_show_string, NULL), (_var) } #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) int device_create_file(struct device *device, const struct device_attribute *entry); void device_remove_file(struct device *dev, const struct device_attribute *attr); bool device_remove_file_self(struct device *dev, const struct device_attribute *attr); int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr); /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name) __malloc; #define devres_alloc(release, size, gfp) \ __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) #define devres_alloc_node(release, size, gfp, nid) \ __devres_alloc_node(release, size, gfp, nid, #release) void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), void *data); void devres_free(void *res); void devres_add(struct device *dev, void *res); void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data); void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); /* devres group */ void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); void devres_close_group(struct device *dev, void *id); void devres_remove_group(struct device *dev, void *id); int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __alloc_size(2); void *devm_krealloc(struct device *dev, void *ptr, size_t size, gfp_t gfp) __must_check __realloc_size(3); __printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap) __malloc; __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...) __malloc; static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) { return devm_kmalloc(dev, size, gfp | __GFP_ZERO); } static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return devm_kmalloc(dev, bytes, flags); } static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags) { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } static inline __realloc_size(3, 4) void * __must_check devm_krealloc_array(struct device *dev, void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return devm_krealloc(dev, p, bytes, flags); } void devm_kfree(struct device *dev, const void *p); char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp) __realloc_size(3); unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order); void devm_free_pages(struct device *dev, unsigned long addr); #ifdef CONFIG_HAS_IOMEM void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res); void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size); #else static inline void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res) { return ERR_PTR(-EINVAL); } static inline void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res) { return ERR_PTR(-EINVAL); } static inline void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size) { return ERR_PTR(-EINVAL); } #endif /* allows to add/remove a custom action to devres stack */ void devm_remove_action(struct device *dev, void (*action)(void *), void *data); void devm_release_action(struct device *dev, void (*action)(void *), void *data); int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); #define devm_add_action(dev, action, data) \ __devm_add_action(dev, action, data, #action) static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), void *data, const char *name) { int ret; ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } #define devm_add_action_or_reset(dev, action, data) \ __devm_add_action_or_reset(dev, action, data, #action) /** * devm_alloc_percpu - Resource-managed alloc_percpu * @dev: Device to allocate per-cpu memory for * @type: Type to allocate per-cpu memory for * * Managed alloc_percpu. Per-cpu memory allocated with this function is * automatically freed on driver detach. * * RETURNS: * Pointer to allocated memory on success, NULL on failure. */ #define devm_alloc_percpu(dev, type) \ ((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \ __alignof__(type))) void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, size_t align); void devm_free_percpu(struct device *dev, void __percpu *pdata); struct device_dma_parameters { /* * a low level driver may set these to teach IOMMU code about * sg limitations. */ unsigned int max_segment_size; unsigned int min_align_mask; unsigned long segment_boundary_mask; }; /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. * @DL_STATE_DORMANT: None of the supplier/consumer drivers is present. * @DL_STATE_AVAILABLE: The supplier driver is present, but the consumer is not. * @DL_STATE_CONSUMER_PROBE: The consumer is probing (supplier driver present). * @DL_STATE_ACTIVE: Both the supplier and consumer drivers are present. * @DL_STATE_SUPPLIER_UNBIND: The supplier driver is unbinding. */ enum device_link_state { DL_STATE_NONE = -1, DL_STATE_DORMANT = 0, DL_STATE_AVAILABLE, DL_STATE_CONSUMER_PROBE, DL_STATE_ACTIVE, DL_STATE_SUPPLIER_UNBIND, }; /* * Device link flags. * * STATELESS: The core will not remove this link automatically. * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. * MANAGED: The core tracks presence of supplier/consumer drivers (internal). * SYNC_STATE_ONLY: Link only affects sync_state() behavior. * INFERRED: Inferred from data (eg: firmware) and not from driver actions. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) #define DL_FLAG_INFERRED BIT(8) #define DL_FLAG_CYCLE BIT(9) /** * enum dl_dev_state - Device driver presence tracking information. * @DL_DEV_NO_DRIVER: There is no driver attached to the device. * @DL_DEV_PROBING: A driver is probing. * @DL_DEV_DRIVER_BOUND: The driver has been bound to the device. * @DL_DEV_UNBINDING: The driver is unbinding from the device. */ enum dl_dev_state { DL_DEV_NO_DRIVER = 0, DL_DEV_PROBING, DL_DEV_DRIVER_BOUND, DL_DEV_UNBINDING, }; /** * enum device_removable - Whether the device is removable. The criteria for a * device to be classified as removable is determined by its subsystem or bus. * @DEVICE_REMOVABLE_NOT_SUPPORTED: This attribute is not supported for this * device (default). * @DEVICE_REMOVABLE_UNKNOWN: Device location is Unknown. * @DEVICE_FIXED: Device is not removable by the user. * @DEVICE_REMOVABLE: Device is removable by the user. */ enum device_removable { DEVICE_REMOVABLE_NOT_SUPPORTED = 0, /* must be 0 */ DEVICE_REMOVABLE_UNKNOWN, DEVICE_FIXED, DEVICE_REMOVABLE, }; /** * struct dev_links_info - Device data related to device links. * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @defer_sync: Hook to global list of devices that have deferred sync_state. * @status: Driver status information. */ struct dev_links_info { struct list_head suppliers; struct list_head consumers; struct list_head defer_sync; enum dl_dev_state status; }; /** * struct dev_msi_info - Device data related to MSI * @domain: The MSI interrupt domain associated to the device * @data: Pointer to MSI device data */ struct dev_msi_info { #ifdef CONFIG_GENERIC_MSI_IRQ struct irq_domain *domain; struct msi_device_data *data; #endif }; /** * enum device_physical_location_panel - Describes which panel surface of the * system's housing the device connection point resides on. * @DEVICE_PANEL_TOP: Device connection point is on the top panel. * @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel. * @DEVICE_PANEL_LEFT: Device connection point is on the left panel. * @DEVICE_PANEL_RIGHT: Device connection point is on the right panel. * @DEVICE_PANEL_FRONT: Device connection point is on the front panel. * @DEVICE_PANEL_BACK: Device connection point is on the back panel. * @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown. */ enum device_physical_location_panel { DEVICE_PANEL_TOP, DEVICE_PANEL_BOTTOM, DEVICE_PANEL_LEFT, DEVICE_PANEL_RIGHT, DEVICE_PANEL_FRONT, DEVICE_PANEL_BACK, DEVICE_PANEL_UNKNOWN, }; /** * enum device_physical_location_vertical_position - Describes vertical * position of the device connection point on the panel surface. * @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel. * @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel. */ enum device_physical_location_vertical_position { DEVICE_VERT_POS_UPPER, DEVICE_VERT_POS_CENTER, DEVICE_VERT_POS_LOWER, }; /** * enum device_physical_location_horizontal_position - Describes horizontal * position of the device connection point on the panel surface. * @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel. * @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel. */ enum device_physical_location_horizontal_position { DEVICE_HORI_POS_LEFT, DEVICE_HORI_POS_CENTER, DEVICE_HORI_POS_RIGHT, }; /** * struct device_physical_location - Device data related to physical location * of the device connection point. * @panel: Panel surface of the system's housing that the device connection * point resides on. * @vertical_position: Vertical position of the device connection point within * the panel. * @horizontal_position: Horizontal position of the device connection point * within the panel. * @dock: Set if the device connection point resides in a docking station or * port replicator. * @lid: Set if this device connection point resides on the lid of laptop * system. */ struct device_physical_location { enum device_physical_location_panel panel; enum device_physical_location_vertical_position vertical_position; enum device_physical_location_horizontal_position horizontal_position; bool dock; bool lid; }; /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. * In most cases, a parent device is some sort of bus or host * controller. If parent is NULL, the device, is a top-level device, * which is not usually what you want. * @p: Holds the private data of the driver core portions of the device. * See the comment of the struct device_private for detail. * @kobj: A top-level, abstract class from which other classes are derived. * @init_name: Initial name of the device. * @type: The type of device. * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. * Example: For devices on custom boards, as typical of embedded * and SOC based hardware, Linux often uses platform_data to point * to board-specific structures describing devices and how they * are wired. That can include what ports are available, chip * variants, which GPIO pins act in what additional roles, and so * on. This shrinks the "Board Support Packages" (BSPs) and * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. * @links: Links to suppliers and consumers of this device. * @power: For device power management. * See Documentation/driver-api/pm/devices.rst for details. * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. * @msi: MSI related data * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations * such descriptors. * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller * DMA limit than the device itself supports. * @dma_range_map: map for DMA memory ranges relative to that of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. * @cma_area: Contiguous memory area for dma allocations * @dma_io_tlb_mem: Software IO TLB allocator. Not for driver use. * @dma_io_tlb_pools: List of transient swiotlb memory pools. * @dma_io_tlb_lock: Protects changes to the list of active pools. * @dma_uses_io_tlb: %true if device has used the software IO TLB. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. * @fwnode: Associated device node supplied by platform firmware. * @devt: For creating the sysfs "dev". * @id: device instance * @devres_lock: Spinlock to protect the resource of the device. * @devres_head: The resources list of the device. * @class: The class of the device. * @groups: Optional attribute groups. * @release: Callback to free the device after all references have * gone away. This should be set by the allocator of the * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data * @physical_location: Describes physical location of the device connection * point in the system housing. * @removable: Whether the device can be removed from the system. This * should be set by the subsystem / bus driver that discovered * the device. * * @offline_disabled: If set, the device is permanently online. * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. * @state_synced: The hardware state of this device has been synced to match * the software state of this device by calling the driver/bus * sync_state() callback. * @can_match: The device has matched with a driver at least once or it is in * a bus (like AMBA) which can't check for matching drivers until * other devices probe successfully. * @dma_coherent: this particular device is dma coherent, even if the * architecture supports non-coherent devices. * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the * streaming DMA operations (->map_* / ->unmap_* / ->sync_*), * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers. * @dma_iommu: Device is using default IOMMU implementation for DMA and * doesn't rely on dma_ops structure. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information * that the device model core needs to model the system. Most subsystems, * however, track additional information about the devices they host. As a * result, it is rare for devices to be represented by bare device structures; * instead, that structure, like kobject structures, is usually embedded within * a higher-level representation of the device. */ struct device { struct kobject kobj; struct device *parent; struct device_private *p; const char *init_name; /* initial name of the device */ const struct device_type *type; const struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ struct mutex mutex; /* mutex to synchronize calls to * its driver. */ struct dev_links_info links; struct dev_pm_info power; struct dev_pm_domain *pm_domain; #ifdef CONFIG_ENERGY_MODEL struct em_perf_domain *em_pd; #endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif struct dev_msi_info msi; #ifdef CONFIG_ARCH_HAS_DMA_OPS const struct dma_map_ops *dma_ops; #endif u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ u64 bus_dma_limit; /* upstream dma constraint */ const struct bus_dma_region *dma_range_map; struct device_dma_parameters *dma_parms; struct list_head dma_pools; /* dma pools (if dma'ble) */ #ifdef CONFIG_DMA_DECLARE_COHERENT struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ #endif #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ #endif #ifdef CONFIG_SWIOTLB struct io_tlb_mem *dma_io_tlb_mem; #endif #ifdef CONFIG_SWIOTLB_DYNAMIC struct list_head dma_io_tlb_pools; spinlock_t dma_io_tlb_lock; bool dma_uses_io_tlb; #endif /* arch specific additions */ struct dev_archdata archdata; struct device_node *of_node; /* associated device tree node */ struct fwnode_handle *fwnode; /* firmware device node */ #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ #endif dev_t devt; /* dev_t, creates the sysfs "dev" */ u32 id; /* device instance */ spinlock_t devres_lock; struct list_head devres_head; const struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); struct iommu_group *iommu_group; struct dev_iommu *iommu; struct device_physical_location *physical_location; enum device_removable removable; bool offline_disabled:1; bool offline:1; bool of_node_reused:1; bool state_synced:1; bool can_match:1; #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) bool dma_coherent:1; #endif #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif #ifdef CONFIG_DMA_NEED_SYNC bool dma_skip_sync:1; #endif #ifdef CONFIG_IOMMU_DMA bool dma_iommu:1; #endif }; /** * struct device_link - Device link representation. * @supplier: The device on the supplier end of the link. * @s_node: Hook to the supplier device's list of links to consumers. * @consumer: The device on the consumer end of the link. * @c_node: Hook to the consumer device's list of links to suppliers. * @link_dev: device used to expose link details in sysfs * @status: The state of the link (with respect to the presence of drivers). * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { struct device *supplier; struct list_head s_node; struct device *consumer; struct list_head c_node; struct device link_dev; enum device_link_state status; u32 flags; refcount_t rpm_active; struct kref kref; struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; #define kobj_to_dev(__kobj) container_of_const(__kobj, struct device, kobj) /** * device_iommu_mapped - Returns true when the device DMA is translated * by an IOMMU * @dev: Device to perform the check on */ static inline bool device_iommu_mapped(struct device *dev) { return (dev->iommu_group != NULL); } /* Get the wakeup routines, which depend on struct device */ #include <linux/pm_wakeup.h> /** * dev_name - Return a device's name. * @dev: Device with name to get. * Return: The kobject name of the device, or its initial name if unavailable. */ static inline const char *dev_name(const struct device *dev) { /* Use the init name until the kobject becomes available */ if (dev->init_name) return dev->init_name; return kobject_name(&dev->kobj); } /** * dev_bus_name - Return a device's bus/class name, if at all possible * @dev: struct device to get the bus/class name of * * Will return the name of the bus/class the device is attached to. If it is * not attached to a bus/class, an empty string will be returned. */ static inline const char *dev_bus_name(const struct device *dev) { return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : ""); } __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA static inline int dev_to_node(struct device *dev) { return dev->numa_node; } static inline void set_dev_node(struct device *dev, int node) { dev->numa_node = node; } #else static inline int dev_to_node(struct device *dev) { return NUMA_NO_NODE; } static inline void set_dev_node(struct device *dev, int node) { } #endif static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { #ifdef CONFIG_GENERIC_MSI_IRQ return dev->msi.domain; #else return NULL; #endif } static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { #ifdef CONFIG_GENERIC_MSI_IRQ dev->msi.domain = d; #endif } static inline void *dev_get_drvdata(const struct device *dev) { return dev->driver_data; } static inline void dev_set_drvdata(struct device *dev, void *data) { dev->driver_data = data; } static inline struct pm_subsys_data *dev_to_psd(struct device *dev) { return dev ? dev->power.subsys_data : NULL; } static inline unsigned int dev_get_uevent_suppress(const struct device *dev) { return dev->kobj.uevent_suppress; } static inline void dev_set_uevent_suppress(struct device *dev, int val) { dev->kobj.uevent_suppress = val; } static inline int device_is_registered(struct device *dev) { return dev->kobj.state_in_sysfs; } static inline void device_enable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = false; } static inline bool device_async_suspend_enabled(struct device *dev) { return !!dev->power.async_suspend; } static inline bool device_pm_not_required(struct device *dev) { return dev->power.no_pm; } static inline void device_set_pm_not_required(struct device *dev) { dev->power.no_pm = true; } static inline void dev_pm_syscore_device(struct device *dev, bool val) { #ifdef CONFIG_PM_SLEEP dev->power.syscore = val; #endif } static inline void dev_pm_set_driver_flags(struct device *dev, u32 flags) { dev->power.driver_flags = flags; } static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags) { return !!(dev->power.driver_flags & flags); } static inline void device_lock(struct device *dev) { mutex_lock(&dev->mutex); } static inline int device_lock_interruptible(struct device *dev) { return mutex_lock_interruptible(&dev->mutex); } static inline int device_trylock(struct device *dev) { return mutex_trylock(&dev->mutex); } static inline void device_unlock(struct device *dev) { mutex_unlock(&dev->mutex); } DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T)) static inline void device_lock_assert(struct device *dev) { lockdep_assert_held(&dev->mutex); } static inline bool dev_has_sync_state(struct device *dev) { if (!dev) return false; if (dev->driver && dev->driver->sync_state) return true; if (dev->bus && dev->bus->sync_state) return true; return false; } static inline void dev_set_removable(struct device *dev, enum device_removable removable) { dev->removable = removable; } static inline bool dev_is_removable(struct device *dev) { return dev->removable == DEVICE_REMOVABLE; } static inline bool dev_removable_is_valid(struct device *dev) { return dev->removable != DEVICE_REMOVABLE_NOT_SUPPORTED; } /* * High level routines for use by the bus drivers */ int __must_check device_register(struct device *dev); void device_unregister(struct device *dev); void device_initialize(struct device *dev); int __must_check device_add(struct device *dev); void device_del(struct device *dev); DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); struct device *device_find_child_by_name(struct device *parent, const char *name); struct device *device_find_any_child(struct device *parent); int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); static inline bool device_supports_offline(struct device *dev) { return dev->bus && dev->bus->offline && dev->bus->online; } #define __device_lock_set_class(dev, name, key) \ do { \ struct device *__d2 __maybe_unused = dev; \ lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \ } while (0) /** * device_lock_set_class - Specify a temporary lock class while a device * is attached to a driver * @dev: device to modify * @key: lock class key data * * This must be called with the device_lock() already held, for example * from driver ->probe(). Take care to only override the default * lockdep_no_validate class. */ #ifdef CONFIG_LOCKDEP #define device_lock_set_class(dev, key) \ do { \ struct device *__d = dev; \ dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex, \ &__lockdep_no_validate__), \ "overriding existing custom lock class\n"); \ __device_lock_set_class(__d, #key, key); \ } while (0) #else #define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key) #endif /** * device_lock_reset_class - Return a device to the default lockdep novalidate state * @dev: device to modify * * This must be called with the device_lock() already held, for example * from driver ->remove(). */ #define device_lock_reset_class(dev) \ do { \ struct device *__d __maybe_unused = dev; \ lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex", \ _THIS_IP_); \ } while (0) void lock_device_hotplug(void); void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); int device_offline(struct device *dev); int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_node(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); static inline struct device_node *dev_of_node(struct device *dev) { if (!IS_ENABLED(CONFIG_OF) || !dev) return NULL; return dev->of_node; } static inline int dev_num_vf(struct device *dev) { if (dev->bus && dev->bus->num_vf) return dev->bus->num_vf(dev); return 0; } /* * Root device objects for grouping under /sys/devices */ struct device *__root_device_register(const char *name, struct module *owner); /* This is a macro to avoid include problems with THIS_MODULE */ #define root_device_register(name) \ __root_device_register(name, THIS_MODULE) void root_device_unregister(struct device *root); static inline void *dev_get_platdata(const struct device *dev) { return dev->platform_data; } /* * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ int __must_check device_driver_attach(const struct device_driver *drv, struct device *dev); int __must_check device_bind_driver(struct device *dev); void device_release_driver(struct device *dev); int __must_check device_attach(struct device *dev); int __must_check driver_attach(const struct device_driver *drv); void device_initial_probe(struct device *dev); int __must_check device_reprobe(struct device *dev); bool device_is_bound(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * device_create(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); void device_destroy(const struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); void device_remove_groups(struct device *dev, const struct attribute_group **groups); static inline int __must_check device_add_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_add_groups(dev, groups); } static inline void device_remove_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_remove_groups(dev, groups); } int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); /* * get_device - atomically increment the reference count for the device. * */ struct device *get_device(struct device *dev); void put_device(struct device *dev); DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T)) bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_mount(void); #else static inline int devtmpfs_mount(void) { return 0; } #endif /* drivers/base/power/shutdown.c */ void device_shutdown(void); /* debugging and troubleshooting/diagnostic helpers. */ const char *dev_driver_string(const struct device *dev); /* Device links interface. */ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); void device_link_wait_removal(void); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") #endif /* _DEVICE_H_ */ |
| 198 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sock #if !defined(_TRACE_SOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SOCK_H #include <net/sock.h> #include <net/ipv6.h> #include <linux/tracepoint.h> #include <linux/ipv6.h> #include <linux/tcp.h> #include <trace/events/net_probe_common.h> #define family_names \ EM(AF_INET) \ EMe(AF_INET6) /* The protocol traced by inet_sock_set_state */ #define inet_protocol_names \ EM(IPPROTO_TCP) \ EM(IPPROTO_DCCP) \ EM(IPPROTO_SCTP) \ EMe(IPPROTO_MPTCP) #define tcp_state_names \ EM(TCP_ESTABLISHED) \ EM(TCP_SYN_SENT) \ EM(TCP_SYN_RECV) \ EM(TCP_FIN_WAIT1) \ EM(TCP_FIN_WAIT2) \ EM(TCP_TIME_WAIT) \ EM(TCP_CLOSE) \ EM(TCP_CLOSE_WAIT) \ EM(TCP_LAST_ACK) \ EM(TCP_LISTEN) \ EM(TCP_CLOSING) \ EMe(TCP_NEW_SYN_RECV) #define skmem_kind_names \ EM(SK_MEM_SEND) \ EMe(SK_MEM_RECV) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); family_names inet_protocol_names tcp_state_names skmem_kind_names #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } #define show_family_name(val) \ __print_symbolic(val, family_names) #define show_inet_protocol_name(val) \ __print_symbolic(val, inet_protocol_names) #define show_tcp_state_name(val) \ __print_symbolic(val, tcp_state_names) #define show_skmem_kind_names(val) \ __print_symbolic(val, skmem_kind_names) TRACE_EVENT(sock_rcvqueue_full, TP_PROTO(struct sock *sk, struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( __field(int, rmem_alloc) __field(unsigned int, truesize) __field(int, sk_rcvbuf) ), TP_fast_assign( __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->truesize = skb->truesize; __entry->sk_rcvbuf = READ_ONCE(sk->sk_rcvbuf); ), TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d", __entry->rmem_alloc, __entry->truesize, __entry->sk_rcvbuf) ); TRACE_EVENT(sock_exceed_buf_limit, TP_PROTO(struct sock *sk, struct proto *prot, long allocated, int kind), TP_ARGS(sk, prot, allocated, kind), TP_STRUCT__entry( __array(char, name, 32) __array(long, sysctl_mem, 3) __field(long, allocated) __field(int, sysctl_rmem) __field(int, rmem_alloc) __field(int, sysctl_wmem) __field(int, wmem_alloc) __field(int, wmem_queued) __field(int, kind) ), TP_fast_assign( strscpy(__entry->name, prot->name, 32); __entry->sysctl_mem[0] = READ_ONCE(prot->sysctl_mem[0]); __entry->sysctl_mem[1] = READ_ONCE(prot->sysctl_mem[1]); __entry->sysctl_mem[2] = READ_ONCE(prot->sysctl_mem[2]); __entry->allocated = allocated; __entry->sysctl_rmem = sk_get_rmem0(sk, prot); __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->sysctl_wmem = sk_get_wmem0(sk, prot); __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc); __entry->wmem_queued = READ_ONCE(sk->sk_wmem_queued); __entry->kind = kind; ), TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld sysctl_rmem=%d rmem_alloc=%d sysctl_wmem=%d wmem_alloc=%d wmem_queued=%d kind=%s", __entry->name, __entry->sysctl_mem[0], __entry->sysctl_mem[1], __entry->sysctl_mem[2], __entry->allocated, __entry->sysctl_rmem, __entry->rmem_alloc, __entry->sysctl_wmem, __entry->wmem_alloc, __entry->wmem_queued, show_skmem_kind_names(__entry->kind) ) ); TRACE_EVENT(inet_sock_set_state, TP_PROTO(const struct sock *sk, const int oldstate, const int newstate), TP_ARGS(sk, oldstate, newstate), TP_STRUCT__entry( __field(const void *, skaddr) __field(int, oldstate) __field(int, newstate) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __entry->oldstate = oldstate; __entry->newstate = newstate; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->oldstate), show_tcp_state_name(__entry->newstate)) ); TRACE_EVENT(inet_sk_error_report, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(int, error) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->error = sk->sk_err; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c error=%d", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->error) ); TRACE_EVENT(sk_data_ready, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, family) __field(__u16, protocol) __field(unsigned long, ip) ), TP_fast_assign( __entry->skaddr = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ip = _RET_IP_; ), TP_printk("family=%u protocol=%u func=%ps", __entry->family, __entry->protocol, (void *)__entry->ip) ); /* * sock send/recv msg length */ DECLARE_EVENT_CLASS(sock_msg_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags), TP_STRUCT__entry( __field(void *, sk) __field(__u16, family) __field(__u16, protocol) __field(int, ret) __field(int, flags) ), TP_fast_assign( __entry->sk = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ret = ret; __entry->flags = flags; ), TP_printk("sk address = %p, family = %s protocol = %s, length = %d, error = %d, flags = 0x%x", __entry->sk, show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), !(__entry->flags & MSG_PEEK) ? (__entry->ret > 0 ? __entry->ret : 0) : 0, __entry->ret < 0 ? __entry->ret : 0, __entry->flags) ); DEFINE_EVENT(sock_msg_length, sock_send_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); DEFINE_EVENT(sock_msg_length, sock_recv_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); #endif /* _TRACE_SOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io */ /* Devmaps primary use is as a backend map for XDP BPF helper call * bpf_redirect_map(). Because XDP is mostly concerned with performance we * spent some effort to ensure the datapath with redirect maps does not use * any locking. This is a quick note on the details. * * We have three possible paths to get into the devmap control plane bpf * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall * will invoke an update, delete, or lookup operation. To ensure updates and * deletes appear atomic from the datapath side xchg() is used to modify the * netdev_map array. Then because the datapath does a lookup into the netdev_map * array (read-only) from an RCU critical section we use call_rcu() to wait for * an rcu grace period before free'ing the old data structures. This ensures the * datapath always has a valid copy. However, the datapath does a "flush" * operation that pushes any pending packets in the driver outside the RCU * critical section. Each bpf_dtab_netdev tracks these pending operations using * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until * this list is empty, indicating outstanding flush operations have completed. * * BPF syscalls may race with BPF program calls on any of the update, delete * or lookup operations. As noted above the xchg() operation also keep the * netdev_map consistent in this case. From the devmap side BPF programs * calling into these operations are the same as multiple user space threads * making system calls. * * Finally, any of the above may race with a netdev_unregister notifier. The * unregister notifier must search for net devices in the map structure that * contain a reference to the net device and remove them. This is a two step * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b) * check to see if the ifindex is the same as the net_device being removed. * When removing the dev a cmpxchg() is used to ensure the correct dev is * removed, in the case of a concurrent update or delete operation it is * possible that the initially referenced dev is no longer in the map. As the * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. * * The devmap_hash type is a map type which interprets keys as ifindexes and * indexes these using a hashmap. This allows maps that use ifindex as key to be * densely packed instead of having holes in the lookup array for unused * ifindexes. The setup and packet enqueue/send code is shared between the two * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> #include <linux/btf_ids.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; struct net_device *dev; struct net_device *dev_rx; struct bpf_prog *xdp_prog; unsigned int count; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; struct bpf_devmap_val val; }; struct bpf_dtab { struct bpf_map map; struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ struct hlist_head *dev_index_head; spinlock_t index_lock; unsigned int items; u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); static struct hlist_head *dev_map_create_hash(unsigned int entries, int numa_node) { int i; struct hlist_head *hash; hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, int idx) { return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; } static int dev_map_alloc_check(union bpf_attr *attr) { u32 valsize = attr->value_size; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex * 8 bytes: ifindex + prog fd */ if (attr->max_entries == 0 || attr->key_size != 4 || (valsize != offsetofend(struct bpf_devmap_val, ifindex) && valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return -EINVAL; if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2; roundup_pow_of_two() * can overflow into UB on 32-bit arches */ if (attr->max_entries > 1UL << 31) return -EINVAL; } return 0; } static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2 */ dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) return -ENOMEM; } return 0; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; int err; dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE); if (!dtab) return ERR_PTR(-ENOMEM); err = dev_map_init_map(dtab, attr); if (err) { bpf_map_area_free(dtab); return ERR_PTR(err); } spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; } static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); int i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were * disconnected from events. The following synchronize_rcu() guarantees * both rcu read critical sections complete and waits for * preempt-disable regions (NAPI being the relevant context here) so we * are certain there will be no further reads against the netdev_map and * all flush operations are complete. Flush operations can only be done * from NAPI context for this reason. */ spin_lock(&dev_map_lock); list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); /* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map() * during NAPI callback and cleared after the XDP redirect. There is no * explicit RCU read section which protects bpf_redirect_info->map but * local_bh_disable() also marks the beginning an RCU section. This * makes the complete softirq callback RCU protected. Thus after * following synchronize_rcu() there no bpf_redirect_info->map == map * assignment. */ synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ rcu_barrier(); if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } } bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } bpf_map_area_free(dtab->netdev_map); } bpf_map_area_free(dtab); } static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = next_key; if (index >= dtab->map.max_entries) { *next = 0; return 0; } if (index == dtab->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct hlist_head *head = dev_map_index_hash(dtab, key); struct bpf_dtab_netdev *dev; hlist_for_each_entry_rcu(dev, head, index_hlist, lockdep_is_held(&dtab->index_lock)) if (dev->idx == key) return dev; return NULL; } static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 idx, *next = next_key; struct bpf_dtab_netdev *dev, *next_dev; struct hlist_head *head; int i = 0; if (!key) goto find_first; idx = *(u32 *)key; dev = __dev_map_hash_lookup_elem(map, idx); if (!dev) goto find_first; next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } i = idx & (dtab->n_buckets - 1); i++; find_first: for (; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } } return -ENOENT; } static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, struct net_device *dev) { struct xdp_txq_info txq = { .dev = dev }; struct xdp_buff xdp; int i, nframes = 0; for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; u32 act; int err; xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: err = xdp_update_frame_from_buff(&xdp, xdpf); if (unlikely(err < 0)) xdp_return_frame_rx_napi(xdpf); else frames[nframes++] = xdpf; break; default: bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); break; } } return nframes; /* sent frames count */ } static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; unsigned int cnt = bq->count; int sent = 0, err = 0; int to_send = cnt; int i; if (unlikely(!cnt)) return; for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } if (bq->xdp_prog) { to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev); if (!to_send) goto out; } sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { /* If ndo_xdp_xmit fails with an errno, no frames have * been xmit'ed. */ err = sent; sent = 0; } /* If not all frames have been transmitted, it is our * responsibility to free them */ for (i = sent; unlikely(i < to_send); i++) xdp_return_frame_rx_napi(bq->q[i]); out: bq->count = 0; trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } /* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the * driver before returning from its napi->poll() routine. See the comment above * xdp_do_flush() in filter.c. */ void __dev_flush(struct list_head *flush_list) { struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); } } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; obj = rcu_dereference_check(dtab->netdev_map[key], rcu_read_lock_bh_held()); return obj; } /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu * variable access, and map elements stick around. See comment above * xdp_do_flush() in filter.c. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. * * Do the same with xdp_prog and flush_list since these fields * are only ever modified together. */ if (!bq->dev_rx) { struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); bq->dev_rx = dev_rx; bq->xdp_prog = xdp_prog; list_add(&bq->flush_node, flush_list); } bq->q[bq->count++] = xdpf; } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { int err; if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return -EOPNOTSUPP; if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); if (unlikely(err)) return err; bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) { struct xdp_txq_info txq = { .dev = dst->dev }; struct xdp_buff xdp; u32 act; if (!dst->xdp_prog) return XDP_PASS; __skb_pull(skb, skb->mac_len); xdp.txq = &txq; act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); switch (act) { case XDP_PASS: __skb_push(skb, skb->mac_len); break; default: bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dst->dev, dst->xdp_prog, act); fallthrough; case XDP_DROP: kfree_skb(skb); break; } return act; } int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj) return false; if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return false; if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return false; if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf))) return false; return true; } static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, struct net_device *dev_rx, struct xdp_frame *xdpf) { struct xdp_frame *nxdpf; nxdpf = xdpf_clone(xdpf); if (!nxdpf) return -ENOMEM; bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); return 0; } static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex) { while (num_excluded--) { if (ifindex == excluded[num_excluded]) return true; } return false; } /* Get ifindex of each upper device. 'indexes' must be able to hold at * least MAX_NEST_DEV elements. * Returns the number of ifindexes added. */ static int get_upper_ifindexes(struct net_device *dev, int *indexes) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { indexes[n++] = upper->ifindex; } return n; } int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); excluded_devices[num_excluded++] = dev_rx->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } } /* consume the last copy of the frame */ if (last_dst) bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); else xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ return 0; } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { int err; err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; /* Redirect has already succeeded semantically at this point, so we just * return 0 even if packet is dropped. Helper below takes care of * freeing skb. */ if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) return 0; skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); return 0; } static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct sk_buff *nskb; int err; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; err = dev_map_generic_redirect(dst, nskb, xdp_prog); if (unlikely(err)) { consume_skb(nskb); return err; } return 0; } int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; struct hlist_node *next; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev, excluded_devices); excluded_devices[num_excluded++] = dev->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!dst) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dst, next, head, index_hlist) { if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } } /* consume the first skb and return */ if (last_dst) return dev_map_generic_redirect(last_dst, skb, xdp_prog); /* dtab is empty */ consume_skb(skb); return 0; } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void __dev_map_entry_free(struct rcu_head *rcu) { struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } static long dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; int k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); if (old_dev) { call_rcu(&old_dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } return 0; } static long dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; int k = *(u32 *)key; unsigned long flags; int ret = -ENOENT; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, k); if (old_dev) { dtab->items--; hlist_del_init_rcu(&old_dev->index_hlist); call_rcu(&old_dev->rcu, __dev_map_entry_free); ret = 0; } spin_unlock_irqrestore(&dtab->index_lock, flags); return ret; } static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab *dtab, struct bpf_devmap_val *val, unsigned int idx) { struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), GFP_NOWAIT | __GFP_NOWARN, dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); dev->dev = dev_get_by_index(net, val->ifindex); if (!dev->dev) goto err_out; if (val->bpf_prog.fd > 0) { prog = bpf_prog_get_type_dev(val->bpf_prog.fd, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; if (prog->expected_attach_type != BPF_XDP_DEVMAP || !bpf_prog_map_compatible(&dtab->map, prog)) goto err_put_prog; } dev->idx = idx; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; } else { dev->xdp_prog = NULL; dev->val.bpf_prog.id = 0; } dev->val.ifindex = val->ifindex; return dev; err_put_prog: bpf_prog_put(prog); err_put_dev: dev_put(dev->dev); err_out: kfree(dev); return ERR_PTR(-EINVAL); } static long __dev_map_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 i = *(u32 *)key; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; if (unlikely(i >= dtab->map.max_entries)) return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (!val.ifindex) { dev = NULL; /* can not specify fd if ifindex is 0 */ if (val.bpf_prog.fd > 0) return -EINVAL; } else { dev = __dev_map_alloc_node(net, dtab, &val, i); if (IS_ERR(dev)) return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed * Remembering the driver side flush operation will happen before the * net device is removed. */ old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); else atomic_inc((atomic_t *)&dtab->items); return 0; } static long dev_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 idx = *(u32 *)key; unsigned long flags; int err = -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (unlikely(map_flags > BPF_EXIST || !val.ifindex)) return -EINVAL; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, idx); if (old_dev && (map_flags & BPF_NOEXIST)) goto out_err; dev = __dev_map_alloc_node(net, dtab, &val, idx); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out_err; } if (old_dev) { hlist_del_rcu(&old_dev->index_hlist); } else { if (dtab->items >= dtab->map.max_entries) { spin_unlock_irqrestore(&dtab->index_lock, flags); call_rcu(&dev->rcu, __dev_map_entry_free); return -E2BIG; } dtab->items++; } hlist_add_head_rcu(&dev->index_hlist, dev_map_index_hash(dtab, idx)); spin_unlock_irqrestore(&dtab->index_lock, flags); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; out_err: spin_unlock_irqrestore(&dtab->index_lock, flags); return err; } static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_hash_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_hash_lookup_elem); } static u64 dev_map_mem_usage(const struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u64 usage = sizeof(struct bpf_dtab); if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) usage += (u64)dtab->n_buckets * sizeof(struct hlist_head); else usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *); usage += atomic_read((atomic_t *)&dtab->items) * (u64)sizeof(struct bpf_dtab_netdev); return usage; } BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab) const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, .map_lookup_elem = dev_map_lookup_elem, .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_map_redirect, }; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_hash_get_next_key, .map_lookup_elem = dev_map_hash_lookup_elem, .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_hash_map_redirect, }; static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, struct net_device *netdev) { unsigned long flags; u32 i; spin_lock_irqsave(&dtab->index_lock, flags); for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { if (netdev != dev->dev) continue; dtab->items--; hlist_del_rcu(&dev->index_hlist); call_rcu(&dev->rcu, __dev_map_entry_free); } } spin_unlock_irqrestore(&dtab->index_lock, flags); } static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; int i, cpu; switch (event) { case NETDEV_REGISTER: if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) break; /* will be freed in free_netdev() */ netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue); if (!netdev->xdp_bulkq) return NOTIFY_BAD; for_each_possible_cpu(cpu) per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete * operation does not free a netdev_map entry while we * are comparing it against the netdev being unregistered. */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dev_map_hash_remove_netdev(dtab, netdev); continue; } for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) { call_rcu(&dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } } } rcu_read_unlock(); break; default: break; } return NOTIFY_OK; } static struct notifier_block dev_map_notifier = { .notifier_call = dev_map_notification, }; static int __init dev_map_init(void) { /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); return 0; } subsys_initcall(dev_map_init); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/workqueue.h> #include <linux/spinlock.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_tables.h> #include <net/ip.h> /* for ipv4 options. */ #include <net/inet_dscp.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_flow_table.h> struct nft_flow_offload { struct nft_flowtable *flowtable; }; static enum flow_offload_xmit_type nft_xmit_type(struct dst_entry *dst) { if (dst_xfrm(dst)) return FLOW_OFFLOAD_XMIT_XFRM; return FLOW_OFFLOAD_XMIT_NEIGH; } static void nft_default_forward_path(struct nf_flow_route *route, struct dst_entry *dst_cache, enum ip_conntrack_dir dir) { route->tuple[!dir].in.ifindex = dst_cache->dev->ifindex; route->tuple[dir].dst = dst_cache; route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); } static bool nft_is_valid_ether_device(const struct net_device *dev) { if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) return false; return true; } static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct dst_entry *dst_cache, const struct nf_conn *ct, enum ip_conntrack_dir dir, u8 *ha, struct net_device_path_stack *stack) { const void *daddr = &ct->tuplehash[!dir].tuple.src.u3; struct net_device *dev = dst_cache->dev; struct neighbour *n; u8 nud_state; if (!nft_is_valid_ether_device(dev)) goto out; n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -1; read_lock_bh(&n->lock); nud_state = n->nud_state; ether_addr_copy(ha, n->ha); read_unlock_bh(&n->lock); neigh_release(n); if (!(nud_state & NUD_VALID)) return -1; out: return dev_fill_forward_path(dev, ha, stack); } struct nft_forward_info { const struct net_device *indev; const struct net_device *outdev; const struct net_device *hw_outdev; struct id { __u16 id; __be16 proto; } encap[NF_FLOW_TABLE_ENCAP_MAX]; u8 num_encaps; u8 ingress_vlans; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; enum flow_offload_xmit_type xmit_type; }; static void nft_dev_path_info(const struct net_device_path_stack *stack, struct nft_forward_info *info, unsigned char *ha, struct nf_flowtable *flowtable) { const struct net_device_path *path; int i; memcpy(info->h_dest, ha, ETH_ALEN); for (i = 0; i < stack->num_paths; i++) { path = &stack->path[i]; switch (path->type) { case DEV_PATH_ETHERNET: case DEV_PATH_DSA: case DEV_PATH_VLAN: case DEV_PATH_PPPOE: info->indev = path->dev; if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); if (path->type == DEV_PATH_ETHERNET) break; if (path->type == DEV_PATH_DSA) { i = stack->num_paths; break; } /* DEV_PATH_VLAN and DEV_PATH_PPPOE */ if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) { info->indev = NULL; break; } if (!info->outdev) info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; if (path->type == DEV_PATH_PPPOE) memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); break; case DEV_PATH_BRIDGE: if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); switch (path->bridge.vlan_mode) { case DEV_PATH_BR_VLAN_UNTAG_HW: info->ingress_vlans |= BIT(info->num_encaps - 1); break; case DEV_PATH_BR_VLAN_TAG: info->encap[info->num_encaps].id = path->bridge.vlan_id; info->encap[info->num_encaps].proto = path->bridge.vlan_proto; info->num_encaps++; break; case DEV_PATH_BR_VLAN_UNTAG: info->num_encaps--; break; case DEV_PATH_BR_VLAN_KEEP: break; } info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; break; default: info->indev = NULL; break; } } if (!info->outdev) info->outdev = info->indev; info->hw_outdev = info->indev; if (nf_flowtable_hw_offload(flowtable) && nft_is_valid_ether_device(info->indev)) info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; } static bool nft_flowtable_find_dev(const struct net_device *dev, struct nft_flowtable *ft) { struct nft_hook *hook; bool found = false; list_for_each_entry_rcu(hook, &ft->hook_list, list) { if (hook->ops.dev != dev) continue; found = true; break; } return found; } static void nft_dev_forward_path(struct nf_flow_route *route, const struct nf_conn *ct, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { const struct dst_entry *dst = route->tuple[dir].dst; struct net_device_path_stack stack; struct nft_forward_info info = {}; unsigned char ha[ETH_ALEN]; int i; if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0) nft_dev_path_info(&stack, &info, ha, &ft->data); if (!info.indev || !nft_flowtable_find_dev(info.indev, ft)) return; route->tuple[!dir].in.ifindex = info.indev->ifindex; for (i = 0; i < info.num_encaps; i++) { route->tuple[!dir].in.encap[i].id = info.encap[i].id; route->tuple[!dir].in.encap[i].proto = info.encap[i].proto; } route->tuple[!dir].in.num_encaps = info.num_encaps; route->tuple[!dir].in.ingress_vlans = info.ingress_vlans; if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) { memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN); memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN); route->tuple[dir].out.ifindex = info.outdev->ifindex; route->tuple[dir].out.hw_ifindex = info.hw_outdev->ifindex; route->tuple[dir].xmit_type = info.xmit_type; } } static int nft_flow_route(const struct nft_pktinfo *pkt, const struct nf_conn *ct, struct nf_flow_route *route, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { struct dst_entry *this_dst = skb_dst(pkt->skb); struct dst_entry *other_dst = NULL; struct flowi fl; memset(&fl, 0, sizeof(fl)); switch (nft_pf(pkt)) { case NFPROTO_IPV4: fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip; fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; fl.u.ip4.flowi4_iif = this_dst->dev->ifindex; fl.u.ip4.flowi4_tos = ip_hdr(pkt->skb)->tos & INET_DSCP_MASK; fl.u.ip4.flowi4_mark = pkt->skb->mark; fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC; break; case NFPROTO_IPV6: fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; fl.u.ip6.saddr = ct->tuplehash[!dir].tuple.src.u3.in6; fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex; fl.u.ip6.flowi6_iif = this_dst->dev->ifindex; fl.u.ip6.flowlabel = ip6_flowinfo(ipv6_hdr(pkt->skb)); fl.u.ip6.flowi6_mark = pkt->skb->mark; fl.u.ip6.flowi6_flags = FLOWI_FLAG_ANYSRC; break; } if (!dst_hold_safe(this_dst)) return -ENOENT; nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt)); if (!other_dst) { dst_release(this_dst); return -ENOENT; } nft_default_forward_path(route, this_dst, dir); nft_default_forward_path(route, other_dst, !dir); if (route->tuple[dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH && route->tuple[!dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) { nft_dev_forward_path(route, ct, dir, ft); nft_dev_forward_path(route, ct, !dir, ft); } return 0; } static bool nft_flow_offload_skip(struct sk_buff *skb, int family) { if (skb_sec_path(skb)) return true; if (family == NFPROTO_IPV4) { const struct ip_options *opt; opt = &(IPCB(skb)->opt); if (unlikely(opt->optlen)) return true; } return false; } static void nft_flow_offload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; struct tcphdr _tcph, *tcph = NULL; struct nf_flow_route route = {}; enum ip_conntrack_info ctinfo; struct flow_offload *flow; enum ip_conntrack_dir dir; struct nf_conn *ct; int ret; if (nft_flow_offload_skip(pkt->skb, nft_pf(pkt))) goto out; ct = nf_ct_get(pkt->skb, &ctinfo); if (!ct) goto out; switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) { case IPPROTO_TCP: tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); if (unlikely(!tcph || tcph->fin || tcph->rst || !nf_conntrack_tcp_established(ct))) goto out; break; case IPPROTO_UDP: break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; if (ct->status & IPS_NAT_MASK) goto out; tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) goto out; break; } #endif default: goto out; } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH)) goto out; if (!nf_ct_is_confirmed(ct)) goto out; if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status)) goto out; dir = CTINFO2DIR(ctinfo); if (nft_flow_route(pkt, ct, &route, dir, priv->flowtable) < 0) goto err_flow_route; flow = flow_offload_alloc(ct); if (!flow) goto err_flow_alloc; flow_offload_route_init(flow, &route); if (tcph) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); ret = flow_offload_add(flowtable, flow); if (ret < 0) goto err_flow_add; return; err_flow_add: flow_offload_free(flow); err_flow_alloc: dst_release(route.tuple[dir].dst); dst_release(route.tuple[!dir].dst); err_flow_route: clear_bit(IPS_OFFLOAD_BIT, &ct->status); out: regs->verdict.code = NFT_BREAK; } static int nft_flow_offload_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { unsigned int hook_mask = (1 << NF_INET_FORWARD); if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, hook_mask); } static const struct nla_policy nft_flow_offload_policy[NFTA_FLOW_MAX + 1] = { [NFTA_FLOW_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_NAME_MAXLEN - 1 }, }; static int nft_flow_offload_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_flow_offload *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_flowtable *flowtable; if (!tb[NFTA_FLOW_TABLE_NAME]) return -EINVAL; flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME], genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); if (!nft_use_inc(&flowtable->use)) return -EMFILE; priv->flowtable = flowtable; return nf_ct_netns_get(ctx->net, ctx->family); } static void nft_flow_offload_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_flow_offload *priv = nft_expr_priv(expr); nf_tables_deactivate_flowtable(ctx, priv->flowtable, phase); } static void nft_flow_offload_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_flow_offload *priv = nft_expr_priv(expr); nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nf_ct_netns_put(ctx->net, ctx->family); } static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_flow_offload *priv = nft_expr_priv(expr); if (nla_put_string(skb, NFTA_FLOW_TABLE_NAME, priv->flowtable->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static struct nft_expr_type nft_flow_offload_type; static const struct nft_expr_ops nft_flow_offload_ops = { .type = &nft_flow_offload_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)), .eval = nft_flow_offload_eval, .init = nft_flow_offload_init, .activate = nft_flow_offload_activate, .deactivate = nft_flow_offload_deactivate, .destroy = nft_flow_offload_destroy, .validate = nft_flow_offload_validate, .dump = nft_flow_offload_dump, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_flow_offload_type __read_mostly = { .name = "flow_offload", .ops = &nft_flow_offload_ops, .policy = nft_flow_offload_policy, .maxattr = NFTA_FLOW_MAX, .owner = THIS_MODULE, }; static int flow_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event != NETDEV_DOWN) return NOTIFY_DONE; nf_flow_table_cleanup(dev); return NOTIFY_DONE; } static struct notifier_block flow_offload_netdev_notifier = { .notifier_call = flow_offload_netdev_event, }; static int __init nft_flow_offload_module_init(void) { int err; err = register_netdevice_notifier(&flow_offload_netdev_notifier); if (err) goto err; err = nft_register_expr(&nft_flow_offload_type); if (err < 0) goto register_expr; return 0; register_expr: unregister_netdevice_notifier(&flow_offload_netdev_notifier); err: return err; } static void __exit nft_flow_offload_module_exit(void) { nft_unregister_expr(&nft_flow_offload_type); unregister_netdevice_notifier(&flow_offload_netdev_notifier); } module_init(nft_flow_offload_module_init); module_exit(nft_flow_offload_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("flow_offload"); MODULE_DESCRIPTION("nftables hardware flow offload module"); |
| 126 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 /* * Copyright IBM Corporation, 2021 * * Author: Mike Rapoport <rppt@linux.ibm.com> */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/swap.h> #include <linux/mount.h> #include <linux/memfd.h> #include <linux/bitops.h> #include <linux/printk.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/pseudo_fs.h> #include <linux/secretmem.h> #include <linux/set_memory.h> #include <linux/sched/signal.h> #include <uapi/linux/magic.h> #include <asm/tlbflush.h> #include "internal.h" #undef pr_fmt #define pr_fmt(fmt) "secretmem: " fmt /* * Define mode and flag masks to allow validation of the system call * parameters. */ #define SECRETMEM_MODE_MASK (0x0) #define SECRETMEM_FLAGS_MASK SECRETMEM_MODE_MASK static bool secretmem_enable __ro_after_init = 1; module_param_named(enable, secretmem_enable, bool, 0400); MODULE_PARM_DESC(secretmem_enable, "Enable secretmem and memfd_secret(2) system call"); static atomic_t secretmem_users; bool secretmem_active(void) { return !!atomic_read(&secretmem_users); } static vm_fault_t secretmem_fault(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct inode *inode = file_inode(vmf->vma->vm_file); pgoff_t offset = vmf->pgoff; gfp_t gfp = vmf->gfp_mask; unsigned long addr; struct page *page; struct folio *folio; vm_fault_t ret; int err; if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode)) return vmf_error(-EINVAL); filemap_invalidate_lock_shared(mapping); retry: page = find_lock_page(mapping, offset); if (!page) { folio = folio_alloc(gfp | __GFP_ZERO, 0); if (!folio) { ret = VM_FAULT_OOM; goto out; } page = &folio->page; err = set_direct_map_invalid_noflush(page); if (err) { folio_put(folio); ret = vmf_error(err); goto out; } __folio_mark_uptodate(folio); err = filemap_add_folio(mapping, folio, offset, gfp); if (unlikely(err)) { folio_put(folio); /* * If a split of large page was required, it * already happened when we marked the page invalid * which guarantees that this call won't fail */ set_direct_map_default_noflush(page); if (err == -EEXIST) goto retry; ret = vmf_error(err); goto out; } addr = (unsigned long)page_address(page); flush_tlb_kernel_range(addr, addr + PAGE_SIZE); } vmf->page = page; ret = VM_FAULT_LOCKED; out: filemap_invalidate_unlock_shared(mapping); return ret; } static const struct vm_operations_struct secretmem_vm_ops = { .fault = secretmem_fault, }; static int secretmem_release(struct inode *inode, struct file *file) { atomic_dec(&secretmem_users); return 0; } static int secretmem_mmap(struct file *file, struct vm_area_struct *vma) { unsigned long len = vma->vm_end - vma->vm_start; if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0) return -EINVAL; if (!mlock_future_ok(vma->vm_mm, vma->vm_flags | VM_LOCKED, len)) return -EAGAIN; vm_flags_set(vma, VM_LOCKED | VM_DONTDUMP); vma->vm_ops = &secretmem_vm_ops; return 0; } bool vma_is_secretmem(struct vm_area_struct *vma) { return vma->vm_ops == &secretmem_vm_ops; } static const struct file_operations secretmem_fops = { .release = secretmem_release, .mmap = secretmem_mmap, }; static int secretmem_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { return -EBUSY; } static void secretmem_free_folio(struct folio *folio) { set_direct_map_default_noflush(&folio->page); folio_zero_segment(folio, 0, folio_size(folio)); } const struct address_space_operations secretmem_aops = { .dirty_folio = noop_dirty_folio, .free_folio = secretmem_free_folio, .migrate_folio = secretmem_migrate_folio, }; static int secretmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); struct address_space *mapping = inode->i_mapping; unsigned int ia_valid = iattr->ia_valid; int ret; filemap_invalidate_lock(mapping); if ((ia_valid & ATTR_SIZE) && inode->i_size) ret = -EINVAL; else ret = simple_setattr(idmap, dentry, iattr); filemap_invalidate_unlock(mapping); return ret; } static const struct inode_operations secretmem_iops = { .setattr = secretmem_setattr, }; static struct vfsmount *secretmem_mnt; static struct file *secretmem_file_create(unsigned long flags) { struct file *file; struct inode *inode; const char *anon_name = "[secretmem]"; const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name)); int err; inode = alloc_anon_inode(secretmem_mnt->mnt_sb); if (IS_ERR(inode)) return ERR_CAST(inode); err = security_inode_init_security_anon(inode, &qname, NULL); if (err) { file = ERR_PTR(err); goto err_free_inode; } file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem", O_RDWR, &secretmem_fops); if (IS_ERR(file)) goto err_free_inode; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); inode->i_op = &secretmem_iops; inode->i_mapping->a_ops = &secretmem_aops; /* pretend we are a normal file with zero size */ inode->i_mode |= S_IFREG; inode->i_size = 0; return file; err_free_inode: iput(inode); return file; } SYSCALL_DEFINE1(memfd_secret, unsigned int, flags) { struct file *file; int fd, err; /* make sure local flags do not confict with global fcntl.h */ BUILD_BUG_ON(SECRETMEM_FLAGS_MASK & O_CLOEXEC); if (!secretmem_enable || !can_set_direct_map()) return -ENOSYS; if (flags & ~(SECRETMEM_FLAGS_MASK | O_CLOEXEC)) return -EINVAL; if (atomic_read(&secretmem_users) < 0) return -ENFILE; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; file = secretmem_file_create(flags); if (IS_ERR(file)) { err = PTR_ERR(file); goto err_put_fd; } file->f_flags |= O_LARGEFILE; atomic_inc(&secretmem_users); fd_install(fd, file); return fd; err_put_fd: put_unused_fd(fd); return err; } static int secretmem_init_fs_context(struct fs_context *fc) { return init_pseudo(fc, SECRETMEM_MAGIC) ? 0 : -ENOMEM; } static struct file_system_type secretmem_fs = { .name = "secretmem", .init_fs_context = secretmem_init_fs_context, .kill_sb = kill_anon_super, }; static int __init secretmem_init(void) { if (!secretmem_enable || !can_set_direct_map()) return 0; secretmem_mnt = kern_mount(&secretmem_fs); if (IS_ERR(secretmem_mnt)) return PTR_ERR(secretmem_mnt); /* prevent secretmem mappings from ever getting PROT_EXEC */ secretmem_mnt->mnt_flags |= MNT_NOEXEC; return 0; } fs_initcall(secretmem_init); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xfrm_device.c - IPsec device offloading code. * * Copyright (c) 2015 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/errno.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/dst.h> #include <net/gso.h> #include <net/xfrm.h> #include <linux/notifier.h> #ifdef CONFIG_XFRM_OFFLOAD static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); skb_reset_mac_len(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header -= x->props.header_len; pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len); } static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); pskb_pull(skb, skb->mac_len + x->props.header_len); } static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); int phlen = 0; if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); if (x->sel.family != AF_INET6) { phlen = IPV4_BEET_PHMAXLEN; if (x->outer_mode.family == AF_INET6) phlen += sizeof(struct ipv6hdr) - sizeof(struct iphdr); } pskb_pull(skb, skb->mac_len + hsize + (x->props.header_len - phlen)); } /* Adjust pointers into the packet when IPsec is done at layer2 */ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) { switch (x->outer_mode.encap) { case XFRM_MODE_TUNNEL: if (x->outer_mode.family == AF_INET) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_TRANSPORT: if (x->outer_mode.family == AF_INET) return __xfrm_transport_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_transport_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_BEET: if (x->outer_mode.family == AF_INET) return __xfrm_mode_beet_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_beet_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: break; } } static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) { struct xfrm_offload *xo = xfrm_offload(skb); __u32 seq = xo->seq.low; seq += skb_shinfo(skb)->gso_segs; if (unlikely(seq < xo->seq.low)) return true; return false; } struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; unsigned long flags; struct xfrm_state *x; struct softnet_data *sd; struct sk_buff *skb2, *nskb, *pskb = NULL; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); struct net_device *dev = skb->dev; struct sec_path *sp; if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; if (xo->flags & XFRM_GRO || x->xso.dir == XFRM_DEV_OFFLOAD_IN) return skb; /* The packet was sent to HW IPsec packet offload engine, * but to wrong device. Drop the packet, so it won't skip * XFRM stack. */ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->xso.dev != dev) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } /* This skb was already validated on the upper/virtual dev */ if ((x->xso.dev != dev) && (x->xso.real_dev == dev)) return skb; local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); err = !skb_queue_empty(&sd->xfrm_backlog); local_irq_restore(flags); if (err) { *again = true; return skb; } if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ esp_features = esp_features & ~(NETIF_F_HW_ESP | NETIF_F_GSO_ESP); segs = skb_gso_segment(skb, esp_features); if (IS_ERR(segs)) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } else { consume_skb(skb); skb = segs; } } if (!skb->next) { esp_features |= skb->dev->gso_partial_features; xfrm_outer_mode_prep(x, skb); xo->flags |= XFRM_DEV_RESUME; err = x->type_offload->xmit(x, skb, esp_features); if (err) { if (err == -EINPROGRESS) return NULL; XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); kfree_skb(skb); return NULL; } skb_push(skb, skb->data - skb_mac_header(skb)); return skb; } skb_list_walk_safe(skb, skb2, nskb) { esp_features |= skb->dev->gso_partial_features; skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; xfrm_outer_mode_prep(x, skb2); err = x->type_offload->xmit(x, skb2, esp_features); if (!err) { skb2->next = nskb; } else if (err != -EINPROGRESS) { XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); skb2->next = nskb; kfree_skb_list(skb2); return NULL; } else { if (skb == skb2) skb = nskb; else pskb->next = nskb; continue; } skb_push(skb2, skb2->data - skb_mac_header(skb2)); pskb = skb2; } return skb; } EXPORT_SYMBOL_GPL(validate_xmit_xfrm); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { int err; struct dst_entry *dst; struct net_device *dev; struct xfrm_dev_offload *xso = &x->xso; xfrm_address_t *saddr; xfrm_address_t *daddr; bool is_packet_offload; if (!x->type_offload) { NL_SET_ERR_MSG(extack, "Type doesn't support offload"); return -EINVAL; } if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) { NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } if ((xuo->flags & XFRM_OFFLOAD_INBOUND && x->dir == XFRM_SA_DIR_OUT) || (!(xuo->flags & XFRM_OFFLOAD_INBOUND) && x->dir == XFRM_SA_DIR_IN)) { NL_SET_ERR_MSG(extack, "Mismatched SA and offload direction"); return -EINVAL; } is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET; /* We don't yet support TFC padding. */ if (x->tfcpad) { NL_SET_ERR_MSG(extack, "TFC padding can't be offloaded"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { saddr = &x->props.saddr; daddr = &x->id.daddr; } else { saddr = &x->id.daddr; daddr = &x->props.saddr; } dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, x->props.family, xfrm_smark_get(0, x)); if (IS_ERR(dst)) return (is_packet_offload) ? -EINVAL : 0; dev = dst->dev; dev_hold(dev); dst_release(dst); } if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { xso->dev = NULL; dev_put(dev); return (is_packet_offload) ? -EINVAL : 0; } if (!is_packet_offload && x->props.flags & XFRM_STATE_ESN && !dev->xfrmdev_ops->xdo_dev_state_advance_esn) { NL_SET_ERR_MSG(extack, "Device doesn't support offload with ESN"); xso->dev = NULL; dev_put(dev); return -EINVAL; } xso->dev = dev; netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); xso->real_dev = dev; if (xuo->flags & XFRM_OFFLOAD_INBOUND) xso->dir = XFRM_DEV_OFFLOAD_IN; else xso->dir = XFRM_DEV_OFFLOAD_OUT; if (is_packet_offload) xso->type = XFRM_DEV_OFFLOAD_PACKET; else xso->type = XFRM_DEV_OFFLOAD_CRYPTO; err = dev->xfrmdev_ops->xdo_dev_state_add(x, extack); if (err) { xso->dev = NULL; xso->dir = 0; xso->real_dev = NULL; netdev_put(dev, &xso->dev_tracker); xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; /* User explicitly requested packet offload mode and configured * policy in addition to the XFRM state. So be civil to users, * and return an error instead of taking fallback path. */ if ((err != -EOPNOTSUPP && !is_packet_offload) || is_packet_offload) { NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state"); return err; } } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_state_add); int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack) { struct xfrm_dev_offload *xdo = &xp->xdo; struct net_device *dev; int err; if (!xuo->flags || xuo->flags & ~XFRM_OFFLOAD_PACKET) { /* We support only packet offload mode and it means * that user must set XFRM_OFFLOAD_PACKET bit. */ NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) return -EINVAL; if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_policy_add) { xdo->dev = NULL; dev_put(dev); NL_SET_ERR_MSG(extack, "Policy offload is not supported"); return -EINVAL; } xdo->dev = dev; netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC); xdo->real_dev = dev; xdo->type = XFRM_DEV_OFFLOAD_PACKET; switch (dir) { case XFRM_POLICY_IN: xdo->dir = XFRM_DEV_OFFLOAD_IN; break; case XFRM_POLICY_OUT: xdo->dir = XFRM_DEV_OFFLOAD_OUT; break; case XFRM_POLICY_FWD: xdo->dir = XFRM_DEV_OFFLOAD_FWD; break; default: xdo->dev = NULL; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack); if (err) { xdo->dev = NULL; xdo->real_dev = NULL; xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xdo->dir = 0; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this policy"); return err; } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_policy_add); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { int mtu; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; if (!x->type_offload || (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET || ((!dev || (dev == xfrm_dst_path(dst)->dev)) && !xdst->child->xfrm)) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } return false; ok: if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_offload_ok) return x->xso.dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x); return true; } EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok); void xfrm_dev_resume(struct sk_buff *skb) { struct net_device *dev = skb->dev; int ret = NETDEV_TX_BUSY; struct netdev_queue *txq; struct softnet_data *sd; unsigned long flags; rcu_read_lock(); txq = netdev_core_pick_tx(dev, skb, NULL); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); HARD_TX_UNLOCK(dev, txq); if (!dev_xmit_complete(ret)) { local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); skb_queue_tail(&sd->xfrm_backlog, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(xfrm_dev_resume); void xfrm_dev_backlog(struct softnet_data *sd) { struct sk_buff_head *xfrm_backlog = &sd->xfrm_backlog; struct sk_buff_head list; struct sk_buff *skb; if (skb_queue_empty(xfrm_backlog)) return; __skb_queue_head_init(&list); spin_lock(&xfrm_backlog->lock); skb_queue_splice_init(xfrm_backlog, &list); spin_unlock(&xfrm_backlog->lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); xfrm_dev_resume(skb); } } #endif static int xfrm_api_check(struct net_device *dev) { #ifdef CONFIG_XFRM_OFFLOAD if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) && !(dev->features & NETIF_F_HW_ESP)) return NOTIFY_BAD; if ((dev->features & NETIF_F_HW_ESP) && (!(dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_state_add && dev->xfrmdev_ops->xdo_dev_state_delete))) return NOTIFY_BAD; #else if (dev->features & (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM)) return NOTIFY_BAD; #endif return NOTIFY_DONE; } static int xfrm_dev_down(struct net_device *dev) { if (dev->features & NETIF_F_HW_ESP) { xfrm_dev_state_flush(dev_net(dev), dev, true); xfrm_dev_policy_flush(dev_net(dev), dev, true); } return NOTIFY_DONE; } static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_REGISTER: return xfrm_api_check(dev); case NETDEV_FEAT_CHANGE: return xfrm_api_check(dev); case NETDEV_DOWN: case NETDEV_UNREGISTER: return xfrm_dev_down(dev); } return NOTIFY_DONE; } static struct notifier_block xfrm_dev_notifier = { .notifier_call = xfrm_dev_event, }; void __init xfrm_dev_init(void) { register_netdevice_notifier(&xfrm_dev_notifier); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004 Infinicon Corporation. All rights reserved. * Copyright (c) 2004, 2020 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. * Copyright (c) 2004 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005, 2006, 2007 Cisco Systems. All rights reserved. */ #ifndef IB_VERBS_H #define IB_VERBS_H #include <linux/ethtool.h> #include <linux/types.h> #include <linux/device.h> #include <linux/dma-mapping.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/rwsem.h> #include <linux/workqueue.h> #include <linux/irq_poll.h> #include <uapi/linux/if_ether.h> #include <net/ipv6.h> #include <net/ip.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/refcount.h> #include <linux/if_link.h> #include <linux/atomic.h> #include <linux/mmu_notifier.h> #include <linux/uaccess.h> #include <linux/cgroup_rdma.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/dim.h> #include <uapi/rdma/ib_user_verbs.h> #include <rdma/rdma_counter.h> #include <rdma/restrack.h> #include <rdma/signature.h> #include <uapi/rdma/rdma_user_ioctl.h> #include <uapi/rdma/ib_user_ioctl_verbs.h> #define IB_FW_VERSION_NAME_MAX ETHTOOL_FWVERS_LEN struct ib_umem_odp; struct ib_uqp_object; struct ib_usrq_object; struct ib_uwq_object; struct rdma_cm_id; struct ib_port; struct hw_stats_device_data; extern struct workqueue_struct *ib_wq; extern struct workqueue_struct *ib_comp_wq; extern struct workqueue_struct *ib_comp_unbound_wq; struct ib_ucq_object; __printf(3, 4) __cold void ibdev_printk(const char *level, const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_emerg(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_alert(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_crit(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_err(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_warn(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_notice(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_info(const struct ib_device *ibdev, const char *format, ...); #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define ibdev_dbg(__dev, format, args...) \ dynamic_ibdev_dbg(__dev, format, ##args) #else __printf(2, 3) __cold static inline void ibdev_dbg(const struct ib_device *ibdev, const char *format, ...) {} #endif #define ibdev_level_ratelimited(ibdev_level, ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ if (__ratelimit(&_rs)) \ ibdev_level(ibdev, fmt, ##__VA_ARGS__); \ } while (0) #define ibdev_emerg_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_emerg, ibdev, fmt, ##__VA_ARGS__) #define ibdev_alert_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_alert, ibdev, fmt, ##__VA_ARGS__) #define ibdev_crit_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_crit, ibdev, fmt, ##__VA_ARGS__) #define ibdev_err_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_err, ibdev, fmt, ##__VA_ARGS__) #define ibdev_warn_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_warn, ibdev, fmt, ##__VA_ARGS__) #define ibdev_notice_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_notice, ibdev, fmt, ##__VA_ARGS__) #define ibdev_info_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define ibdev_dbg_ratelimited(ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && __ratelimit(&_rs)) \ __dynamic_ibdev_dbg(&descriptor, ibdev, fmt, \ ##__VA_ARGS__); \ } while (0) #else __printf(2, 3) __cold static inline void ibdev_dbg_ratelimited(const struct ib_device *ibdev, const char *format, ...) {} #endif union ib_gid { u8 raw[16]; struct { __be64 subnet_prefix; __be64 interface_id; } global; }; extern union ib_gid zgid; enum ib_gid_type { IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB, IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1, IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2, IB_GID_TYPE_SIZE }; #define ROCE_V2_UDP_DPORT 4791 struct ib_gid_attr { struct net_device __rcu *ndev; struct ib_device *device; union ib_gid gid; enum ib_gid_type gid_type; u16 index; u32 port_num; }; enum { /* set the local administered indication */ IB_SA_WELL_KNOWN_GUID = BIT_ULL(57) | 2, }; enum rdma_transport_type { RDMA_TRANSPORT_IB, RDMA_TRANSPORT_IWARP, RDMA_TRANSPORT_USNIC, RDMA_TRANSPORT_USNIC_UDP, RDMA_TRANSPORT_UNSPECIFIED, }; enum rdma_protocol_type { RDMA_PROTOCOL_IB, RDMA_PROTOCOL_IBOE, RDMA_PROTOCOL_IWARP, RDMA_PROTOCOL_USNIC_UDP }; __attribute_const__ enum rdma_transport_type rdma_node_get_transport(unsigned int node_type); enum rdma_network_type { RDMA_NETWORK_IB, RDMA_NETWORK_ROCE_V1, RDMA_NETWORK_IPV4, RDMA_NETWORK_IPV6 }; static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type) { if (network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) return IB_GID_TYPE_ROCE_UDP_ENCAP; else if (network_type == RDMA_NETWORK_ROCE_V1) return IB_GID_TYPE_ROCE; else return IB_GID_TYPE_IB; } static inline enum rdma_network_type rdma_gid_attr_network_type(const struct ib_gid_attr *attr) { if (attr->gid_type == IB_GID_TYPE_IB) return RDMA_NETWORK_IB; if (attr->gid_type == IB_GID_TYPE_ROCE) return RDMA_NETWORK_ROCE_V1; if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid)) return RDMA_NETWORK_IPV4; else return RDMA_NETWORK_IPV6; } enum rdma_link_layer { IB_LINK_LAYER_UNSPECIFIED, IB_LINK_LAYER_INFINIBAND, IB_LINK_LAYER_ETHERNET, }; enum ib_device_cap_flags { IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR, IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR, IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR, IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI, IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG, IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT, IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE, IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD, IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT, /* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */ IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT, IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID, IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN, IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE, IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ, /* Reserved, old SEND_W_INV = 1 << 16,*/ IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW, /* * Devices should set IB_DEVICE_UD_IP_SUM if they support * insertion of UDP and TCP checksum on outgoing UD IPoIB * messages and can verify the validity of checksum for * incoming messages. Setting this flag implies that the * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM, IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC, /* * This device supports the IB "base memory management extension", * which includes support for fast registrations (IB_WR_REG_MR, * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs). This flag should * also be set by any iWarp device which must support FRs to comply * to the iWarp verbs spec. iWarp devices also support the * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the * stag. */ IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS, IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A, IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B, IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM, /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM, IB_DEVICE_MANAGED_FLOW_STEERING = IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING, /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS, /* The device supports padding incoming writes to cacheline. */ IB_DEVICE_PCI_WRITE_END_PADDING = IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING, /* Placement type attributes */ IB_DEVICE_FLUSH_GLOBAL = IB_UVERBS_DEVICE_FLUSH_GLOBAL, IB_DEVICE_FLUSH_PERSISTENT = IB_UVERBS_DEVICE_FLUSH_PERSISTENT, IB_DEVICE_ATOMIC_WRITE = IB_UVERBS_DEVICE_ATOMIC_WRITE, }; enum ib_kernel_cap_flags { /* * This device supports a per-device lkey or stag that can be * used without performing a memory registration for the local * memory. Note that ULPs should never check this flag, but * instead of use the local_dma_lkey flag in the ib_pd structure, * which will always contain a usable lkey. */ IBK_LOCAL_DMA_LKEY = 1 << 0, /* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */ IBK_INTEGRITY_HANDOVER = 1 << 1, /* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */ IBK_ON_DEMAND_PAGING = 1 << 2, /* IB_MR_TYPE_SG_GAPS is supported */ IBK_SG_GAPS_REG = 1 << 3, /* Driver supports RDMA_NLDEV_CMD_DELLINK */ IBK_ALLOW_USER_UNREG = 1 << 4, /* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */ IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5, /* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */ IBK_UD_TSO = 1 << 6, /* iopib will use the device ops: * get_vf_config * get_vf_guid * get_vf_stats * set_vf_guid * set_vf_link_state */ IBK_VIRTUAL_FUNCTION = 1 << 7, /* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */ IBK_RDMA_NETDEV_OPA = 1 << 8, }; enum ib_atomic_cap { IB_ATOMIC_NONE, IB_ATOMIC_HCA, IB_ATOMIC_GLOB }; enum ib_odp_general_cap_bits { IB_ODP_SUPPORT = 1 << 0, IB_ODP_SUPPORT_IMPLICIT = 1 << 1, }; enum ib_odp_transport_cap_bits { IB_ODP_SUPPORT_SEND = 1 << 0, IB_ODP_SUPPORT_RECV = 1 << 1, IB_ODP_SUPPORT_WRITE = 1 << 2, IB_ODP_SUPPORT_READ = 1 << 3, IB_ODP_SUPPORT_ATOMIC = 1 << 4, IB_ODP_SUPPORT_SRQ_RECV = 1 << 5, }; struct ib_odp_caps { uint64_t general_caps; struct { uint32_t rc_odp_caps; uint32_t uc_odp_caps; uint32_t ud_odp_caps; uint32_t xrc_odp_caps; } per_transport_caps; }; struct ib_rss_caps { /* Corresponding bit will be set if qp type from * 'enum ib_qp_type' is supported, e.g. * supported_qpts |= 1 << IB_QPT_UD */ u32 supported_qpts; u32 max_rwq_indirection_tables; u32 max_rwq_indirection_table_size; }; enum ib_tm_cap_flags { /* Support tag matching with rendezvous offload for RC transport */ IB_TM_CAP_RNDV_RC = 1 << 0, }; struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ u32 max_num_tags; /* From enum ib_tm_cap_flags */ u32 flags; /* Max number of outstanding list operations */ u32 max_ops; /* Max number of SGE in tag matching entry */ u32 max_sge; }; struct ib_cq_init_attr { unsigned int cqe; u32 comp_vector; u32 flags; }; enum ib_cq_attr_mask { IB_CQ_MODERATE = 1 << 0, }; struct ib_cq_caps { u16 max_cq_moderation_count; u16 max_cq_moderation_period; }; struct ib_dm_mr_attr { u64 length; u64 offset; u32 access_flags; }; struct ib_dm_alloc_attr { u64 length; u32 alignment; u32 flags; }; struct ib_device_attr { u64 fw_ver; __be64 sys_image_guid; u64 max_mr_size; u64 page_size_cap; u32 vendor_id; u32 vendor_part_id; u32 hw_ver; int max_qp; int max_qp_wr; u64 device_cap_flags; u64 kernel_cap_flags; int max_send_sge; int max_recv_sge; int max_sge_rd; int max_cq; int max_cqe; int max_mr; int max_pd; int max_qp_rd_atom; int max_ee_rd_atom; int max_res_rd_atom; int max_qp_init_rd_atom; int max_ee_init_rd_atom; enum ib_atomic_cap atomic_cap; enum ib_atomic_cap masked_atomic_cap; int max_ee; int max_rdd; int max_mw; int max_raw_ipv6_qp; int max_raw_ethy_qp; int max_mcast_grp; int max_mcast_qp_attach; int max_total_mcast_qp_attach; int max_ah; int max_srq; int max_srq_wr; int max_srq_sge; unsigned int max_fast_reg_page_list_len; unsigned int max_pi_fast_reg_page_list_len; u16 max_pkeys; u8 local_ca_ack_delay; int sig_prot_cap; int sig_guard_cap; struct ib_odp_caps odp_caps; uint64_t timestamp_mask; uint64_t hca_core_clock; /* in KHZ */ struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ struct ib_tm_caps tm_caps; struct ib_cq_caps cq_caps; u64 max_dm_size; /* Max entries for sgl for optimized performance per READ */ u32 max_sgl_rd; }; enum ib_mtu { IB_MTU_256 = 1, IB_MTU_512 = 2, IB_MTU_1024 = 3, IB_MTU_2048 = 4, IB_MTU_4096 = 5 }; enum opa_mtu { OPA_MTU_8192 = 6, OPA_MTU_10240 = 7 }; static inline int ib_mtu_enum_to_int(enum ib_mtu mtu) { switch (mtu) { case IB_MTU_256: return 256; case IB_MTU_512: return 512; case IB_MTU_1024: return 1024; case IB_MTU_2048: return 2048; case IB_MTU_4096: return 4096; default: return -1; } } static inline enum ib_mtu ib_mtu_int_to_enum(int mtu) { if (mtu >= 4096) return IB_MTU_4096; else if (mtu >= 2048) return IB_MTU_2048; else if (mtu >= 1024) return IB_MTU_1024; else if (mtu >= 512) return IB_MTU_512; else return IB_MTU_256; } static inline int opa_mtu_enum_to_int(enum opa_mtu mtu) { switch (mtu) { case OPA_MTU_8192: return 8192; case OPA_MTU_10240: return 10240; default: return(ib_mtu_enum_to_int((enum ib_mtu)mtu)); } } static inline enum opa_mtu opa_mtu_int_to_enum(int mtu) { if (mtu >= 10240) return OPA_MTU_10240; else if (mtu >= 8192) return OPA_MTU_8192; else return ((enum opa_mtu)ib_mtu_int_to_enum(mtu)); } enum ib_port_state { IB_PORT_NOP = 0, IB_PORT_DOWN = 1, IB_PORT_INIT = 2, IB_PORT_ARMED = 3, IB_PORT_ACTIVE = 4, IB_PORT_ACTIVE_DEFER = 5 }; enum ib_port_phys_state { IB_PORT_PHYS_STATE_SLEEP = 1, IB_PORT_PHYS_STATE_POLLING = 2, IB_PORT_PHYS_STATE_DISABLED = 3, IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING = 4, IB_PORT_PHYS_STATE_LINK_UP = 5, IB_PORT_PHYS_STATE_LINK_ERROR_RECOVERY = 6, IB_PORT_PHYS_STATE_PHY_TEST = 7, }; enum ib_port_width { IB_WIDTH_1X = 1, IB_WIDTH_2X = 16, IB_WIDTH_4X = 2, IB_WIDTH_8X = 4, IB_WIDTH_12X = 8 }; static inline int ib_width_enum_to_int(enum ib_port_width width) { switch (width) { case IB_WIDTH_1X: return 1; case IB_WIDTH_2X: return 2; case IB_WIDTH_4X: return 4; case IB_WIDTH_8X: return 8; case IB_WIDTH_12X: return 12; default: return -1; } } enum ib_port_speed { IB_SPEED_SDR = 1, IB_SPEED_DDR = 2, IB_SPEED_QDR = 4, IB_SPEED_FDR10 = 8, IB_SPEED_FDR = 16, IB_SPEED_EDR = 32, IB_SPEED_HDR = 64, IB_SPEED_NDR = 128, IB_SPEED_XDR = 256, }; enum ib_stat_flag { IB_STAT_FLAG_OPTIONAL = 1 << 0, }; /** * struct rdma_stat_desc * @name - The name of the counter * @flags - Flags of the counter; For example, IB_STAT_FLAG_OPTIONAL * @priv - Driver private information; Core code should not use */ struct rdma_stat_desc { const char *name; unsigned int flags; const void *priv; }; /** * struct rdma_hw_stats * @lock - Mutex to protect parallel write access to lifespan and values * of counters, which are 64bits and not guaranteed to be written * atomicaly on 32bits systems. * @timestamp - Used by the core code to track when the last update was * @lifespan - Used by the core code to determine how old the counters * should be before being updated again. Stored in jiffies, defaults * to 10 milliseconds, drivers can override the default be specifying * their own value during their allocation routine. * @descs - Array of pointers to static descriptors used for the counters * in directory. * @is_disabled - A bitmap to indicate each counter is currently disabled * or not. * @num_counters - How many hardware counters there are. If name is * shorter than this number, a kernel oops will result. Driver authors * are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters) * in their code to prevent this. * @value - Array of u64 counters that are accessed by the sysfs code and * filled in by the drivers get_stats routine */ struct rdma_hw_stats { struct mutex lock; /* Protect lifespan and values[] */ unsigned long timestamp; unsigned long lifespan; const struct rdma_stat_desc *descs; unsigned long *is_disabled; int num_counters; u64 value[] __counted_by(num_counters); }; #define RDMA_HW_STATS_DEFAULT_LIFESPAN 10 struct rdma_hw_stats *rdma_alloc_hw_stats_struct( const struct rdma_stat_desc *descs, int num_counters, unsigned long lifespan); void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats); /* Define bits for the various functionality this port needs to be supported by * the core. */ /* Management 0x00000FFF */ #define RDMA_CORE_CAP_IB_MAD 0x00000001 #define RDMA_CORE_CAP_IB_SMI 0x00000002 #define RDMA_CORE_CAP_IB_CM 0x00000004 #define RDMA_CORE_CAP_IW_CM 0x00000008 #define RDMA_CORE_CAP_IB_SA 0x00000010 #define RDMA_CORE_CAP_OPA_MAD 0x00000020 /* Address format 0x000FF000 */ #define RDMA_CORE_CAP_AF_IB 0x00001000 #define RDMA_CORE_CAP_ETH_AH 0x00002000 #define RDMA_CORE_CAP_OPA_AH 0x00004000 #define RDMA_CORE_CAP_IB_GRH_REQUIRED 0x00008000 /* Protocol 0xFFF00000 */ #define RDMA_CORE_CAP_PROT_IB 0x00100000 #define RDMA_CORE_CAP_PROT_ROCE 0x00200000 #define RDMA_CORE_CAP_PROT_IWARP 0x00400000 #define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000 #define RDMA_CORE_CAP_PROT_RAW_PACKET 0x01000000 #define RDMA_CORE_CAP_PROT_USNIC 0x02000000 #define RDMA_CORE_PORT_IB_GRH_REQUIRED (RDMA_CORE_CAP_IB_GRH_REQUIRED \ | RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP) #define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_SMI \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_IB_SA \ | RDMA_CORE_CAP_AF_IB) #define RDMA_CORE_PORT_IBA_ROCE (RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP \ (RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \ | RDMA_CORE_CAP_IW_CM) #define RDMA_CORE_PORT_INTEL_OPA (RDMA_CORE_PORT_IBA_IB \ | RDMA_CORE_CAP_OPA_MAD) #define RDMA_CORE_PORT_RAW_PACKET (RDMA_CORE_CAP_PROT_RAW_PACKET) #define RDMA_CORE_PORT_USNIC (RDMA_CORE_CAP_PROT_USNIC) struct ib_port_attr { u64 subnet_prefix; enum ib_port_state state; enum ib_mtu max_mtu; enum ib_mtu active_mtu; u32 phys_mtu; int gid_tbl_len; unsigned int ip_gids:1; /* This is the value from PortInfo CapabilityMask, defined by IBA */ u32 port_cap_flags; u32 max_msg_sz; u32 bad_pkey_cntr; u32 qkey_viol_cntr; u16 pkey_tbl_len; u32 sm_lid; u32 lid; u8 lmc; u8 max_vl_num; u8 sm_sl; u8 subnet_timeout; u8 init_type_reply; u8 active_width; u16 active_speed; u8 phys_state; u16 port_cap_flags2; }; enum ib_device_modify_flags { IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 << 0, IB_DEVICE_MODIFY_NODE_DESC = 1 << 1 }; #define IB_DEVICE_NODE_DESC_MAX 64 struct ib_device_modify { u64 sys_image_guid; char node_desc[IB_DEVICE_NODE_DESC_MAX]; }; enum ib_port_modify_flags { IB_PORT_SHUTDOWN = 1, IB_PORT_INIT_TYPE = (1<<2), IB_PORT_RESET_QKEY_CNTR = (1<<3), IB_PORT_OPA_MASK_CHG = (1<<4) }; struct ib_port_modify { u32 set_port_cap_mask; u32 clr_port_cap_mask; u8 init_type; }; enum ib_event_type { IB_EVENT_CQ_ERR, IB_EVENT_QP_FATAL, IB_EVENT_QP_REQ_ERR, IB_EVENT_QP_ACCESS_ERR, IB_EVENT_COMM_EST, IB_EVENT_SQ_DRAINED, IB_EVENT_PATH_MIG, IB_EVENT_PATH_MIG_ERR, IB_EVENT_DEVICE_FATAL, IB_EVENT_PORT_ACTIVE, IB_EVENT_PORT_ERR, IB_EVENT_LID_CHANGE, IB_EVENT_PKEY_CHANGE, IB_EVENT_SM_CHANGE, IB_EVENT_SRQ_ERR, IB_EVENT_SRQ_LIMIT_REACHED, IB_EVENT_QP_LAST_WQE_REACHED, IB_EVENT_CLIENT_REREGISTER, IB_EVENT_GID_CHANGE, IB_EVENT_WQ_FATAL, }; const char *__attribute_const__ ib_event_msg(enum ib_event_type event); struct ib_event { struct ib_device *device; union { struct ib_cq *cq; struct ib_qp *qp; struct ib_srq *srq; struct ib_wq *wq; u32 port_num; } element; enum ib_event_type event; }; struct ib_event_handler { struct ib_device *device; void (*handler)(struct ib_event_handler *, struct ib_event *); struct list_head list; }; #define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler) \ do { \ (_ptr)->device = _device; \ (_ptr)->handler = _handler; \ INIT_LIST_HEAD(&(_ptr)->list); \ } while (0) struct ib_global_route { const struct ib_gid_attr *sgid_attr; union ib_gid dgid; u32 flow_label; u8 sgid_index; u8 hop_limit; u8 traffic_class; }; struct ib_grh { __be32 version_tclass_flow; __be16 paylen; u8 next_hdr; u8 hop_limit; union ib_gid sgid; union ib_gid dgid; }; union rdma_network_hdr { struct ib_grh ibgrh; struct { /* The IB spec states that if it's IPv4, the header * is located in the last 20 bytes of the header. */ u8 reserved[20]; struct iphdr roce4grh; }; }; #define IB_QPN_MASK 0xFFFFFF enum { IB_MULTICAST_QPN = 0xffffff }; #define IB_LID_PERMISSIVE cpu_to_be16(0xFFFF) #define IB_MULTICAST_LID_BASE cpu_to_be16(0xC000) enum ib_ah_flags { IB_AH_GRH = 1 }; enum ib_rate { IB_RATE_PORT_CURRENT = 0, IB_RATE_2_5_GBPS = 2, IB_RATE_5_GBPS = 5, IB_RATE_10_GBPS = 3, IB_RATE_20_GBPS = 6, IB_RATE_30_GBPS = 4, IB_RATE_40_GBPS = 7, IB_RATE_60_GBPS = 8, IB_RATE_80_GBPS = 9, IB_RATE_120_GBPS = 10, IB_RATE_14_GBPS = 11, IB_RATE_56_GBPS = 12, IB_RATE_112_GBPS = 13, IB_RATE_168_GBPS = 14, IB_RATE_25_GBPS = 15, IB_RATE_100_GBPS = 16, IB_RATE_200_GBPS = 17, IB_RATE_300_GBPS = 18, IB_RATE_28_GBPS = 19, IB_RATE_50_GBPS = 20, IB_RATE_400_GBPS = 21, IB_RATE_600_GBPS = 22, IB_RATE_800_GBPS = 23, }; /** * ib_rate_to_mult - Convert the IB rate enum to a multiple of the * base rate of 2.5 Gbit/sec. For example, IB_RATE_5_GBPS will be * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mult(enum ib_rate rate); /** * ib_rate_to_mbps - Convert the IB rate enum to Mbps. * For example, IB_RATE_2_5_GBPS will be converted to 2500. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate); /** * enum ib_mr_type - memory region type * @IB_MR_TYPE_MEM_REG: memory region that is used for * normal registration * @IB_MR_TYPE_SG_GAPS: memory region that is capable to * register any arbitrary sg lists (without * the normal mr constraints - see * ib_map_mr_sg) * @IB_MR_TYPE_DM: memory region that is used for device * memory registration * @IB_MR_TYPE_USER: memory region that is used for the user-space * application * @IB_MR_TYPE_DMA: memory region that is used for DMA operations * without address translations (VA=PA) * @IB_MR_TYPE_INTEGRITY: memory region that is used for * data integrity operations */ enum ib_mr_type { IB_MR_TYPE_MEM_REG, IB_MR_TYPE_SG_GAPS, IB_MR_TYPE_DM, IB_MR_TYPE_USER, IB_MR_TYPE_DMA, IB_MR_TYPE_INTEGRITY, }; enum ib_mr_status_check { IB_MR_CHECK_SIG_STATUS = 1, }; /** * struct ib_mr_status - Memory region status container * * @fail_status: Bitmask of MR checks status. For each * failed check a corresponding status bit is set. * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS * failure. */ struct ib_mr_status { u32 fail_status; struct ib_sig_err sig_err; }; /** * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate * enum. * @mult: multiple to convert. */ __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); struct rdma_ah_init_attr { struct rdma_ah_attr *ah_attr; u32 flags; struct net_device *xmit_slave; }; enum rdma_ah_attr_type { RDMA_AH_ATTR_TYPE_UNDEFINED, RDMA_AH_ATTR_TYPE_IB, RDMA_AH_ATTR_TYPE_ROCE, RDMA_AH_ATTR_TYPE_OPA, }; struct ib_ah_attr { u16 dlid; u8 src_path_bits; }; struct roce_ah_attr { u8 dmac[ETH_ALEN]; }; struct opa_ah_attr { u32 dlid; u8 src_path_bits; bool make_grd; }; struct rdma_ah_attr { struct ib_global_route grh; u8 sl; u8 static_rate; u32 port_num; u8 ah_flags; enum rdma_ah_attr_type type; union { struct ib_ah_attr ib; struct roce_ah_attr roce; struct opa_ah_attr opa; }; }; enum ib_wc_status { IB_WC_SUCCESS, IB_WC_LOC_LEN_ERR, IB_WC_LOC_QP_OP_ERR, IB_WC_LOC_EEC_OP_ERR, IB_WC_LOC_PROT_ERR, IB_WC_WR_FLUSH_ERR, IB_WC_MW_BIND_ERR, IB_WC_BAD_RESP_ERR, IB_WC_LOC_ACCESS_ERR, IB_WC_REM_INV_REQ_ERR, IB_WC_REM_ACCESS_ERR, IB_WC_REM_OP_ERR, IB_WC_RETRY_EXC_ERR, IB_WC_RNR_RETRY_EXC_ERR, IB_WC_LOC_RDD_VIOL_ERR, IB_WC_REM_INV_RD_REQ_ERR, IB_WC_REM_ABORT_ERR, IB_WC_INV_EECN_ERR, IB_WC_INV_EEC_STATE_ERR, IB_WC_FATAL_ERR, IB_WC_RESP_TIMEOUT_ERR, IB_WC_GENERAL_ERR }; const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status); enum ib_wc_opcode { IB_WC_SEND = IB_UVERBS_WC_SEND, IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE, IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ, IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP, IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD, IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW, IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV, IB_WC_LSO = IB_UVERBS_WC_TSO, IB_WC_ATOMIC_WRITE = IB_UVERBS_WC_ATOMIC_WRITE, IB_WC_REG_MR, IB_WC_MASKED_COMP_SWAP, IB_WC_MASKED_FETCH_ADD, IB_WC_FLUSH = IB_UVERBS_WC_FLUSH, /* * Set value of IB_WC_RECV so consumers can test if a completion is a * receive by testing (opcode & IB_WC_RECV). */ IB_WC_RECV = 1 << 7, IB_WC_RECV_RDMA_WITH_IMM }; enum ib_wc_flags { IB_WC_GRH = 1, IB_WC_WITH_IMM = (1<<1), IB_WC_WITH_INVALIDATE = (1<<2), IB_WC_IP_CSUM_OK = (1<<3), IB_WC_WITH_SMAC = (1<<4), IB_WC_WITH_VLAN = (1<<5), IB_WC_WITH_NETWORK_HDR_TYPE = (1<<6), }; struct ib_wc { union { u64 wr_id; struct ib_cqe *wr_cqe; }; enum ib_wc_status status; enum ib_wc_opcode opcode; u32 vendor_err; u32 byte_len; struct ib_qp *qp; union { __be32 imm_data; u32 invalidate_rkey; } ex; u32 src_qp; u32 slid; int wc_flags; u16 pkey_index; u8 sl; u8 dlid_path_bits; u32 port_num; /* valid only for DR SMPs on switches */ u8 smac[ETH_ALEN]; u16 vlan_id; u8 network_hdr_type; }; enum ib_cq_notify_flags { IB_CQ_SOLICITED = 1 << 0, IB_CQ_NEXT_COMP = 1 << 1, IB_CQ_SOLICITED_MASK = IB_CQ_SOLICITED | IB_CQ_NEXT_COMP, IB_CQ_REPORT_MISSED_EVENTS = 1 << 2, }; enum ib_srq_type { IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC, IB_SRQT_XRC = IB_UVERBS_SRQT_XRC, IB_SRQT_TM = IB_UVERBS_SRQT_TM, }; static inline bool ib_srq_has_cq(enum ib_srq_type srq_type) { return srq_type == IB_SRQT_XRC || srq_type == IB_SRQT_TM; } enum ib_srq_attr_mask { IB_SRQ_MAX_WR = 1 << 0, IB_SRQ_LIMIT = 1 << 1, }; struct ib_srq_attr { u32 max_wr; u32 max_sge; u32 srq_limit; }; struct ib_srq_init_attr { void (*event_handler)(struct ib_event *, void *); void *srq_context; struct ib_srq_attr attr; enum ib_srq_type srq_type; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; } xrc; struct { u32 max_num_tags; } tag_matching; }; } ext; }; struct ib_qp_cap { u32 max_send_wr; u32 max_recv_wr; u32 max_send_sge; u32 max_recv_sge; u32 max_inline_data; /* * Maximum number of rdma_rw_ctx structures in flight at a time. * ib_create_qp() will calculate the right amount of needed WRs * and MRs based on this. */ u32 max_rdma_ctxs; }; enum ib_sig_type { IB_SIGNAL_ALL_WR, IB_SIGNAL_REQ_WR }; enum ib_qp_type { /* * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries * here (and in that order) since the MAD layer uses them as * indices into a 2-entry table. */ IB_QPT_SMI, IB_QPT_GSI, IB_QPT_RC = IB_UVERBS_QPT_RC, IB_QPT_UC = IB_UVERBS_QPT_UC, IB_QPT_UD = IB_UVERBS_QPT_UD, IB_QPT_RAW_IPV6, IB_QPT_RAW_ETHERTYPE, IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET, IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI, IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT, IB_QPT_MAX, IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER, /* Reserve a range for qp types internal to the low level driver. * These qp types will not be visible at the IB core layer, so the * IB_QPT_MAX usages should not be affected in the core layer */ IB_QPT_RESERVED1 = 0x1000, IB_QPT_RESERVED2, IB_QPT_RESERVED3, IB_QPT_RESERVED4, IB_QPT_RESERVED5, IB_QPT_RESERVED6, IB_QPT_RESERVED7, IB_QPT_RESERVED8, IB_QPT_RESERVED9, IB_QPT_RESERVED10, }; enum ib_qp_create_flags { IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0, IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK, IB_QP_CREATE_CROSS_CHANNEL = 1 << 2, IB_QP_CREATE_MANAGED_SEND = 1 << 3, IB_QP_CREATE_MANAGED_RECV = 1 << 4, IB_QP_CREATE_NETIF_QP = 1 << 5, IB_QP_CREATE_INTEGRITY_EN = 1 << 6, IB_QP_CREATE_NETDEV_USE = 1 << 7, IB_QP_CREATE_SCATTER_FCS = IB_UVERBS_QP_CREATE_SCATTER_FCS, IB_QP_CREATE_CVLAN_STRIPPING = IB_UVERBS_QP_CREATE_CVLAN_STRIPPING, IB_QP_CREATE_SOURCE_QPN = 1 << 10, IB_QP_CREATE_PCI_WRITE_END_PADDING = IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, }; /* * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler * callback to destroy the passed in QP. */ struct ib_qp_init_attr { /* This callback occurs in workqueue context */ void (*event_handler)(struct ib_event *, void *); void *qp_context; struct ib_cq *send_cq; struct ib_cq *recv_cq; struct ib_srq *srq; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct ib_qp_cap cap; enum ib_sig_type sq_sig_type; enum ib_qp_type qp_type; u32 create_flags; /* * Only needed for special QP types, or when using the RW API. */ u32 port_num; struct ib_rwq_ind_table *rwq_ind_tbl; u32 source_qpn; }; struct ib_qp_open_attr { void (*event_handler)(struct ib_event *, void *); void *qp_context; u32 qp_num; enum ib_qp_type qp_type; }; enum ib_rnr_timeout { IB_RNR_TIMER_655_36 = 0, IB_RNR_TIMER_000_01 = 1, IB_RNR_TIMER_000_02 = 2, IB_RNR_TIMER_000_03 = 3, IB_RNR_TIMER_000_04 = 4, IB_RNR_TIMER_000_06 = 5, IB_RNR_TIMER_000_08 = 6, IB_RNR_TIMER_000_12 = 7, IB_RNR_TIMER_000_16 = 8, IB_RNR_TIMER_000_24 = 9, IB_RNR_TIMER_000_32 = 10, IB_RNR_TIMER_000_48 = 11, IB_RNR_TIMER_000_64 = 12, IB_RNR_TIMER_000_96 = 13, IB_RNR_TIMER_001_28 = 14, IB_RNR_TIMER_001_92 = 15, IB_RNR_TIMER_002_56 = 16, IB_RNR_TIMER_003_84 = 17, IB_RNR_TIMER_005_12 = 18, IB_RNR_TIMER_007_68 = 19, IB_RNR_TIMER_010_24 = 20, IB_RNR_TIMER_015_36 = 21, IB_RNR_TIMER_020_48 = 22, IB_RNR_TIMER_030_72 = 23, IB_RNR_TIMER_040_96 = 24, IB_RNR_TIMER_061_44 = 25, IB_RNR_TIMER_081_92 = 26, IB_RNR_TIMER_122_88 = 27, IB_RNR_TIMER_163_84 = 28, IB_RNR_TIMER_245_76 = 29, IB_RNR_TIMER_327_68 = 30, IB_RNR_TIMER_491_52 = 31 }; enum ib_qp_attr_mask { IB_QP_STATE = 1, IB_QP_CUR_STATE = (1<<1), IB_QP_EN_SQD_ASYNC_NOTIFY = (1<<2), IB_QP_ACCESS_FLAGS = (1<<3), IB_QP_PKEY_INDEX = (1<<4), IB_QP_PORT = (1<<5), IB_QP_QKEY = (1<<6), IB_QP_AV = (1<<7), IB_QP_PATH_MTU = (1<<8), IB_QP_TIMEOUT = (1<<9), IB_QP_RETRY_CNT = (1<<10), IB_QP_RNR_RETRY = (1<<11), IB_QP_RQ_PSN = (1<<12), IB_QP_MAX_QP_RD_ATOMIC = (1<<13), IB_QP_ALT_PATH = (1<<14), IB_QP_MIN_RNR_TIMER = (1<<15), IB_QP_SQ_PSN = (1<<16), IB_QP_MAX_DEST_RD_ATOMIC = (1<<17), IB_QP_PATH_MIG_STATE = (1<<18), IB_QP_CAP = (1<<19), IB_QP_DEST_QPN = (1<<20), IB_QP_RESERVED1 = (1<<21), IB_QP_RESERVED2 = (1<<22), IB_QP_RESERVED3 = (1<<23), IB_QP_RESERVED4 = (1<<24), IB_QP_RATE_LIMIT = (1<<25), IB_QP_ATTR_STANDARD_BITS = GENMASK(20, 0), }; enum ib_qp_state { IB_QPS_RESET, IB_QPS_INIT, IB_QPS_RTR, IB_QPS_RTS, IB_QPS_SQD, IB_QPS_SQE, IB_QPS_ERR }; enum ib_mig_state { IB_MIG_MIGRATED, IB_MIG_REARM, IB_MIG_ARMED }; enum ib_mw_type { IB_MW_TYPE_1 = 1, IB_MW_TYPE_2 = 2 }; struct ib_qp_attr { enum ib_qp_state qp_state; enum ib_qp_state cur_qp_state; enum ib_mtu path_mtu; enum ib_mig_state path_mig_state; u32 qkey; u32 rq_psn; u32 sq_psn; u32 dest_qp_num; int qp_access_flags; struct ib_qp_cap cap; struct rdma_ah_attr ah_attr; struct rdma_ah_attr alt_ah_attr; u16 pkey_index; u16 alt_pkey_index; u8 en_sqd_async_notify; u8 sq_draining; u8 max_rd_atomic; u8 max_dest_rd_atomic; u8 min_rnr_timer; u32 port_num; u8 timeout; u8 retry_cnt; u8 rnr_retry; u32 alt_port_num; u8 alt_timeout; u32 rate_limit; struct net_device *xmit_slave; }; enum ib_wr_opcode { /* These are shared with userspace */ IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE, IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM, IB_WR_SEND = IB_UVERBS_WR_SEND, IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM, IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ, IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP, IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD, IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW, IB_WR_LSO = IB_UVERBS_WR_TSO, IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV, IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV, IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV, IB_WR_MASKED_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP, IB_WR_MASKED_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD, IB_WR_FLUSH = IB_UVERBS_WR_FLUSH, IB_WR_ATOMIC_WRITE = IB_UVERBS_WR_ATOMIC_WRITE, /* These are kernel only and can not be issued by userspace */ IB_WR_REG_MR = 0x20, IB_WR_REG_MR_INTEGRITY, /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. */ IB_WR_RESERVED1 = 0xf0, IB_WR_RESERVED2, IB_WR_RESERVED3, IB_WR_RESERVED4, IB_WR_RESERVED5, IB_WR_RESERVED6, IB_WR_RESERVED7, IB_WR_RESERVED8, IB_WR_RESERVED9, IB_WR_RESERVED10, }; enum ib_send_flags { IB_SEND_FENCE = 1, IB_SEND_SIGNALED = (1<<1), IB_SEND_SOLICITED = (1<<2), IB_SEND_INLINE = (1<<3), IB_SEND_IP_CSUM = (1<<4), /* reserve bits 26-31 for low level drivers' internal use */ IB_SEND_RESERVED_START = (1 << 26), IB_SEND_RESERVED_END = (1 << 31), }; struct ib_sge { u64 addr; u32 length; u32 lkey; }; struct ib_cqe { void (*done)(struct ib_cq *cq, struct ib_wc *wc); }; struct ib_send_wr { struct ib_send_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; enum ib_wr_opcode opcode; int send_flags; union { __be32 imm_data; u32 invalidate_rkey; } ex; }; struct ib_rdma_wr { struct ib_send_wr wr; u64 remote_addr; u32 rkey; }; static inline const struct ib_rdma_wr *rdma_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_rdma_wr, wr); } struct ib_atomic_wr { struct ib_send_wr wr; u64 remote_addr; u64 compare_add; u64 swap; u64 compare_add_mask; u64 swap_mask; u32 rkey; }; static inline const struct ib_atomic_wr *atomic_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_atomic_wr, wr); } struct ib_ud_wr { struct ib_send_wr wr; struct ib_ah *ah; void *header; int hlen; int mss; u32 remote_qpn; u32 remote_qkey; u16 pkey_index; /* valid for GSI only */ u32 port_num; /* valid for DR SMPs on switch only */ }; static inline const struct ib_ud_wr *ud_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_ud_wr, wr); } struct ib_reg_wr { struct ib_send_wr wr; struct ib_mr *mr; u32 key; int access; }; static inline const struct ib_reg_wr *reg_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_reg_wr, wr); } struct ib_recv_wr { struct ib_recv_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; }; enum ib_access_flags { IB_ACCESS_LOCAL_WRITE = IB_UVERBS_ACCESS_LOCAL_WRITE, IB_ACCESS_REMOTE_WRITE = IB_UVERBS_ACCESS_REMOTE_WRITE, IB_ACCESS_REMOTE_READ = IB_UVERBS_ACCESS_REMOTE_READ, IB_ACCESS_REMOTE_ATOMIC = IB_UVERBS_ACCESS_REMOTE_ATOMIC, IB_ACCESS_MW_BIND = IB_UVERBS_ACCESS_MW_BIND, IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED, IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND, IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB, IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING, IB_ACCESS_FLUSH_GLOBAL = IB_UVERBS_ACCESS_FLUSH_GLOBAL, IB_ACCESS_FLUSH_PERSISTENT = IB_UVERBS_ACCESS_FLUSH_PERSISTENT, IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE, IB_ACCESS_SUPPORTED = ((IB_ACCESS_FLUSH_PERSISTENT << 1) - 1) | IB_ACCESS_OPTIONAL, }; /* * XXX: these are apparently used for ->rereg_user_mr, no idea why they * are hidden here instead of a uapi header! */ enum ib_mr_rereg_flags { IB_MR_REREG_TRANS = 1, IB_MR_REREG_PD = (1<<1), IB_MR_REREG_ACCESS = (1<<2), IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1) }; struct ib_umem; enum rdma_remove_reason { /* * Userspace requested uobject deletion or initial try * to remove uobject via cleanup. Call could fail */ RDMA_REMOVE_DESTROY, /* Context deletion. This call should delete the actual object itself */ RDMA_REMOVE_CLOSE, /* Driver is being hot-unplugged. This call should delete the actual object itself */ RDMA_REMOVE_DRIVER_REMOVE, /* uobj is being cleaned-up before being committed */ RDMA_REMOVE_ABORT, /* The driver failed to destroy the uobject and is being disconnected */ RDMA_REMOVE_DRIVER_FAILURE, }; struct ib_rdmacg_object { #ifdef CONFIG_CGROUP_RDMA struct rdma_cgroup *cg; /* owner rdma cgroup */ #endif }; struct ib_ucontext { struct ib_device *device; struct ib_uverbs_file *ufile; struct ib_rdmacg_object cg_obj; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; struct xarray mmap_xa; }; struct ib_uobject { u64 user_handle; /* handle given to us by userspace */ /* ufile & ucontext owning this object */ struct ib_uverbs_file *ufile; /* FIXME, save memory: ufile->context == context */ struct ib_ucontext *context; /* associated user context */ void *object; /* containing object */ struct list_head list; /* link to context's list */ struct ib_rdmacg_object cg_obj; /* rdmacg object */ int id; /* index into kernel idr */ struct kref ref; atomic_t usecnt; /* protects exclusive access */ struct rcu_head rcu; /* kfree_rcu() overhead */ const struct uverbs_api_object *uapi_object; }; struct ib_udata { const void __user *inbuf; void __user *outbuf; size_t inlen; size_t outlen; }; struct ib_pd { u32 local_dma_lkey; u32 flags; struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; /* count all resources */ u32 unsafe_global_rkey; /* * Implementation details of the RDMA core, don't use in drivers: */ struct ib_mr *__internal_mr; struct rdma_restrack_entry res; }; struct ib_xrcd { struct ib_device *device; atomic_t usecnt; /* count all exposed resources */ struct inode *inode; struct rw_semaphore tgt_qps_rwsem; struct xarray tgt_qps; }; struct ib_ah { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; const struct ib_gid_attr *sgid_attr; enum rdma_ah_attr_type type; }; typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context); enum ib_poll_context { IB_POLL_SOFTIRQ, /* poll from softirq context */ IB_POLL_WORKQUEUE, /* poll from workqueue */ IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */ IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE, IB_POLL_DIRECT, /* caller context, no hw completions */ }; struct ib_cq { struct ib_device *device; struct ib_ucq_object *uobject; ib_comp_handler comp_handler; void (*event_handler)(struct ib_event *, void *); void *cq_context; int cqe; unsigned int cqe_used; atomic_t usecnt; /* count number of work queues */ enum ib_poll_context poll_ctx; struct ib_wc *wc; struct list_head pool_entry; union { struct irq_poll iop; struct work_struct work; }; struct workqueue_struct *comp_wq; struct dim *dim; /* updated only by trace points */ ktime_t timestamp; u8 interrupt:1; u8 shared:1; unsigned int comp_vector; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_srq { struct ib_device *device; struct ib_pd *pd; struct ib_usrq_object *uobject; void (*event_handler)(struct ib_event *, void *); void *srq_context; enum ib_srq_type srq_type; atomic_t usecnt; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; u32 srq_num; } xrc; }; } ext; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; enum ib_raw_packet_caps { /* * Strip cvlan from incoming packet and report it in the matching work * completion is supported. */ IB_RAW_PACKET_CAP_CVLAN_STRIPPING = IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING, /* * Scatter FCS field of an incoming packet to host memory is supported. */ IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS, /* Checksum offloads are supported (for both send and receive). */ IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM, /* * When a packet is received for an RQ with no receive WQEs, the * packet processing is delayed. */ IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP, }; enum ib_wq_type { IB_WQT_RQ = IB_UVERBS_WQT_RQ, }; enum ib_wq_state { IB_WQS_RESET, IB_WQS_RDY, IB_WQS_ERR }; struct ib_wq { struct ib_device *device; struct ib_uwq_object *uobject; void *wq_context; void (*event_handler)(struct ib_event *, void *); struct ib_pd *pd; struct ib_cq *cq; u32 wq_num; enum ib_wq_state state; enum ib_wq_type wq_type; atomic_t usecnt; }; enum ib_wq_flags { IB_WQ_FLAGS_CVLAN_STRIPPING = IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING, IB_WQ_FLAGS_SCATTER_FCS = IB_UVERBS_WQ_FLAGS_SCATTER_FCS, IB_WQ_FLAGS_DELAY_DROP = IB_UVERBS_WQ_FLAGS_DELAY_DROP, IB_WQ_FLAGS_PCI_WRITE_END_PADDING = IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING, }; struct ib_wq_init_attr { void *wq_context; enum ib_wq_type wq_type; u32 max_wr; u32 max_sge; struct ib_cq *cq; void (*event_handler)(struct ib_event *, void *); u32 create_flags; /* Use enum ib_wq_flags */ }; enum ib_wq_attr_mask { IB_WQ_STATE = 1 << 0, IB_WQ_CUR_STATE = 1 << 1, IB_WQ_FLAGS = 1 << 2, }; struct ib_wq_attr { enum ib_wq_state wq_state; enum ib_wq_state curr_wq_state; u32 flags; /* Use enum ib_wq_flags */ u32 flags_mask; /* Use enum ib_wq_flags */ }; struct ib_rwq_ind_table { struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; u32 ind_tbl_num; u32 log_ind_tbl_size; struct ib_wq **ind_tbl; }; struct ib_rwq_ind_table_init_attr { u32 log_ind_tbl_size; /* Each entry is a pointer to Receive Work Queue */ struct ib_wq **ind_tbl; }; enum port_pkey_state { IB_PORT_PKEY_NOT_VALID = 0, IB_PORT_PKEY_VALID = 1, IB_PORT_PKEY_LISTED = 2, }; struct ib_qp_security; struct ib_port_pkey { enum port_pkey_state state; u16 pkey_index; u32 port_num; struct list_head qp_list; struct list_head to_error_list; struct ib_qp_security *sec; }; struct ib_ports_pkeys { struct ib_port_pkey main; struct ib_port_pkey alt; }; struct ib_qp_security { struct ib_qp *qp; struct ib_device *dev; /* Hold this mutex when changing port and pkey settings. */ struct mutex mutex; struct ib_ports_pkeys *ports_pkeys; /* A list of all open shared QP handles. Required to enforce security * properly for all users of a shared QP. */ struct list_head shared_qp_list; void *security; bool destroying; atomic_t error_list_count; struct completion error_complete; int error_comps_pending; }; /* * @max_write_sge: Maximum SGE elements per RDMA WRITE request. * @max_read_sge: Maximum SGE elements per RDMA READ request. */ struct ib_qp { struct ib_device *device; struct ib_pd *pd; struct ib_cq *send_cq; struct ib_cq *recv_cq; spinlock_t mr_lock; int mrs_used; struct list_head rdma_mrs; struct list_head sig_mrs; struct ib_srq *srq; struct completion srq_completion; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct list_head xrcd_list; /* count times opened, mcast attaches, flow attaches */ atomic_t usecnt; struct list_head open_list; struct ib_qp *real_qp; struct ib_uqp_object *uobject; void (*event_handler)(struct ib_event *, void *); void (*registered_event_handler)(struct ib_event *, void *); void *qp_context; /* sgid_attrs associated with the AV's */ const struct ib_gid_attr *av_sgid_attr; const struct ib_gid_attr *alt_path_sgid_attr; u32 qp_num; u32 max_write_sge; u32 max_read_sge; enum ib_qp_type qp_type; struct ib_rwq_ind_table *rwq_ind_tbl; struct ib_qp_security *qp_sec; u32 port; bool integrity_en; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; /* The counter the qp is bind to */ struct rdma_counter *counter; }; struct ib_dm { struct ib_device *device; u32 length; u32 flags; struct ib_uobject *uobject; atomic_t usecnt; }; struct ib_mr { struct ib_device *device; struct ib_pd *pd; u32 lkey; u32 rkey; u64 iova; u64 length; unsigned int page_size; enum ib_mr_type type; bool need_inval; union { struct ib_uobject *uobject; /* user */ struct list_head qp_entry; /* FR */ }; struct ib_dm *dm; struct ib_sig_attrs *sig_attrs; /* only for IB_MR_TYPE_INTEGRITY MRs */ /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_mw { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; u32 rkey; enum ib_mw_type type; }; /* Supported steering options */ enum ib_flow_attr_type { /* steering according to rule specifications */ IB_FLOW_ATTR_NORMAL = 0x0, /* default unicast and multicast rule - * receive all Eth traffic which isn't steered to any QP */ IB_FLOW_ATTR_ALL_DEFAULT = 0x1, /* default multicast rule - * receive all Eth multicast traffic which isn't steered to any QP */ IB_FLOW_ATTR_MC_DEFAULT = 0x2, /* sniffer rule - receive all port traffic */ IB_FLOW_ATTR_SNIFFER = 0x3 }; /* Supported steering header types */ enum ib_flow_spec_type { /* L2 headers*/ IB_FLOW_SPEC_ETH = 0x20, IB_FLOW_SPEC_IB = 0x22, /* L3 header*/ IB_FLOW_SPEC_IPV4 = 0x30, IB_FLOW_SPEC_IPV6 = 0x31, IB_FLOW_SPEC_ESP = 0x34, /* L4 headers*/ IB_FLOW_SPEC_TCP = 0x40, IB_FLOW_SPEC_UDP = 0x41, IB_FLOW_SPEC_VXLAN_TUNNEL = 0x50, IB_FLOW_SPEC_GRE = 0x51, IB_FLOW_SPEC_MPLS = 0x60, IB_FLOW_SPEC_INNER = 0x100, /* Actions */ IB_FLOW_SPEC_ACTION_TAG = 0x1000, IB_FLOW_SPEC_ACTION_DROP = 0x1001, IB_FLOW_SPEC_ACTION_HANDLE = 0x1002, IB_FLOW_SPEC_ACTION_COUNT = 0x1003, }; #define IB_FLOW_SPEC_LAYER_MASK 0xF0 #define IB_FLOW_SPEC_SUPPORT_LAYERS 10 enum ib_flow_flags { IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */ IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */ IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 3 /* Must be last */ }; struct ib_flow_eth_filter { u8 dst_mac[6]; u8 src_mac[6]; __be16 ether_type; __be16 vlan_tag; }; struct ib_flow_spec_eth { u32 type; u16 size; struct ib_flow_eth_filter val; struct ib_flow_eth_filter mask; }; struct ib_flow_ib_filter { __be16 dlid; __u8 sl; }; struct ib_flow_spec_ib { u32 type; u16 size; struct ib_flow_ib_filter val; struct ib_flow_ib_filter mask; }; /* IPv4 header flags */ enum ib_ipv4_flags { IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */ IB_IPV4_MORE_FRAG = 0X4 /* For All fragmented packets except the last have this flag set */ }; struct ib_flow_ipv4_filter { __be32 src_ip; __be32 dst_ip; u8 proto; u8 tos; u8 ttl; u8 flags; }; struct ib_flow_spec_ipv4 { u32 type; u16 size; struct ib_flow_ipv4_filter val; struct ib_flow_ipv4_filter mask; }; struct ib_flow_ipv6_filter { u8 src_ip[16]; u8 dst_ip[16]; __be32 flow_label; u8 next_hdr; u8 traffic_class; u8 hop_limit; } __packed; struct ib_flow_spec_ipv6 { u32 type; u16 size; struct ib_flow_ipv6_filter val; struct ib_flow_ipv6_filter mask; }; struct ib_flow_tcp_udp_filter { __be16 dst_port; __be16 src_port; }; struct ib_flow_spec_tcp_udp { u32 type; u16 size; struct ib_flow_tcp_udp_filter val; struct ib_flow_tcp_udp_filter mask; }; struct ib_flow_tunnel_filter { __be32 tunnel_id; }; /* ib_flow_spec_tunnel describes the Vxlan tunnel * the tunnel_id from val has the vni value */ struct ib_flow_spec_tunnel { u32 type; u16 size; struct ib_flow_tunnel_filter val; struct ib_flow_tunnel_filter mask; }; struct ib_flow_esp_filter { __be32 spi; __be32 seq; }; struct ib_flow_spec_esp { u32 type; u16 size; struct ib_flow_esp_filter val; struct ib_flow_esp_filter mask; }; struct ib_flow_gre_filter { __be16 c_ks_res0_ver; __be16 protocol; __be32 key; }; struct ib_flow_spec_gre { u32 type; u16 size; struct ib_flow_gre_filter val; struct ib_flow_gre_filter mask; }; struct ib_flow_mpls_filter { __be32 tag; }; struct ib_flow_spec_mpls { u32 type; u16 size; struct ib_flow_mpls_filter val; struct ib_flow_mpls_filter mask; }; struct ib_flow_spec_action_tag { enum ib_flow_spec_type type; u16 size; u32 tag_id; }; struct ib_flow_spec_action_drop { enum ib_flow_spec_type type; u16 size; }; struct ib_flow_spec_action_handle { enum ib_flow_spec_type type; u16 size; struct ib_flow_action *act; }; enum ib_counters_description { IB_COUNTER_PACKETS, IB_COUNTER_BYTES, }; struct ib_flow_spec_action_count { enum ib_flow_spec_type type; u16 size; struct ib_counters *counters; }; union ib_flow_spec { struct { u32 type; u16 size; }; struct ib_flow_spec_eth eth; struct ib_flow_spec_ib ib; struct ib_flow_spec_ipv4 ipv4; struct ib_flow_spec_tcp_udp tcp_udp; struct ib_flow_spec_ipv6 ipv6; struct ib_flow_spec_tunnel tunnel; struct ib_flow_spec_esp esp; struct ib_flow_spec_gre gre; struct ib_flow_spec_mpls mpls; struct ib_flow_spec_action_tag flow_tag; struct ib_flow_spec_action_drop drop; struct ib_flow_spec_action_handle action; struct ib_flow_spec_action_count flow_count; }; struct ib_flow_attr { enum ib_flow_attr_type type; u16 size; u16 priority; u32 flags; u8 num_of_specs; u32 port; union ib_flow_spec flows[]; }; struct ib_flow { struct ib_qp *qp; struct ib_device *device; struct ib_uobject *uobject; }; enum ib_flow_action_type { IB_FLOW_ACTION_UNSPECIFIED, IB_FLOW_ACTION_ESP = 1, }; struct ib_flow_action_attrs_esp_keymats { enum ib_uverbs_flow_action_esp_keymat protocol; union { struct ib_uverbs_flow_action_esp_keymat_aes_gcm aes_gcm; } keymat; }; struct ib_flow_action_attrs_esp_replays { enum ib_uverbs_flow_action_esp_replay protocol; union { struct ib_uverbs_flow_action_esp_replay_bmp bmp; } replay; }; enum ib_flow_action_attrs_esp_flags { /* All user-space flags at the top: Use enum ib_uverbs_flow_action_esp_flags * This is done in order to share the same flags between user-space and * kernel and spare an unnecessary translation. */ /* Kernel flags */ IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED = 1ULL << 32, IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS = 1ULL << 33, }; struct ib_flow_spec_list { struct ib_flow_spec_list *next; union ib_flow_spec spec; }; struct ib_flow_action_attrs_esp { struct ib_flow_action_attrs_esp_keymats *keymat; struct ib_flow_action_attrs_esp_replays *replay; struct ib_flow_spec_list *encap; /* Used only if IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED is enabled. * Value of 0 is a valid value. */ u32 esn; u32 spi; u32 seq; u32 tfc_pad; /* Use enum ib_flow_action_attrs_esp_flags */ u64 flags; u64 hard_limit_pkts; }; struct ib_flow_action { struct ib_device *device; struct ib_uobject *uobject; enum ib_flow_action_type type; atomic_t usecnt; }; struct ib_mad; enum ib_process_mad_flags { IB_MAD_IGNORE_MKEY = 1, IB_MAD_IGNORE_BKEY = 2, IB_MAD_IGNORE_ALL = IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY }; enum ib_mad_result { IB_MAD_RESULT_FAILURE = 0, /* (!SUCCESS is the important flag) */ IB_MAD_RESULT_SUCCESS = 1 << 0, /* MAD was successfully processed */ IB_MAD_RESULT_REPLY = 1 << 1, /* Reply packet needs to be sent */ IB_MAD_RESULT_CONSUMED = 1 << 2 /* Packet consumed: stop processing */ }; struct ib_port_cache { u64 subnet_prefix; struct ib_pkey_cache *pkey; struct ib_gid_table *gid; u8 lmc; enum ib_port_state port_state; }; struct ib_port_immutable { int pkey_tbl_len; int gid_tbl_len; u32 core_cap_flags; u32 max_mad_size; }; struct ib_port_data { struct ib_device *ib_dev; struct ib_port_immutable immutable; spinlock_t pkey_list_lock; spinlock_t netdev_lock; struct list_head pkey_list; struct ib_port_cache cache; struct net_device __rcu *netdev; netdevice_tracker netdev_tracker; struct hlist_node ndev_hash_link; struct rdma_port_counter port_counter; struct ib_port *sysfs; }; /* rdma netdev type - specifies protocol type */ enum rdma_netdev_t { RDMA_NETDEV_OPA_VNIC, RDMA_NETDEV_IPOIB, }; /** * struct rdma_netdev - rdma netdev * For cases where netstack interfacing is required. */ struct rdma_netdev { void *clnt_priv; struct ib_device *hca; u32 port_num; int mtu; /* * cleanup function must be specified. * FIXME: This is only used for OPA_VNIC and that usage should be * removed too. */ void (*free_rdma_netdev)(struct net_device *netdev); /* control functions */ void (*set_id)(struct net_device *netdev, int id); /* send packet */ int (*send)(struct net_device *dev, struct sk_buff *skb, struct ib_ah *address, u32 dqpn); /* multicast */ int (*attach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid, int set_qkey, u32 qkey); int (*detach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid); /* timeout */ void (*tx_timeout)(struct net_device *dev, unsigned int txqueue); }; struct rdma_netdev_alloc_params { size_t sizeof_priv; unsigned int txqs; unsigned int rxqs; void *param; int (*initialize_rdma_netdev)(struct ib_device *device, u32 port_num, struct net_device *netdev, void *param); }; struct ib_odp_counters { atomic64_t faults; atomic64_t invalidations; atomic64_t prefetch; }; struct ib_counters { struct ib_device *device; struct ib_uobject *uobject; /* num of objects attached */ atomic_t usecnt; }; struct ib_counters_read_attr { u64 *counters_buff; u32 ncounters; u32 flags; /* use enum ib_read_counters_flags */ }; struct uverbs_attr_bundle; struct iw_cm_id; struct iw_cm_conn_param; #define INIT_RDMA_OBJ_SIZE(ib_struct, drv_struct, member) \ .size_##ib_struct = \ (sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof(struct drv_struct, member)) + \ BUILD_BUG_ON_ZERO( \ !__same_type(((struct drv_struct *)NULL)->member, \ struct ib_struct))) #define rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, gfp) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ gfp, false)) #define rdma_zalloc_drv_obj_numa(ib_dev, ib_type) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ GFP_KERNEL, true)) #define rdma_zalloc_drv_obj(ib_dev, ib_type) \ rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, GFP_KERNEL) #define DECLARE_RDMA_OBJ_SIZE(ib_struct) size_t size_##ib_struct struct rdma_user_mmap_entry { struct kref ref; struct ib_ucontext *ucontext; unsigned long start_pgoff; size_t npages; bool driver_removed; }; /* Return the offset (in bytes) the user should pass to libc's mmap() */ static inline u64 rdma_user_mmap_get_offset(const struct rdma_user_mmap_entry *entry) { return (u64)entry->start_pgoff << PAGE_SHIFT; } /** * struct ib_device_ops - InfiniBand device operations * This structure defines all the InfiniBand device operations, providers will * need to define the supported operations, otherwise they will be set to null. */ struct ib_device_ops { struct module *owner; enum rdma_driver_id driver_id; u32 uverbs_abi_ver; unsigned int uverbs_no_driver_id_binding:1; /* * NOTE: New drivers should not make use of device_group; instead new * device parameter should be exposed via netlink command. This * mechanism exists only for existing drivers. */ const struct attribute_group *device_group; const struct attribute_group **port_groups; int (*post_send)(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr); int (*post_recv)(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); void (*drain_rq)(struct ib_qp *qp); void (*drain_sq)(struct ib_qp *qp); int (*poll_cq)(struct ib_cq *cq, int num_entries, struct ib_wc *wc); int (*peek_cq)(struct ib_cq *cq, int wc_cnt); int (*req_notify_cq)(struct ib_cq *cq, enum ib_cq_notify_flags flags); int (*post_srq_recv)(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); int (*process_mad)(struct ib_device *device, int process_mad_flags, u32 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad *in_mad, struct ib_mad *out_mad, size_t *out_mad_size, u16 *out_mad_pkey_index); int (*query_device)(struct ib_device *device, struct ib_device_attr *device_attr, struct ib_udata *udata); int (*modify_device)(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); void (*get_dev_fw_str)(struct ib_device *device, char *str); const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev, int comp_vector); int (*query_port)(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); int (*modify_port)(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); /** * The following mandatory functions are used only at device * registration. Keep functions such as these at the end of this * structure to avoid cache line misses when accessing struct ib_device * in fast paths. */ int (*get_port_immutable)(struct ib_device *device, u32 port_num, struct ib_port_immutable *immutable); enum rdma_link_layer (*get_link_layer)(struct ib_device *device, u32 port_num); /** * When calling get_netdev, the HW vendor's driver should return the * net device of device @device at port @port_num or NULL if such * a net device doesn't exist. The vendor driver should call dev_hold * on this net device. The HW vendor's device driver must guarantee * that this function returns NULL before the net device has finished * NETDEV_UNREGISTER state. */ struct net_device *(*get_netdev)(struct ib_device *device, u32 port_num); /** * rdma netdev operation * * Driver implementing alloc_rdma_netdev or rdma_netdev_get_params * must return -EOPNOTSUPP if it doesn't support the specified type. */ struct net_device *(*alloc_rdma_netdev)( struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int (*rdma_netdev_get_params)(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, struct rdma_netdev_alloc_params *params); /** * query_gid should be return GID value for @device, when @port_num * link layer is either IB or iWarp. It is no-op if @port_num port * is RoCE link layer. */ int (*query_gid)(struct ib_device *device, u32 port_num, int index, union ib_gid *gid); /** * When calling add_gid, the HW vendor's driver should add the gid * of device of port at gid index available at @attr. Meta-info of * that gid (for example, the network device related to this gid) is * available at @attr. @context allows the HW vendor driver to store * extra information together with a GID entry. The HW vendor driver may * allocate memory to contain this information and store it in @context * when a new GID entry is written to. Params are consistent until the * next call of add_gid or delete_gid. The function should return 0 on * success or error otherwise. The function could be called * concurrently for different ports. This function is only called when * roce_gid_table is used. */ int (*add_gid)(const struct ib_gid_attr *attr, void **context); /** * When calling del_gid, the HW vendor's driver should delete the * gid of device @device at gid index gid_index of port port_num * available in @attr. * Upon the deletion of a GID entry, the HW vendor must free any * allocated memory. The caller will clear @context afterwards. * This function is only called when roce_gid_table is used. */ int (*del_gid)(const struct ib_gid_attr *attr, void **context); int (*query_pkey)(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int (*alloc_ucontext)(struct ib_ucontext *context, struct ib_udata *udata); void (*dealloc_ucontext)(struct ib_ucontext *context); int (*mmap)(struct ib_ucontext *context, struct vm_area_struct *vma); /** * This will be called once refcount of an entry in mmap_xa reaches * zero. The type of the memory that was mapped may differ between * entries and is opaque to the rdma_user_mmap interface. * Therefore needs to be implemented by the driver in mmap_free. */ void (*mmap_free)(struct rdma_user_mmap_entry *entry); void (*disassociate_ucontext)(struct ib_ucontext *ibcontext); int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*create_user_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*destroy_ah)(struct ib_ah *ah, u32 flags); int (*create_srq)(struct ib_srq *srq, struct ib_srq_init_attr *srq_init_attr, struct ib_udata *udata); int (*modify_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask, struct ib_udata *udata); int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr); int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata); int (*create_qp)(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr, struct ib_udata *udata); int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata); int (*query_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata); int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr, struct uverbs_attr_bundle *attrs); int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata); int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata); struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags); struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_udata *udata); struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset, u64 length, u64 virt_addr, int fd, int mr_access_flags, struct uverbs_attr_bundle *attrs); struct ib_mr *(*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_pd *pd, struct ib_udata *udata); int (*dereg_mr)(struct ib_mr *mr, struct ib_udata *udata); struct ib_mr *(*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *(*alloc_mr_integrity)(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); int (*advise_mr)(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge, struct uverbs_attr_bundle *attrs); /* * Kernel users should universally support relaxed ordering (RO), as * they are designed to read data only after observing the CQE and use * the DMA API correctly. * * Some drivers implicitly enable RO if platform supports it. */ int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata); int (*dealloc_mw)(struct ib_mw *mw); int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); struct ib_flow *(*create_flow)(struct ib_qp *qp, struct ib_flow_attr *flow_attr, struct ib_udata *udata); int (*destroy_flow)(struct ib_flow *flow_id); int (*destroy_flow_action)(struct ib_flow_action *action); int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port, int state); int (*get_vf_config)(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *ivf); int (*get_vf_stats)(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int (*get_vf_guid)(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int (*set_vf_guid)(struct ib_device *device, int vf, u32 port, u64 guid, int type); struct ib_wq *(*create_wq)(struct ib_pd *pd, struct ib_wq_init_attr *init_attr, struct ib_udata *udata); int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata); int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table, struct ib_rwq_ind_table_init_attr *init_attr, struct ib_udata *udata); int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); struct ib_dm *(*alloc_dm)(struct ib_device *device, struct ib_ucontext *context, struct ib_dm_alloc_attr *attr, struct uverbs_attr_bundle *attrs); int (*dealloc_dm)(struct ib_dm *dm, struct uverbs_attr_bundle *attrs); struct ib_mr *(*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm, struct ib_dm_mr_attr *attr, struct uverbs_attr_bundle *attrs); int (*create_counters)(struct ib_counters *counters, struct uverbs_attr_bundle *attrs); int (*destroy_counters)(struct ib_counters *counters); int (*read_counters)(struct ib_counters *counters, struct ib_counters_read_attr *counters_read_attr, struct uverbs_attr_bundle *attrs); int (*map_mr_sg_pi)(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset); /** * alloc_hw_[device,port]_stats - Allocate a struct rdma_hw_stats and * fill in the driver initialized data. The struct is kfree()'ed by * the sysfs core when the device is removed. A lifespan of -1 in the * return struct tells the core to set a default lifespan. */ struct rdma_hw_stats *(*alloc_hw_device_stats)(struct ib_device *device); struct rdma_hw_stats *(*alloc_hw_port_stats)(struct ib_device *device, u32 port_num); /** * get_hw_stats - Fill in the counter value(s) in the stats struct. * @index - The index in the value array we wish to have updated, or * num_counters if we want all stats updated * Return codes - * < 0 - Error, no counters updated * index - Updated the single counter pointed to by index * num_counters - Updated all counters (will reset the timestamp * and prevent further calls for lifespan milliseconds) * Drivers are allowed to update all counters in leiu of just the * one given in index at their option */ int (*get_hw_stats)(struct ib_device *device, struct rdma_hw_stats *stats, u32 port, int index); /** * modify_hw_stat - Modify the counter configuration * @enable: true/false when enable/disable a counter * Return codes - 0 on success or error code otherwise. */ int (*modify_hw_stat)(struct ib_device *device, u32 port, unsigned int counter_index, bool enable); /** * Allows rdma drivers to add their own restrack attributes. */ int (*fill_res_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_mr_entry_raw)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_cq_entry)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_cq_entry_raw)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_qp_entry)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_qp_entry_raw)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_cm_id_entry)(struct sk_buff *msg, struct rdma_cm_id *id); int (*fill_res_srq_entry)(struct sk_buff *msg, struct ib_srq *ib_srq); int (*fill_res_srq_entry_raw)(struct sk_buff *msg, struct ib_srq *ib_srq); /* Device lifecycle callbacks */ /* * Called after the device becomes registered, before clients are * attached */ int (*enable_driver)(struct ib_device *dev); /* * This is called as part of ib_dealloc_device(). */ void (*dealloc_driver)(struct ib_device *dev); /* iWarp CM callbacks */ void (*iw_add_ref)(struct ib_qp *qp); void (*iw_rem_ref)(struct ib_qp *qp); struct ib_qp *(*iw_get_qp)(struct ib_device *device, int qpn); int (*iw_connect)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_accept)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_reject)(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len); int (*iw_create_listen)(struct iw_cm_id *cm_id, int backlog); int (*iw_destroy_listen)(struct iw_cm_id *cm_id); /** * counter_bind_qp - Bind a QP to a counter. * @counter - The counter to be bound. If counter->id is zero then * the driver needs to allocate a new counter and set counter->id */ int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp); /** * counter_unbind_qp - Unbind the qp from the dynamically-allocated * counter and bind it onto the default one */ int (*counter_unbind_qp)(struct ib_qp *qp); /** * counter_dealloc -De-allocate the hw counter */ int (*counter_dealloc)(struct rdma_counter *counter); /** * counter_alloc_stats - Allocate a struct rdma_hw_stats and fill in * the driver initialized data. */ struct rdma_hw_stats *(*counter_alloc_stats)( struct rdma_counter *counter); /** * counter_update_stats - Query the stats value of this counter */ int (*counter_update_stats)(struct rdma_counter *counter); /** * Allows rdma drivers to add their own restrack attributes * dumped via 'rdma stat' iproute2 command. */ int (*fill_stat_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); /* query driver for its ucontext properties */ int (*query_ucontext)(struct ib_ucontext *context, struct uverbs_attr_bundle *attrs); /* * Provide NUMA node. This API exists for rdmavt/hfi1 only. * Everyone else relies on Linux memory management model. */ int (*get_numa_node)(struct ib_device *dev); /** * add_sub_dev - Add a sub IB device */ struct ib_device *(*add_sub_dev)(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name); /** * del_sub_dev - Delete a sub IB device */ void (*del_sub_dev)(struct ib_device *sub_dev); DECLARE_RDMA_OBJ_SIZE(ib_ah); DECLARE_RDMA_OBJ_SIZE(ib_counters); DECLARE_RDMA_OBJ_SIZE(ib_cq); DECLARE_RDMA_OBJ_SIZE(ib_mw); DECLARE_RDMA_OBJ_SIZE(ib_pd); DECLARE_RDMA_OBJ_SIZE(ib_qp); DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table); DECLARE_RDMA_OBJ_SIZE(ib_srq); DECLARE_RDMA_OBJ_SIZE(ib_ucontext); DECLARE_RDMA_OBJ_SIZE(ib_xrcd); }; struct ib_core_device { /* device must be the first element in structure until, * union of ib_core_device and device exists in ib_device. */ struct device dev; possible_net_t rdma_net; struct kobject *ports_kobj; struct list_head port_list; struct ib_device *owner; /* reach back to owner ib_device */ }; struct rdma_restrack_root; struct ib_device { /* Do not access @dma_device directly from ULP nor from HW drivers. */ struct device *dma_device; struct ib_device_ops ops; char name[IB_DEVICE_NAME_MAX]; struct rcu_head rcu_head; struct list_head event_handler_list; /* Protects event_handler_list */ struct rw_semaphore event_handler_rwsem; /* Protects QP's event_handler calls and open_qp list */ spinlock_t qp_open_list_lock; struct rw_semaphore client_data_rwsem; struct xarray client_data; struct mutex unregistration_lock; /* Synchronize GID, Pkey cache entries, subnet prefix, LMC */ rwlock_t cache_lock; /** * port_data is indexed by port number */ struct ib_port_data *port_data; int num_comp_vectors; union { struct device dev; struct ib_core_device coredev; }; /* First group is for device attributes, * Second group is for driver provided attributes (optional). * Third group is for the hw_stats * It is a NULL terminated array. */ const struct attribute_group *groups[4]; u64 uverbs_cmd_mask; char node_desc[IB_DEVICE_NODE_DESC_MAX]; __be64 node_guid; u32 local_dma_lkey; u16 is_switch:1; /* Indicates kernel verbs support, should not be used in drivers */ u16 kverbs_provider:1; /* CQ adaptive moderation (RDMA DIM) */ u16 use_cq_dim:1; u8 node_type; u32 phys_port_cnt; struct ib_device_attr attrs; struct hw_stats_device_data *hw_stats_data; #ifdef CONFIG_CGROUP_RDMA struct rdmacg_device cg_device; #endif u32 index; spinlock_t cq_pools_lock; struct list_head cq_pools[IB_POLL_LAST_POOL_TYPE + 1]; struct rdma_restrack_root *res; const struct uapi_definition *driver_def; /* * Positive refcount indicates that the device is currently * registered and cannot be unregistered. */ refcount_t refcount; struct completion unreg_completion; struct work_struct unregistration_work; const struct rdma_link_ops *link_ops; /* Protects compat_devs xarray modifications */ struct mutex compat_devs_mutex; /* Maintains compat devices for each net namespace */ struct xarray compat_devs; /* Used by iWarp CM */ char iw_ifname[IFNAMSIZ]; u32 iw_driver_flags; u32 lag_flags; /* A parent device has a list of sub-devices */ struct mutex subdev_lock; struct list_head subdev_list_head; /* A sub device has a type and a parent */ enum rdma_nl_dev_type type; struct ib_device *parent; struct list_head subdev_list; enum rdma_nl_name_assign_type name_assign_type; }; static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size, gfp_t gfp, bool is_numa_aware) { if (is_numa_aware && dev->ops.get_numa_node) return kzalloc_node(size, gfp, dev->ops.get_numa_node(dev)); return kzalloc(size, gfp); } struct ib_client_nl_info; struct ib_client { const char *name; int (*add)(struct ib_device *ibdev); void (*remove)(struct ib_device *, void *client_data); void (*rename)(struct ib_device *dev, void *client_data); int (*get_nl_info)(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res); int (*get_global_nl_info)(struct ib_client_nl_info *res); /* Returns the net_dev belonging to this ib_client and matching the * given parameters. * @dev: An RDMA device that the net_dev use for communication. * @port: A physical port number on the RDMA device. * @pkey: P_Key that the net_dev uses if applicable. * @gid: A GID that the net_dev uses to communicate. * @addr: An IP address the net_dev is configured with. * @client_data: The device's client data set by ib_set_client_data(). * * An ib_client that implements a net_dev on top of RDMA devices * (such as IP over IB) should implement this callback, allowing the * rdma_cm module to find the right net_dev for a given request. * * The caller is responsible for calling dev_put on the returned * netdev. */ struct net_device *(*get_net_dev_by_params)( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); refcount_t uses; struct completion uses_zero; u32 client_id; /* kverbs are not required by the client */ u8 no_kverbs_req:1; }; /* * IB block DMA iterator * * Iterates the DMA-mapped SGL in contiguous memory blocks aligned * to a HW supported page size. */ struct ib_block_iter { /* internal states */ struct scatterlist *__sg; /* sg holding the current aligned block */ dma_addr_t __dma_addr; /* unaligned DMA address of this block */ size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */ unsigned int __sg_nents; /* number of SG entries */ unsigned int __sg_advance; /* number of bytes to advance in sg in next step */ unsigned int __pg_bit; /* alignment of current block */ }; struct ib_device *_ib_alloc_device(size_t size); #define ib_alloc_device(drv_struct, member) \ container_of(_ib_alloc_device(sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ struct drv_struct, member))), \ struct drv_struct, member) void ib_dealloc_device(struct ib_device *device); void ib_get_device_fw_str(struct ib_device *device, char *str); int ib_register_device(struct ib_device *device, const char *name, struct device *dma_device); void ib_unregister_device(struct ib_device *device); void ib_unregister_driver(enum rdma_driver_id driver_id); void ib_unregister_device_and_put(struct ib_device *device); void ib_unregister_device_queued(struct ib_device *ib_dev); int ib_register_client (struct ib_client *client); void ib_unregister_client(struct ib_client *client); void __rdma_block_iter_start(struct ib_block_iter *biter, struct scatterlist *sglist, unsigned int nents, unsigned long pgsz); bool __rdma_block_iter_next(struct ib_block_iter *biter); /** * rdma_block_iter_dma_address - get the aligned dma address of the current * block held by the block iterator. * @biter: block iterator holding the memory block */ static inline dma_addr_t rdma_block_iter_dma_address(struct ib_block_iter *biter) { return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1); } /** * rdma_for_each_block - iterate over contiguous memory blocks of the sg list * @sglist: sglist to iterate over * @biter: block iterator holding the memory block * @nents: maximum number of sg entries to iterate over * @pgsz: best HW supported page size to use * * Callers may use rdma_block_iter_dma_address() to get each * blocks aligned DMA address. */ #define rdma_for_each_block(sglist, biter, nents, pgsz) \ for (__rdma_block_iter_start(biter, sglist, nents, \ pgsz); \ __rdma_block_iter_next(biter);) /** * ib_get_client_data - Get IB client context * @device:Device to get context for * @client:Client to get context for * * ib_get_client_data() returns the client context data set with * ib_set_client_data(). This can only be called while the client is * registered to the device, once the ib_client remove() callback returns this * cannot be called. */ static inline void *ib_get_client_data(struct ib_device *device, struct ib_client *client) { return xa_load(&device->client_data, client->client_id); } void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data); void ib_set_device_ops(struct ib_device *device, const struct ib_device_ops *ops); int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma, unsigned long pfn, unsigned long size, pgprot_t prot, struct rdma_user_mmap_entry *entry); int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length); int rdma_user_mmap_entry_insert_range(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 min_pgoff, u32 max_pgoff); static inline int rdma_user_mmap_entry_insert_exact(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 pgoff) { return rdma_user_mmap_entry_insert_range(ucontext, entry, length, pgoff, pgoff); } struct rdma_user_mmap_entry * rdma_user_mmap_entry_get_pgoff(struct ib_ucontext *ucontext, unsigned long pgoff); struct rdma_user_mmap_entry * rdma_user_mmap_entry_get(struct ib_ucontext *ucontext, struct vm_area_struct *vma); void rdma_user_mmap_entry_put(struct rdma_user_mmap_entry *entry); void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry); static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len) { return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0; } static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len) { return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0; } static inline bool ib_is_buffer_cleared(const void __user *p, size_t len) { bool ret; u8 *buf; if (len > USHRT_MAX) return false; buf = memdup_user(p, len); if (IS_ERR(buf)) return false; ret = !memchr_inv(buf, 0, len); kfree(buf); return ret; } static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t offset, size_t len) { return ib_is_buffer_cleared(udata->inbuf + offset, len); } /** * ib_modify_qp_is_ok - Check that the supplied attribute mask * contains all required attributes and no attributes not allowed for * the given QP state transition. * @cur_state: Current QP state * @next_state: Next QP state * @type: QP type * @mask: Mask of supplied QP attributes * * This function is a helper function that a low-level driver's * modify_qp method can use to validate the consumer's input. It * checks that cur_state and next_state are valid QP states, that a * transition from cur_state to next_state is allowed by the IB spec, * and that the attribute mask supplied is allowed for the transition. */ bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, enum ib_qp_type type, enum ib_qp_attr_mask mask); void ib_register_event_handler(struct ib_event_handler *event_handler); void ib_unregister_event_handler(struct ib_event_handler *event_handler); void ib_dispatch_event(const struct ib_event *event); int ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u32 port_num); /** * rdma_cap_ib_switch - Check if the device is IB switch * @device: Device to check * * Device driver is responsible for setting is_switch bit on * in ib_device structure at init time. * * Return: true if the device is IB switch. */ static inline bool rdma_cap_ib_switch(const struct ib_device *device) { return device->is_switch; } /** * rdma_start_port - Return the first valid port number for the device * specified * * @device: Device to be checked * * Return start port number */ static inline u32 rdma_start_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : 1; } /** * rdma_for_each_port - Iterate over all valid port numbers of the IB device * @device - The struct ib_device * to iterate over * @iter - The unsigned int to store the port number */ #define rdma_for_each_port(device, iter) \ for (iter = rdma_start_port(device + \ BUILD_BUG_ON_ZERO(!__same_type(u32, \ iter))); \ iter <= rdma_end_port(device); iter++) /** * rdma_end_port - Return the last valid port number for the device * specified * * @device: Device to be checked * * Return last port number */ static inline u32 rdma_end_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt; } static inline int rdma_is_port_valid(const struct ib_device *device, unsigned int port) { return (port >= rdma_start_port(device) && port <= rdma_end_port(device)); } static inline bool rdma_is_grh_required(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_IB_GRH_REQUIRED; } static inline bool rdma_protocol_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IB; } static inline bool rdma_protocol_roce(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & (RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP); } static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP; } static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE; } static inline bool rdma_protocol_iwarp(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IWARP; } static inline bool rdma_ib_or_roce(const struct ib_device *device, u32 port_num) { return rdma_protocol_ib(device, port_num) || rdma_protocol_roce(device, port_num); } static inline bool rdma_protocol_raw_packet(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_RAW_PACKET; } static inline bool rdma_protocol_usnic(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_USNIC; } /** * rdma_cap_ib_mad - Check if the port of a device supports Infiniband * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Management Datagrams (MAD) are a required part of the InfiniBand * specification and are supported on all InfiniBand devices. A slightly * extended version are also supported on OPA interfaces. * * Return: true if the port supports sending/receiving of MAD packets. */ static inline bool rdma_cap_ib_mad(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_MAD; } /** * rdma_cap_opa_mad - Check if the port of device provides support for OPA * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Intel OmniPath devices extend and/or replace the InfiniBand Management * datagrams with their own versions. These OPA MADs share many but not all of * the characteristics of InfiniBand MADs. * * OPA MADs differ in the following ways: * * 1) MADs are variable size up to 2K * IBTA defined MADs remain fixed at 256 bytes * 2) OPA SMPs must carry valid PKeys * 3) OPA SMP packets are a different format * * Return: true if the port supports OPA MAD packet formats. */ static inline bool rdma_cap_opa_mad(struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_MAD; } /** * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI). * @device: Device to check * @port_num: Port number to check * * Each InfiniBand node is required to provide a Subnet Management Agent * that the subnet manager can access. Prior to the fabric being fully * configured by the subnet manager, the SMA is accessed via a well known * interface called the Subnet Management Interface (SMI). This interface * uses directed route packets to communicate with the SM to get around the * chicken and egg problem of the SM needing to know what's on the fabric * in order to configure the fabric, and needing to configure the fabric in * order to send packets to the devices on the fabric. These directed * route packets do not need the fabric fully configured in order to reach * their destination. The SMI is the only method allowed to send * directed route packets on an InfiniBand fabric. * * Return: true if the port provides an SMI. */ static inline bool rdma_cap_ib_smi(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SMI; } /** * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband * Communication Manager. * @device: Device to check * @port_num: Port number to check * * The InfiniBand Communication Manager is one of many pre-defined General * Service Agents (GSA) that are accessed via the General Service * Interface (GSI). It's role is to facilitate establishment of connections * between nodes as well as other management related tasks for established * connections. * * Return: true if the port supports an IB CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_ib_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_CM; } /** * rdma_cap_iw_cm - Check if the port of device has the capability IWARP * Communication Manager. * @device: Device to check * @port_num: Port number to check * * Similar to above, but specific to iWARP connections which have a different * managment protocol than InfiniBand. * * Return: true if the port supports an iWARP CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_iw_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IW_CM; } /** * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband * Subnet Administration. * @device: Device to check * @port_num: Port number to check * * An InfiniBand Subnet Administration (SA) service is a pre-defined General * Service Agent (GSA) provided by the Subnet Manager (SM). On InfiniBand * fabrics, devices should resolve routes to other hosts by contacting the * SA to query the proper route. * * Return: true if the port should act as a client to the fabric Subnet * Administration interface. This does not imply that the SA service is * running locally. */ static inline bool rdma_cap_ib_sa(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SA; } /** * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband * Multicast. * @device: Device to check * @port_num: Port number to check * * InfiniBand multicast registration is more complex than normal IPv4 or * IPv6 multicast registration. Each Host Channel Adapter must register * with the Subnet Manager when it wishes to join a multicast group. It * should do so only once regardless of how many queue pairs it subscribes * to this group. And it should leave the group only after all queue pairs * attached to the group have been detached. * * Return: true if the port must undertake the additional adminstrative * overhead of registering/unregistering with the SM and tracking of the * total number of queue pairs attached to the multicast group. */ static inline bool rdma_cap_ib_mcast(const struct ib_device *device, u32 port_num) { return rdma_cap_ib_sa(device, port_num); } /** * rdma_cap_af_ib - Check if the port of device has the capability * Native Infiniband Address. * @device: Device to check * @port_num: Port number to check * * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default * GID. RoCE uses a different mechanism, but still generates a GID via * a prescribed mechanism and port specific data. * * Return: true if the port uses a GID address to identify devices on the * network. */ static inline bool rdma_cap_af_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_AF_IB; } /** * rdma_cap_eth_ah - Check if the port of device has the capability * Ethernet Address Handle. * @device: Device to check * @port_num: Port number to check * * RoCE is InfiniBand over Ethernet, and it uses a well defined technique * to fabricate GIDs over Ethernet/IP specific addresses native to the * port. Normally, packet headers are generated by the sending host * adapter, but when sending connectionless datagrams, we must manually * inject the proper headers for the fabric we are communicating over. * * Return: true if we are running as a RoCE port and must force the * addition of a Global Route Header built from our Ethernet Address * Handle into our header list for connectionless packets. */ static inline bool rdma_cap_eth_ah(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_ETH_AH; } /** * rdma_cap_opa_ah - Check if the port of device supports * OPA Address handles * @device: Device to check * @port_num: Port number to check * * Return: true if we are running on an OPA device which supports * the extended OPA addressing. */ static inline bool rdma_cap_opa_ah(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH; } /** * rdma_max_mad_size - Return the max MAD size required by this RDMA Port. * * @device: Device * @port_num: Port number * * This MAD size includes the MAD headers and MAD payload. No other headers * are included. * * Return the max MAD size required by the Port. Will return 0 if the port * does not support MADs */ static inline size_t rdma_max_mad_size(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.max_mad_size; } /** * rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table * @device: Device to check * @port_num: Port number to check * * RoCE GID table mechanism manages the various GIDs for a device. * * NOTE: if allocating the port's GID table has failed, this call will still * return true, but any RoCE GID table API will fail. * * Return: true if the port uses RoCE GID table mechanism in order to manage * its GIDs. */ static inline bool rdma_cap_roce_gid_table(const struct ib_device *device, u32 port_num) { return rdma_protocol_roce(device, port_num) && device->ops.add_gid && device->ops.del_gid; } /* * Check if the device supports READ W/ INVALIDATE. */ static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num) { /* * iWarp drivers must support READ W/ INVALIDATE. No other protocol * has support for it yet. */ return rdma_protocol_iwarp(dev, port_num); } /** * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not. * @device: Device * @port_num: 1 based Port number * * Return true if port is an Intel OPA port , false if not */ static inline bool rdma_core_cap_opa_port(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_INTEL_OPA) == RDMA_CORE_PORT_INTEL_OPA; } /** * rdma_mtu_enum_to_int - Return the mtu of the port as an integer value. * @device: Device * @port_num: Port number * @mtu: enum value of MTU * * Return the MTU size supported by the port as an integer value. Will return * -1 if enum value of mtu is not supported. */ static inline int rdma_mtu_enum_to_int(struct ib_device *device, u32 port, int mtu) { if (rdma_core_cap_opa_port(device, port)) return opa_mtu_enum_to_int((enum opa_mtu)mtu); else return ib_mtu_enum_to_int((enum ib_mtu)mtu); } /** * rdma_mtu_from_attr - Return the mtu of the port from the port attribute. * @device: Device * @port_num: Port number * @attr: port attribute * * Return the MTU size supported by the port as an integer value. */ static inline int rdma_mtu_from_attr(struct ib_device *device, u32 port, struct ib_port_attr *attr) { if (rdma_core_cap_opa_port(device, port)) return attr->phys_mtu; else return ib_mtu_enum_to_int(attr->max_mtu); } int ib_set_vf_link_state(struct ib_device *device, int vf, u32 port, int state); int ib_get_vf_config(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *info); int ib_get_vf_stats(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int ib_get_vf_guid(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int ib_set_vf_guid(struct ib_device *device, int vf, u32 port, u64 guid, int type); int ib_query_pkey(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int ib_modify_device(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); int ib_modify_port(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); int ib_find_gid(struct ib_device *device, union ib_gid *gid, u32 *port_num, u16 *index); int ib_find_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index); enum ib_pd_flags { /* * Create a memory registration for all memory in the system and place * the rkey for it into pd->unsafe_global_rkey. This can be used by * ULPs to avoid the overhead of dynamic MRs. * * This flag is generally considered unsafe and must only be used in * extremly trusted environments. Every use of it will log a warning * in the kernel log. */ IB_PD_UNSAFE_GLOBAL_RKEY = 0x01, }; struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags, const char *caller); /** * ib_alloc_pd - Allocates an unused protection domain. * @device: The device on which to allocate the protection domain. * @flags: protection domain flags * * A protection domain object provides an association between QPs, shared * receive queues, address handles, memory regions, and memory windows. * * Every PD has a local_dma_lkey which can be used as the lkey value for local * memory operations. */ #define ib_alloc_pd(device, flags) \ __ib_alloc_pd((device), (flags), KBUILD_MODNAME) int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata); /** * ib_dealloc_pd - Deallocate kernel PD * @pd: The protection domain * * NOTE: for user PD use ib_dealloc_pd_user with valid udata! */ static inline void ib_dealloc_pd(struct ib_pd *pd) { int ret = ib_dealloc_pd_user(pd, NULL); WARN_ONCE(ret, "Destroy of kernel PD shouldn't fail"); } enum rdma_create_ah_flags { /* In a sleepable context */ RDMA_CREATE_AH_SLEEPABLE = BIT(0), }; /** * rdma_create_ah - Creates an address handle for the given address vector. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @flags: Create address handle flags (see enum rdma_create_ah_flags). * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, u32 flags); /** * rdma_create_user_ah - Creates an address handle for the given address vector. * It resolves destination mac address for ah attribute of RoCE type. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @udata: pointer to user's input output buffer information need by * provider driver. * * It returns 0 on success and returns appropriate error code on error. * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_user_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, struct ib_udata *udata); /** * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header * work completion. * @hdr: the L3 header to parse * @net_type: type of header to parse * @sgid: place to store source gid * @dgid: place to store destination gid */ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, enum rdma_network_type net_type, union ib_gid *sgid, union ib_gid *dgid); /** * ib_get_rdma_header_version - Get the header version * @hdr: the L3 header to parse */ int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); /** * ib_init_ah_attr_from_wc - Initializes address handle attributes from a * work completion. * @device: Device on which the received message arrived. * @port_num: Port on which the received message arrived. * @wc: Work completion associated with the received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @ah_attr: Returned attributes that can be used when creating an address * handle for replying to the message. * When ib_init_ah_attr_from_wc() returns success, * (a) for IB link layer it optionally contains a reference to SGID attribute * when GRH is present for IB link layer. * (b) for RoCE link layer it contains a reference to SGID attribute. * User must invoke rdma_cleanup_ah_attr_gid_attr() to release reference to SGID * attributes which are initialized using ib_init_ah_attr_from_wc(). * */ int ib_init_ah_attr_from_wc(struct ib_device *device, u32 port_num, const struct ib_wc *wc, const struct ib_grh *grh, struct rdma_ah_attr *ah_attr); /** * ib_create_ah_from_wc - Creates an address handle associated with the * sender of the specified work completion. * @pd: The protection domain associated with the address handle. * @wc: Work completion information associated with a received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @port_num: The outbound port number to associate with the address. * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc, const struct ib_grh *grh, u32 port_num); /** * rdma_modify_ah - Modifies the address vector associated with an address * handle. * @ah: The address handle to modify. * @ah_attr: The new address vector attributes to associate with the * address handle. */ int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); /** * rdma_query_ah - Queries the address vector associated with an address * handle. * @ah: The address handle to query. * @ah_attr: The address vector attributes associated with the address * handle. */ int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); enum rdma_destroy_ah_flags { /* In a sleepable context */ RDMA_DESTROY_AH_SLEEPABLE = BIT(0), }; /** * rdma_destroy_ah_user - Destroys an address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * @udata: Valid user data or NULL for kernel objects */ int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata); /** * rdma_destroy_ah - Destroys an kernel address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * * NOTE: for user ah use rdma_destroy_ah_user with valid udata! */ static inline void rdma_destroy_ah(struct ib_ah *ah, u32 flags) { int ret = rdma_destroy_ah_user(ah, flags, NULL); WARN_ONCE(ret, "Destroy of kernel AH shouldn't fail"); } struct ib_srq *ib_create_srq_user(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr, struct ib_usrq_object *uobject, struct ib_udata *udata); static inline struct ib_srq * ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr) { if (!pd->device->ops.create_srq) return ERR_PTR(-EOPNOTSUPP); return ib_create_srq_user(pd, srq_init_attr, NULL, NULL); } /** * ib_modify_srq - Modifies the attributes for the specified SRQ. * @srq: The SRQ to modify. * @srq_attr: On input, specifies the SRQ attributes to modify. On output, * the current values of selected SRQ attributes are returned. * @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ * are being modified. * * The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or * IB_SRQ_LIMIT to set the SRQ's limit and request notification when * the number of receives queued drops below the limit. */ int ib_modify_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask); /** * ib_query_srq - Returns the attribute list and current values for the * specified SRQ. * @srq: The SRQ to query. * @srq_attr: The attributes of the specified SRQ. */ int ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr); /** * ib_destroy_srq_user - Destroys the specified SRQ. * @srq: The SRQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata); /** * ib_destroy_srq - Destroys the specified kernel SRQ. * @srq: The SRQ to destroy. * * NOTE: for user srq use ib_destroy_srq_user with valid udata! */ static inline void ib_destroy_srq(struct ib_srq *srq) { int ret = ib_destroy_srq_user(srq, NULL); WARN_ONCE(ret, "Destroy of kernel SRQ shouldn't fail"); } /** * ib_post_srq_recv - Posts a list of work requests to the specified SRQ. * @srq: The SRQ to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_srq_recv(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return srq->device->ops.post_srq_recv(srq, recv_wr, bad_recv_wr ? : &dummy); } struct ib_qp *ib_create_qp_kernel(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr, const char *caller); /** * ib_create_qp - Creates a kernel QP associated with the specific protection * domain. * @pd: The protection domain associated with the QP. * @init_attr: A list of initial attributes required to create the * QP. If QP creation succeeds, then the attributes are updated to * the actual capabilities of the created QP. */ static inline struct ib_qp *ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *init_attr) { return ib_create_qp_kernel(pd, init_attr, KBUILD_MODNAME); } /** * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. * @qp: The QP to modify. * @attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. * @udata: pointer to user's input output buffer information * are being modified. * It returns 0 on success and returns appropriate error code on error. */ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata); /** * ib_modify_qp - Modifies the attributes for the specified QP and then * transitions the QP to the given state. * @qp: The QP to modify. * @qp_attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @qp_attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. */ int ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask); /** * ib_query_qp - Returns the attribute list and current values for the * specified QP. * @qp: The QP to query. * @qp_attr: The attributes of the specified QP. * @qp_attr_mask: A bit-mask used to select specific attributes to query. * @qp_init_attr: Additional attributes of the selected QP. * * The qp_attr_mask may be used to limit the query to gathering only the * selected attributes. */ int ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); /** * ib_destroy_qp - Destroys the specified QP. * @qp: The QP to destroy. * @udata: Valid udata or NULL for kernel objects */ int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata); /** * ib_destroy_qp - Destroys the specified kernel QP. * @qp: The QP to destroy. * * NOTE: for user qp use ib_destroy_qp_user with valid udata! */ static inline int ib_destroy_qp(struct ib_qp *qp) { return ib_destroy_qp_user(qp, NULL); } /** * ib_open_qp - Obtain a reference to an existing sharable QP. * @xrcd - XRC domain * @qp_open_attr: Attributes identifying the QP to open. * * Returns a reference to a sharable QP. */ struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd, struct ib_qp_open_attr *qp_open_attr); /** * ib_close_qp - Release an external reference to a QP. * @qp: The QP handle to release * * The opened QP handle is released by the caller. The underlying * shared QP is not destroyed until all internal references are released. */ int ib_close_qp(struct ib_qp *qp); /** * ib_post_send - Posts a list of work requests to the send queue of * the specified QP. * @qp: The QP to post the work request on. * @send_wr: A list of work requests to post on the send queue. * @bad_send_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. * * While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate * error is returned, the QP state shall not be affected, * ib_post_send() will return an immediate error after queueing any * earlier work requests in the list. */ static inline int ib_post_send(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr) { const struct ib_send_wr *dummy; return qp->device->ops.post_send(qp, send_wr, bad_send_wr ? : &dummy); } /** * ib_post_recv - Posts a list of work requests to the receive queue of * the specified QP. * @qp: The QP to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy); } struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx, const char *caller); static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx) { return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx, KBUILD_MODNAME); } struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx, const char *caller); /** * ib_alloc_cq_any: Allocate kernel CQ * @dev: The IB device * @private: Private data attached to the CQE * @nr_cqe: Number of CQEs in the CQ * @poll_ctx: Context used for polling the CQ */ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx) { return __ib_alloc_cq_any(dev, private, nr_cqe, poll_ctx, KBUILD_MODNAME); } void ib_free_cq(struct ib_cq *cq); int ib_process_cq_direct(struct ib_cq *cq, int budget); /** * ib_create_cq - Creates a CQ on the specified device. * @device: The device on which to create the CQ. * @comp_handler: A user-specified callback that is invoked when a * completion event occurs on the CQ. * @event_handler: A user-specified callback that is invoked when an * asynchronous event not associated with a completion occurs on the CQ. * @cq_context: Context associated with the CQ returned to the user via * the associated completion and event handlers. * @cq_attr: The attributes the CQ should be created upon. * * Users can examine the cq structure to determine the actual CQ size. */ struct ib_cq *__ib_create_cq(struct ib_device *device, ib_comp_handler comp_handler, void (*event_handler)(struct ib_event *, void *), void *cq_context, const struct ib_cq_init_attr *cq_attr, const char *caller); #define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \ __ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME) /** * ib_resize_cq - Modifies the capacity of the CQ. * @cq: The CQ to resize. * @cqe: The minimum size of the CQ. * * Users can examine the cq structure to determine the actual CQ size. */ int ib_resize_cq(struct ib_cq *cq, int cqe); /** * rdma_set_cq_moderation - Modifies moderation params of the CQ * @cq: The CQ to modify. * @cq_count: number of CQEs that will trigger an event * @cq_period: max period of time in usec before triggering an event * */ int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period); /** * ib_destroy_cq_user - Destroys the specified CQ. * @cq: The CQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata); /** * ib_destroy_cq - Destroys the specified kernel CQ. * @cq: The CQ to destroy. * * NOTE: for user cq use ib_destroy_cq_user with valid udata! */ static inline void ib_destroy_cq(struct ib_cq *cq) { int ret = ib_destroy_cq_user(cq, NULL); WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail"); } /** * ib_poll_cq - poll a CQ for completion(s) * @cq:the CQ being polled * @num_entries:maximum number of completions to return * @wc:array of at least @num_entries &struct ib_wc where completions * will be returned * * Poll a CQ for (possibly multiple) completions. If the return value * is < 0, an error occurred. If the return value is >= 0, it is the * number of completions returned. If the return value is * non-negative and < num_entries, then the CQ was emptied. */ static inline int ib_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { return cq->device->ops.poll_cq(cq, num_entries, wc); } /** * ib_req_notify_cq - Request completion notification on a CQ. * @cq: The CQ to generate an event for. * @flags: * Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP * to request an event on the next solicited event or next work * completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS * may also be |ed in to request a hint about missed events, as * described below. * * Return Value: * < 0 means an error occurred while requesting notification * == 0 means notification was requested successfully, and if * IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events * were missed and it is safe to wait for another event. In * this case is it guaranteed that any work completions added * to the CQ since the last CQ poll will trigger a completion * notification event. * > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed * in. It means that the consumer must poll the CQ again to * make sure it is empty to avoid missing an event because of a * race between requesting notification and an entry being * added to the CQ. This return value means it is possible * (but not guaranteed) that a work completion has been added * to the CQ since the last poll without triggering a * completion notification event. */ static inline int ib_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags) { return cq->device->ops.req_notify_cq(cq, flags); } struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe, int comp_vector_hint, enum ib_poll_context poll_ctx); void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe); /* * Drivers that don't need a DMA mapping at the RDMA layer, set dma_device to * NULL. This causes the ib_dma* helpers to just stash the kernel virtual * address into the dma address. */ static inline bool ib_uses_virt_dma(struct ib_device *dev) { return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device; } /* * Check if a IB device's underlying DMA mapping supports P2PDMA transfers. */ static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return false; return dma_pci_p2pdma_supported(dev->dma_device); } /** * ib_virt_dma_to_ptr - Convert a dma_addr to a kernel pointer * @dma_addr: The DMA address * * Used by ib_uses_virt_dma() devices to get back to the kernel pointer after * going through the dma_addr marshalling. */ static inline void *ib_virt_dma_to_ptr(u64 dma_addr) { /* virt_dma mode maps the kvs's directly into the dma addr */ return (void *)(uintptr_t)dma_addr; } /** * ib_virt_dma_to_page - Convert a dma_addr to a struct page * @dma_addr: The DMA address * * Used by ib_uses_virt_dma() device to get back to the struct page after going * through the dma_addr marshalling. */ static inline struct page *ib_virt_dma_to_page(u64 dma_addr) { return virt_to_page(ib_virt_dma_to_ptr(dma_addr)); } /** * ib_dma_mapping_error - check a DMA addr for error * @dev: The device for which the dma_addr was created * @dma_addr: The DMA address to check */ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) { if (ib_uses_virt_dma(dev)) return 0; return dma_mapping_error(dev->dma_device, dma_addr); } /** * ib_dma_map_single - Map a kernel virtual address to DMA address * @dev: The device for which the dma_addr is to be created * @cpu_addr: The kernel virtual address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_single(struct ib_device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)cpu_addr; return dma_map_single(dev->dma_device, cpu_addr, size, direction); } /** * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_single(dev->dma_device, addr, size, direction); } /** * ib_dma_map_page - Map a physical page to DMA address * @dev: The device for which the dma_addr is to be created * @page: The page to be mapped * @offset: The offset within the page * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_page(struct ib_device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)(page_address(page) + offset); return dma_map_page(dev->dma_device, page, offset, size, direction); } /** * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_page(dev->dma_device, addr, size, direction); } int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents); static inline int ib_dma_map_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (ib_uses_virt_dma(dev)) return ib_dma_virt_map_sg(dev, sg, nents); return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } /** * ib_dma_map_sgtable_attrs - Map a scatter/gather table to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The sg_table object describing the buffer * @direction: The direction of the DMA * @attrs: Optional DMA attributes for the map operation */ static inline int ib_dma_map_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { int nents; if (ib_uses_virt_dma(dev)) { nents = ib_dma_virt_map_sg(dev, sgt->sgl, sgt->orig_nents); if (!nents) return -EIO; sgt->nents = nents; return 0; } return dma_map_sgtable(dev->dma_device, sgt, direction, dma_attrs); } static inline void ib_dma_unmap_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sgtable(dev->dma_device, sgt, direction, dma_attrs); } /** * ib_dma_map_sg - Map a scatter/gather list to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline int ib_dma_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { return ib_dma_map_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses * @dev: The device for which the DMA addresses were created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline void ib_dma_unmap_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { ib_dma_unmap_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_max_seg_size - Return the size limit of a single DMA transfer * @dev: The device to query * * The returned value represents a size in bytes. */ static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return UINT_MAX; return dma_get_max_seg_size(dev->dma_device); } /** * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); } /** * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_device(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_device(dev->dma_device, addr, size, dir); } /* ib_reg_user_mr - register a memory region for virtual addresses from kernel * space. This function should be called when 'current' is the owning MM. */ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags); /* ib_advise_mr - give an advice about an address range in a memory region */ int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge); /** * ib_dereg_mr_user - Deregisters a memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * @udata: Valid user data or NULL for kernel object * * This function can fail, if the memory region has memory windows bound to it. */ int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata); /** * ib_dereg_mr - Deregisters a kernel memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * * This function can fail, if the memory region has memory windows bound to it. * * NOTE: for user mr use ib_dereg_mr_user with valid udata! */ static inline int ib_dereg_mr(struct ib_mr *mr) { return ib_dereg_mr_user(mr, NULL); } struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); /** * ib_update_fast_reg_key - updates the key portion of the fast_reg MR * R_Key and L_Key. * @mr - struct ib_mr pointer to be updated. * @newkey - new key to be used. */ static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey) { mr->lkey = (mr->lkey & 0xffffff00) | newkey; mr->rkey = (mr->rkey & 0xffffff00) | newkey; } /** * ib_inc_rkey - increments the key portion of the given rkey. Can be used * for calculating a new rkey for type 2 memory windows. * @rkey - the rkey to increment. */ static inline u32 ib_inc_rkey(u32 rkey) { const u32 mask = 0x000000ff; return ((rkey + 1) & mask) | (rkey & ~mask); } /** * ib_attach_mcast - Attaches the specified QP to a multicast group. * @qp: QP to attach to the multicast group. The QP must be type * IB_QPT_UD. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. * * In order to send and receive multicast packets, subnet * administration must have created the multicast group and configured * the fabric appropriately. The port associated with the specified * QP must also be a member of the multicast group. */ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); /** * ib_detach_mcast - Detaches the specified QP from a multicast group. * @qp: QP to detach from the multicast group. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. */ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); struct ib_xrcd *ib_alloc_xrcd_user(struct ib_device *device, struct inode *inode, struct ib_udata *udata); int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata); static inline int ib_check_mr_access(struct ib_device *ib_dev, unsigned int flags) { u64 device_cap = ib_dev->attrs.device_cap_flags; /* * Local write permission is required if remote write or * remote atomic permission is also requested. */ if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) && !(flags & IB_ACCESS_LOCAL_WRITE)) return -EINVAL; if (flags & ~IB_ACCESS_SUPPORTED) return -EINVAL; if (flags & IB_ACCESS_ON_DEMAND && !(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING)) return -EOPNOTSUPP; if ((flags & IB_ACCESS_FLUSH_GLOBAL && !(device_cap & IB_DEVICE_FLUSH_GLOBAL)) || (flags & IB_ACCESS_FLUSH_PERSISTENT && !(device_cap & IB_DEVICE_FLUSH_PERSISTENT))) return -EOPNOTSUPP; return 0; } static inline bool ib_access_writable(int access_flags) { /* * We have writable memory backing the MR if any of the following * access flags are set. "Local write" and "remote write" obviously * require write access. "Remote atomic" can do things like fetch and * add, which will modify memory, and "MW bind" can change permissions * by binding a window. */ return access_flags & (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND); } /** * ib_check_mr_status: lightweight check of MR status. * This routine may provide status checks on a selected * ib_mr. first use is for signature status check. * * @mr: A memory region. * @check_mask: Bitmask of which checks to perform from * ib_mr_status_check enumeration. * @mr_status: The container of relevant status checks. * failed checks will be indicated in the status bitmask * and the relevant info shall be in the error item. */ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); /** * ib_device_try_get: Hold a registration lock * device: The device to lock * * A device under an active registration lock cannot become unregistered. It * is only possible to obtain a registration lock on a device that is fully * registered, otherwise this function returns false. * * The registration lock is only necessary for actions which require the * device to still be registered. Uses that only require the device pointer to * be valid should use get_device(&ibdev->dev) to hold the memory. * */ static inline bool ib_device_try_get(struct ib_device *dev) { return refcount_inc_not_zero(&dev->refcount); } void ib_device_put(struct ib_device *device); struct ib_device *ib_device_get_by_netdev(struct net_device *ndev, enum rdma_driver_id driver_id); struct ib_device *ib_device_get_by_name(const char *name, enum rdma_driver_id driver_id); struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, unsigned int port); struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port); struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr); int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); int ib_map_mr_sg_pi(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset, unsigned int page_size); static inline int ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size) { int n; n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size); mr->iova = 0; return n; } int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents, unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64)); void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); void ib_drain_qp(struct ib_qp *qp); int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width); static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_ROCE) return attr->roce.dmac; return NULL; } static inline void rdma_ah_set_dlid(struct rdma_ah_attr *attr, u32 dlid) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.dlid = (u16)dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.dlid = dlid; } static inline u32 rdma_ah_get_dlid(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.dlid; return 0; } static inline void rdma_ah_set_sl(struct rdma_ah_attr *attr, u8 sl) { attr->sl = sl; } static inline u8 rdma_ah_get_sl(const struct rdma_ah_attr *attr) { return attr->sl; } static inline void rdma_ah_set_path_bits(struct rdma_ah_attr *attr, u8 src_path_bits) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.src_path_bits = src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.src_path_bits = src_path_bits; } static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.src_path_bits; return 0; } static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr, bool make_grd) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.make_grd = make_grd; } static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.make_grd; return false; } static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u32 port_num) { attr->port_num = port_num; } static inline u32 rdma_ah_get_port_num(const struct rdma_ah_attr *attr) { return attr->port_num; } static inline void rdma_ah_set_static_rate(struct rdma_ah_attr *attr, u8 static_rate) { attr->static_rate = static_rate; } static inline u8 rdma_ah_get_static_rate(const struct rdma_ah_attr *attr) { return attr->static_rate; } static inline void rdma_ah_set_ah_flags(struct rdma_ah_attr *attr, enum ib_ah_flags flag) { attr->ah_flags = flag; } static inline enum ib_ah_flags rdma_ah_get_ah_flags(const struct rdma_ah_attr *attr) { return attr->ah_flags; } static inline const struct ib_global_route *rdma_ah_read_grh(const struct rdma_ah_attr *attr) { return &attr->grh; } /*To retrieve and modify the grh */ static inline struct ib_global_route *rdma_ah_retrieve_grh(struct rdma_ah_attr *attr) { return &attr->grh; } static inline void rdma_ah_set_dgid_raw(struct rdma_ah_attr *attr, void *dgid) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); memcpy(grh->dgid.raw, dgid, sizeof(grh->dgid)); } static inline void rdma_ah_set_subnet_prefix(struct rdma_ah_attr *attr, __be64 prefix) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.subnet_prefix = prefix; } static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr, __be64 if_id) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.interface_id = if_id; } static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 sgid_index, u8 hop_limit, u8 traffic_class) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); attr->ah_flags = IB_AH_GRH; if (dgid) grh->dgid = *dgid; grh->flow_label = flow_label; grh->sgid_index = sgid_index; grh->hop_limit = hop_limit; grh->traffic_class = traffic_class; grh->sgid_attr = NULL; } void rdma_destroy_ah_attr(struct rdma_ah_attr *ah_attr); void rdma_move_grh_sgid_attr(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 hop_limit, u8 traffic_class, const struct ib_gid_attr *sgid_attr); void rdma_copy_ah_attr(struct rdma_ah_attr *dest, const struct rdma_ah_attr *src); void rdma_replace_ah_attr(struct rdma_ah_attr *old, const struct rdma_ah_attr *new); void rdma_move_ah_attr(struct rdma_ah_attr *dest, struct rdma_ah_attr *src); /** * rdma_ah_find_type - Return address handle type. * * @dev: Device to be checked * @port_num: Port number */ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev, u32 port_num) { if (rdma_protocol_roce(dev, port_num)) return RDMA_AH_ATTR_TYPE_ROCE; if (rdma_protocol_ib(dev, port_num)) { if (rdma_cap_opa_ah(dev, port_num)) return RDMA_AH_ATTR_TYPE_OPA; return RDMA_AH_ATTR_TYPE_IB; } if (dev->type == RDMA_DEVICE_TYPE_SMI) return RDMA_AH_ATTR_TYPE_IB; return RDMA_AH_ATTR_TYPE_UNDEFINED; } /** * ib_lid_cpu16 - Return lid in 16bit CPU encoding. * In the current implementation the only way to * get the 32bit lid is from other sources for OPA. * For IB, lids will always be 16bits so cast the * value accordingly. * * @lid: A 32bit LID */ static inline u16 ib_lid_cpu16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return (u16)lid; } /** * ib_lid_be16 - Return lid in 16bit BE encoding. * * @lid: A 32bit LID */ static inline __be16 ib_lid_be16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return cpu_to_be16((u16)lid); } /** * ib_get_vector_affinity - Get the affinity mappings of a given completion * vector * @device: the rdma device * @comp_vector: index of completion vector * * Returns NULL on failure, otherwise a corresponding cpu map of the * completion vector (returns all-cpus map if the device driver doesn't * implement get_vector_affinity). */ static inline const struct cpumask * ib_get_vector_affinity(struct ib_device *device, int comp_vector) { if (comp_vector < 0 || comp_vector >= device->num_comp_vectors || !device->ops.get_vector_affinity) return NULL; return device->ops.get_vector_affinity(device, comp_vector); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @device: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ibdev); struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile); int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs); struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int rdma_init_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), struct net_device *netdev); /** * rdma_device_to_ibdev - Get ib_device pointer from device pointer * * @device: device pointer for which ib_device pointer to retrieve * * rdma_device_to_ibdev() retrieves ib_device pointer from device. * */ static inline struct ib_device *rdma_device_to_ibdev(struct device *device) { struct ib_core_device *coredev = container_of(device, struct ib_core_device, dev); return coredev->owner; } /** * ibdev_to_node - return the NUMA node for a given ib_device * @dev: device to get the NUMA node for. */ static inline int ibdev_to_node(struct ib_device *ibdev) { struct device *parent = ibdev->dev.parent; if (!parent) return NUMA_NO_NODE; return dev_to_node(parent); } /** * rdma_device_to_drv_device - Helper macro to reach back to driver's * ib_device holder structure from device pointer. * * NOTE: New drivers should not make use of this API; This API is only for * existing drivers who have exposed sysfs entries using * ops->device_group. */ #define rdma_device_to_drv_device(dev, drv_dev_struct, ibdev_member) \ container_of(rdma_device_to_ibdev(dev), drv_dev_struct, ibdev_member) bool rdma_dev_access_netns(const struct ib_device *device, const struct net *net); #define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000) #define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF) #define IB_GRH_FLOWLABEL_MASK (0x000FFFFF) /** * rdma_flow_label_to_udp_sport - generate a RoCE v2 UDP src port value based * on the flow_label * * This function will convert the 20 bit flow_label input to a valid RoCE v2 * UDP src port 14 bit value. All RoCE V2 drivers should use this same * convention. */ static inline u16 rdma_flow_label_to_udp_sport(u32 fl) { u32 fl_low = fl & 0x03fff, fl_high = fl & 0xFC000; fl_low ^= fl_high >> 14; return (u16)(fl_low | IB_ROCE_UDP_ENCAP_VALID_PORT_MIN); } /** * rdma_calc_flow_label - generate a RDMA symmetric flow label value based on * local and remote qpn values * * This function folded the multiplication results of two qpns, 24 bit each, * fields, and converts it to a 20 bit results. * * This function will create symmetric flow_label value based on the local * and remote qpn values. this will allow both the requester and responder * to calculate the same flow_label for a given connection. * * This helper function should be used by driver in case the upper layer * provide a zero flow_label value. This is to improve entropy of RDMA * traffic in the network. */ static inline u32 rdma_calc_flow_label(u32 lqpn, u32 rqpn) { u64 v = (u64)lqpn * rqpn; v ^= v >> 20; v ^= v >> 40; return (u32)(v & IB_GRH_FLOWLABEL_MASK); } /** * rdma_get_udp_sport - Calculate and set UDP source port based on the flow * label. If flow label is not defined in GRH then * calculate it based on lqpn/rqpn. * * @fl: flow label from GRH * @lqpn: local qp number * @rqpn: remote qp number */ static inline u16 rdma_get_udp_sport(u32 fl, u32 lqpn, u32 rqpn) { if (!fl) fl = rdma_calc_flow_label(lqpn, rqpn); return rdma_flow_label_to_udp_sport(fl); } const struct ib_port_immutable* ib_port_immutable_read(struct ib_device *dev, unsigned int port); /** ib_add_sub_device - Add a sub IB device on an existing one * * @parent: The IB device that needs to add a sub device * @type: The type of the new sub device * @name: The name of the new sub device * * * Return 0 on success, an error code otherwise */ int ib_add_sub_device(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name); /** ib_del_sub_device_and_put - Delect an IB sub device while holding a 'get' * * @sub: The sub device that is going to be deleted * * Return 0 on success, an error code otherwise */ int ib_del_sub_device_and_put(struct ib_device *sub); static inline void ib_mark_name_assigned_by_user(struct ib_device *ibdev) { ibdev->name_assign_type = RDMA_NAME_ASSIGN_TYPE_USER; } #endif /* IB_VERBS_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2007 Patrick McHardy <kaber@trash.net> * * The code this is based on carried the following copyright notice: * --- * (C) Copyright 2001-2006 * Alex Zeffertt, Cambridge Broadband Ltd, ajz@cambridgebroadband.com * Re-worked by Ben Greear <greearb@candelatech.com> * --- */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/rculist.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/net_tstamp.h> #include <linux/ethtool.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/if_link.h> #include <linux/if_macvlan.h> #include <linux/hash.h> #include <linux/workqueue.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <linux/netpoll.h> #include <linux/phy.h> #define MACVLAN_HASH_BITS 8 #define MACVLAN_HASH_SIZE (1<<MACVLAN_HASH_BITS) #define MACVLAN_DEFAULT_BC_QUEUE_LEN 1000 #define MACVLAN_F_PASSTHRU 1 #define MACVLAN_F_ADDRCHANGE 2 struct macvlan_port { struct net_device *dev; struct hlist_head vlan_hash[MACVLAN_HASH_SIZE]; struct list_head vlans; struct sk_buff_head bc_queue; struct work_struct bc_work; u32 bc_queue_len_used; int bc_cutoff; u32 flags; int count; struct hlist_head vlan_source_hash[MACVLAN_HASH_SIZE]; DECLARE_BITMAP(bc_filter, MACVLAN_MC_FILTER_SZ); DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ); unsigned char perm_addr[ETH_ALEN]; }; struct macvlan_source_entry { struct hlist_node hlist; struct macvlan_dev *vlan; unsigned char addr[6+2] __aligned(sizeof(u16)); struct rcu_head rcu; }; struct macvlan_skb_cb { const struct macvlan_dev *src; }; #define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0])) static void macvlan_port_destroy(struct net_device *dev); static void update_port_bc_queue_len(struct macvlan_port *port); static inline bool macvlan_passthru(const struct macvlan_port *port) { return port->flags & MACVLAN_F_PASSTHRU; } static inline void macvlan_set_passthru(struct macvlan_port *port) { port->flags |= MACVLAN_F_PASSTHRU; } static inline bool macvlan_addr_change(const struct macvlan_port *port) { return port->flags & MACVLAN_F_ADDRCHANGE; } static inline void macvlan_set_addr_change(struct macvlan_port *port) { port->flags |= MACVLAN_F_ADDRCHANGE; } static inline void macvlan_clear_addr_change(struct macvlan_port *port) { port->flags &= ~MACVLAN_F_ADDRCHANGE; } /* Hash Ethernet address */ static u32 macvlan_eth_hash(const unsigned char *addr) { u64 value = get_unaligned((u64 *)addr); /* only want 6 bytes */ #ifdef __BIG_ENDIAN value >>= 16; #else value <<= 16; #endif return hash_64(value, MACVLAN_HASH_BITS); } static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->rx_handler_data); } static struct macvlan_port *macvlan_port_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->rx_handler_data); } static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port, const unsigned char *addr) { struct macvlan_dev *vlan; u32 idx = macvlan_eth_hash(addr); hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr)) return vlan; } return NULL; } static struct macvlan_source_entry *macvlan_hash_lookup_source( const struct macvlan_dev *vlan, const unsigned char *addr) { struct macvlan_source_entry *entry; u32 idx = macvlan_eth_hash(addr); struct hlist_head *h = &vlan->port->vlan_source_hash[idx]; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(entry->addr, addr) && entry->vlan == vlan) return entry; } return NULL; } static int macvlan_hash_add_source(struct macvlan_dev *vlan, const unsigned char *addr) { struct macvlan_port *port = vlan->port; struct macvlan_source_entry *entry; struct hlist_head *h; entry = macvlan_hash_lookup_source(vlan, addr); if (entry) return 0; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; ether_addr_copy(entry->addr, addr); entry->vlan = vlan; h = &port->vlan_source_hash[macvlan_eth_hash(addr)]; hlist_add_head_rcu(&entry->hlist, h); vlan->macaddr_count++; return 0; } static void macvlan_hash_add(struct macvlan_dev *vlan) { struct macvlan_port *port = vlan->port; const unsigned char *addr = vlan->dev->dev_addr; u32 idx = macvlan_eth_hash(addr); hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[idx]); } static void macvlan_hash_del_source(struct macvlan_source_entry *entry) { hlist_del_rcu(&entry->hlist); kfree_rcu(entry, rcu); } static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync) { hlist_del_rcu(&vlan->hlist); if (sync) synchronize_rcu(); } static void macvlan_hash_change_addr(struct macvlan_dev *vlan, const unsigned char *addr) { macvlan_hash_del(vlan, true); /* Now that we are unhashed it is safe to change the device * address without confusing packet delivery. */ eth_hw_addr_set(vlan->dev, addr); macvlan_hash_add(vlan); } static bool macvlan_addr_busy(const struct macvlan_port *port, const unsigned char *addr) { /* Test to see if the specified address is * currently in use by the underlying device or * another macvlan. */ if (!macvlan_passthru(port) && !macvlan_addr_change(port) && ether_addr_equal_64bits(port->dev->dev_addr, addr)) return true; if (macvlan_hash_lookup(port, addr)) return true; return false; } static int macvlan_broadcast_one(struct sk_buff *skb, const struct macvlan_dev *vlan, const struct ethhdr *eth, bool local) { struct net_device *dev = vlan->dev; if (local) return __dev_forward_skb(dev, skb); skb->dev = dev; if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; return 0; } static u32 macvlan_hash_mix(const struct macvlan_dev *vlan) { return (u32)(((unsigned long)vlan) >> L1_CACHE_SHIFT); } static unsigned int mc_hash(const struct macvlan_dev *vlan, const unsigned char *addr) { u32 val = __get_unaligned_cpu32(addr + 2); val ^= macvlan_hash_mix(vlan); return hash_32(val, MACVLAN_MC_FILTER_BITS); } static void macvlan_broadcast(struct sk_buff *skb, const struct macvlan_port *port, struct net_device *src, enum macvlan_mode mode) { const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; struct sk_buff *nskb; unsigned int i; int err; unsigned int hash; if (skb->protocol == htons(ETH_P_PAUSE)) return; hash_for_each_rcu(port->vlan_hash, i, vlan, hlist) { if (vlan->dev == src || !(vlan->mode & mode)) continue; hash = mc_hash(vlan, eth->h_dest); if (!test_bit(hash, vlan->mc_filter)) continue; err = NET_RX_DROP; nskb = skb_clone(skb, GFP_ATOMIC); if (likely(nskb)) err = macvlan_broadcast_one(nskb, vlan, eth, mode == MACVLAN_MODE_BRIDGE) ?: netif_rx(nskb); macvlan_count_rx(vlan, skb->len + ETH_HLEN, err == NET_RX_SUCCESS, true); } } static void macvlan_multicast_rx(const struct macvlan_port *port, const struct macvlan_dev *src, struct sk_buff *skb) { if (!src) /* frame comes from an external address */ macvlan_broadcast(skb, port, NULL, MACVLAN_MODE_PRIVATE | MACVLAN_MODE_VEPA | MACVLAN_MODE_PASSTHRU| MACVLAN_MODE_BRIDGE); else if (src->mode == MACVLAN_MODE_VEPA) /* flood to everyone except source */ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA | MACVLAN_MODE_BRIDGE); else /* * flood only to VEPA ports, bridge ports * already saw the frame on the way out. */ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA); } static void macvlan_process_broadcast(struct work_struct *w) { struct macvlan_port *port = container_of(w, struct macvlan_port, bc_work); struct sk_buff *skb; struct sk_buff_head list; __skb_queue_head_init(&list); spin_lock_bh(&port->bc_queue.lock); skb_queue_splice_tail_init(&port->bc_queue, &list); spin_unlock_bh(&port->bc_queue.lock); while ((skb = __skb_dequeue(&list))) { const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; rcu_read_lock(); macvlan_multicast_rx(port, src, skb); rcu_read_unlock(); if (src) dev_put(src->dev); consume_skb(skb); cond_resched(); } } static void macvlan_broadcast_enqueue(struct macvlan_port *port, const struct macvlan_dev *src, struct sk_buff *skb) { struct sk_buff *nskb; int err = -ENOMEM; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) goto err; MACVLAN_SKB_CB(nskb)->src = src; spin_lock(&port->bc_queue.lock); if (skb_queue_len(&port->bc_queue) < port->bc_queue_len_used) { if (src) dev_hold(src->dev); __skb_queue_tail(&port->bc_queue, nskb); err = 0; } spin_unlock(&port->bc_queue.lock); queue_work(system_unbound_wq, &port->bc_work); if (err) goto free_nskb; return; free_nskb: kfree_skb(nskb); err: dev_core_stats_rx_dropped_inc(skb->dev); } static void macvlan_flush_sources(struct macvlan_port *port, struct macvlan_dev *vlan) { struct macvlan_source_entry *entry; struct hlist_node *next; int i; hash_for_each_safe(port->vlan_source_hash, i, next, entry, hlist) if (entry->vlan == vlan) macvlan_hash_del_source(entry); vlan->macaddr_count = 0; } static void macvlan_forward_source_one(struct sk_buff *skb, struct macvlan_dev *vlan) { struct sk_buff *nskb; struct net_device *dev; int len; int ret; dev = vlan->dev; if (unlikely(!(dev->flags & IFF_UP))) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; len = nskb->len + ETH_HLEN; nskb->dev = dev; if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr)) nskb->pkt_type = PACKET_HOST; ret = __netif_rx(nskb); macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); } static bool macvlan_forward_source(struct sk_buff *skb, struct macvlan_port *port, const unsigned char *addr) { struct macvlan_source_entry *entry; u32 idx = macvlan_eth_hash(addr); struct hlist_head *h = &port->vlan_source_hash[idx]; bool consume = false; hlist_for_each_entry_rcu(entry, h, hlist) { if (ether_addr_equal_64bits(entry->addr, addr)) { if (entry->vlan->flags & MACVLAN_FLAG_NODST) consume = true; macvlan_forward_source_one(skb, entry->vlan); } } return consume; } /* called under rcu_read_lock() from netif_receive_skb */ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) { struct macvlan_port *port; struct sk_buff *skb = *pskb; const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; const struct macvlan_dev *src; struct net_device *dev; unsigned int len = 0; int ret; rx_handler_result_t handle_res; /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; port = macvlan_port_get_rcu(skb->dev); if (is_multicast_ether_addr(eth->h_dest)) { unsigned int hash; skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN); if (!skb) return RX_HANDLER_CONSUMED; *pskb = skb; eth = eth_hdr(skb); if (macvlan_forward_source(skb, port, eth->h_source)) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } src = macvlan_hash_lookup(port, eth->h_source); if (src && src->mode != MACVLAN_MODE_VEPA && src->mode != MACVLAN_MODE_BRIDGE) { /* forward to original port. */ vlan = src; ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?: __netif_rx(skb); handle_res = RX_HANDLER_CONSUMED; goto out; } hash = mc_hash(NULL, eth->h_dest); if (test_bit(hash, port->bc_filter)) macvlan_broadcast_enqueue(port, src, skb); else if (test_bit(hash, port->mc_filter)) macvlan_multicast_rx(port, src, skb); return RX_HANDLER_PASS; } if (macvlan_forward_source(skb, port, eth->h_source)) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } if (macvlan_passthru(port)) vlan = list_first_or_null_rcu(&port->vlans, struct macvlan_dev, list); else vlan = macvlan_hash_lookup(port, eth->h_dest); if (!vlan || vlan->mode == MACVLAN_MODE_SOURCE) return RX_HANDLER_PASS; dev = vlan->dev; if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } len = skb->len + ETH_HLEN; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) { ret = NET_RX_DROP; handle_res = RX_HANDLER_CONSUMED; goto out; } *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; ret = NET_RX_SUCCESS; handle_res = RX_HANDLER_ANOTHER; out: macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); return handle_res; } static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) { const struct macvlan_dev *vlan = netdev_priv(dev); const struct macvlan_port *port = vlan->port; const struct macvlan_dev *dest; if (vlan->mode == MACVLAN_MODE_BRIDGE) { const struct ethhdr *eth = skb_eth_hdr(skb); /* send to other bridge ports directly */ if (is_multicast_ether_addr(eth->h_dest)) { skb_reset_mac_header(skb); macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE); goto xmit_world; } dest = macvlan_hash_lookup(port, eth->h_dest); if (dest && dest->mode == MACVLAN_MODE_BRIDGE) { /* send to lowerdev first for its network taps */ dev_forward_skb(vlan->lowerdev, skb); return NET_XMIT_SUCCESS; } } xmit_world: skb->dev = vlan->lowerdev; return dev_queue_xmit_accel(skb, netdev_get_sb_channel(dev) ? dev : NULL); } static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER return netpoll_send_skb(vlan->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); unsigned int len = skb->len; int ret; if (unlikely(netpoll_tx_running(dev))) return macvlan_netpoll_send_skb(vlan, skb); ret = macvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct vlan_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->tx_packets); u64_stats_add(&pcpu_stats->tx_bytes, len); u64_stats_update_end(&pcpu_stats->syncp); } else { this_cpu_inc(vlan->pcpu_stats->tx_dropped); } return ret; } static int macvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { const struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; return dev_hard_header(skb, lowerdev, type, daddr, saddr ? : dev->dev_addr, len); } static const struct header_ops macvlan_hard_header_ops = { .create = macvlan_hard_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; static int macvlan_open(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; int err; if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) { err = dev_set_promiscuity(lowerdev, 1); if (err < 0) goto out; } goto hash_add; } err = -EADDRINUSE; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out; /* Attempt to populate accel_priv which is used to offload the L2 * forwarding requests for unicast packets. */ if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) vlan->accel_priv = lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); /* If earlier attempt to offload failed, or accel_priv is not * populated we must add the unicast address to the lower device. */ if (IS_ERR_OR_NULL(vlan->accel_priv)) { vlan->accel_priv = NULL; err = dev_uc_add(lowerdev, dev->dev_addr); if (err < 0) goto out; } if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(lowerdev, 1); if (err < 0) goto del_unicast; } if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(lowerdev, 1); if (err < 0) goto clear_multi; } hash_add: macvlan_hash_add(vlan); return 0; clear_multi: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); del_unicast: if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->accel_priv); vlan->accel_priv = NULL; } else { dev_uc_del(lowerdev, dev->dev_addr); } out: return err; } static int macvlan_stop(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->accel_priv); vlan->accel_priv = NULL; } dev_uc_unsync(lowerdev, dev); dev_mc_unsync(lowerdev, dev); if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) dev_set_promiscuity(lowerdev, -1); goto hash_del; } if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(lowerdev, -1); dev_uc_del(lowerdev, dev->dev_addr); hash_del: macvlan_hash_del(vlan, !dev->dismantle); return 0; } static int macvlan_sync_address(struct net_device *dev, const unsigned char *addr) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; struct macvlan_port *port = vlan->port; int err; if (!(dev->flags & IFF_UP)) { /* Just copy in the new address */ eth_hw_addr_set(dev, addr); } else { /* Rehash and update the device filters */ if (macvlan_addr_busy(vlan->port, addr)) return -EADDRINUSE; if (!macvlan_passthru(port)) { err = dev_uc_add(lowerdev, addr); if (err) return err; dev_uc_del(lowerdev, dev->dev_addr); } macvlan_hash_change_addr(vlan, addr); } if (macvlan_passthru(port) && !macvlan_addr_change(port)) { /* Since addr_change isn't set, we are here due to lower * device change. Save the lower-dev address so we can * restore it later. */ ether_addr_copy(vlan->port->perm_addr, lowerdev->dev_addr); } macvlan_clear_addr_change(port); return 0; } static int macvlan_set_mac_address(struct net_device *dev, void *p) { struct macvlan_dev *vlan = netdev_priv(dev); struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; /* If the addresses are the same, this is a no-op */ if (ether_addr_equal(dev->dev_addr, addr->sa_data)) return 0; if (vlan->mode == MACVLAN_MODE_PASSTHRU) { macvlan_set_addr_change(vlan->port); return dev_set_mac_address(vlan->lowerdev, addr, NULL); } if (macvlan_addr_busy(vlan->port, addr->sa_data)) return -EADDRINUSE; return macvlan_sync_address(dev, addr->sa_data); } static void macvlan_change_rx_flags(struct net_device *dev, int change) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; if (dev->flags & IFF_UP) { if (change & IFF_ALLMULTI) dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC) dev_set_promiscuity(lowerdev, dev->flags & IFF_PROMISC ? 1 : -1); } } static void macvlan_compute_filter(unsigned long *mc_filter, struct net_device *dev, struct macvlan_dev *vlan, int cutoff) { if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { bitmap_fill(mc_filter, MACVLAN_MC_FILTER_SZ); } else { DECLARE_BITMAP(filter, MACVLAN_MC_FILTER_SZ); struct netdev_hw_addr *ha; bitmap_zero(filter, MACVLAN_MC_FILTER_SZ); netdev_for_each_mc_addr(ha, dev) { if (!vlan && ha->synced <= cutoff) continue; __set_bit(mc_hash(vlan, ha->addr), filter); } __set_bit(mc_hash(vlan, dev->broadcast), filter); bitmap_copy(mc_filter, filter, MACVLAN_MC_FILTER_SZ); } } static void macvlan_recompute_bc_filter(struct macvlan_dev *vlan) { if (vlan->port->bc_cutoff < 0) { bitmap_zero(vlan->port->bc_filter, MACVLAN_MC_FILTER_SZ); return; } macvlan_compute_filter(vlan->port->bc_filter, vlan->lowerdev, NULL, vlan->port->bc_cutoff); } static void macvlan_set_mac_lists(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); macvlan_compute_filter(vlan->mc_filter, dev, vlan, 0); dev_uc_sync(vlan->lowerdev, dev); dev_mc_sync(vlan->lowerdev, dev); /* This is slightly inaccurate as we're including the subscription * list of vlan->lowerdev too. * * Bug alert: This only works if everyone has the same broadcast * address as lowerdev. As soon as someone changes theirs this * will break. * * However, this is already broken as when you change your broadcast * address we don't get called. * * The solution is to maintain a list of broadcast addresses like * we do for uc/mc, if you care. */ macvlan_compute_filter(vlan->port->mc_filter, vlan->lowerdev, NULL, 0); macvlan_recompute_bc_filter(vlan); } static void update_port_bc_cutoff(struct macvlan_dev *vlan, int cutoff) { if (vlan->port->bc_cutoff == cutoff) return; vlan->port->bc_cutoff = cutoff; macvlan_recompute_bc_filter(vlan); } static int macvlan_change_mtu(struct net_device *dev, int new_mtu) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->lowerdev->mtu < new_mtu) return -EINVAL; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int macvlan_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { struct net_device *real_dev = macvlan_dev_real_dev(dev); return generic_hwtstamp_get_lower(real_dev, cfg); } static int macvlan_hwtstamp_set(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { struct net_device *real_dev = macvlan_dev_real_dev(dev); if (!net_eq(dev_net(dev), &init_net)) return -EOPNOTSUPP; return generic_hwtstamp_set_lower(real_dev, cfg, extack); } /* * macvlan network devices have devices nesting below it and are a special * "super class" of normal network devices; split their locks off into a * separate class since they always nest. */ static struct lock_class_key macvlan_netdev_addr_lock_key; #define ALWAYS_ON_OFFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL) #define ALWAYS_ON_FEATURES ALWAYS_ON_OFFLOADS #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_LRO | \ NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) #define MACVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) static void macvlan_set_lockdep_class(struct net_device *dev) { netdev_lockdep_set_classes(dev); lockdep_set_class(&dev->addr_list_lock, &macvlan_netdev_addr_lock_key); } static int macvlan_init(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; struct macvlan_port *port = vlan->port; dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; dev->features |= ALWAYS_ON_FEATURES; dev->hw_features |= NETIF_F_LRO; dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->hw_enc_features |= dev->features; dev->lltx = true; netif_inherit_tso_max(dev, lowerdev); dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->pcpu_stats) return -ENOMEM; port->count += 1; /* Get macvlan's reference to lowerdev */ netdev_hold(lowerdev, &vlan->dev_tracker, GFP_KERNEL); return 0; } static void macvlan_uninit(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port = vlan->port; free_percpu(vlan->pcpu_stats); macvlan_flush_sources(port, vlan); port->count -= 1; if (!port->count) macvlan_port_destroy(port->dev); } static void macvlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->pcpu_stats) { struct vlan_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; u32 rx_errors = 0, tx_dropped = 0; unsigned int start; int i; for_each_possible_cpu(i) { p = per_cpu_ptr(vlan->pcpu_stats, i); do { start = u64_stats_fetch_begin(&p->syncp); rx_packets = u64_stats_read(&p->rx_packets); rx_bytes = u64_stats_read(&p->rx_bytes); rx_multicast = u64_stats_read(&p->rx_multicast); tx_packets = u64_stats_read(&p->tx_packets); tx_bytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; stats->multicast += rx_multicast; stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; /* rx_errors & tx_dropped are u32, updated * without syncp protection. */ rx_errors += READ_ONCE(p->rx_errors); tx_dropped += READ_ONCE(p->tx_dropped); } stats->rx_errors = rx_errors; stats->rx_dropped = rx_errors; stats->tx_dropped = tx_dropped; } } static int macvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; return vlan_vid_add(lowerdev, proto, vid); } static int macvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; vlan_vid_del(lowerdev, proto, vid); return 0; } static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (flags & NLM_F_REPLACE) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) err = dev_uc_add_excl(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_add_excl(dev, addr); return err; } static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) err = dev_uc_del(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_del(dev, addr); return err; } static void macvlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "macvlan", sizeof(drvinfo->driver)); strscpy(drvinfo->version, "0.1", sizeof(drvinfo->version)); } static int macvlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct macvlan_dev *vlan = netdev_priv(dev); return __ethtool_get_link_ksettings(vlan->lowerdev, cmd); } static int macvlan_ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) { struct net_device *real_dev = macvlan_dev_real_dev(dev); return ethtool_get_ts_info_by_layer(real_dev, info); } static netdev_features_t macvlan_fix_features(struct net_device *dev, netdev_features_t features) { struct macvlan_dev *vlan = netdev_priv(dev); netdev_features_t lowerdev_features = vlan->lowerdev->features; netdev_features_t mask; features |= NETIF_F_ALL_FOR_ALL; features &= (vlan->set_features | ~MACVLAN_FEATURES); mask = features; lowerdev_features &= (features | ~NETIF_F_LRO); features = netdev_increment_features(lowerdev_features, features, mask); features |= ALWAYS_ON_FEATURES; features &= (ALWAYS_ON_FEATURES | MACVLAN_FEATURES); return features; } #ifdef CONFIG_NET_POLL_CONTROLLER static void macvlan_dev_poll_controller(struct net_device *dev) { return; } static int macvlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *real_dev = vlan->lowerdev; struct netpoll *netpoll; int err; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); err = -ENOMEM; if (!netpoll) goto out; err = __netpoll_setup(netpoll, real_dev); if (err) { kfree(netpoll); goto out; } vlan->netpoll = netpoll; out: return err; } static void macvlan_dev_netpoll_cleanup(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct netpoll *netpoll = vlan->netpoll; if (!netpoll) return; vlan->netpoll = NULL; __netpoll_free(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ static int macvlan_dev_get_iflink(const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); return READ_ONCE(vlan->lowerdev->ifindex); } static const struct ethtool_ops macvlan_ethtool_ops = { .get_link = ethtool_op_get_link, .get_link_ksettings = macvlan_ethtool_get_link_ksettings, .get_drvinfo = macvlan_ethtool_get_drvinfo, .get_ts_info = macvlan_ethtool_get_ts_info, }; static const struct net_device_ops macvlan_netdev_ops = { .ndo_init = macvlan_init, .ndo_uninit = macvlan_uninit, .ndo_open = macvlan_open, .ndo_stop = macvlan_stop, .ndo_start_xmit = macvlan_start_xmit, .ndo_change_mtu = macvlan_change_mtu, .ndo_fix_features = macvlan_fix_features, .ndo_change_rx_flags = macvlan_change_rx_flags, .ndo_set_mac_address = macvlan_set_mac_address, .ndo_set_rx_mode = macvlan_set_mac_lists, .ndo_get_stats64 = macvlan_dev_get_stats64, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = macvlan_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = macvlan_vlan_rx_kill_vid, .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = macvlan_dev_poll_controller, .ndo_netpoll_setup = macvlan_dev_netpoll_setup, .ndo_netpoll_cleanup = macvlan_dev_netpoll_cleanup, #endif .ndo_get_iflink = macvlan_dev_get_iflink, .ndo_features_check = passthru_features_check, .ndo_hwtstamp_get = macvlan_hwtstamp_get, .ndo_hwtstamp_set = macvlan_hwtstamp_set, }; static void macvlan_dev_free(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); /* Get rid of the macvlan's reference to lowerdev */ netdev_put(vlan->lowerdev, &vlan->dev_tracker); } void macvlan_common_setup(struct net_device *dev) { ether_setup(dev); /* ether_setup() has set dev->min_mtu to ETH_MIN_MTU. */ dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); dev->priv_flags |= IFF_UNICAST_FLT; dev->change_proto_down = true; dev->netdev_ops = &macvlan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = macvlan_dev_free; dev->header_ops = &macvlan_hard_header_ops; dev->ethtool_ops = &macvlan_ethtool_ops; } EXPORT_SYMBOL_GPL(macvlan_common_setup); static void macvlan_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->priv_flags |= IFF_NO_QUEUE; } static int macvlan_port_create(struct net_device *dev) { struct macvlan_port *port; unsigned int i; int err; if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK) return -EINVAL; if (netdev_is_rx_handler_busy(dev)) return -EBUSY; port = kzalloc(sizeof(*port), GFP_KERNEL); if (port == NULL) return -ENOMEM; port->dev = dev; ether_addr_copy(port->perm_addr, dev->dev_addr); INIT_LIST_HEAD(&port->vlans); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_hash[i]); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_source_hash[i]); port->bc_queue_len_used = 0; port->bc_cutoff = 1; skb_queue_head_init(&port->bc_queue); INIT_WORK(&port->bc_work, macvlan_process_broadcast); err = netdev_rx_handler_register(dev, macvlan_handle_frame, port); if (err) kfree(port); else dev->priv_flags |= IFF_MACVLAN_PORT; return err; } static void macvlan_port_destroy(struct net_device *dev) { struct macvlan_port *port = macvlan_port_get_rtnl(dev); struct sk_buff *skb; dev->priv_flags &= ~IFF_MACVLAN_PORT; netdev_rx_handler_unregister(dev); /* After this point, no packet can schedule bc_work anymore, * but we need to cancel it and purge left skbs if any. */ cancel_work_sync(&port->bc_work); while ((skb = __skb_dequeue(&port->bc_queue))) { const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; if (src) dev_put(src->dev); kfree_skb(skb); } /* If the lower device address has been changed by passthru * macvlan, put it back. */ if (macvlan_passthru(port) && !ether_addr_equal(port->dev->dev_addr, port->perm_addr)) { struct sockaddr sa; sa.sa_family = port->dev->type; memcpy(&sa.sa_data, port->perm_addr, port->dev->addr_len); dev_set_mac_address(port->dev, &sa, NULL); } kfree(port); } static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct nlattr *nla, *head; int rem, len; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; if (data[IFLA_MACVLAN_FLAGS] && nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~(MACVLAN_FLAG_NOPROMISC | MACVLAN_FLAG_NODST)) return -EINVAL; if (data[IFLA_MACVLAN_MODE]) { switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) { case MACVLAN_MODE_PRIVATE: case MACVLAN_MODE_VEPA: case MACVLAN_MODE_BRIDGE: case MACVLAN_MODE_PASSTHRU: case MACVLAN_MODE_SOURCE: break; default: return -EINVAL; } } if (data[IFLA_MACVLAN_MACADDR_MODE]) { switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) { case MACVLAN_MACADDR_ADD: case MACVLAN_MACADDR_DEL: case MACVLAN_MACADDR_FLUSH: case MACVLAN_MACADDR_SET: break; default: return -EINVAL; } } if (data[IFLA_MACVLAN_MACADDR]) { if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(data[IFLA_MACVLAN_MACADDR]))) return -EADDRNOTAVAIL; } if (data[IFLA_MACVLAN_MACADDR_DATA]) { head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { if (nla_type(nla) != IFLA_MACVLAN_MACADDR || nla_len(nla) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(nla))) return -EADDRNOTAVAIL; } } if (data[IFLA_MACVLAN_MACADDR_COUNT]) return -EINVAL; return 0; } /* * reconfigure list of remote source mac address * (only for macvlan devices in source mode) * Note regarding alignment: all netlink data is aligned to 4 Byte, which * suffices for both ether_addr_copy and ether_addr_equal_64bits usage. */ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, struct nlattr *data[]) { char *addr = NULL; int ret, rem, len; struct nlattr *nla, *head; struct macvlan_source_entry *entry; if (data[IFLA_MACVLAN_MACADDR]) addr = nla_data(data[IFLA_MACVLAN_MACADDR]); if (mode == MACVLAN_MACADDR_ADD) { if (!addr) return -EINVAL; return macvlan_hash_add_source(vlan, addr); } else if (mode == MACVLAN_MACADDR_DEL) { if (!addr) return -EINVAL; entry = macvlan_hash_lookup_source(vlan, addr); if (entry) { macvlan_hash_del_source(entry); vlan->macaddr_count--; } } else if (mode == MACVLAN_MACADDR_FLUSH) { macvlan_flush_sources(vlan->port, vlan); } else if (mode == MACVLAN_MACADDR_SET) { macvlan_flush_sources(vlan->port, vlan); if (addr) { ret = macvlan_hash_add_source(vlan, addr); if (ret) return ret; } if (!data[IFLA_MACVLAN_MACADDR_DATA]) return 0; head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { addr = nla_data(nla); ret = macvlan_hash_add_source(vlan, addr); if (ret) return ret; } } else { return -EINVAL; } return 0; } int macvlan_common_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port; struct net_device *lowerdev; int err; int macmode; bool create = false; if (!tb[IFLA_LINK]) return -EINVAL; lowerdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (lowerdev == NULL) return -ENODEV; /* When creating macvlans or macvtaps on top of other macvlans - use * the real device as the lowerdev. */ if (netif_is_macvlan(lowerdev)) lowerdev = macvlan_dev_real_dev(lowerdev); if (!tb[IFLA_MTU]) dev->mtu = lowerdev->mtu; else if (dev->mtu > lowerdev->mtu) return -EINVAL; /* MTU range: 68 - lowerdev->max_mtu */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = lowerdev->max_mtu; if (!tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); if (!netif_is_macvlan_port(lowerdev)) { err = macvlan_port_create(lowerdev); if (err < 0) return err; create = true; } port = macvlan_port_get_rtnl(lowerdev); /* Only 1 macvlan device can be created in passthru mode */ if (macvlan_passthru(port)) { /* The macvlan port must be not created this time, * still goto destroy_macvlan_port for readability. */ err = -EINVAL; goto destroy_macvlan_port; } vlan->lowerdev = lowerdev; vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); if (data && data[IFLA_MACVLAN_FLAGS]) vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); if (vlan->mode == MACVLAN_MODE_PASSTHRU) { if (port->count) { err = -EINVAL; goto destroy_macvlan_port; } macvlan_set_passthru(port); eth_hw_addr_inherit(dev, lowerdev); } if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { if (vlan->mode != MACVLAN_MODE_SOURCE) { err = -EINVAL; goto destroy_macvlan_port; } macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); err = macvlan_changelink_sources(vlan, macmode, data); if (err) goto destroy_macvlan_port; } vlan->bc_queue_len_req = MACVLAN_DEFAULT_BC_QUEUE_LEN; if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); if (data && data[IFLA_MACVLAN_BC_CUTOFF]) update_port_bc_cutoff( vlan, nla_get_s32(data[IFLA_MACVLAN_BC_CUTOFF])); err = register_netdevice(dev); if (err < 0) goto destroy_macvlan_port; dev->priv_flags |= IFF_MACVLAN; err = netdev_upper_dev_link(lowerdev, dev, extack); if (err) goto unregister_netdev; list_add_tail_rcu(&vlan->list, &port->vlans); update_port_bc_queue_len(vlan->port); netif_stacked_transfer_operstate(lowerdev, dev); linkwatch_fire_event(dev); return 0; unregister_netdev: /* macvlan_uninit would free the macvlan port */ unregister_netdevice(dev); return err; destroy_macvlan_port: /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ if (create && macvlan_port_get_rtnl(lowerdev)) { macvlan_flush_sources(port, vlan); macvlan_port_destroy(port->dev); } return err; } EXPORT_SYMBOL_GPL(macvlan_common_newlink); static int macvlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return macvlan_common_newlink(src_net, dev, tb, data, extack); } void macvlan_dellink(struct net_device *dev, struct list_head *head) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->mode == MACVLAN_MODE_SOURCE) macvlan_flush_sources(vlan->port, vlan); list_del_rcu(&vlan->list); update_port_bc_queue_len(vlan->port); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(vlan->lowerdev, dev); } EXPORT_SYMBOL_GPL(macvlan_dellink); static int macvlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); enum macvlan_mode mode; bool set_mode = false; enum macvlan_macaddr_mode macmode; int ret; /* Validate mode, but don't set yet: setting flags may fail. */ if (data && data[IFLA_MACVLAN_MODE]) { set_mode = true; mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); /* Passthrough mode can't be set or cleared dynamically */ if ((mode == MACVLAN_MODE_PASSTHRU) != (vlan->mode == MACVLAN_MODE_PASSTHRU)) return -EINVAL; if (vlan->mode == MACVLAN_MODE_SOURCE && vlan->mode != mode) macvlan_flush_sources(vlan->port, vlan); } if (data && data[IFLA_MACVLAN_FLAGS]) { __u16 flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); bool promisc = (flags ^ vlan->flags) & MACVLAN_FLAG_NOPROMISC; if (macvlan_passthru(vlan->port) && promisc) { int err; if (flags & MACVLAN_FLAG_NOPROMISC) err = dev_set_promiscuity(vlan->lowerdev, -1); else err = dev_set_promiscuity(vlan->lowerdev, 1); if (err < 0) return err; } vlan->flags = flags; } if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) { vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); update_port_bc_queue_len(vlan->port); } if (data && data[IFLA_MACVLAN_BC_CUTOFF]) update_port_bc_cutoff( vlan, nla_get_s32(data[IFLA_MACVLAN_BC_CUTOFF])); if (set_mode) vlan->mode = mode; if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { if (vlan->mode != MACVLAN_MODE_SOURCE) return -EINVAL; macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); ret = macvlan_changelink_sources(vlan, macmode, data); if (ret) return ret; } return 0; } static size_t macvlan_get_size_mac(const struct macvlan_dev *vlan) { if (vlan->macaddr_count == 0) return 0; return nla_total_size(0) /* IFLA_MACVLAN_MACADDR_DATA */ + vlan->macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN); } static size_t macvlan_get_size(const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); return (0 + nla_total_size(4) /* IFLA_MACVLAN_MODE */ + nla_total_size(2) /* IFLA_MACVLAN_FLAGS */ + nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */ + macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN_USED */ ); } static int macvlan_fill_info_macaddr(struct sk_buff *skb, const struct macvlan_dev *vlan, const int i) { struct hlist_head *h = &vlan->port->vlan_source_hash[i]; struct macvlan_source_entry *entry; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (entry->vlan != vlan) continue; if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr)) return 1; } return 0; } static int macvlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port = vlan->port; int i; struct nlattr *nest; if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count)) goto nla_put_failure; if (vlan->macaddr_count > 0) { nest = nla_nest_start_noflag(skb, IFLA_MACVLAN_MACADDR_DATA); if (nest == NULL) goto nla_put_failure; for (i = 0; i < MACVLAN_HASH_SIZE; i++) { if (macvlan_fill_info_macaddr(skb, vlan, i)) goto nla_put_failure; } nla_nest_end(skb, nest); } if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN, vlan->bc_queue_len_req)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED, port->bc_queue_len_used)) goto nla_put_failure; if (port->bc_cutoff != 1 && nla_put_s32(skb, IFLA_MACVLAN_BC_CUTOFF, port->bc_cutoff)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = { [IFLA_MACVLAN_MODE] = { .type = NLA_U32 }, [IFLA_MACVLAN_FLAGS] = { .type = NLA_U16 }, [IFLA_MACVLAN_MACADDR_MODE] = { .type = NLA_U32 }, [IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED }, [IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 }, [IFLA_MACVLAN_BC_QUEUE_LEN] = { .type = NLA_U32 }, [IFLA_MACVLAN_BC_QUEUE_LEN_USED] = { .type = NLA_REJECT }, [IFLA_MACVLAN_BC_CUTOFF] = { .type = NLA_S32 }, }; int macvlan_link_register(struct rtnl_link_ops *ops) { /* common fields */ ops->validate = macvlan_validate; ops->maxtype = IFLA_MACVLAN_MAX; ops->policy = macvlan_policy; ops->changelink = macvlan_changelink; ops->get_size = macvlan_get_size; ops->fill_info = macvlan_fill_info; return rtnl_link_register(ops); }; EXPORT_SYMBOL_GPL(macvlan_link_register); static struct net *macvlan_get_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvlan_link_ops = { .kind = "macvlan", .setup = macvlan_setup, .newlink = macvlan_newlink, .dellink = macvlan_dellink, .get_link_net = macvlan_get_link_net, .priv_size = sizeof(struct macvlan_dev), }; static void update_port_bc_queue_len(struct macvlan_port *port) { u32 max_bc_queue_len_req = 0; struct macvlan_dev *vlan; list_for_each_entry(vlan, &port->vlans, list) { if (vlan->bc_queue_len_req > max_bc_queue_len_req) max_bc_queue_len_req = vlan->bc_queue_len_req; } port->bc_queue_len_used = max_bc_queue_len_req; } static int macvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvlan_dev *vlan, *next; struct macvlan_port *port; LIST_HEAD(list_kill); if (!netif_is_macvlan_port(dev)) return NOTIFY_DONE; port = macvlan_port_get_rtnl(dev); switch (event) { case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: list_for_each_entry(vlan, &port->vlans, list) netif_stacked_transfer_operstate(vlan->lowerdev, vlan->dev); break; case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { netif_inherit_tso_max(vlan->dev, dev); netdev_update_features(vlan->dev); } break; case NETDEV_CHANGEMTU: list_for_each_entry(vlan, &port->vlans, list) { if (vlan->dev->mtu <= dev->mtu) continue; dev_set_mtu(vlan->dev, dev->mtu); } break; case NETDEV_CHANGEADDR: if (!macvlan_passthru(port)) return NOTIFY_DONE; vlan = list_first_entry_or_null(&port->vlans, struct macvlan_dev, list); if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr)) return NOTIFY_BAD; break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) break; list_for_each_entry_safe(vlan, next, &port->vlans, list) vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill); unregister_netdevice_many(&list_kill); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: /* Propagate to all vlans */ list_for_each_entry(vlan, &port->vlans, list) call_netdevice_notifiers(event, vlan->dev); } return NOTIFY_DONE; } static struct notifier_block macvlan_notifier_block __read_mostly = { .notifier_call = macvlan_device_event, }; static int __init macvlan_init_module(void) { int err; register_netdevice_notifier(&macvlan_notifier_block); err = macvlan_link_register(&macvlan_link_ops); if (err < 0) goto err1; return 0; err1: unregister_netdevice_notifier(&macvlan_notifier_block); return err; } static void __exit macvlan_cleanup_module(void) { rtnl_link_unregister(&macvlan_link_ops); unregister_netdevice_notifier(&macvlan_notifier_block); } module_init(macvlan_init_module); module_exit(macvlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Driver for MAC address based VLANs"); MODULE_ALIAS_RTNL_LINK("macvlan"); |
| 348 351 123 121 33 91 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005-2010 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> * Kylene Hall <kjhall@us.ibm.com> * * File: evm_main.c * implements evm_inode_setxattr, evm_inode_post_setxattr, * evm_inode_removexattr, evm_verifyxattr, and evm_inode_set_acl. */ #define pr_fmt(fmt) "EVM: "fmt #include <linux/init.h> #include <linux/audit.h> #include <linux/xattr.h> #include <linux/integrity.h> #include <linux/evm.h> #include <linux/magic.h> #include <linux/posix_acl_xattr.h> #include <linux/lsm_hooks.h> #include <crypto/hash.h> #include <crypto/hash_info.h> #include <crypto/utils.h> #include "evm.h" int evm_initialized; static const char * const integrity_status_msg[] = { "pass", "pass_immutable", "fail", "fail_immutable", "no_label", "no_xattrs", "unknown" }; int evm_hmac_attrs; static struct xattr_list evm_config_default_xattrnames[] = { { .name = XATTR_NAME_SELINUX, .enabled = IS_ENABLED(CONFIG_SECURITY_SELINUX) }, { .name = XATTR_NAME_SMACK, .enabled = IS_ENABLED(CONFIG_SECURITY_SMACK) }, { .name = XATTR_NAME_SMACKEXEC, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_SMACKTRANSMUTE, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_SMACKMMAP, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_APPARMOR, .enabled = IS_ENABLED(CONFIG_SECURITY_APPARMOR) }, { .name = XATTR_NAME_IMA, .enabled = IS_ENABLED(CONFIG_IMA_APPRAISE) }, { .name = XATTR_NAME_CAPS, .enabled = true }, }; LIST_HEAD(evm_config_xattrnames); static int evm_fixmode __ro_after_init; static int __init evm_set_fixmode(char *str) { if (strncmp(str, "fix", 3) == 0) evm_fixmode = 1; else pr_err("invalid \"%s\" mode", str); return 1; } __setup("evm=", evm_set_fixmode); static void __init evm_init_config(void) { int i, xattrs; xattrs = ARRAY_SIZE(evm_config_default_xattrnames); pr_info("Initialising EVM extended attributes:\n"); for (i = 0; i < xattrs; i++) { pr_info("%s%s\n", evm_config_default_xattrnames[i].name, !evm_config_default_xattrnames[i].enabled ? " (disabled)" : ""); list_add_tail(&evm_config_default_xattrnames[i].list, &evm_config_xattrnames); } #ifdef CONFIG_EVM_ATTR_FSUUID evm_hmac_attrs |= EVM_ATTR_FSUUID; #endif pr_info("HMAC attrs: 0x%x\n", evm_hmac_attrs); } static bool evm_key_loaded(void) { return (bool)(evm_initialized & EVM_KEY_MASK); } /* * This function determines whether or not it is safe to ignore verification * errors, based on the ability of EVM to calculate HMACs. If the HMAC key * is not loaded, and it cannot be loaded in the future due to the * EVM_SETUP_COMPLETE initialization flag, allowing an operation despite the * attrs/xattrs being found invalid will not make them valid. */ static bool evm_hmac_disabled(void) { if (evm_initialized & EVM_INIT_HMAC) return false; if (!(evm_initialized & EVM_SETUP_COMPLETE)) return false; return true; } static int evm_find_protected_xattrs(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); struct xattr_list *xattr; int error; int count = 0; if (!(inode->i_opflags & IOP_XATTR)) return -EOPNOTSUPP; list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { error = __vfs_getxattr(dentry, inode, xattr->name, NULL, 0); if (error < 0) { if (error == -ENODATA) continue; return error; } count++; } return count; } static int is_unsupported_hmac_fs(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); if (inode->i_sb->s_iflags & SB_I_EVM_HMAC_UNSUPPORTED) { pr_info_once("%s not supported\n", inode->i_sb->s_type->name); return 1; } return 0; } /* * evm_verify_hmac - calculate and compare the HMAC with the EVM xattr * * Compute the HMAC on the dentry's protected set of extended attributes * and compare it against the stored security.evm xattr. * * For performance: * - use the previoulsy retrieved xattr value and length to calculate the * HMAC.) * - cache the verification result in the iint, when available. * * Returns integrity status */ static enum integrity_status evm_verify_hmac(struct dentry *dentry, const char *xattr_name, char *xattr_value, size_t xattr_value_len) { struct evm_ima_xattr_data *xattr_data = NULL; struct signature_v2_hdr *hdr; enum integrity_status evm_status = INTEGRITY_PASS; struct evm_digest digest; struct inode *inode = d_backing_inode(dentry); struct evm_iint_cache *iint = evm_iint_inode(inode); int rc, xattr_len, evm_immutable = 0; if (iint && (iint->evm_status == INTEGRITY_PASS || iint->evm_status == INTEGRITY_PASS_IMMUTABLE)) return iint->evm_status; /* * On unsupported filesystems without EVM_INIT_X509 enabled, skip * signature verification. */ if (!(evm_initialized & EVM_INIT_X509) && is_unsupported_hmac_fs(dentry)) return INTEGRITY_UNKNOWN; /* if status is not PASS, try to check again - against -ENOMEM */ /* first need to know the sig type */ rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) { evm_status = INTEGRITY_FAIL; if (rc == -ENODATA) { rc = evm_find_protected_xattrs(dentry); if (rc > 0) evm_status = INTEGRITY_NOLABEL; else if (rc == 0) evm_status = INTEGRITY_NOXATTRS; /* new file */ } else if (rc == -EOPNOTSUPP) { evm_status = INTEGRITY_UNKNOWN; } goto out; } xattr_len = rc; /* check value type */ switch (xattr_data->type) { case EVM_XATTR_HMAC: if (xattr_len != sizeof(struct evm_xattr)) { evm_status = INTEGRITY_FAIL; goto out; } digest.hdr.algo = HASH_ALGO_SHA1; rc = evm_calc_hmac(dentry, xattr_name, xattr_value, xattr_value_len, &digest, iint); if (rc) break; rc = crypto_memneq(xattr_data->data, digest.digest, SHA1_DIGEST_SIZE); if (rc) rc = -EINVAL; break; case EVM_XATTR_PORTABLE_DIGSIG: evm_immutable = 1; fallthrough; case EVM_IMA_XATTR_DIGSIG: /* accept xattr with non-empty signature field */ if (xattr_len <= sizeof(struct signature_v2_hdr)) { evm_status = INTEGRITY_FAIL; goto out; } hdr = (struct signature_v2_hdr *)xattr_data; digest.hdr.algo = hdr->hash_algo; rc = evm_calc_hash(dentry, xattr_name, xattr_value, xattr_value_len, xattr_data->type, &digest, iint); if (rc) break; rc = integrity_digsig_verify(INTEGRITY_KEYRING_EVM, (const char *)xattr_data, xattr_len, digest.digest, digest.hdr.length); if (!rc) { if (xattr_data->type == EVM_XATTR_PORTABLE_DIGSIG) { if (iint) iint->flags |= EVM_IMMUTABLE_DIGSIG; evm_status = INTEGRITY_PASS_IMMUTABLE; } else if (!IS_RDONLY(inode) && !(inode->i_sb->s_readonly_remount) && !IS_IMMUTABLE(inode) && !is_unsupported_hmac_fs(dentry)) { evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } } break; default: rc = -EINVAL; break; } if (rc) { if (rc == -ENODATA) evm_status = INTEGRITY_NOXATTRS; else if (evm_immutable) evm_status = INTEGRITY_FAIL_IMMUTABLE; else evm_status = INTEGRITY_FAIL; } pr_debug("digest: (%d) [%*phN]\n", digest.hdr.length, digest.hdr.length, digest.digest); out: if (iint) iint->evm_status = evm_status; kfree(xattr_data); return evm_status; } static int evm_protected_xattr_common(const char *req_xattr_name, bool all_xattrs) { int namelen; int found = 0; struct xattr_list *xattr; namelen = strlen(req_xattr_name); list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { if (!all_xattrs && !xattr->enabled) continue; if ((strlen(xattr->name) == namelen) && (strncmp(req_xattr_name, xattr->name, namelen) == 0)) { found = 1; break; } if (strncmp(req_xattr_name, xattr->name + XATTR_SECURITY_PREFIX_LEN, strlen(req_xattr_name)) == 0) { found = 1; break; } } return found; } int evm_protected_xattr(const char *req_xattr_name) { return evm_protected_xattr_common(req_xattr_name, false); } int evm_protected_xattr_if_enabled(const char *req_xattr_name) { return evm_protected_xattr_common(req_xattr_name, true); } /** * evm_read_protected_xattrs - read EVM protected xattr names, lengths, values * @dentry: dentry of the read xattrs * @buffer: buffer xattr names, lengths or values are copied to * @buffer_size: size of buffer * @type: n: names, l: lengths, v: values * @canonical_fmt: data format (true: little endian, false: native format) * * Read protected xattr names (separated by |), lengths (u32) or values for a * given dentry and return the total size of copied data. If buffer is NULL, * just return the total size. * * Returns the total size on success, a negative value on error. */ int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, int buffer_size, char type, bool canonical_fmt) { struct xattr_list *xattr; int rc, size, total_size = 0; list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { rc = __vfs_getxattr(dentry, d_backing_inode(dentry), xattr->name, NULL, 0); if (rc < 0 && rc == -ENODATA) continue; else if (rc < 0) return rc; switch (type) { case 'n': size = strlen(xattr->name) + 1; if (buffer) { if (total_size) *(buffer + total_size - 1) = '|'; memcpy(buffer + total_size, xattr->name, size); } break; case 'l': size = sizeof(u32); if (buffer) { if (canonical_fmt) rc = (__force int)cpu_to_le32(rc); *(u32 *)(buffer + total_size) = rc; } break; case 'v': size = rc; if (buffer) { rc = __vfs_getxattr(dentry, d_backing_inode(dentry), xattr->name, buffer + total_size, buffer_size - total_size); if (rc < 0) return rc; } break; default: return -EINVAL; } total_size += size; } return total_size; } /** * evm_verifyxattr - verify the integrity of the requested xattr * @dentry: object of the verify xattr * @xattr_name: requested xattr * @xattr_value: requested xattr value * @xattr_value_len: requested xattr value length * * Calculate the HMAC for the given dentry and verify it against the stored * security.evm xattr. For performance, use the xattr value and length * previously retrieved to calculate the HMAC. * * Returns the xattr integrity status. * * This function requires the caller to lock the inode's i_mutex before it * is executed. */ enum integrity_status evm_verifyxattr(struct dentry *dentry, const char *xattr_name, void *xattr_value, size_t xattr_value_len) { if (!evm_key_loaded() || !evm_protected_xattr(xattr_name)) return INTEGRITY_UNKNOWN; return evm_verify_hmac(dentry, xattr_name, xattr_value, xattr_value_len); } EXPORT_SYMBOL_GPL(evm_verifyxattr); /* * evm_verify_current_integrity - verify the dentry's metadata integrity * @dentry: pointer to the affected dentry * * Verify and return the dentry's metadata integrity. The exceptions are * before EVM is initialized or in 'fix' mode. */ static enum integrity_status evm_verify_current_integrity(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); if (!evm_key_loaded() || !S_ISREG(inode->i_mode) || evm_fixmode) return INTEGRITY_PASS; return evm_verify_hmac(dentry, NULL, NULL, 0); } /* * evm_xattr_change - check if passed xattr value differs from current value * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: requested xattr * @xattr_value: requested xattr value * @xattr_value_len: requested xattr value length * * Check if passed xattr value differs from current value. * * Returns 1 if passed xattr value differs from current value, 0 otherwise. */ static int evm_xattr_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { char *xattr_data = NULL; int rc = 0; rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, xattr_name, &xattr_data, 0, GFP_NOFS); if (rc < 0) { rc = 1; goto out; } if (rc == xattr_value_len) rc = !!memcmp(xattr_value, xattr_data, rc); else rc = 1; out: kfree(xattr_data); return rc; } /* * evm_protect_xattr - protect the EVM extended attribute * * Prevent security.evm from being modified or removed without the * necessary permissions or when the existing value is invalid. * * The posix xattr acls are 'system' prefixed, which normally would not * affect security.evm. An interesting side affect of writing posix xattr * acls is their modifying of the i_mode, which is included in security.evm. * For posix xattr acls only, permit security.evm, even if it currently * doesn't exist, to be updated unless the EVM signature is immutable. */ static int evm_protect_xattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { enum integrity_status evm_status; if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (is_unsupported_hmac_fs(dentry)) return -EPERM; } else if (!evm_protected_xattr(xattr_name)) { if (!posix_xattr_acl(xattr_name)) return 0; if (is_unsupported_hmac_fs(dentry)) return 0; evm_status = evm_verify_current_integrity(dentry); if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS)) return 0; goto out; } else if (is_unsupported_hmac_fs(dentry)) return 0; evm_status = evm_verify_current_integrity(dentry); if (evm_status == INTEGRITY_NOXATTRS) { struct evm_iint_cache *iint; /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled()) return 0; iint = evm_iint_inode(d_backing_inode(dentry)); if (iint && (iint->flags & EVM_NEW_FILE)) return 0; /* exception for pseudo filesystems */ if (dentry->d_sb->s_magic == TMPFS_MAGIC || dentry->d_sb->s_magic == SYSFS_MAGIC) return 0; integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode, dentry->d_name.name, "update_metadata", integrity_status_msg[evm_status], -EPERM, 0); } out: /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN)) return 0; /* * Writing other xattrs is safe for portable signatures, as portable * signatures are immutable and can never be updated. */ if (evm_status == INTEGRITY_FAIL_IMMUTABLE) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_xattr_change(idmap, dentry, xattr_name, xattr_value, xattr_value_len)) return 0; if (evm_status != INTEGRITY_PASS && evm_status != INTEGRITY_PASS_IMMUTABLE) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return evm_status == INTEGRITY_PASS ? 0 : -EPERM; } /** * evm_inode_setxattr - protect the EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * @flags: flags to pass into filesystem operations * * Before allowing the 'security.evm' protected xattr to be updated, * verify the existing value is valid. As only the kernel should have * access to the EVM encrypted key needed to calculate the HMAC, prevent * userspace from writing HMAC value. Writing 'security.evm' requires * requires CAP_SYS_ADMIN privileges. */ static int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xattr_data = xattr_value; /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { if (!xattr_value_len) return -EINVAL; if (xattr_data->type != EVM_IMA_XATTR_DIGSIG && xattr_data->type != EVM_XATTR_PORTABLE_DIGSIG) return -EPERM; } return evm_protect_xattr(idmap, dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_removexattr - protect the EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * * Removing 'security.evm' requires CAP_SYS_ADMIN privileges and that * the current value is valid. */ static int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; return evm_protect_xattr(idmap, dentry, xattr_name, NULL, 0); } #ifdef CONFIG_FS_POSIX_ACL static int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) { int rc; umode_t mode; struct inode *inode = d_backing_inode(dentry); if (!kacl) return 1; rc = posix_acl_update_mode(idmap, inode, &mode, &kacl); if (rc || (inode->i_mode != mode)) return 1; return 0; } #else static inline int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) { return 0; } #endif /** * evm_inode_set_acl - protect the EVM extended attribute from posix acls * @idmap: idmap of the idmapped mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * @kacl: pointer to the posix acls * * Prevent modifying posix acls causing the EVM HMAC to be re-calculated * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. * * Return: zero on success, -EPERM on failure. */ static int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { enum integrity_status evm_status; /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; evm_status = evm_verify_current_integrity(dentry); if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS)) return 0; /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN)) return 0; /* * Writing other xattrs is safe for portable signatures, as portable * signatures are immutable and can never be updated. */ if (evm_status == INTEGRITY_FAIL_IMMUTABLE) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_inode_set_acl_change(idmap, dentry, acl_name, kacl)) return 0; if (evm_status != INTEGRITY_PASS_IMMUTABLE) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return -EPERM; } /** * evm_inode_remove_acl - Protect the EVM extended attribute from posix acls * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * * Prevent removing posix acls causing the EVM HMAC to be re-calculated * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. * * Return: zero on success, -EPERM on failure. */ static int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return evm_inode_set_acl(idmap, dentry, acl_name, NULL); } static void evm_reset_status(struct inode *inode) { struct evm_iint_cache *iint; iint = evm_iint_inode(inode); if (iint) iint->evm_status = INTEGRITY_UNKNOWN; } /** * evm_metadata_changed: Detect changes to the metadata * @inode: a file's inode * @metadata_inode: metadata inode * * On a stacked filesystem detect whether the metadata has changed. If this is * the case reset the evm_status associated with the inode that represents the * file. */ bool evm_metadata_changed(struct inode *inode, struct inode *metadata_inode) { struct evm_iint_cache *iint = evm_iint_inode(inode); bool ret = false; if (iint) { ret = (!IS_I_VERSION(metadata_inode) || integrity_inode_attrs_changed(&iint->metadata_inode, metadata_inode)); if (ret) iint->evm_status = INTEGRITY_UNKNOWN; } return ret; } /** * evm_revalidate_status - report whether EVM status re-validation is necessary * @xattr_name: pointer to the affected extended attribute name * * Report whether callers of evm_verifyxattr() should re-validate the * EVM status. * * Return true if re-validation is necessary, false otherwise. */ bool evm_revalidate_status(const char *xattr_name) { if (!evm_key_loaded()) return false; /* evm_inode_post_setattr() passes NULL */ if (!xattr_name) return true; if (!evm_protected_xattr(xattr_name) && !posix_xattr_acl(xattr_name) && strcmp(xattr_name, XATTR_NAME_EVM)) return false; return true; } /** * evm_inode_post_setxattr - update 'security.evm' to reflect the changes * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * @flags: flags to pass into filesystem operations * * Update the HMAC stored in 'security.evm' to reflect the change. * * No need to take the i_mutex lock here, as this function is called from * __vfs_setxattr_noperm(). The caller of which has taken the inode's * i_mutex lock. */ static void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { if (!evm_revalidate_status(xattr_name)) return; evm_reset_status(dentry->d_inode); if (!strcmp(xattr_name, XATTR_NAME_EVM)) return; if (!(evm_initialized & EVM_INIT_HMAC)) return; if (is_unsupported_hmac_fs(dentry)) return; evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_post_set_acl - Update the EVM extended attribute from posix acls * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * @kacl: pointer to the posix acls * * Update the 'security.evm' xattr with the EVM HMAC re-calculated after setting * posix acls. */ static void evm_inode_post_set_acl(struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return evm_inode_post_setxattr(dentry, acl_name, NULL, 0, 0); } /** * evm_inode_post_removexattr - update 'security.evm' after removing the xattr * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * * Update the HMAC stored in 'security.evm' to reflect removal of the xattr. * * No need to take the i_mutex lock here, as this function is called from * vfs_removexattr() which takes the i_mutex. */ static void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name) { if (!evm_revalidate_status(xattr_name)) return; evm_reset_status(dentry->d_inode); if (!strcmp(xattr_name, XATTR_NAME_EVM)) return; if (!(evm_initialized & EVM_INIT_HMAC)) return; evm_update_evmxattr(dentry, xattr_name, NULL, 0); } /** * evm_inode_post_remove_acl - Update the EVM extended attribute from posix acls * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * * Update the 'security.evm' xattr with the EVM HMAC re-calculated after * removing posix acls. */ static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { evm_inode_post_removexattr(dentry, acl_name); } static int evm_attr_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = attr->ia_valid; if (!i_uid_needs_update(idmap, attr, inode) && !i_gid_needs_update(idmap, attr, inode) && (!(ia_valid & ATTR_MODE) || attr->ia_mode == inode->i_mode)) return 0; return 1; } /** * evm_inode_setattr - prevent updating an invalid EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @attr: iattr structure containing the new file attributes * * Permit update of file attributes when files have a valid EVM signature, * except in the case of them having an immutable portable signature. */ static int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; enum integrity_status evm_status; /* Policy permits modification of the protected attrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; if (is_unsupported_hmac_fs(dentry)) return 0; if (!(ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))) return 0; evm_status = evm_verify_current_integrity(dentry); /* * Writing attrs is safe for portable signatures, as portable signatures * are immutable and can never be updated. */ if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS) || (evm_status == INTEGRITY_FAIL_IMMUTABLE) || (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN))) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_attr_change(idmap, dentry, attr)) return 0; integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return -EPERM; } /** * evm_inode_post_setattr - update 'security.evm' after modifying metadata * @idmap: idmap of the idmapped mount * @dentry: pointer to the affected dentry * @ia_valid: for the UID and GID status * * For now, update the HMAC stored in 'security.evm' to reflect UID/GID * changes. * * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ static void evm_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { if (!evm_revalidate_status(NULL)) return; evm_reset_status(dentry->d_inode); if (!(evm_initialized & EVM_INIT_HMAC)) return; if (is_unsupported_hmac_fs(dentry)) return; if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) evm_update_evmxattr(dentry, NULL, NULL, 0); } static int evm_inode_copy_up_xattr(struct dentry *src, const char *name) { struct evm_ima_xattr_data *xattr_data = NULL; int rc; if (strcmp(name, XATTR_NAME_EVM) != 0) return -EOPNOTSUPP; /* first need to know the sig type */ rc = vfs_getxattr_alloc(&nop_mnt_idmap, src, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) return -EPERM; if (rc < offsetof(struct evm_ima_xattr_data, type) + sizeof(xattr_data->type)) return -EPERM; switch (xattr_data->type) { case EVM_XATTR_PORTABLE_DIGSIG: rc = 0; /* allow copy-up */ break; case EVM_XATTR_HMAC: case EVM_IMA_XATTR_DIGSIG: default: rc = -ECANCELED; /* discard */ } kfree(xattr_data); return rc; } /* * evm_inode_init_security - initializes security.evm HMAC value */ int evm_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) { struct evm_xattr *xattr_data; struct xattr *xattr, *evm_xattr; bool evm_protected_xattrs = false; int rc; if (!(evm_initialized & EVM_INIT_HMAC) || !xattrs) return 0; /* * security_inode_init_security() makes sure that the xattrs array is * contiguous, there is enough space for security.evm, and that there is * a terminator at the end of the array. */ for (xattr = xattrs; xattr->name; xattr++) { if (evm_protected_xattr(xattr->name)) evm_protected_xattrs = true; } /* EVM xattr not needed. */ if (!evm_protected_xattrs) return 0; evm_xattr = lsm_get_xattr_slot(xattrs, xattr_count); /* * Array terminator (xattr name = NULL) must be the first non-filled * xattr slot. */ WARN_ONCE(evm_xattr != xattr, "%s: xattrs terminator is not the first non-filled slot\n", __func__); xattr_data = kzalloc(sizeof(*xattr_data), GFP_NOFS); if (!xattr_data) return -ENOMEM; xattr_data->data.type = EVM_XATTR_HMAC; rc = evm_init_hmac(inode, xattrs, xattr_data->digest); if (rc < 0) goto out; evm_xattr->value = xattr_data; evm_xattr->value_len = sizeof(*xattr_data); evm_xattr->name = XATTR_EVM_SUFFIX; return 0; out: kfree(xattr_data); return rc; } EXPORT_SYMBOL_GPL(evm_inode_init_security); static int evm_inode_alloc_security(struct inode *inode) { struct evm_iint_cache *iint = evm_iint_inode(inode); /* Called by security_inode_alloc(), it cannot be NULL. */ iint->flags = 0UL; iint->evm_status = INTEGRITY_UNKNOWN; return 0; } static void evm_file_release(struct file *file) { struct inode *inode = file_inode(file); struct evm_iint_cache *iint = evm_iint_inode(inode); fmode_t mode = file->f_mode; if (!S_ISREG(inode->i_mode) || !(mode & FMODE_WRITE)) return; if (iint && atomic_read(&inode->i_writecount) == 1) iint->flags &= ~EVM_NEW_FILE; } static void evm_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); struct evm_iint_cache *iint = evm_iint_inode(inode); if (!S_ISREG(inode->i_mode)) return; if (iint) iint->flags |= EVM_NEW_FILE; } #ifdef CONFIG_EVM_LOAD_X509 void __init evm_load_x509(void) { int rc; rc = integrity_load_x509(INTEGRITY_KEYRING_EVM, CONFIG_EVM_X509_PATH); if (!rc) evm_initialized |= EVM_INIT_X509; } #endif static int __init init_evm(void) { int error; struct list_head *pos, *q; evm_init_config(); error = integrity_init_keyring(INTEGRITY_KEYRING_EVM); if (error) goto error; error = evm_init_secfs(); if (error < 0) { pr_info("Error registering secfs\n"); goto error; } error: if (error != 0) { if (!list_empty(&evm_config_xattrnames)) { list_for_each_safe(pos, q, &evm_config_xattrnames) list_del(pos); } } return error; } static struct security_hook_list evm_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_setattr, evm_inode_setattr), LSM_HOOK_INIT(inode_post_setattr, evm_inode_post_setattr), LSM_HOOK_INIT(inode_copy_up_xattr, evm_inode_copy_up_xattr), LSM_HOOK_INIT(inode_setxattr, evm_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, evm_inode_post_setxattr), LSM_HOOK_INIT(inode_set_acl, evm_inode_set_acl), LSM_HOOK_INIT(inode_post_set_acl, evm_inode_post_set_acl), LSM_HOOK_INIT(inode_remove_acl, evm_inode_remove_acl), LSM_HOOK_INIT(inode_post_remove_acl, evm_inode_post_remove_acl), LSM_HOOK_INIT(inode_removexattr, evm_inode_removexattr), LSM_HOOK_INIT(inode_post_removexattr, evm_inode_post_removexattr), LSM_HOOK_INIT(inode_init_security, evm_inode_init_security), LSM_HOOK_INIT(inode_alloc_security, evm_inode_alloc_security), LSM_HOOK_INIT(file_release, evm_file_release), LSM_HOOK_INIT(path_post_mknod, evm_post_path_mknod), }; static const struct lsm_id evm_lsmid = { .name = "evm", .id = LSM_ID_EVM, }; static int __init init_evm_lsm(void) { security_add_hooks(evm_hooks, ARRAY_SIZE(evm_hooks), &evm_lsmid); return 0; } struct lsm_blob_sizes evm_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct evm_iint_cache), .lbs_xattr_count = 1, }; DEFINE_LSM(evm) = { .name = "evm", .init = init_evm_lsm, .order = LSM_ORDER_LAST, .blobs = &evm_blob_sizes, }; late_initcall(init_evm); |
| 939 940 7 7 940 938 940 286 936 482 483 483 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> #include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define RCU_SEQ_CTR_SHIFT 2 #define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); struct rcu_gp_oldstate; unsigned long get_completed_synchronize_rcu(void); void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); // Maximum number of unsigned long values corresponding to // not-yet-completed RCU grace periods. #define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 /** * same_state_synchronize_rcu - 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_rcu(), start_poll_synchronize_rcu(), or * get_completed_synchronize_rcu(). 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_rcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict() do { } while (0) #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_LAZY void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func); #else static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } #endif /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); #ifdef CONFIG_TASKS_RCU_GENERIC void rcu_init_tasks_generic(void); #else static inline void rcu_init_tasks_generic(void) { } #endif #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) void rcu_irq_work_resched(void); #else static inline void rcu_irq_work_resched(void) { } #endif #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); #define RCU_NOCB_LOCKDEP_WARN(c, s) RCU_LOCKDEP_WARN(c, s) #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #define RCU_NOCB_LOCKDEP_WARN(c, s) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU # define rcu_tasks_classic_qs(t, preempt) \ do { \ if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void rcu_tasks_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif # ifdef CONFIG_TASKS_TRACE_RCU // Bits for ->trc_reader_special.b.need_qs field. #define TRC_NEED_QS 0x1 // Task needs a quiescent state. #define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state. u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new); void rcu_tasks_trace_qs_blkd(struct task_struct *t); # define rcu_tasks_trace_qs(t) \ do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ } \ } while (0) void rcu_tasks_trace_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ rcu_tasks_trace_qs(t); \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU void synchronize_rcu_tasks_rude(void); void rcu_tasks_rude_torture_stats_print(char *tt, char *tf); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? * * As an accident of implementation, an RCU Tasks Trace grace period also * acts as an RCU grace period. However, this could change at any time. * Code relying on this accident must call this function to verify that * this accident is still happening. * * You have been warned! */ static inline bool rcu_trace_implies_rcu_gp(void) { return true; } /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_try_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_try_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } static inline int debug_lockdep_rcu_enabled(void) { return 0; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message * * This checks debug_lockdep_rcu_enabled() before checking (c) to * prevent early boot splats due to lockdep not yet being initialized, * and rechecks it after checking (c) to prevent false-positive splats * due to races with lockdep being disabled. See commit 3066820034b5dd * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data.unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } #endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) // See RCU_LOCKDEP_WARN() for an explanation of the double call to // debug_lockdep_rcu_enabled(). static inline bool lockdep_assert_rcu_helper(bool c) { return debug_lockdep_rcu_enabled() && (c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) && debug_lockdep_rcu_enabled(); } /** * lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock() * * Splats if lockdep is enabled and there is no rcu_read_lock() in effect. */ #define lockdep_assert_in_rcu_read_lock() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map))) /** * lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh() * * Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect. * Note that local_bh_disable() and friends do not suffice here, instead an * actual rcu_read_lock_bh() is required. */ #define lockdep_assert_in_rcu_read_lock_bh() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map))) /** * lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched() * * Splats if lockdep is enabled and there is no rcu_read_lock_sched() * in effect. Note that preempt_disable() and friends do not suffice here, * instead an actual rcu_read_lock_sched() is required. */ #define lockdep_assert_in_rcu_read_lock_sched() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map))) /** * lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader * * Splats if lockdep is enabled and there is no RCU reader of any * type in effect. Note that regions of code protected by things like * preempt_disable, local_bh_disable(), and local_irq_disable() all qualify * as RCU readers. * * Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY * kernels that are not also built with PREEMPT_COUNT. But if you have * lockdep enabled, you might as well also enable PREEMPT_COUNT. */ #define lockdep_assert_in_rcu_reader() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \ !lock_is_held(&rcu_bh_lock_map) && \ !lock_is_held(&rcu_sched_lock_map) && \ preemptible())) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) #define lockdep_assert_in_rcu_read_lock() do { } while (0) #define lockdep_assert_in_rcu_read_lock_bh() do { } while (0) #define lockdep_assert_in_rcu_read_lock_sched() do { } while (0) #define lockdep_assert_in_rcu_reader() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ #define __unrcu_pointer(p, local) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(local)); \ }) /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property * * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ #define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu)) #define __rcu_access_pointer(p, local, space) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_protected(p, local, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define __rcu_dereference_raw(p, local) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) local = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * Within an RCU read-side critical section, there is little reason to * use rcu_access_pointer(). * * It is usually best to test the rcu_access_pointer() return value * directly in order to avoid accidental dereferences being introduced * by later inattentive changes. In other words, assigning the * rcu_access_pointer() return value to a local variable results in an * accident waiting to happen. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as is * the case in the context of the RCU callback that is freeing up the data, * or after a synchronize_rcu() returns. This can be useful when tearing * down multi-linked structures after a grace period has elapsed. However, * rcu_dereference_protected() is normally preferred for this use case. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). However, * please note that starting in v5.0 kernels, vanilla RCU grace periods * wait for local_bh_disable() regions of code in addition to regions of * code demarked by rcu_read_lock() and rcu_read_unlock(). This means * that synchronize_rcu(), call_rcu, and friends all take not only * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). * However, please note that starting in v5.0 kernels, vanilla RCU grace * periods wait for preempt_disable() regions of code in addition to * regions of code demarked by rcu_read_lock() and rcu_read_unlock(). * This means that synchronize_rcu(), call_rcu, and friends all take not * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_sched_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * In v5.0 and later kernels, synchronize_rcu() and call_rcu() also * wait for regions of code with preemption disabled, including regions of * code with interrupts or softirqs disabled. In pre-v5.0 kernels, which * define synchronize_sched(), only code enclosed within rcu_read_lock() * and rcu_read_unlock() are guaranteed to be waited for. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In almost all situations, rcu_read_unlock() is immune from deadlock. * In recent kernels that have consolidated synchronize_sched() and * synchronize_rcu_bh() into synchronize_rcu(), this deadlock immunity * also extends to the scheduler's runqueue and priority-inheritance * spinlocks, courtesy of the quiescent-state deferral that is carried * out when rcu_read_unlock() is invoked with interrupts disabled. * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent to rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as an RCU * read-side critical section. However, please note that this equivalence * applies only to v5.0 and later. Before v5.0, rcu_read_lock() and * rcu_read_lock_bh() were unrelated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent to rcu_read_lock(), but also disables preemption. * Read-side critical sections can also be introduced by anything else that * disables preemption, including local_irq_disable() and friends. However, * please note that the equivalence to rcu_read_lock() applies only to * v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched() * were unrelated. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kvfree_rcu()? */ #define __is_kvfree_rcu_offset(offset) ((offset) < 4096) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree for double-argument invocations. * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. Rather than encoding a * function address in the embedded rcu_head structure, kfree_rcu() instead * encodes the offset of the rcu_head structure within the base structure. * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * The object to be freed can be allocated either by kmalloc() or * kmem_cache_alloc(). * * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) #define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) /** * kfree_rcu_mightsleep() - kfree an object after a grace period. * @ptr: pointer to kfree for single-argument invocations. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * * kfree_rcu_mightsleep(ptr); * * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ #define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) { \ BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf))); \ kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (void *) (___p)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; DEFINE_LOCK_GUARD_0(rcu, do { rcu_read_lock(); /* * sparse doesn't call the cleanup function, * so just release immediately and don't track * the context. We don't need to anyway, since * the whole point of the guard is to not need * the explicit unlock. */ __release(RCU); } while (0), rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> #include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> struct dsa_8021q_context; struct tc_action; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 #define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 #define DSA_TAG_PROTO_DSA_VALUE 3 #define DSA_TAG_PROTO_EDSA_VALUE 4 #define DSA_TAG_PROTO_GSWIP_VALUE 5 #define DSA_TAG_PROTO_KSZ9477_VALUE 6 #define DSA_TAG_PROTO_KSZ9893_VALUE 7 #define DSA_TAG_PROTO_LAN9303_VALUE 8 #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 #define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, }; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); int (*connect)(struct dsa_switch *ds); void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC * address, in which case the DSA conduit would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ bool promisc_on_conduit; }; struct dsa_lag { struct net_device *dev; unsigned int id; struct mutex fdb_lock; struct list_head fdbs; refcount_t refcount; }; struct dsa_switch_tree { struct list_head list; /* List of switch ports */ struct list_head ports; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ unsigned int index; /* Number of switches attached to this tree */ struct kref refcount; /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; /* Default tagging protocol preferred by the switches in this * tree. */ enum dsa_tag_protocol default_proto; /* Has this tree been applied to the hardware? */ bool setup; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* List of DSA links composing the routing table */ struct list_head rtable; /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ unsigned int last_switch; }; /* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { struct dsa_lag *lag = dsa_lag_by_id(dst, id); if (lag->dev == lag_dev) return lag->id; } return -ENODEV; } /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, DSA_PORT_MALL_POLICER, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC port policer entry */ struct dsa_mall_policer_tc_entry { u32 burst; u64 rate_bytes_per_sec; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; struct dsa_mall_policer_tc_entry policer; }; }; struct dsa_bridge { struct net_device *dev; unsigned int num; bool tx_fwd_offload; refcount_t refcount; }; struct dsa_port { /* A CPU port is physically connected to a conduit device. A user port * exposes a network device to user-space, called 'user' here. */ union { struct net_device *conduit; struct net_device *user; }; /* Copy of the tagging protocol operations, for quicker access * in the data path. Valid only for the CPU ports. */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in conduit receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); struct dsa_switch *ds; unsigned int index; enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, DSA_PORT_TYPE_DSA, DSA_PORT_TYPE_USER, } type; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; u8 stp_state; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u8 vlan_filtering:1; /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ u8 learning:1; u8 lag_tx_enabled:1; /* conduit state bits, valid only on CPU ports */ u8 conduit_admin_up:1; u8 conduit_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; u8 setup:1; struct device_node *dn; unsigned int ageing_time; struct dsa_bridge *bridge; struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; /* * Original copy of the conduit netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; struct mutex vlans_lock; union { /* List of VLANs that CPU and DSA ports are members of. * Access to this is serialized by the sleepable @vlans_lock. */ struct list_head vlans; /* List of VLANs that user ports are members of. * Access to this is serialized by netif_addr_lock_bh(). */ struct list_head user_vlans; }; }; static inline struct dsa_port * dsa_phylink_to_port(struct phylink_config *config) { return container_of(config, struct dsa_port, pl_config); } /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ struct dsa_link { struct dsa_port *dp; struct dsa_port *link_dp; struct list_head list; }; enum dsa_db_type { DSA_DB_PORT, DSA_DB_LAG, DSA_DB_BRIDGE, }; struct dsa_db { enum dsa_db_type type; union { const struct dsa_port *dp; struct dsa_lag lag; struct dsa_bridge bridge; }; }; struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; struct dsa_db db; }; struct dsa_vlan { u16 vid; refcount_t refcount; struct list_head list; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; unsigned int index; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u32 setup:1; /* Disallow bridge core from requesting different VLAN awareness * settings on ports if not hardware-supported */ u32 vlan_filtering_is_global:1; /* Keep VLAN filtering enabled on ports not offloading any upper */ u32 needs_standalone_vlan_filtering:1; /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this * would break things or not. */ u32 configure_vlan_while_not_filtering:1; /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. * DEPRECATED: Do NOT set this field in new drivers. Instead look at * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. * Useful if the switch cannot preserve the VLAN tag as seen on the * wire for user port ingress, and chooses to send all frames as * VLAN-tagged to the CPU, including those which were originally * untagged. */ u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. */ u32 assisted_learning_on_cpu_port:1; /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ u32 vlan_filtering:1; /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. */ u32 mtu_enforcement_ingress:1; /* Drivers that isolate the FDBs of multiple bridges must set this * to true to receive the bridge as an argument in .port_fdb_{add,del} * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be * passed as zero. */ u32 fdb_isolation:1; /* Drivers that have global DSCP mapping settings must set this to * true to automatically apply the settings to all ports. */ u32 dscp_prio_mapping_is_global:1; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; void *tagger_data; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * Allow a DSA switch driver to override the phylink MAC ops */ const struct phylink_mac_ops *phylink_mac_ops; /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; struct mii_bus *user_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* Storage for drivers using tag_8021q */ struct dsa_8021q_context *tag_8021q_ctx; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at * least_ these many IDs, accessible to drivers via * dsa_lag_id(). */ unsigned int num_lag_ids; /* Drivers that support bridge forwarding offload or FDB isolation * should set this to the maximum number of bridges spanning the same * switch tree (or all trees, in the case of cross-tree bridging * support) that can be offloaded. */ unsigned int max_num_bridges; unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dp->ds == ds && dp->index == p) return dp; return NULL; } static inline bool dsa_port_is_dsa(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_port_is_cpu(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_port_is_user(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_USER; } static inline bool dsa_port_is_unused(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp) { return dsa_port_is_cpu(dp) && dp->conduit_admin_up && dp->conduit_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } #define dsa_tree_for_each_user_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_available_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (!dsa_port_is_unused((_dp))) #define dsa_switch_for_each_user_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_user_port(dp, ds) mask |= BIT(dp->index); return mask; } static inline u32 dsa_cpu_ports(struct dsa_switch *ds) { struct dsa_port *cpu_dp; u32 mask = 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) mask |= BIT(cpu_dp->index); return mask; } /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { struct dsa_switch_tree *dst = ds->dst; struct dsa_link *dl; list_for_each_entry(dl, &dst->rtable, list) if (dl->dp->ds == ds && dl->link_dp->ds->index == device) return dl->dp->index; return ds->num_ports; } /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) { if (device == ds->index) return port; else return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) { const struct dsa_port *dp = dsa_to_port(ds, port); const struct dsa_port *cpu_dp = dp->cpu_dp; if (!cpu_dp) return port; return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } /* Return true if this is the local port used to reach the CPU port */ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) { if (dsa_is_unused_port(ds, port)) return false; return port == dsa_upstream_port(ds, port); } /* Return true if this is a DSA port leading away from the CPU */ static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) { return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); } /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { struct dsa_port *dp; dsa_switch_for_each_available_port(dp, ds) { return dsa_upstream_port(ds, dp->index); } return ds->num_ports; } /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. */ static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, struct dsa_switch *downstream_ds) { int routing_port; if (upstream_ds == downstream_ds) return true; routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); return dsa_is_upstream_port(downstream_ds, routing_port); } static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; if (ds->vlan_filtering_is_global) return ds->vlan_filtering; else return dp->vlan_filtering; } static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) { return dp->lag ? dp->lag->id : 0; } static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) { return dp->lag ? dp->lag->dev : NULL; } static inline bool dsa_port_offloads_lag(struct dsa_port *dp, const struct dsa_lag *lag) { return dsa_port_lag_dev_get(dp) == lag->dev; } static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); return dp->cpu_dp->conduit; } static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; if (dp->lag) return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; return dp->user; } static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, const struct dsa_port *b) { struct net_device *br_a = dsa_port_bridge_dev_get(a); struct net_device *br_b = dsa_port_bridge_dev_get(b); /* Standalone ports are not in the same bridge with one another */ return (!br_a || !br_b) ? false : (br_a == br_b); } static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge_dev(struct dsa_port *dp, const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. */ return dsa_port_bridge_dev_get(dp) == bridge_dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, const struct dsa_bridge *bridge) { return dsa_port_bridge_dev_get(dp) == bridge->dev; } /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; } /* Returns true if any port of this tree offloads the given bridge */ static inline bool dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, const struct net_device *bridge_dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) return true; return false; } static inline bool dsa_port_tree_same(const struct dsa_port *a, const struct dsa_port *b) { return a->ds->dst == b->ds->dst; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Tagging protocol helpers called for the CPU ports and DSA links. * @get_tag_protocol retrieves the initial tagging protocol and is * mandatory. Switches which can operate using multiple tagging * protocols should implement @change_tag_protocol and report in * @get_tag_protocol the tagger in current use. */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver * in current use. The switch driver can provide handlers for certain * types of packets for switch management. */ int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); int (*port_change_conduit)(struct dsa_switch *ds, int port, struct net_device *conduit, struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); /* Per-port initialization and destruction methods. Mandatory if the * driver registers devlink port regions, optional otherwise. */ int (*port_setup)(struct dsa_switch *ds, int port); void (*port_teardown)(struct dsa_switch *ds, int port); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, int port, phy_interface_t iface); void (*phylink_mac_config)(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state); void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); void (*phylink_mac_link_up)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, struct phy_device *phydev, int speed, int duplex, bool tx_pause, bool rx_pause); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, struct kernel_ethtool_ts_info *ts); /* * ethtool MAC merge layer */ int (*get_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_state *state); int (*set_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack); void (*get_mm_stats)(struct dsa_switch *ds, int port, struct ethtool_mm_stats *stats); /* * DCB ops */ int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_set_apptrust)(struct dsa_switch *ds, int port, const u8 *sel, int nsel); int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, int *nsel); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); /* * Notification for MAC address changes on user ports. Drivers can * currently only veto operations. They should not use the method to * program the hardware, since the operation is not rolled back in case * of other errors. */ int (*port_set_mac_address)(struct dsa_switch *ds, int port, const unsigned char *addr); /* * Compatibility between device trees defining multiple CPU ports and * drivers which are not OK to use by default the numerically smallest * CPU port of a switch for its local ports. This can return NULL, * meaning "don't know/don't care". */ struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); /* * Port's MAC EEE settings */ int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); int (*get_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Upper device tracking. */ int (*port_prechangeupper)(struct dsa_switch *ds, int port, struct netdev_notifier_changeupper_info *info); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); int (*port_mst_state_set)(struct dsa_switch *ds, int port, const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); void (*port_set_host_flood)(struct dsa_switch *ds, int port, bool uc, bool mc); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, const struct switchdev_vlan_msti *msti); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*cls_flower_add)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_del)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_stats)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, struct dsa_mall_policer_tc_entry *policer); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge, struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); /* * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, struct ifreq *ifr); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct ifreq *ifr); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); int (*devlink_sb_pool_get)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack); int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 *p_pool_index, u32 *p_threshold); int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_cur, u32 *p_max); int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through * this method. By MTU, one understands the SDU (L2 payload) length. * If the switch needs to account for the DSA tag on the CPU port, this * method needs to do so privately. */ int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); /* * LAG integration */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); /* * HSR integration */ int (*port_hsr_join)(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); /* * MRP integration */ int (*port_mrp_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); /* * tag_8021q operations */ int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* * DSA conduit tracking operations */ void (*conduit_state_change)(struct dsa_switch *ds, const struct net_device *conduit, bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); void dsa_devlink_params_unregister(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); int dsa_devlink_resource_register(struct dsa_switch *ds, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); void dsa_devlink_resources_unregister(struct dsa_switch *ds); void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); struct devlink_region * dsa_devlink_port_region_create(struct dsa_switch *ds, int port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) { struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) { struct devlink *dl = port->devlink; struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline int dsa_devlink_port_to_port(struct devlink_port *port) { return port->index; } struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; }; bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. * * We need to return: * - offset: the (B - A) difference between: * A. the position of the real EtherType and * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes * after the normal EtherType was supposed to be) * The offset in bytes is exactly equal to the tagger overhead (and half of * that, in __be16 shorts). * * - proto: the value of the real EtherType. */ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; #endif } void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) bool dsa_user_dev_check(const struct net_device *dev); #else static inline bool dsa_user_dev_check(const struct net_device *dev) { return false; } #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); #endif |
| 549 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux security data structures for kernel objects. * * Author(s): Stephen Smalley, <stephen.smalley.work@gmail.com> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2016 Mellanox Technologies */ #ifndef _SELINUX_OBJSEC_H_ #define _SELINUX_OBJSEC_H_ #include <linux/list.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/binfmts.h> #include <linux/in.h> #include <linux/spinlock.h> #include <linux/lsm_hooks.h> #include <linux/msg.h> #include <net/net_namespace.h> #include "flask.h" #include "avc.h" struct task_security_struct { u32 osid; /* SID prior to last execve */ u32 sid; /* current SID */ u32 exec_sid; /* exec SID */ u32 create_sid; /* fscreate SID */ u32 keycreate_sid; /* keycreate SID */ u32 sockcreate_sid; /* fscreate SID */ } __randomize_layout; enum label_initialized { LABEL_INVALID, /* invalid or not initialized */ LABEL_INITIALIZED, /* initialized */ LABEL_PENDING }; struct inode_security_struct { struct inode *inode; /* back pointer to inode object */ struct list_head list; /* list of inode_security_struct */ u32 task_sid; /* SID of creating task */ u32 sid; /* SID of this object */ u16 sclass; /* security class of this object */ unsigned char initialized; /* initialization flag */ spinlock_t lock; }; struct file_security_struct { u32 sid; /* SID of open file description */ u32 fown_sid; /* SID of file owner (for SIGIO) */ u32 isid; /* SID of inode at the time of file open */ u32 pseqno; /* Policy seqno at the time of file open */ }; struct superblock_security_struct { u32 sid; /* SID of file system superblock */ u32 def_sid; /* default SID for labeling */ u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */ unsigned short behavior; /* labeling behavior */ unsigned short flags; /* which mount options were specified */ struct mutex lock; struct list_head isec_head; spinlock_t isec_lock; }; struct msg_security_struct { u32 sid; /* SID of message */ }; struct ipc_security_struct { u16 sclass; /* security class of this object */ u32 sid; /* SID of IPC resource */ }; struct netif_security_struct { struct net *ns; /* network namespace */ int ifindex; /* device index */ u32 sid; /* SID for this interface */ }; struct netnode_security_struct { union { __be32 ipv4; /* IPv4 node address */ struct in6_addr ipv6; /* IPv6 node address */ } addr; u32 sid; /* SID for this node */ u16 family; /* address family */ }; struct netport_security_struct { u32 sid; /* SID for this node */ u16 port; /* port number */ u8 protocol; /* transport protocol */ }; struct sk_security_struct { #ifdef CONFIG_NETLABEL enum { /* NetLabel state */ NLBL_UNSET = 0, NLBL_REQUIRE, NLBL_LABELED, NLBL_REQSKB, NLBL_CONNLABELED, } nlbl_state; struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */ #endif u32 sid; /* SID of this object */ u32 peer_sid; /* SID of peer */ u16 sclass; /* sock security class */ enum { /* SCTP association state */ SCTP_ASSOC_UNSET = 0, SCTP_ASSOC_SET, } sctp_assoc_state; }; struct tun_security_struct { u32 sid; /* SID for the tun device sockets */ }; struct key_security_struct { u32 sid; /* SID of key */ }; struct ib_security_struct { u32 sid; /* SID of the queue pair or MAD agent */ }; struct pkey_security_struct { u64 subnet_prefix; /* Port subnet prefix */ u16 pkey; /* PKey number */ u32 sid; /* SID of pkey */ }; struct bpf_security_struct { u32 sid; /* SID of bpf obj creator */ }; struct perf_event_security_struct { u32 sid; /* SID of perf_event obj creator */ }; extern struct lsm_blob_sizes selinux_blob_sizes; static inline struct task_security_struct *selinux_cred(const struct cred *cred) { return cred->security + selinux_blob_sizes.lbs_cred; } static inline struct file_security_struct *selinux_file(const struct file *file) { return file->f_security + selinux_blob_sizes.lbs_file; } static inline struct inode_security_struct * selinux_inode(const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + selinux_blob_sizes.lbs_inode; } static inline struct msg_security_struct * selinux_msg_msg(const struct msg_msg *msg_msg) { return msg_msg->security + selinux_blob_sizes.lbs_msg_msg; } static inline struct ipc_security_struct * selinux_ipc(const struct kern_ipc_perm *ipc) { return ipc->security + selinux_blob_sizes.lbs_ipc; } /* * get the subjective security ID of the current task */ static inline u32 current_sid(void) { const struct task_security_struct *tsec = selinux_cred(current_cred()); return tsec->sid; } static inline struct superblock_security_struct * selinux_superblock(const struct super_block *superblock) { return superblock->s_security + selinux_blob_sizes.lbs_superblock; } #ifdef CONFIG_KEYS static inline struct key_security_struct *selinux_key(const struct key *key) { return key->security + selinux_blob_sizes.lbs_key; } #endif /* CONFIG_KEYS */ static inline struct sk_security_struct *selinux_sock(const struct sock *sock) { return sock->sk_security + selinux_blob_sizes.lbs_sock; } static inline struct tun_security_struct *selinux_tun_dev(void *security) { return security + selinux_blob_sizes.lbs_tun_dev; } static inline struct ib_security_struct *selinux_ib(void *ib_sec) { return ib_sec + selinux_blob_sizes.lbs_ib; } static inline struct perf_event_security_struct * selinux_perf_event(void *perf_event) { return perf_event + selinux_blob_sizes.lbs_perf_event; } #endif /* _SELINUX_OBJSEC_H_ */ |
| 211 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/processor.h * * Copyright (C) 1995-1999 Russell King * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PROCESSOR_H #define __ASM_PROCESSOR_H /* * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is * no point in shifting all network buffers by 2 bytes just to make some IP * header fields appear aligned in memory, potentially sacrificing some DMA * performance on some platforms. */ #define NET_IP_ALIGN 0 #define MTE_CTRL_GCR_USER_EXCL_SHIFT 0 #define MTE_CTRL_GCR_USER_EXCL_MASK 0xffff #define MTE_CTRL_TCF_SYNC (1UL << 16) #define MTE_CTRL_TCF_ASYNC (1UL << 17) #define MTE_CTRL_TCF_ASYMM (1UL << 18) #ifndef __ASSEMBLY__ #include <linux/build_bug.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/thread_info.h> #include <vdso/processor.h> #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> #include <asm/kasan.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> #include <asm/pointer_auth.h> #include <asm/ptrace.h> #include <asm/spectre.h> #include <asm/types.h> /* * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area. */ #define DEFAULT_MAP_WINDOW_64 (UL(1) << VA_BITS_MIN) #define TASK_SIZE_64 (UL(1) << vabits_actual) #define TASK_SIZE_MAX (UL(1) << VA_BITS) #ifdef CONFIG_COMPAT #if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS) /* * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied * by the compat vectors page. */ #define TASK_SIZE_32 UL(0x100000000) #else #define TASK_SIZE_32 (UL(0x100000000) - PAGE_SIZE) #endif /* CONFIG_ARM64_64K_PAGES */ #define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) #define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) #define DEFAULT_MAP_WINDOW (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : DEFAULT_MAP_WINDOW_64) #else #define TASK_SIZE TASK_SIZE_64 #define DEFAULT_MAP_WINDOW DEFAULT_MAP_WINDOW_64 #endif /* CONFIG_COMPAT */ #ifdef CONFIG_ARM64_FORCE_52BIT #define STACK_TOP_MAX TASK_SIZE_64 #define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 4)) #else #define STACK_TOP_MAX DEFAULT_MAP_WINDOW_64 #define TASK_UNMAPPED_BASE (PAGE_ALIGN(DEFAULT_MAP_WINDOW / 4)) #endif /* CONFIG_ARM64_FORCE_52BIT */ #ifdef CONFIG_COMPAT #define AARCH32_VECTORS_BASE 0xffff0000 #define STACK_TOP (test_thread_flag(TIF_32BIT) ? \ AARCH32_VECTORS_BASE : STACK_TOP_MAX) #else #define STACK_TOP STACK_TOP_MAX #endif /* CONFIG_COMPAT */ #ifndef CONFIG_ARM64_FORCE_52BIT #define arch_get_mmap_end(addr, len, flags) \ (((addr) > DEFAULT_MAP_WINDOW) ? TASK_SIZE : DEFAULT_MAP_WINDOW) #define arch_get_mmap_base(addr, base) ((addr > DEFAULT_MAP_WINDOW) ? \ base + TASK_SIZE - DEFAULT_MAP_WINDOW :\ base) #endif /* CONFIG_ARM64_FORCE_52BIT */ extern phys_addr_t arm64_dma_phys_limit; #define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) struct debug_info { #ifdef CONFIG_HAVE_HW_BREAKPOINT /* Have we suspended stepping by a debugger? */ int suspended_step; /* Allow breakpoints and watchpoints to be disabled for this thread. */ int bps_disabled; int wps_disabled; /* Hardware breakpoints pinned to this task. */ struct perf_event *hbp_break[ARM_MAX_BRP]; struct perf_event *hbp_watch[ARM_MAX_WRP]; #endif }; enum vec_type { ARM64_VEC_SVE = 0, ARM64_VEC_SME, ARM64_VEC_MAX, }; enum fp_type { FP_STATE_CURRENT, /* Save based on current task state. */ FP_STATE_FPSIMD, FP_STATE_SVE, }; struct cpu_context { unsigned long x19; unsigned long x20; unsigned long x21; unsigned long x22; unsigned long x23; unsigned long x24; unsigned long x25; unsigned long x26; unsigned long x27; unsigned long x28; unsigned long fp; unsigned long sp; unsigned long pc; }; struct thread_struct { struct cpu_context cpu_context; /* cpu context */ /* * Whitelisted fields for hardened usercopy: * Maintainers must ensure manually that this contains no * implicit padding. */ struct { unsigned long tp_value; /* TLS register */ unsigned long tp2_value; u64 fpmr; unsigned long pad; struct user_fpsimd_state fpsimd_state; } uw; enum fp_type fp_type; /* registers FPSIMD or SVE? */ unsigned int fpsimd_cpu; void *sve_state; /* SVE registers, if any */ void *sme_state; /* ZA and ZT state, if any */ unsigned int vl[ARM64_VEC_MAX]; /* vector length */ unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */ unsigned long fault_address; /* fault info */ unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ struct user_fpsimd_state kernel_fpsimd_state; unsigned int kernel_fpsimd_cpu; #ifdef CONFIG_ARM64_PTR_AUTH struct ptrauth_keys_user keys_user; #ifdef CONFIG_ARM64_PTR_AUTH_KERNEL struct ptrauth_keys_kernel keys_kernel; #endif #endif #ifdef CONFIG_ARM64_MTE u64 mte_ctrl; #endif u64 sctlr_user; u64 svcr; u64 tpidr2_el0; u64 por_el0; }; static inline unsigned int thread_get_vl(struct thread_struct *thread, enum vec_type type) { return thread->vl[type]; } static inline unsigned int thread_get_sve_vl(struct thread_struct *thread) { return thread_get_vl(thread, ARM64_VEC_SVE); } static inline unsigned int thread_get_sme_vl(struct thread_struct *thread) { return thread_get_vl(thread, ARM64_VEC_SME); } static inline unsigned int thread_get_cur_vl(struct thread_struct *thread) { if (system_supports_sme() && (thread->svcr & SVCR_SM_MASK)) return thread_get_sme_vl(thread); else return thread_get_sve_vl(thread); } unsigned int task_get_vl(const struct task_struct *task, enum vec_type type); void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl); void task_set_vl_onexec(struct task_struct *task, enum vec_type type, unsigned long vl); unsigned int task_get_vl_onexec(const struct task_struct *task, enum vec_type type); static inline unsigned int task_get_sve_vl(const struct task_struct *task) { return task_get_vl(task, ARM64_VEC_SVE); } static inline unsigned int task_get_sme_vl(const struct task_struct *task) { return task_get_vl(task, ARM64_VEC_SME); } static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl) { task_set_vl(task, ARM64_VEC_SVE, vl); } static inline unsigned int task_get_sve_vl_onexec(const struct task_struct *task) { return task_get_vl_onexec(task, ARM64_VEC_SVE); } static inline void task_set_sve_vl_onexec(struct task_struct *task, unsigned long vl) { task_set_vl_onexec(task, ARM64_VEC_SVE, vl); } #define SCTLR_USER_MASK \ (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | SCTLR_ELx_ENDA | SCTLR_ELx_ENDB | \ SCTLR_EL1_TCF0_MASK) static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Verify that there is no padding among the whitelisted fields: */ BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) != sizeof_field(struct thread_struct, uw.tp_value) + sizeof_field(struct thread_struct, uw.tp2_value) + sizeof_field(struct thread_struct, uw.fpmr) + sizeof_field(struct thread_struct, uw.pad) + sizeof_field(struct thread_struct, uw.fpsimd_state)); *offset = offsetof(struct thread_struct, uw); *size = sizeof_field(struct thread_struct, uw); } #ifdef CONFIG_COMPAT #define task_user_tls(t) \ ({ \ unsigned long *__tls; \ if (is_compat_thread(task_thread_info(t))) \ __tls = &(t)->thread.uw.tp2_value; \ else \ __tls = &(t)->thread.uw.tp_value; \ __tls; \ }) #else #define task_user_tls(t) (&(t)->thread.uw.tp_value) #endif /* Sync TPIDR_EL0 back to thread_struct for current */ void tls_preserve_current_state(void); #define INIT_THREAD { \ .fpsimd_cpu = NR_CPUS, \ } static inline void start_thread_common(struct pt_regs *regs, unsigned long pc) { s32 previous_syscall = regs->syscallno; memset(regs, 0, sizeof(*regs)); regs->syscallno = previous_syscall; regs->pc = pc; if (system_uses_irq_prio_masking()) regs->pmr_save = GIC_PRIO_IRQON; } static inline void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { start_thread_common(regs, pc); regs->pstate = PSR_MODE_EL0t; spectre_v4_enable_task_mitigation(current); regs->sp = sp; } #ifdef CONFIG_COMPAT static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { start_thread_common(regs, pc); regs->pstate = PSR_AA32_MODE_USR; if (pc & 1) regs->pstate |= PSR_AA32_T_BIT; #ifdef __AARCH64EB__ regs->pstate |= PSR_AA32_E_BIT; #endif spectre_v4_enable_task_mitigation(current); regs->compat_sp = sp; } #endif static __always_inline bool is_ttbr0_addr(unsigned long addr) { /* entry assembly clears tags for TTBR0 addrs */ return addr < TASK_SIZE; } static __always_inline bool is_ttbr1_addr(unsigned long addr) { /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; } /* Forward declaration, a strange C thing */ struct task_struct; unsigned long __get_wchan(struct task_struct *p); void update_sctlr_el1(u64 sctlr); /* Thread switching */ extern struct task_struct *cpu_switch_to(struct task_struct *prev, struct task_struct *next); #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1) #define KSTK_EIP(tsk) ((unsigned long)task_pt_regs(tsk)->pc) #define KSTK_ESP(tsk) user_stack_pointer(task_pt_regs(tsk)) /* * Prefetching support */ #define ARCH_HAS_PREFETCH static inline void prefetch(const void *ptr) { asm volatile("prfm pldl1keep, %a0\n" : : "p" (ptr)); } #define ARCH_HAS_PREFETCHW static inline void prefetchw(const void *ptr) { asm volatile("prfm pstl1keep, %a0\n" : : "p" (ptr)); } extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */ extern void __init minsigstksz_setup(void); /* * Not at the top of the file due to a direct #include cycle between * <asm/fpsimd.h> and <asm/processor.h>. Deferring this #include * ensures that contents of processor.h are visible to fpsimd.h even if * processor.h is included first. * * These prctl helpers are the only things in this file that require * fpsimd.h. The core code expects them to be in this header. */ #include <asm/fpsimd.h> /* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() #define SME_SET_VL(arg) sme_set_current_vl(arg) #define SME_GET_VL() sme_get_current_vl() /* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) /* PR_PAC_{SET,GET}_ENABLED_KEYS prctl */ #define PAC_SET_ENABLED_KEYS(tsk, keys, enabled) \ ptrauth_set_enabled_keys(tsk, keys, enabled) #define PAC_GET_ENABLED_KEYS(tsk) ptrauth_get_enabled_keys(tsk) #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI /* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg); long get_tagged_addr_ctrl(struct task_struct *task); #define SET_TAGGED_ADDR_CTRL(arg) set_tagged_addr_ctrl(current, arg) #define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl(current) #endif int get_tsc_mode(unsigned long adr); int set_tsc_mode(unsigned int val); #define GET_TSC_CTL(adr) get_tsc_mode((adr)) #define SET_TSC_CTL(val) set_tsc_mode((val)) #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_POLL_H #define _LINUX_POLL_H #include <linux/compiler.h> #include <linux/ktime.h> #include <linux/wait.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> #include <uapi/linux/eventpoll.h> /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #define MAX_STACK_ALLOC 832 #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC #define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC) #define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry)) #define DEFAULT_POLLMASK (EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM) struct poll_table_struct; /* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* * Do not touch the structure directly, use the access functions * poll_does_not_wait() and poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; __poll_t _key; } poll_table; static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { if (p && p->_qproc && wait_address) p->_qproc(filp, wait_address, p); } /* * Return true if it is guaranteed that poll will not wait. This is the case * if the poll() of another file descriptor in the set got an event, so there * is no need for waiting. */ static inline bool poll_does_not_wait(const poll_table *p) { return p == NULL || p->_qproc == NULL; } /* * Return the set of events that the application wants to poll for. * This is useful for drivers that need to know whether a DMA transfer has * to be started implicitly on poll(). You typically only want to do that * if the application is actually polling for POLLIN and/or POLLOUT. */ static inline __poll_t poll_requested_events(const poll_table *p) { return p ? p->_key : ~(__poll_t)0; } static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) { pt->_qproc = qproc; pt->_key = ~(__poll_t)0; /* all events enabled */ } static inline bool file_can_poll(struct file *file) { return file->f_op->poll; } static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt) { if (unlikely(!file->f_op->poll)) return DEFAULT_POLLMASK; return file->f_op->poll(file, pt); } struct poll_table_entry { struct file *filp; __poll_t key; wait_queue_entry_t wait; wait_queue_head_t *wait_address; }; /* * Structures and helpers for select/poll syscall */ struct poll_wqueues { poll_table pt; struct poll_table_page *table; struct task_struct *polling_task; int triggered; int error; int inline_index; struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES]; }; extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern u64 select_estimate_accuracy(struct timespec64 *tv); #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1) extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time); extern int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec); #define __MAP(v, from, to) \ (from < to ? (v & from) * (to/from) : (v & from) / (from/to)) static inline __u16 mangle_poll(__poll_t val) { __u16 v = (__force __u16)val; #define M(X) __MAP(v, (__force __u16)EPOLL##X, POLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } static inline __poll_t demangle_poll(u16 val) { #define M(X) (__force __poll_t)__MAP(val, POLL##X, (__force __u16)EPOLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } #undef __MAP #endif /* _LINUX_POLL_H */ |
| 2 2 2 2 10 39 39 48 39 39 39 10 10 10 10 39 38 34 33 1 23 23 38 37 37 38 2 45 43 1 2 2 2 2 1 1 1 2 1 1 3 1 2 37 37 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 Linaro Ltd. * Author: Shannon Zhao <shannon.zhao@linaro.org> */ #include <linux/cpu.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/list.h> #include <linux/perf_event.h> #include <linux/perf/arm_pmu.h> #include <linux/uaccess.h> #include <asm/kvm_emulate.h> #include <kvm/arm_pmu.h> #include <kvm/arm_vgic.h> #define PERF_ATTR_CFG1_COUNTER_64BIT BIT(0) DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available); static LIST_HEAD(arm_pmus); static DEFINE_MUTEX(arm_pmus_lock); static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc); static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc); static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc) { return container_of(pmc, struct kvm_vcpu, arch.pmu.pmc[pmc->idx]); } static struct kvm_pmc *kvm_vcpu_idx_to_pmc(struct kvm_vcpu *vcpu, int cnt_idx) { return &vcpu->arch.pmu.pmc[cnt_idx]; } static u32 __kvm_pmu_event_mask(unsigned int pmuver) { switch (pmuver) { case ID_AA64DFR0_EL1_PMUVer_IMP: return GENMASK(9, 0); case ID_AA64DFR0_EL1_PMUVer_V3P1: case ID_AA64DFR0_EL1_PMUVer_V3P4: case ID_AA64DFR0_EL1_PMUVer_V3P5: case ID_AA64DFR0_EL1_PMUVer_V3P7: return GENMASK(15, 0); default: /* Shouldn't be here, just for sanity */ WARN_ONCE(1, "Unknown PMU version %d\n", pmuver); return 0; } } static u32 kvm_pmu_event_mask(struct kvm *kvm) { u64 dfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1); u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, dfr0); return __kvm_pmu_event_mask(pmuver); } u64 kvm_pmu_evtyper_mask(struct kvm *kvm) { u64 mask = ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMU_EXCLUDE_EL0 | kvm_pmu_event_mask(kvm); if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL2, IMP)) mask |= ARMV8_PMU_INCLUDE_EL2; if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL3, IMP)) mask |= ARMV8_PMU_EXCLUDE_NS_EL0 | ARMV8_PMU_EXCLUDE_NS_EL1 | ARMV8_PMU_EXCLUDE_EL3; return mask; } /** * kvm_pmc_is_64bit - determine if counter is 64bit * @pmc: counter context */ static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); return (pmc->idx == ARMV8_PMU_CYCLE_IDX || kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)); } static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc) { u64 val = kvm_vcpu_read_pmcr(kvm_pmc_to_vcpu(pmc)); return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) || (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC)); } static bool kvm_pmu_counter_can_chain(struct kvm_pmc *pmc) { return (!(pmc->idx & 1) && (pmc->idx + 1) < ARMV8_PMU_CYCLE_IDX && !kvm_pmc_has_64bit_overflow(pmc)); } static u32 counter_index_to_reg(u64 idx) { return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + idx; } static u32 counter_index_to_evtreg(u64 idx) { return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + idx; } static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 counter, reg, enabled, running; reg = counter_index_to_reg(pmc->idx); counter = __vcpu_sys_reg(vcpu, reg); /* * The real counter value is equal to the value of counter register plus * the value perf event counts. */ if (pmc->perf_event) counter += perf_event_read_value(pmc->perf_event, &enabled, &running); if (!kvm_pmc_is_64bit(pmc)) counter = lower_32_bits(counter); return counter; } /** * kvm_pmu_get_counter_value - get PMU counter value * @vcpu: The vcpu pointer * @select_idx: The counter index */ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) { if (!kvm_vcpu_has_pmu(vcpu)) return 0; return kvm_pmu_get_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx)); } static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 reg; kvm_pmu_release_perf_event(pmc); reg = counter_index_to_reg(pmc->idx); if (vcpu_mode_is_32bit(vcpu) && pmc->idx != ARMV8_PMU_CYCLE_IDX && !force) { /* * Even with PMUv3p5, AArch32 cannot write to the top * 32bit of the counters. The only possible course of * action is to use PMCR.P, which will reset them to * 0 (the only use of the 'force' parameter). */ val = __vcpu_sys_reg(vcpu, reg) & GENMASK(63, 32); val |= lower_32_bits(val); } __vcpu_sys_reg(vcpu, reg) = val; /* Recreate the perf event to reflect the updated sample_period */ kvm_pmu_create_perf_event(pmc); } /** * kvm_pmu_set_counter_value - set PMU counter value * @vcpu: The vcpu pointer * @select_idx: The counter index * @val: The counter value */ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { if (!kvm_vcpu_has_pmu(vcpu)) return; kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false); } /** * kvm_pmu_release_perf_event - remove the perf event * @pmc: The PMU counter pointer */ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { perf_event_disable(pmc->perf_event); perf_event_release_kernel(pmc->perf_event); pmc->perf_event = NULL; } } /** * kvm_pmu_stop_counter - stop PMU counter * @pmc: The PMU counter pointer * * If this counter has been configured to monitor some event, release it here. */ static void kvm_pmu_stop_counter(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); u64 reg, val; if (!pmc->perf_event) return; val = kvm_pmu_get_pmc_value(pmc); reg = counter_index_to_reg(pmc->idx); __vcpu_sys_reg(vcpu, reg) = val; kvm_pmu_release_perf_event(pmc); } /** * kvm_pmu_vcpu_init - assign pmu counter idx for cpu * @vcpu: The vcpu pointer * */ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) { int i; struct kvm_pmu *pmu = &vcpu->arch.pmu; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) pmu->pmc[i].idx = i; } /** * kvm_pmu_vcpu_reset - reset pmu state for cpu * @vcpu: The vcpu pointer * */ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) { unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); int i; for_each_set_bit(i, &mask, 32) kvm_pmu_stop_counter(kvm_vcpu_idx_to_pmc(vcpu, i)); } /** * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu * @vcpu: The vcpu pointer * */ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) { int i; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i)); irq_work_sync(&vcpu->arch.pmu.overflow_work); } u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu) { u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu)); if (val == 0) return BIT(ARMV8_PMU_CYCLE_IDX); else return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX); } /** * kvm_pmu_enable_counter_mask - enable selected PMU counters * @vcpu: The vcpu pointer * @val: the value guest writes to PMCNTENSET register * * Call perf_event_enable to start counting the perf event */ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; if (!kvm_vcpu_has_pmu(vcpu)) return; if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val) return; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { struct kvm_pmc *pmc; if (!(val & BIT(i))) continue; pmc = kvm_vcpu_idx_to_pmc(vcpu, i); if (!pmc->perf_event) { kvm_pmu_create_perf_event(pmc); } else { perf_event_enable(pmc->perf_event); if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) kvm_debug("fail to enable perf event\n"); } } } /** * kvm_pmu_disable_counter_mask - disable selected PMU counters * @vcpu: The vcpu pointer * @val: the value guest writes to PMCNTENCLR register * * Call perf_event_disable to stop counting the perf event */ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; if (!kvm_vcpu_has_pmu(vcpu) || !val) return; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { struct kvm_pmc *pmc; if (!(val & BIT(i))) continue; pmc = kvm_vcpu_idx_to_pmc(vcpu, i); if (pmc->perf_event) perf_event_disable(pmc->perf_event); } } static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu) { u64 reg = 0; if ((kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) { reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1); } return reg; } static void kvm_pmu_update_state(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = &vcpu->arch.pmu; bool overflow; if (!kvm_vcpu_has_pmu(vcpu)) return; overflow = !!kvm_pmu_overflow_status(vcpu); if (pmu->irq_level == overflow) return; pmu->irq_level = overflow; if (likely(irqchip_in_kernel(vcpu->kvm))) { int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu, pmu->irq_num, overflow, pmu); WARN_ON(ret); } } bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_sync_regs *sregs = &vcpu->run->s.regs; bool run_level = sregs->device_irq_level & KVM_ARM_DEV_PMU; if (likely(irqchip_in_kernel(vcpu->kvm))) return false; return pmu->irq_level != run_level; } /* * Reflect the PMU overflow interrupt output level into the kvm_run structure */ void kvm_pmu_update_run(struct kvm_vcpu *vcpu) { struct kvm_sync_regs *regs = &vcpu->run->s.regs; /* Populate the timer bitmap for user space */ regs->device_irq_level &= ~KVM_ARM_DEV_PMU; if (vcpu->arch.pmu.irq_level) regs->device_irq_level |= KVM_ARM_DEV_PMU; } /** * kvm_pmu_flush_hwstate - flush pmu state to cpu * @vcpu: The vcpu pointer * * Check if the PMU has overflowed while we were running in the host, and inject * an interrupt if that was the case. */ void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) { kvm_pmu_update_state(vcpu); } /** * kvm_pmu_sync_hwstate - sync pmu state from cpu * @vcpu: The vcpu pointer * * Check if the PMU has overflowed while we were running in the guest, and * inject an interrupt if that was the case. */ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) { kvm_pmu_update_state(vcpu); } /* * When perf interrupt is an NMI, we cannot safely notify the vcpu corresponding * to the event. * This is why we need a callback to do it once outside of the NMI context. */ static void kvm_pmu_perf_overflow_notify_vcpu(struct irq_work *work) { struct kvm_vcpu *vcpu; vcpu = container_of(work, struct kvm_vcpu, arch.pmu.overflow_work); kvm_vcpu_kick(vcpu); } /* * Perform an increment on any of the counters described in @mask, * generating the overflow if required, and propagate it as a chained * event if possible. */ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu, unsigned long mask, u32 event) { int i; if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) return; /* Weed out disabled counters */ mask &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); for_each_set_bit(i, &mask, ARMV8_PMU_CYCLE_IDX) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); u64 type, reg; /* Filter on event type */ type = __vcpu_sys_reg(vcpu, counter_index_to_evtreg(i)); type &= kvm_pmu_event_mask(vcpu->kvm); if (type != event) continue; /* Increment this counter */ reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1; if (!kvm_pmc_is_64bit(pmc)) reg = lower_32_bits(reg); __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) = reg; /* No overflow? move on */ if (kvm_pmc_has_64bit_overflow(pmc) ? reg : lower_32_bits(reg)) continue; /* Mark overflow */ __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i); if (kvm_pmu_counter_can_chain(pmc)) kvm_pmu_counter_increment(vcpu, BIT(i + 1), ARMV8_PMUV3_PERFCTR_CHAIN); } } /* Compute the sample period for a given counter value */ static u64 compute_period(struct kvm_pmc *pmc, u64 counter) { u64 val; if (kvm_pmc_is_64bit(pmc) && kvm_pmc_has_64bit_overflow(pmc)) val = (-counter) & GENMASK(63, 0); else val = (-counter) & GENMASK(31, 0); return val; } /* * When the perf event overflows, set the overflow status and inform the vcpu. */ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, struct perf_sample_data *data, struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu); struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); int idx = pmc->idx; u64 period; cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE); /* * Reset the sample period to the architectural limit, * i.e. the point where the counter overflows. */ period = compute_period(pmc, local64_read(&perf_event->count)); local64_set(&perf_event->hw.period_left, 0); perf_event->attr.sample_period = period; perf_event->hw.sample_period = period; __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx); if (kvm_pmu_counter_can_chain(pmc)) kvm_pmu_counter_increment(vcpu, BIT(idx + 1), ARMV8_PMUV3_PERFCTR_CHAIN); if (kvm_pmu_overflow_status(vcpu)) { kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); if (!in_nmi()) kvm_vcpu_kick(vcpu); else irq_work_queue(&vcpu->arch.pmu.overflow_work); } cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD); } /** * kvm_pmu_software_increment - do software increment * @vcpu: The vcpu pointer * @val: the value guest writes to PMSWINC register */ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) { kvm_pmu_counter_increment(vcpu, val, ARMV8_PMUV3_PERFCTR_SW_INCR); } /** * kvm_pmu_handle_pmcr - handle PMCR register * @vcpu: The vcpu pointer * @val: the value guest writes to PMCR register */ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { int i; if (!kvm_vcpu_has_pmu(vcpu)) return; /* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */ if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) val &= ~ARMV8_PMU_PMCR_LP; /* The reset bits don't indicate any state, and shouldn't be saved. */ __vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P); if (val & ARMV8_PMU_PMCR_E) { kvm_pmu_enable_counter_mask(vcpu, __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); } else { kvm_pmu_disable_counter_mask(vcpu, __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); } if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); mask &= ~BIT(ARMV8_PMU_CYCLE_IDX); for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } kvm_vcpu_pmu_restore_guest(vcpu); } static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); return (kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) && (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx)); } /** * kvm_pmu_create_perf_event - create a perf event for a counter * @pmc: Counter context */ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) { struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu; struct perf_event *event; struct perf_event_attr attr; u64 eventsel, reg, data; bool p, u, nsk, nsu; reg = counter_index_to_evtreg(pmc->idx); data = __vcpu_sys_reg(vcpu, reg); kvm_pmu_stop_counter(pmc); if (pmc->idx == ARMV8_PMU_CYCLE_IDX) eventsel = ARMV8_PMUV3_PERFCTR_CPU_CYCLES; else eventsel = data & kvm_pmu_event_mask(vcpu->kvm); /* * Neither SW increment nor chained events need to be backed * by a perf event. */ if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR || eventsel == ARMV8_PMUV3_PERFCTR_CHAIN) return; /* * If we have a filter in place and that the event isn't allowed, do * not install a perf event either. */ if (vcpu->kvm->arch.pmu_filter && !test_bit(eventsel, vcpu->kvm->arch.pmu_filter)) return; p = data & ARMV8_PMU_EXCLUDE_EL1; u = data & ARMV8_PMU_EXCLUDE_EL0; nsk = data & ARMV8_PMU_EXCLUDE_NS_EL1; nsu = data & ARMV8_PMU_EXCLUDE_NS_EL0; memset(&attr, 0, sizeof(struct perf_event_attr)); attr.type = arm_pmu->pmu.type; attr.size = sizeof(attr); attr.pinned = 1; attr.disabled = !kvm_pmu_counter_is_enabled(pmc); attr.exclude_user = (u != nsu); attr.exclude_kernel = (p != nsk); attr.exclude_hv = 1; /* Don't count EL2 events */ attr.exclude_host = 1; /* Don't count host events */ attr.config = eventsel; /* * If counting with a 64bit counter, advertise it to the perf * code, carefully dealing with the initial sample period * which also depends on the overflow. */ if (kvm_pmc_is_64bit(pmc)) attr.config1 |= PERF_ATTR_CFG1_COUNTER_64BIT; attr.sample_period = compute_period(pmc, kvm_pmu_get_pmc_value(pmc)); event = perf_event_create_kernel_counter(&attr, -1, current, kvm_pmu_perf_overflow, pmc); if (IS_ERR(event)) { pr_err_once("kvm: pmu event creation failed %ld\n", PTR_ERR(event)); return; } pmc->perf_event = event; } /** * kvm_pmu_set_counter_event_type - set selected counter to monitor some event * @vcpu: The vcpu pointer * @data: The data guest writes to PMXEVTYPER_EL0 * @select_idx: The number of selected counter * * When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an * event with given hardware event number. Here we call perf_event API to * emulate this action and create a kernel perf event for it. */ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx); u64 reg; if (!kvm_vcpu_has_pmu(vcpu)) return; reg = counter_index_to_evtreg(pmc->idx); __vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm); kvm_pmu_create_perf_event(pmc); } void kvm_host_pmu_init(struct arm_pmu *pmu) { struct arm_pmu_entry *entry; /* * Check the sanitised PMU version for the system, as KVM does not * support implementations where PMUv3 exists on a subset of CPUs. */ if (!pmuv3_implemented(kvm_arm_pmu_get_pmuver_limit())) return; mutex_lock(&arm_pmus_lock); entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) goto out_unlock; entry->arm_pmu = pmu; list_add_tail(&entry->entry, &arm_pmus); if (list_is_singular(&arm_pmus)) static_branch_enable(&kvm_arm_pmu_available); out_unlock: mutex_unlock(&arm_pmus_lock); } static struct arm_pmu *kvm_pmu_probe_armpmu(void) { struct arm_pmu *tmp, *pmu = NULL; struct arm_pmu_entry *entry; int cpu; mutex_lock(&arm_pmus_lock); /* * It is safe to use a stale cpu to iterate the list of PMUs so long as * the same value is used for the entirety of the loop. Given this, and * the fact that no percpu data is used for the lookup there is no need * to disable preemption. * * It is still necessary to get a valid cpu, though, to probe for the * default PMU instance as userspace is not required to specify a PMU * type. In order to uphold the preexisting behavior KVM selects the * PMU instance for the core during vcpu init. A dependent use * case would be a user with disdain of all things big.LITTLE that * affines the VMM to a particular cluster of cores. * * In any case, userspace should just do the sane thing and use the UAPI * to select a PMU type directly. But, be wary of the baggage being * carried here. */ cpu = raw_smp_processor_id(); list_for_each_entry(entry, &arm_pmus, entry) { tmp = entry->arm_pmu; if (cpumask_test_cpu(cpu, &tmp->supported_cpus)) { pmu = tmp; break; } } mutex_unlock(&arm_pmus_lock); return pmu; } u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { unsigned long *bmap = vcpu->kvm->arch.pmu_filter; u64 val, mask = 0; int base, i, nr_events; if (!kvm_vcpu_has_pmu(vcpu)) return 0; if (!pmceid1) { val = read_sysreg(pmceid0_el0); /* always support CHAIN */ val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN); base = 0; } else { val = read_sysreg(pmceid1_el0); /* * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled * as RAZ */ val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) | BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) | BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32)); base = 32; } if (!bmap) return val; nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1; for (i = 0; i < 32; i += 8) { u64 byte; byte = bitmap_get_value8(bmap, base + i); mask |= byte << i; if (nr_events >= (0x4000 + base + 32)) { byte = bitmap_get_value8(bmap, 0x4000 + base + i); mask |= byte << (32 + i); } } return val & mask; } void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) { u64 mask = kvm_pmu_valid_counter_mask(vcpu); kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu)); __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask; __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask; __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask; } int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) { if (!kvm_vcpu_has_pmu(vcpu)) return 0; if (!vcpu->arch.pmu.created) return -EINVAL; /* * A valid interrupt configuration for the PMU is either to have a * properly configured interrupt number and using an in-kernel * irqchip, or to not have an in-kernel GIC and not set an IRQ. */ if (irqchip_in_kernel(vcpu->kvm)) { int irq = vcpu->arch.pmu.irq_num; /* * If we are using an in-kernel vgic, at this point we know * the vgic will be initialized, so we can check the PMU irq * number against the dimensions of the vgic and make sure * it's valid. */ if (!irq_is_ppi(irq) && !vgic_valid_spi(vcpu->kvm, irq)) return -EINVAL; } else if (kvm_arm_pmu_irq_initialized(vcpu)) { return -EINVAL; } /* One-off reload of the PMU on first run */ kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); return 0; } static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) { if (irqchip_in_kernel(vcpu->kvm)) { int ret; /* * If using the PMU with an in-kernel virtual GIC * implementation, we require the GIC to be already * initialized when initializing the PMU. */ if (!vgic_initialized(vcpu->kvm)) return -ENODEV; if (!kvm_arm_pmu_irq_initialized(vcpu)) return -ENXIO; ret = kvm_vgic_set_owner(vcpu, vcpu->arch.pmu.irq_num, &vcpu->arch.pmu); if (ret) return ret; } init_irq_work(&vcpu->arch.pmu.overflow_work, kvm_pmu_perf_overflow_notify_vcpu); vcpu->arch.pmu.created = true; return 0; } /* * For one VM the interrupt type must be same for each vcpu. * As a PPI, the interrupt number is the same for all vcpus, * while as an SPI it must be a separate number per vcpu. */ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_arm_pmu_irq_initialized(vcpu)) continue; if (irq_is_ppi(irq)) { if (vcpu->arch.pmu.irq_num != irq) return false; } else { if (vcpu->arch.pmu.irq_num == irq) return false; } } return true; } /** * kvm_arm_pmu_get_max_counters - Return the max number of PMU counters. * @kvm: The kvm pointer */ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) { struct arm_pmu *arm_pmu = kvm->arch.arm_pmu; /* * The arm_pmu->cntr_mask considers the fixed counter(s) as well. * Ignore those and return only the general-purpose counters. */ return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS); } static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu) { lockdep_assert_held(&kvm->arch.config_lock); kvm->arch.arm_pmu = arm_pmu; kvm->arch.pmcr_n = kvm_arm_pmu_get_max_counters(kvm); } /** * kvm_arm_set_default_pmu - No PMU set, get the default one. * @kvm: The kvm pointer * * The observant among you will notice that the supported_cpus * mask does not get updated for the default PMU even though it * is quite possible the selected instance supports only a * subset of cores in the system. This is intentional, and * upholds the preexisting behavior on heterogeneous systems * where vCPUs can be scheduled on any core but the guest * counters could stop working. */ int kvm_arm_set_default_pmu(struct kvm *kvm) { struct arm_pmu *arm_pmu = kvm_pmu_probe_armpmu(); if (!arm_pmu) return -ENODEV; kvm_arm_set_pmu(kvm, arm_pmu); return 0; } static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) { struct kvm *kvm = vcpu->kvm; struct arm_pmu_entry *entry; struct arm_pmu *arm_pmu; int ret = -ENXIO; lockdep_assert_held(&kvm->arch.config_lock); mutex_lock(&arm_pmus_lock); list_for_each_entry(entry, &arm_pmus, entry) { arm_pmu = entry->arm_pmu; if (arm_pmu->pmu.type == pmu_id) { if (kvm_vm_has_ran_once(kvm) || (kvm->arch.pmu_filter && kvm->arch.arm_pmu != arm_pmu)) { ret = -EBUSY; break; } kvm_arm_set_pmu(kvm, arm_pmu); cpumask_copy(kvm->arch.supported_cpus, &arm_pmu->supported_cpus); ret = 0; break; } } mutex_unlock(&arm_pmus_lock); return ret; } int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { struct kvm *kvm = vcpu->kvm; lockdep_assert_held(&kvm->arch.config_lock); if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (vcpu->arch.pmu.created) return -EBUSY; switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: { int __user *uaddr = (int __user *)(long)attr->addr; int irq; if (!irqchip_in_kernel(kvm)) return -EINVAL; if (get_user(irq, uaddr)) return -EFAULT; /* The PMU overflow interrupt can be a PPI or a valid SPI. */ if (!(irq_is_ppi(irq) || irq_is_spi(irq))) return -EINVAL; if (!pmu_irq_is_valid(kvm, irq)) return -EINVAL; if (kvm_arm_pmu_irq_initialized(vcpu)) return -EBUSY; kvm_debug("Set kvm ARM PMU irq: %d\n", irq); vcpu->arch.pmu.irq_num = irq; return 0; } case KVM_ARM_VCPU_PMU_V3_FILTER: { u8 pmuver = kvm_arm_pmu_get_pmuver_limit(); struct kvm_pmu_event_filter __user *uaddr; struct kvm_pmu_event_filter filter; int nr_events; /* * Allow userspace to specify an event filter for the entire * event range supported by PMUVer of the hardware, rather * than the guest's PMUVer for KVM backward compatibility. */ nr_events = __kvm_pmu_event_mask(pmuver) + 1; uaddr = (struct kvm_pmu_event_filter __user *)(long)attr->addr; if (copy_from_user(&filter, uaddr, sizeof(filter))) return -EFAULT; if (((u32)filter.base_event + filter.nevents) > nr_events || (filter.action != KVM_PMU_EVENT_ALLOW && filter.action != KVM_PMU_EVENT_DENY)) return -EINVAL; if (kvm_vm_has_ran_once(kvm)) return -EBUSY; if (!kvm->arch.pmu_filter) { kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT); if (!kvm->arch.pmu_filter) return -ENOMEM; /* * The default depends on the first applied filter. * If it allows events, the default is to deny. * Conversely, if the first filter denies a set of * events, the default is to allow. */ if (filter.action == KVM_PMU_EVENT_ALLOW) bitmap_zero(kvm->arch.pmu_filter, nr_events); else bitmap_fill(kvm->arch.pmu_filter, nr_events); } if (filter.action == KVM_PMU_EVENT_ALLOW) bitmap_set(kvm->arch.pmu_filter, filter.base_event, filter.nevents); else bitmap_clear(kvm->arch.pmu_filter, filter.base_event, filter.nevents); return 0; } case KVM_ARM_VCPU_PMU_V3_SET_PMU: { int __user *uaddr = (int __user *)(long)attr->addr; int pmu_id; if (get_user(pmu_id, uaddr)) return -EFAULT; return kvm_arm_pmu_v3_set_pmu(vcpu, pmu_id); } case KVM_ARM_VCPU_PMU_V3_INIT: return kvm_arm_pmu_v3_init(vcpu); } return -ENXIO; } int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: { int __user *uaddr = (int __user *)(long)attr->addr; int irq; if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (!kvm_arm_pmu_irq_initialized(vcpu)) return -ENXIO; irq = vcpu->arch.pmu.irq_num; return put_user(irq, uaddr); } } return -ENXIO; } int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: case KVM_ARM_VCPU_PMU_V3_INIT: case KVM_ARM_VCPU_PMU_V3_FILTER: case KVM_ARM_VCPU_PMU_V3_SET_PMU: if (kvm_vcpu_has_pmu(vcpu)) return 0; } return -ENXIO; } u8 kvm_arm_pmu_get_pmuver_limit(void) { u64 tmp; tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1); tmp = cpuid_feature_cap_perfmon_field(tmp, ID_AA64DFR0_EL1_PMUVer_SHIFT, ID_AA64DFR0_EL1_PMUVer_V3P5); return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp); } /** * kvm_vcpu_read_pmcr - Read PMCR_EL0 register for the vCPU * @vcpu: The vcpu pointer */ u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu) { u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0); return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N); } |
| 197 75 75 75 198 198 198 197 198 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @node: where to begin the search * @tag: the tag index * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset = 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 804 830 564 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_ALTERNATIVE_MACROS_H #define __ASM_ALTERNATIVE_MACROS_H #include <linux/const.h> #include <vdso/bits.h> #include <asm/cpucaps.h> #include <asm/insn-def.h> /* * Binutils 2.27.0 can't handle a 'UL' suffix on constants, so for the assembly * macros below we must use we must use `(1 << ARM64_CB_SHIFT)`. */ #define ARM64_CB_SHIFT 15 #define ARM64_CB_BIT BIT(ARM64_CB_SHIFT) #if ARM64_NCAPS >= ARM64_CB_BIT #error "cpucaps have overflown ARM64_CB_BIT" #endif #ifndef __ASSEMBLY__ #include <linux/stringify.h> #define ALTINSTR_ENTRY(cpucap) \ " .word 661b - .\n" /* label */ \ " .word 663f - .\n" /* new instruction */ \ " .hword " __stringify(cpucap) "\n" /* cpucap */ \ " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ #define ALTINSTR_ENTRY_CB(cpucap, cb) \ " .word 661b - .\n" /* label */ \ " .word " __stringify(cb) "- .\n" /* callback */ \ " .hword " __stringify(cpucap) "\n" /* cpucap */ \ " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ /* * alternative assembly primitive: * * If any of these .org directive fail, it means that insn1 and insn2 * don't have the same length. This used to be written as * * .if ((664b-663b) != (662b-661b)) * .error "Alternatives instruction length mismatch" * .endif * * but most assemblers die if insn1 or insn2 have a .inst. This should * be fixed in a binutils release posterior to 2.25.51.0.2 (anything * containing commit 4e4d08cf7399b606 or c1baaddf8861). * * Alternatives with callbacks do not generate replacement instructions. */ #define __ALTERNATIVE_CFG(oldinstr, newinstr, cpucap, cfg_enabled) \ ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(cpucap) \ ".popsection\n" \ ".subsection 1\n" \ "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ ".org . - (662b-661b) + (664b-663b)\n\t" \ ".previous\n" \ ".endif\n" #define __ALTERNATIVE_CFG_CB(oldinstr, cpucap, cfg_enabled, cb) \ ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY_CB(cpucap, cb) \ ".popsection\n" \ "663:\n\t" \ "664:\n\t" \ ".endif\n" #define _ALTERNATIVE_CFG(oldinstr, newinstr, cpucap, cfg, ...) \ __ALTERNATIVE_CFG(oldinstr, newinstr, cpucap, IS_ENABLED(cfg)) #define ALTERNATIVE_CB(oldinstr, cpucap, cb) \ __ALTERNATIVE_CFG_CB(oldinstr, (1 << ARM64_CB_SHIFT) | (cpucap), 1, cb) #else #include <asm/assembler.h> .macro altinstruction_entry orig_offset alt_offset cpucap orig_len alt_len .word \orig_offset - . .word \alt_offset - . .hword (\cpucap) .byte \orig_len .byte \alt_len .endm .macro alternative_insn insn1, insn2, cap, enable = 1 .if \enable 661: \insn1 662: .pushsection .altinstructions, "a" altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f .popsection .subsection 1 663: \insn2 664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .previous .endif .endm /* * Alternative sequences * * The code for the case where the capability is not present will be * assembled and linked as normal. There are no restrictions on this * code. * * The code for the case where the capability is present will be * assembled into a special section to be used for dynamic patching. * Code for that case must: * * 1. Be exactly the same length (in bytes) as the default code * sequence. * * 2. Not contain a branch target that is used outside of the * alternative sequence it is defined in (branches into an * alternative sequence are not fixed up). */ /* * Begin an alternative code sequence. */ .macro alternative_if_not cap .set .Lasm_alt_mode, 0 .pushsection .altinstructions, "a" altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f .popsection 661: .endm .macro alternative_if cap .set .Lasm_alt_mode, 1 .pushsection .altinstructions, "a" altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f .popsection .subsection 1 .align 2 /* So GAS knows label 661 is suitably aligned */ 661: .endm .macro alternative_cb cap, cb .set .Lasm_alt_mode, 0 .pushsection .altinstructions, "a" altinstruction_entry 661f, \cb, (1 << ARM64_CB_SHIFT) | \cap, 662f-661f, 0 .popsection 661: .endm /* * Provide the other half of the alternative code sequence. */ .macro alternative_else 662: .if .Lasm_alt_mode==0 .subsection 1 .else .previous .endif 663: .endm /* * Complete an alternative code sequence. */ .macro alternative_endif 664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .if .Lasm_alt_mode==0 .previous .endif .endm /* * Callback-based alternative epilogue */ .macro alternative_cb_end 662: .endm /* * Provides a trivial alternative or default sequence consisting solely * of NOPs. The number of NOPs is chosen automatically to match the * previous case. */ .macro alternative_else_nop_endif alternative_else nops (662b-661b) / AARCH64_INSN_SIZE alternative_endif .endm #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) #endif /* __ASSEMBLY__ */ /* * Usage: asm(ALTERNATIVE(oldinstr, newinstr, cpucap)); * * Usage: asm(ALTERNATIVE(oldinstr, newinstr, cpucap, CONFIG_FOO)); * N.B. If CONFIG_FOO is specified, but not selected, the whole block * will be omitted, including oldinstr. */ #define ALTERNATIVE(oldinstr, newinstr, ...) \ _ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1) #ifndef __ASSEMBLY__ #include <linux/types.h> static __always_inline bool alternative_has_cap_likely(const unsigned long cpucap) { if (!cpucap_is_possible(cpucap)) return false; asm goto( #ifdef BUILD_VDSO ALTERNATIVE("b %l[l_no]", "nop", %[cpucap]) #else ALTERNATIVE_CB("b %l[l_no]", %[cpucap], alt_cb_patch_nops) #endif : : [cpucap] "i" (cpucap) : : l_no); return true; l_no: return false; } static __always_inline bool alternative_has_cap_unlikely(const unsigned long cpucap) { if (!cpucap_is_possible(cpucap)) return false; asm goto( ALTERNATIVE("nop", "b %l[l_yes]", %[cpucap]) : : [cpucap] "i" (cpucap) : : l_yes); return false; l_yes: return true; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_ALTERNATIVE_MACROS_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/cacheflush.h * * Copyright (C) 1999-2002 Russell King. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_CACHEFLUSH_H #define __ASM_CACHEFLUSH_H #include <linux/kgdb.h> #include <linux/mm.h> /* * This flag is used to indicate that the page pointed to by a pte is clean * and does not require cleaning before returning it to the user. */ #define PG_dcache_clean PG_arch_1 /* * MM Cache Management * =================== * * The arch/arm64/mm/cache.S implements these methods. * * Start addresses are inclusive and end addresses are exclusive; start * addresses should be rounded down, end addresses up. * * See Documentation/core-api/cachetlb.rst for more information. Please note that * the implementation assumes non-aliasing VIPT D-cache and (aliasing) * VIPT I-cache. * * All functions below apply to the interval [start, end) * - start - virtual start address (inclusive) * - end - virtual end address (exclusive) * * caches_clean_inval_pou(start, end) * * Ensure coherency between the I-cache and the D-cache region to * the Point of Unification. * * caches_clean_inval_user_pou(start, end) * * Ensure coherency between the I-cache and the D-cache region to * the Point of Unification. * Use only if the region might access user memory. * * icache_inval_pou(start, end) * * Invalidate I-cache region to the Point of Unification. * * dcache_clean_inval_poc(start, end) * * Clean and invalidate D-cache region to the Point of Coherency. * * dcache_inval_poc(start, end) * * Invalidate D-cache region to the Point of Coherency. * * dcache_clean_poc(start, end) * * Clean D-cache region to the Point of Coherency. * * dcache_clean_pop(start, end) * * Clean D-cache region to the Point of Persistence. * * dcache_clean_pou(start, end) * * Clean D-cache region to the Point of Unification. */ extern void caches_clean_inval_pou(unsigned long start, unsigned long end); extern void icache_inval_pou(unsigned long start, unsigned long end); extern void dcache_clean_inval_poc(unsigned long start, unsigned long end); extern void dcache_inval_poc(unsigned long start, unsigned long end); extern void dcache_clean_poc(unsigned long start, unsigned long end); extern void dcache_clean_pop(unsigned long start, unsigned long end); extern void dcache_clean_pou(unsigned long start, unsigned long end); extern long caches_clean_inval_user_pou(unsigned long start, unsigned long end); extern void sync_icache_aliases(unsigned long start, unsigned long end); static inline void flush_icache_range(unsigned long start, unsigned long end) { caches_clean_inval_pou(start, end); /* * IPI all online CPUs so that they undergo a context synchronization * event and are forced to refetch the new instructions. */ /* * KGDB performs cache maintenance with interrupts disabled, so we * will deadlock trying to IPI the secondary CPUs. In theory, we can * set CACHE_FLUSH_IS_SAFE to 0 to avoid this known issue, but that * just means that KGDB will elide the maintenance altogether! As it * turns out, KGDB uses IPIs to round-up the secondary CPUs during * the patching operation, so we don't need extra IPIs here anyway. * In which case, add a KGDB-specific bodge and return early. */ if (in_dbg_master()) return; kick_all_cpus_sync(); } #define flush_icache_range flush_icache_range /* * Copy user data from/to a page which is mapped into a different * processes address space. Really, we want to allow our "user * space" model to handle this. */ extern void copy_to_user_page(struct vm_area_struct *, struct page *, unsigned long, void *, const void *, unsigned long); #define copy_to_user_page copy_to_user_page /* * flush_dcache_folio is used when the kernel has written to the page * cache page at virtual address page->virtual. * * If this page isn't mapped (ie, folio_mapping == NULL), or it might * have userspace mappings, then we _must_ always clean + invalidate * the dcache entries associated with the kernel mapping. * * Otherwise we can defer the operation, and clean the cache when we are * about to change to user space. This is the same method as used on SPARC64. * See update_mmu_cache for the user space part. */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); void flush_dcache_folio(struct folio *); #define flush_dcache_folio flush_dcache_folio static __always_inline void icache_inval_all_pou(void) { if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC)) return; asm("ic ialluis"); dsb(ish); } #include <asm-generic/cacheflush.h> #endif /* __ASM_CACHEFLUSH_H */ |
| 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 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/module.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/netdevice.h> #include <net/net_namespace.h> #include <linux/security.h> #include <linux/notifier.h> #include <linux/hashtable.h> #include <rdma/rdma_netlink.h> #include <rdma/ib_addr.h> #include <rdma/ib_cache.h> #include <rdma/rdma_counter.h> #include "core_priv.h" #include "restrack.h" MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("core kernel InfiniBand API"); MODULE_LICENSE("Dual BSD/GPL"); struct workqueue_struct *ib_comp_wq; struct workqueue_struct *ib_comp_unbound_wq; struct workqueue_struct *ib_wq; EXPORT_SYMBOL_GPL(ib_wq); static struct workqueue_struct *ib_unreg_wq; /* * Each of the three rwsem locks (devices, clients, client_data) protects the * xarray of the same name. Specifically it allows the caller to assert that * the MARK will/will not be changing under the lock, and for devices and * clients, that the value in the xarray is still a valid pointer. Change of * the MARK is linked to the object state, so holding the lock and testing the * MARK also asserts that the contained object is in a certain state. * * This is used to build a two stage register/unregister flow where objects * can continue to be in the xarray even though they are still in progress to * register/unregister. * * The xarray itself provides additional locking, and restartable iteration, * which is also relied on. * * Locks should not be nested, with the exception of client_data, which is * allowed to nest under the read side of the other two locks. * * The devices_rwsem also protects the device name list, any change or * assignment of device name must also hold the write side to guarantee unique * names. */ /* * devices contains devices that have had their names assigned. The * devices may not be registered. Users that care about the registration * status need to call ib_device_try_get() on the device to ensure it is * registered, and keep it registered, for the required duration. * */ static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC); static DECLARE_RWSEM(devices_rwsem); #define DEVICE_REGISTERED XA_MARK_1 static u32 highest_client_id; #define CLIENT_REGISTERED XA_MARK_1 static DEFINE_XARRAY_FLAGS(clients, XA_FLAGS_ALLOC); static DECLARE_RWSEM(clients_rwsem); static void ib_client_put(struct ib_client *client) { if (refcount_dec_and_test(&client->uses)) complete(&client->uses_zero); } /* * If client_data is registered then the corresponding client must also still * be registered. */ #define CLIENT_DATA_REGISTERED XA_MARK_1 unsigned int rdma_dev_net_id; /* * A list of net namespaces is maintained in an xarray. This is necessary * because we can't get the locking right using the existing net ns list. We * would require a init_net callback after the list is updated. */ static DEFINE_XARRAY_FLAGS(rdma_nets, XA_FLAGS_ALLOC); /* * rwsem to protect accessing the rdma_nets xarray entries. */ static DECLARE_RWSEM(rdma_nets_rwsem); bool ib_devices_shared_netns = true; module_param_named(netns_mode, ib_devices_shared_netns, bool, 0444); MODULE_PARM_DESC(netns_mode, "Share device among net namespaces; default=1 (shared)"); /** * rdma_dev_access_netns() - Return whether an rdma device can be accessed * from a specified net namespace or not. * @dev: Pointer to rdma device which needs to be checked * @net: Pointer to net namesapce for which access to be checked * * When the rdma device is in shared mode, it ignores the net namespace. * When the rdma device is exclusive to a net namespace, rdma device net * namespace is checked against the specified one. */ bool rdma_dev_access_netns(const struct ib_device *dev, const struct net *net) { return (ib_devices_shared_netns || net_eq(read_pnet(&dev->coredev.rdma_net), net)); } EXPORT_SYMBOL(rdma_dev_access_netns); /* * xarray has this behavior where it won't iterate over NULL values stored in * allocated arrays. So we need our own iterator to see all values stored in * the array. This does the same thing as xa_for_each except that it also * returns NULL valued entries if the array is allocating. Simplified to only * work on simple xarrays. */ static void *xan_find_marked(struct xarray *xa, unsigned long *indexp, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { entry = xas_find_marked(&xas, ULONG_MAX, filter); if (xa_is_zero(entry)) break; } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) { *indexp = xas.xa_index; if (xa_is_zero(entry)) return NULL; return entry; } return XA_ERROR(-ENOENT); } #define xan_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xan_find_marked(xa, &(index), filter); \ !xa_is_err(entry); \ (index)++, entry = xan_find_marked(xa, &(index), filter)) /* RCU hash table mapping netdevice pointers to struct ib_port_data */ static DEFINE_SPINLOCK(ndev_hash_lock); static DECLARE_HASHTABLE(ndev_hash, 5); static void free_netdevs(struct ib_device *ib_dev); static void ib_unregister_work(struct work_struct *work); static void __ib_unregister_device(struct ib_device *device); static int ib_security_change(struct notifier_block *nb, unsigned long event, void *lsm_data); static void ib_policy_change_task(struct work_struct *work); static DECLARE_WORK(ib_policy_change_work, ib_policy_change_task); static void __ibdev_printk(const char *level, const struct ib_device *ibdev, struct va_format *vaf) { if (ibdev && ibdev->dev.parent) dev_printk_emit(level[1] - '0', ibdev->dev.parent, "%s %s %s: %pV", dev_driver_string(ibdev->dev.parent), dev_name(ibdev->dev.parent), dev_name(&ibdev->dev), vaf); else if (ibdev) printk("%s%s: %pV", level, dev_name(&ibdev->dev), vaf); else printk("%s(NULL ib_device): %pV", level, vaf); } void ibdev_printk(const char *level, const struct ib_device *ibdev, const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; __ibdev_printk(level, ibdev, &vaf); va_end(args); } EXPORT_SYMBOL(ibdev_printk); #define define_ibdev_printk_level(func, level) \ void func(const struct ib_device *ibdev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __ibdev_printk(level, ibdev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_ibdev_printk_level(ibdev_emerg, KERN_EMERG); define_ibdev_printk_level(ibdev_alert, KERN_ALERT); define_ibdev_printk_level(ibdev_crit, KERN_CRIT); define_ibdev_printk_level(ibdev_err, KERN_ERR); define_ibdev_printk_level(ibdev_warn, KERN_WARNING); define_ibdev_printk_level(ibdev_notice, KERN_NOTICE); define_ibdev_printk_level(ibdev_info, KERN_INFO); static struct notifier_block ibdev_lsm_nb = { .notifier_call = ib_security_change, }; static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net, struct net *net); /* Pointer to the RCU head at the start of the ib_port_data array */ struct ib_port_data_rcu { struct rcu_head rcu_head; struct ib_port_data pdata[]; }; static void ib_device_check_mandatory(struct ib_device *device) { #define IB_MANDATORY_FUNC(x) { offsetof(struct ib_device_ops, x), #x } static const struct { size_t offset; char *name; } mandatory_table[] = { IB_MANDATORY_FUNC(query_device), IB_MANDATORY_FUNC(query_port), IB_MANDATORY_FUNC(alloc_pd), IB_MANDATORY_FUNC(dealloc_pd), IB_MANDATORY_FUNC(create_qp), IB_MANDATORY_FUNC(modify_qp), IB_MANDATORY_FUNC(destroy_qp), IB_MANDATORY_FUNC(post_send), IB_MANDATORY_FUNC(post_recv), IB_MANDATORY_FUNC(create_cq), IB_MANDATORY_FUNC(destroy_cq), IB_MANDATORY_FUNC(poll_cq), IB_MANDATORY_FUNC(req_notify_cq), IB_MANDATORY_FUNC(get_dma_mr), IB_MANDATORY_FUNC(reg_user_mr), IB_MANDATORY_FUNC(dereg_mr), IB_MANDATORY_FUNC(get_port_immutable) }; int i; device->kverbs_provider = true; for (i = 0; i < ARRAY_SIZE(mandatory_table); ++i) { if (!*(void **) ((void *) &device->ops + mandatory_table[i].offset)) { device->kverbs_provider = false; break; } } } /* * Caller must perform ib_device_put() to return the device reference count * when ib_device_get_by_index() returns valid device pointer. */ struct ib_device *ib_device_get_by_index(const struct net *net, u32 index) { struct ib_device *device; down_read(&devices_rwsem); device = xa_load(&devices, index); if (device) { if (!rdma_dev_access_netns(device, net)) { device = NULL; goto out; } if (!ib_device_try_get(device)) device = NULL; } out: up_read(&devices_rwsem); return device; } /** * ib_device_put - Release IB device reference * @device: device whose reference to be released * * ib_device_put() releases reference to the IB device to allow it to be * unregistered and eventually free. */ void ib_device_put(struct ib_device *device) { if (refcount_dec_and_test(&device->refcount)) complete(&device->unreg_completion); } EXPORT_SYMBOL(ib_device_put); static struct ib_device *__ib_device_get_by_name(const char *name) { struct ib_device *device; unsigned long index; xa_for_each (&devices, index, device) if (!strcmp(name, dev_name(&device->dev))) return device; return NULL; } /** * ib_device_get_by_name - Find an IB device by name * @name: The name to look for * @driver_id: The driver ID that must match (RDMA_DRIVER_UNKNOWN matches all) * * Find and hold an ib_device by its name. The caller must call * ib_device_put() on the returned pointer. */ struct ib_device *ib_device_get_by_name(const char *name, enum rdma_driver_id driver_id) { struct ib_device *device; down_read(&devices_rwsem); device = __ib_device_get_by_name(name); if (device && driver_id != RDMA_DRIVER_UNKNOWN && device->ops.driver_id != driver_id) device = NULL; if (device) { if (!ib_device_try_get(device)) device = NULL; } up_read(&devices_rwsem); return device; } EXPORT_SYMBOL(ib_device_get_by_name); static int rename_compat_devs(struct ib_device *device) { struct ib_core_device *cdev; unsigned long index; int ret = 0; mutex_lock(&device->compat_devs_mutex); xa_for_each (&device->compat_devs, index, cdev) { ret = device_rename(&cdev->dev, dev_name(&device->dev)); if (ret) { dev_warn(&cdev->dev, "Fail to rename compatdev to new name %s\n", dev_name(&device->dev)); break; } } mutex_unlock(&device->compat_devs_mutex); return ret; } int ib_device_rename(struct ib_device *ibdev, const char *name) { unsigned long index; void *client_data; int ret; down_write(&devices_rwsem); if (!strcmp(name, dev_name(&ibdev->dev))) { up_write(&devices_rwsem); return 0; } if (__ib_device_get_by_name(name)) { up_write(&devices_rwsem); return -EEXIST; } ret = device_rename(&ibdev->dev, name); if (ret) { up_write(&devices_rwsem); return ret; } strscpy(ibdev->name, name, IB_DEVICE_NAME_MAX); ret = rename_compat_devs(ibdev); downgrade_write(&devices_rwsem); down_read(&ibdev->client_data_rwsem); xan_for_each_marked(&ibdev->client_data, index, client_data, CLIENT_DATA_REGISTERED) { struct ib_client *client = xa_load(&clients, index); if (!client || !client->rename) continue; client->rename(ibdev, client_data); } up_read(&ibdev->client_data_rwsem); up_read(&devices_rwsem); return 0; } int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim) { if (use_dim > 1) return -EINVAL; ibdev->use_cq_dim = use_dim; return 0; } static int alloc_name(struct ib_device *ibdev, const char *name) { struct ib_device *device; unsigned long index; struct ida inuse; int rc; int i; lockdep_assert_held_write(&devices_rwsem); ida_init(&inuse); xa_for_each (&devices, index, device) { char buf[IB_DEVICE_NAME_MAX]; if (sscanf(dev_name(&device->dev), name, &i) != 1) continue; if (i < 0 || i >= INT_MAX) continue; snprintf(buf, sizeof buf, name, i); if (strcmp(buf, dev_name(&device->dev)) != 0) continue; rc = ida_alloc_range(&inuse, i, i, GFP_KERNEL); if (rc < 0) goto out; } rc = ida_alloc(&inuse, GFP_KERNEL); if (rc < 0) goto out; rc = dev_set_name(&ibdev->dev, name, rc); out: ida_destroy(&inuse); return rc; } static void ib_device_release(struct device *device) { struct ib_device *dev = container_of(device, struct ib_device, dev); free_netdevs(dev); WARN_ON(refcount_read(&dev->refcount)); if (dev->hw_stats_data) ib_device_release_hw_stats(dev->hw_stats_data); if (dev->port_data) { ib_cache_release_one(dev); ib_security_release_port_pkey_list(dev); rdma_counter_release(dev); kfree_rcu(container_of(dev->port_data, struct ib_port_data_rcu, pdata[0]), rcu_head); } mutex_destroy(&dev->subdev_lock); mutex_destroy(&dev->unregistration_lock); mutex_destroy(&dev->compat_devs_mutex); xa_destroy(&dev->compat_devs); xa_destroy(&dev->client_data); kfree_rcu(dev, rcu_head); } static int ib_device_uevent(const struct device *device, struct kobj_uevent_env *env) { if (add_uevent_var(env, "NAME=%s", dev_name(device))) return -ENOMEM; /* * It would be nice to pass the node GUID with the event... */ return 0; } static const void *net_namespace(const struct device *d) { const struct ib_core_device *coredev = container_of(d, struct ib_core_device, dev); return read_pnet(&coredev->rdma_net); } static struct class ib_class = { .name = "infiniband", .dev_release = ib_device_release, .dev_uevent = ib_device_uevent, .ns_type = &net_ns_type_operations, .namespace = net_namespace, }; static void rdma_init_coredev(struct ib_core_device *coredev, struct ib_device *dev, struct net *net) { /* This BUILD_BUG_ON is intended to catch layout change * of union of ib_core_device and device. * dev must be the first element as ib_core and providers * driver uses it. Adding anything in ib_core_device before * device will break this assumption. */ BUILD_BUG_ON(offsetof(struct ib_device, coredev.dev) != offsetof(struct ib_device, dev)); coredev->dev.class = &ib_class; coredev->dev.groups = dev->groups; device_initialize(&coredev->dev); coredev->owner = dev; INIT_LIST_HEAD(&coredev->port_list); write_pnet(&coredev->rdma_net, net); } /** * _ib_alloc_device - allocate an IB device struct * @size:size of structure to allocate * * Low-level drivers should use ib_alloc_device() to allocate &struct * ib_device. @size is the size of the structure to be allocated, * including any private data used by the low-level driver. * ib_dealloc_device() must be used to free structures allocated with * ib_alloc_device(). */ struct ib_device *_ib_alloc_device(size_t size) { struct ib_device *device; unsigned int i; if (WARN_ON(size < sizeof(struct ib_device))) return NULL; device = kzalloc(size, GFP_KERNEL); if (!device) return NULL; if (rdma_restrack_init(device)) { kfree(device); return NULL; } rdma_init_coredev(&device->coredev, device, &init_net); INIT_LIST_HEAD(&device->event_handler_list); spin_lock_init(&device->qp_open_list_lock); init_rwsem(&device->event_handler_rwsem); mutex_init(&device->unregistration_lock); /* * client_data needs to be alloc because we don't want our mark to be * destroyed if the user stores NULL in the client data. */ xa_init_flags(&device->client_data, XA_FLAGS_ALLOC); init_rwsem(&device->client_data_rwsem); xa_init_flags(&device->compat_devs, XA_FLAGS_ALLOC); mutex_init(&device->compat_devs_mutex); init_completion(&device->unreg_completion); INIT_WORK(&device->unregistration_work, ib_unregister_work); spin_lock_init(&device->cq_pools_lock); for (i = 0; i < ARRAY_SIZE(device->cq_pools); i++) INIT_LIST_HEAD(&device->cq_pools[i]); rwlock_init(&device->cache_lock); device->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_ALLOC_MW) | BIT_ULL(IB_USER_VERBS_CMD_ALLOC_PD) | BIT_ULL(IB_USER_VERBS_CMD_ATTACH_MCAST) | BIT_ULL(IB_USER_VERBS_CMD_CLOSE_XRCD) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_AH) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_CQ) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_QP) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_XSRQ) | BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_MW) | BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_PD) | BIT_ULL(IB_USER_VERBS_CMD_DEREG_MR) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_AH) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_CQ) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_QP) | BIT_ULL(IB_USER_VERBS_CMD_DESTROY_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_DETACH_MCAST) | BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT) | BIT_ULL(IB_USER_VERBS_CMD_MODIFY_QP) | BIT_ULL(IB_USER_VERBS_CMD_MODIFY_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_OPEN_QP) | BIT_ULL(IB_USER_VERBS_CMD_OPEN_XRCD) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_DEVICE) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_PORT) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_QP) | BIT_ULL(IB_USER_VERBS_CMD_QUERY_SRQ) | BIT_ULL(IB_USER_VERBS_CMD_REG_MR) | BIT_ULL(IB_USER_VERBS_CMD_REREG_MR) | BIT_ULL(IB_USER_VERBS_CMD_RESIZE_CQ); mutex_init(&device->subdev_lock); INIT_LIST_HEAD(&device->subdev_list_head); INIT_LIST_HEAD(&device->subdev_list); return device; } EXPORT_SYMBOL(_ib_alloc_device); /** * ib_dealloc_device - free an IB device struct * @device:structure to free * * Free a structure allocated with ib_alloc_device(). */ void ib_dealloc_device(struct ib_device *device) { if (device->ops.dealloc_driver) device->ops.dealloc_driver(device); /* * ib_unregister_driver() requires all devices to remain in the xarray * while their ops are callable. The last op we call is dealloc_driver * above. This is needed to create a fence on op callbacks prior to * allowing the driver module to unload. */ down_write(&devices_rwsem); if (xa_load(&devices, device->index) == device) xa_erase(&devices, device->index); up_write(&devices_rwsem); /* Expedite releasing netdev references */ free_netdevs(device); WARN_ON(!xa_empty(&device->compat_devs)); WARN_ON(!xa_empty(&device->client_data)); WARN_ON(refcount_read(&device->refcount)); rdma_restrack_clean(device); /* Balances with device_initialize */ put_device(&device->dev); } EXPORT_SYMBOL(ib_dealloc_device); /* * add_client_context() and remove_client_context() must be safe against * parallel calls on the same device - registration/unregistration of both the * device and client can be occurring in parallel. * * The routines need to be a fence, any caller must not return until the add * or remove is fully completed. */ static int add_client_context(struct ib_device *device, struct ib_client *client) { int ret = 0; if (!device->kverbs_provider && !client->no_kverbs_req) return 0; down_write(&device->client_data_rwsem); /* * So long as the client is registered hold both the client and device * unregistration locks. */ if (!refcount_inc_not_zero(&client->uses)) goto out_unlock; refcount_inc(&device->refcount); /* * Another caller to add_client_context got here first and has already * completely initialized context. */ if (xa_get_mark(&device->client_data, client->client_id, CLIENT_DATA_REGISTERED)) goto out; ret = xa_err(xa_store(&device->client_data, client->client_id, NULL, GFP_KERNEL)); if (ret) goto out; downgrade_write(&device->client_data_rwsem); if (client->add) { if (client->add(device)) { /* * If a client fails to add then the error code is * ignored, but we won't call any more ops on this * client. */ xa_erase(&device->client_data, client->client_id); up_read(&device->client_data_rwsem); ib_device_put(device); ib_client_put(client); return 0; } } /* Readers shall not see a client until add has been completed */ xa_set_mark(&device->client_data, client->client_id, CLIENT_DATA_REGISTERED); up_read(&device->client_data_rwsem); return 0; out: ib_device_put(device); ib_client_put(client); out_unlock: up_write(&device->client_data_rwsem); return ret; } static void remove_client_context(struct ib_device *device, unsigned int client_id) { struct ib_client *client; void *client_data; down_write(&device->client_data_rwsem); if (!xa_get_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED)) { up_write(&device->client_data_rwsem); return; } client_data = xa_load(&device->client_data, client_id); xa_clear_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED); client = xa_load(&clients, client_id); up_write(&device->client_data_rwsem); /* * Notice we cannot be holding any exclusive locks when calling the * remove callback as the remove callback can recurse back into any * public functions in this module and thus try for any locks those * functions take. * * For this reason clients and drivers should not call the * unregistration functions will holdling any locks. */ if (client->remove) client->remove(device, client_data); xa_erase(&device->client_data, client_id); ib_device_put(device); ib_client_put(client); } static int alloc_port_data(struct ib_device *device) { struct ib_port_data_rcu *pdata_rcu; u32 port; if (device->port_data) return 0; /* This can only be called once the physical port range is defined */ if (WARN_ON(!device->phys_port_cnt)) return -EINVAL; /* Reserve U32_MAX so the logic to go over all the ports is sane */ if (WARN_ON(device->phys_port_cnt == U32_MAX)) return -EINVAL; /* * device->port_data is indexed directly by the port number to make * access to this data as efficient as possible. * * Therefore port_data is declared as a 1 based array with potential * empty slots at the beginning. */ pdata_rcu = kzalloc(struct_size(pdata_rcu, pdata, size_add(rdma_end_port(device), 1)), GFP_KERNEL); if (!pdata_rcu) return -ENOMEM; /* * The rcu_head is put in front of the port data array and the stored * pointer is adjusted since we never need to see that member until * kfree_rcu. */ device->port_data = pdata_rcu->pdata; rdma_for_each_port (device, port) { struct ib_port_data *pdata = &device->port_data[port]; pdata->ib_dev = device; spin_lock_init(&pdata->pkey_list_lock); INIT_LIST_HEAD(&pdata->pkey_list); spin_lock_init(&pdata->netdev_lock); INIT_HLIST_NODE(&pdata->ndev_hash_link); } return 0; } static int verify_immutable(const struct ib_device *dev, u32 port) { return WARN_ON(!rdma_cap_ib_mad(dev, port) && rdma_max_mad_size(dev, port) != 0); } static int setup_port_data(struct ib_device *device) { u32 port; int ret; ret = alloc_port_data(device); if (ret) return ret; rdma_for_each_port (device, port) { struct ib_port_data *pdata = &device->port_data[port]; ret = device->ops.get_port_immutable(device, port, &pdata->immutable); if (ret) return ret; if (verify_immutable(device, port)) return -EINVAL; } return 0; } /** * ib_port_immutable_read() - Read rdma port's immutable data * @dev: IB device * @port: port number whose immutable data to read. It starts with index 1 and * valid upto including rdma_end_port(). */ const struct ib_port_immutable* ib_port_immutable_read(struct ib_device *dev, unsigned int port) { WARN_ON(!rdma_is_port_valid(dev, port)); return &dev->port_data[port].immutable; } EXPORT_SYMBOL(ib_port_immutable_read); void ib_get_device_fw_str(struct ib_device *dev, char *str) { if (dev->ops.get_dev_fw_str) dev->ops.get_dev_fw_str(dev, str); else str[0] = '\0'; } EXPORT_SYMBOL(ib_get_device_fw_str); static void ib_policy_change_task(struct work_struct *work) { struct ib_device *dev; unsigned long index; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { unsigned int i; rdma_for_each_port (dev, i) { u64 sp; ib_get_cached_subnet_prefix(dev, i, &sp); ib_security_cache_change(dev, i, sp); } } up_read(&devices_rwsem); } static int ib_security_change(struct notifier_block *nb, unsigned long event, void *lsm_data) { if (event != LSM_POLICY_CHANGE) return NOTIFY_DONE; schedule_work(&ib_policy_change_work); ib_mad_agent_security_change(); return NOTIFY_OK; } static void compatdev_release(struct device *dev) { struct ib_core_device *cdev = container_of(dev, struct ib_core_device, dev); kfree(cdev); } static int add_one_compat_dev(struct ib_device *device, struct rdma_dev_net *rnet) { struct ib_core_device *cdev; int ret; lockdep_assert_held(&rdma_nets_rwsem); if (!ib_devices_shared_netns) return 0; /* * Create and add compat device in all namespaces other than where it * is currently bound to. */ if (net_eq(read_pnet(&rnet->net), read_pnet(&device->coredev.rdma_net))) return 0; /* * The first of init_net() or ib_register_device() to take the * compat_devs_mutex wins and gets to add the device. Others will wait * for completion here. */ mutex_lock(&device->compat_devs_mutex); cdev = xa_load(&device->compat_devs, rnet->id); if (cdev) { ret = 0; goto done; } ret = xa_reserve(&device->compat_devs, rnet->id, GFP_KERNEL); if (ret) goto done; cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) { ret = -ENOMEM; goto cdev_err; } cdev->dev.parent = device->dev.parent; rdma_init_coredev(cdev, device, read_pnet(&rnet->net)); cdev->dev.release = compatdev_release; ret = dev_set_name(&cdev->dev, "%s", dev_name(&device->dev)); if (ret) goto add_err; ret = device_add(&cdev->dev); if (ret) goto add_err; ret = ib_setup_port_attrs(cdev); if (ret) goto port_err; ret = xa_err(xa_store(&device->compat_devs, rnet->id, cdev, GFP_KERNEL)); if (ret) goto insert_err; mutex_unlock(&device->compat_devs_mutex); return 0; insert_err: ib_free_port_attrs(cdev); port_err: device_del(&cdev->dev); add_err: put_device(&cdev->dev); cdev_err: xa_release(&device->compat_devs, rnet->id); done: mutex_unlock(&device->compat_devs_mutex); return ret; } static void remove_one_compat_dev(struct ib_device *device, u32 id) { struct ib_core_device *cdev; mutex_lock(&device->compat_devs_mutex); cdev = xa_erase(&device->compat_devs, id); mutex_unlock(&device->compat_devs_mutex); if (cdev) { ib_free_port_attrs(cdev); device_del(&cdev->dev); put_device(&cdev->dev); } } static void remove_compat_devs(struct ib_device *device) { struct ib_core_device *cdev; unsigned long index; xa_for_each (&device->compat_devs, index, cdev) remove_one_compat_dev(device, index); } static int add_compat_devs(struct ib_device *device) { struct rdma_dev_net *rnet; unsigned long index; int ret = 0; lockdep_assert_held(&devices_rwsem); down_read(&rdma_nets_rwsem); xa_for_each (&rdma_nets, index, rnet) { ret = add_one_compat_dev(device, rnet); if (ret) break; } up_read(&rdma_nets_rwsem); return ret; } static void remove_all_compat_devs(void) { struct ib_compat_device *cdev; struct ib_device *dev; unsigned long index; down_read(&devices_rwsem); xa_for_each (&devices, index, dev) { unsigned long c_index = 0; /* Hold nets_rwsem so that any other thread modifying this * system param can sync with this thread. */ down_read(&rdma_nets_rwsem); xa_for_each (&dev->compat_devs, c_index, cdev) remove_one_compat_dev(dev, c_index); up_read(&rdma_nets_rwsem); } up_read(&devices_rwsem); } static int add_all_compat_devs(void) { struct rdma_dev_net *rnet; struct ib_device *dev; unsigned long index; int ret = 0; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { unsigned long net_index = 0; /* Hold nets_rwsem so that any other thread modifying this * system param can sync with this thread. */ down_read(&rdma_nets_rwsem); xa_for_each (&rdma_nets, net_index, rnet) { ret = add_one_compat_dev(dev, rnet); if (ret) break; } up_read(&rdma_nets_rwsem); } up_read(&devices_rwsem); if (ret) remove_all_compat_devs(); return ret; } int rdma_compatdev_set(u8 enable) { struct rdma_dev_net *rnet; unsigned long index; int ret = 0; down_write(&rdma_nets_rwsem); if (ib_devices_shared_netns == enable) { up_write(&rdma_nets_rwsem); return 0; } /* enable/disable of compat devices is not supported * when more than default init_net exists. */ xa_for_each (&rdma_nets, index, rnet) { ret++; break; } if (!ret) ib_devices_shared_netns = enable; up_write(&rdma_nets_rwsem); if (ret) return -EBUSY; if (enable) ret = add_all_compat_devs(); else remove_all_compat_devs(); return ret; } static void rdma_dev_exit_net(struct net *net) { struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); struct ib_device *dev; unsigned long index; int ret; down_write(&rdma_nets_rwsem); /* * Prevent the ID from being re-used and hide the id from xa_for_each. */ ret = xa_err(xa_store(&rdma_nets, rnet->id, NULL, GFP_KERNEL)); WARN_ON(ret); up_write(&rdma_nets_rwsem); down_read(&devices_rwsem); xa_for_each (&devices, index, dev) { get_device(&dev->dev); /* * Release the devices_rwsem so that pontentially blocking * device_del, doesn't hold the devices_rwsem for too long. */ up_read(&devices_rwsem); remove_one_compat_dev(dev, rnet->id); /* * If the real device is in the NS then move it back to init. */ rdma_dev_change_netns(dev, net, &init_net); put_device(&dev->dev); down_read(&devices_rwsem); } up_read(&devices_rwsem); rdma_nl_net_exit(rnet); xa_erase(&rdma_nets, rnet->id); } static __net_init int rdma_dev_init_net(struct net *net) { struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); unsigned long index; struct ib_device *dev; int ret; write_pnet(&rnet->net, net); ret = rdma_nl_net_init(rnet); if (ret) return ret; /* No need to create any compat devices in default init_net. */ if (net_eq(net, &init_net)) return 0; ret = xa_alloc(&rdma_nets, &rnet->id, rnet, xa_limit_32b, GFP_KERNEL); if (ret) { rdma_nl_net_exit(rnet); return ret; } down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { /* Hold nets_rwsem so that netlink command cannot change * system configuration for device sharing mode. */ down_read(&rdma_nets_rwsem); ret = add_one_compat_dev(dev, rnet); up_read(&rdma_nets_rwsem); if (ret) break; } up_read(&devices_rwsem); if (ret) rdma_dev_exit_net(net); return ret; } /* * Assign the unique string device name and the unique device index. This is * undone by ib_dealloc_device. */ static int assign_name(struct ib_device *device, const char *name) { static u32 last_id; int ret; down_write(&devices_rwsem); /* Assign a unique name to the device */ if (strchr(name, '%')) ret = alloc_name(device, name); else ret = dev_set_name(&device->dev, name); if (ret) goto out; if (__ib_device_get_by_name(dev_name(&device->dev))) { ret = -ENFILE; goto out; } strscpy(device->name, dev_name(&device->dev), IB_DEVICE_NAME_MAX); ret = xa_alloc_cyclic(&devices, &device->index, device, xa_limit_31b, &last_id, GFP_KERNEL); if (ret > 0) ret = 0; out: up_write(&devices_rwsem); return ret; } /* * setup_device() allocates memory and sets up data that requires calling the * device ops, this is the only reason these actions are not done during * ib_alloc_device. It is undone by ib_dealloc_device(). */ static int setup_device(struct ib_device *device) { struct ib_udata uhw = {.outlen = 0, .inlen = 0}; int ret; ib_device_check_mandatory(device); ret = setup_port_data(device); if (ret) { dev_warn(&device->dev, "Couldn't create per-port data\n"); return ret; } memset(&device->attrs, 0, sizeof(device->attrs)); ret = device->ops.query_device(device, &device->attrs, &uhw); if (ret) { dev_warn(&device->dev, "Couldn't query the device attributes\n"); return ret; } return 0; } static void disable_device(struct ib_device *device) { u32 cid; WARN_ON(!refcount_read(&device->refcount)); down_write(&devices_rwsem); xa_clear_mark(&devices, device->index, DEVICE_REGISTERED); up_write(&devices_rwsem); /* * Remove clients in LIFO order, see assign_client_id. This could be * more efficient if xarray learns to reverse iterate. Since no new * clients can be added to this ib_device past this point we only need * the maximum possible client_id value here. */ down_read(&clients_rwsem); cid = highest_client_id; up_read(&clients_rwsem); while (cid) { cid--; remove_client_context(device, cid); } ib_cq_pool_cleanup(device); /* Pairs with refcount_set in enable_device */ ib_device_put(device); wait_for_completion(&device->unreg_completion); /* * compat devices must be removed after device refcount drops to zero. * Otherwise init_net() may add more compatdevs after removing compat * devices and before device is disabled. */ remove_compat_devs(device); } /* * An enabled device is visible to all clients and to all the public facing * APIs that return a device pointer. This always returns with a new get, even * if it fails. */ static int enable_device_and_get(struct ib_device *device) { struct ib_client *client; unsigned long index; int ret = 0; /* * One ref belongs to the xa and the other belongs to this * thread. This is needed to guard against parallel unregistration. */ refcount_set(&device->refcount, 2); down_write(&devices_rwsem); xa_set_mark(&devices, device->index, DEVICE_REGISTERED); /* * By using downgrade_write() we ensure that no other thread can clear * DEVICE_REGISTERED while we are completing the client setup. */ downgrade_write(&devices_rwsem); if (device->ops.enable_driver) { ret = device->ops.enable_driver(device); if (ret) goto out; } down_read(&clients_rwsem); xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) { ret = add_client_context(device, client); if (ret) break; } up_read(&clients_rwsem); if (!ret) ret = add_compat_devs(device); out: up_read(&devices_rwsem); return ret; } static void prevent_dealloc_device(struct ib_device *ib_dev) { } static void ib_device_notify_register(struct ib_device *device) { struct net_device *netdev; u32 port; int ret; ret = rdma_nl_notify_event(device, 0, RDMA_REGISTER_EVENT); if (ret) return; rdma_for_each_port(device, port) { netdev = ib_device_get_netdev(device, port); if (!netdev) continue; ret = rdma_nl_notify_event(device, port, RDMA_NETDEV_ATTACH_EVENT); dev_put(netdev); if (ret) return; } } /** * ib_register_device - Register an IB device with IB core * @device: Device to register * @name: unique string device name. This may include a '%' which will * cause a unique index to be added to the passed device name. * @dma_device: pointer to a DMA-capable device. If %NULL, then the IB * device will be used. In this case the caller should fully * setup the ibdev for DMA. This usually means using dma_virt_ops. * * Low-level drivers use ib_register_device() to register their * devices with the IB core. All registered clients will receive a * callback for each device that is added. @device must be allocated * with ib_alloc_device(). * * If the driver uses ops.dealloc_driver and calls any ib_unregister_device() * asynchronously then the device pointer may become freed as soon as this * function returns. */ int ib_register_device(struct ib_device *device, const char *name, struct device *dma_device) { int ret; ret = assign_name(device, name); if (ret) return ret; /* * If the caller does not provide a DMA capable device then the IB core * will set up ib_sge and scatterlist structures that stash the kernel * virtual address into the address field. */ WARN_ON(dma_device && !dma_device->dma_parms); device->dma_device = dma_device; ret = setup_device(device); if (ret) return ret; ret = ib_cache_setup_one(device); if (ret) { dev_warn(&device->dev, "Couldn't set up InfiniBand P_Key/GID cache\n"); return ret; } device->groups[0] = &ib_dev_attr_group; device->groups[1] = device->ops.device_group; ret = ib_setup_device_attrs(device); if (ret) goto cache_cleanup; ib_device_register_rdmacg(device); rdma_counter_init(device); /* * Ensure that ADD uevent is not fired because it * is too early amd device is not initialized yet. */ dev_set_uevent_suppress(&device->dev, true); ret = device_add(&device->dev); if (ret) goto cg_cleanup; ret = ib_setup_port_attrs(&device->coredev); if (ret) { dev_warn(&device->dev, "Couldn't register device with driver model\n"); goto dev_cleanup; } ret = enable_device_and_get(device); if (ret) { void (*dealloc_fn)(struct ib_device *); /* * If we hit this error flow then we don't want to * automatically dealloc the device since the caller is * expected to call ib_dealloc_device() after * ib_register_device() fails. This is tricky due to the * possibility for a parallel unregistration along with this * error flow. Since we have a refcount here we know any * parallel flow is stopped in disable_device and will see the * special dealloc_driver pointer, causing the responsibility to * ib_dealloc_device() to revert back to this thread. */ dealloc_fn = device->ops.dealloc_driver; device->ops.dealloc_driver = prevent_dealloc_device; ib_device_put(device); __ib_unregister_device(device); device->ops.dealloc_driver = dealloc_fn; dev_set_uevent_suppress(&device->dev, false); return ret; } dev_set_uevent_suppress(&device->dev, false); /* Mark for userspace that device is ready */ kobject_uevent(&device->dev.kobj, KOBJ_ADD); ib_device_notify_register(device); ib_device_put(device); return 0; dev_cleanup: device_del(&device->dev); cg_cleanup: dev_set_uevent_suppress(&device->dev, false); ib_device_unregister_rdmacg(device); cache_cleanup: ib_cache_cleanup_one(device); return ret; } EXPORT_SYMBOL(ib_register_device); /* Callers must hold a get on the device. */ static void __ib_unregister_device(struct ib_device *ib_dev) { struct ib_device *sub, *tmp; mutex_lock(&ib_dev->subdev_lock); list_for_each_entry_safe_reverse(sub, tmp, &ib_dev->subdev_list_head, subdev_list) { list_del(&sub->subdev_list); ib_dev->ops.del_sub_dev(sub); ib_device_put(ib_dev); } mutex_unlock(&ib_dev->subdev_lock); /* * We have a registration lock so that all the calls to unregister are * fully fenced, once any unregister returns the device is truely * unregistered even if multiple callers are unregistering it at the * same time. This also interacts with the registration flow and * provides sane semantics if register and unregister are racing. */ mutex_lock(&ib_dev->unregistration_lock); if (!refcount_read(&ib_dev->refcount)) goto out; disable_device(ib_dev); rdma_nl_notify_event(ib_dev, 0, RDMA_UNREGISTER_EVENT); /* Expedite removing unregistered pointers from the hash table */ free_netdevs(ib_dev); ib_free_port_attrs(&ib_dev->coredev); device_del(&ib_dev->dev); ib_device_unregister_rdmacg(ib_dev); ib_cache_cleanup_one(ib_dev); /* * Drivers using the new flow may not call ib_dealloc_device except * in error unwind prior to registration success. */ if (ib_dev->ops.dealloc_driver && ib_dev->ops.dealloc_driver != prevent_dealloc_device) { WARN_ON(kref_read(&ib_dev->dev.kobj.kref) <= 1); ib_dealloc_device(ib_dev); } out: mutex_unlock(&ib_dev->unregistration_lock); } /** * ib_unregister_device - Unregister an IB device * @ib_dev: The device to unregister * * Unregister an IB device. All clients will receive a remove callback. * * Callers should call this routine only once, and protect against races with * registration. Typically it should only be called as part of a remove * callback in an implementation of driver core's struct device_driver and * related. * * If ops.dealloc_driver is used then ib_dev will be freed upon return from * this function. */ void ib_unregister_device(struct ib_device *ib_dev) { get_device(&ib_dev->dev); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); } EXPORT_SYMBOL(ib_unregister_device); /** * ib_unregister_device_and_put - Unregister a device while holding a 'get' * @ib_dev: The device to unregister * * This is the same as ib_unregister_device(), except it includes an internal * ib_device_put() that should match a 'get' obtained by the caller. * * It is safe to call this routine concurrently from multiple threads while * holding the 'get'. When the function returns the device is fully * unregistered. * * Drivers using this flow MUST use the driver_unregister callback to clean up * their resources associated with the device and dealloc it. */ void ib_unregister_device_and_put(struct ib_device *ib_dev) { WARN_ON(!ib_dev->ops.dealloc_driver); get_device(&ib_dev->dev); ib_device_put(ib_dev); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); } EXPORT_SYMBOL(ib_unregister_device_and_put); /** * ib_unregister_driver - Unregister all IB devices for a driver * @driver_id: The driver to unregister * * This implements a fence for device unregistration. It only returns once all * devices associated with the driver_id have fully completed their * unregistration and returned from ib_unregister_device*(). * * If device's are not yet unregistered it goes ahead and starts unregistering * them. * * This does not block creation of new devices with the given driver_id, that * is the responsibility of the caller. */ void ib_unregister_driver(enum rdma_driver_id driver_id) { struct ib_device *ib_dev; unsigned long index; down_read(&devices_rwsem); xa_for_each (&devices, index, ib_dev) { if (ib_dev->ops.driver_id != driver_id) continue; get_device(&ib_dev->dev); up_read(&devices_rwsem); WARN_ON(!ib_dev->ops.dealloc_driver); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); down_read(&devices_rwsem); } up_read(&devices_rwsem); } EXPORT_SYMBOL(ib_unregister_driver); static void ib_unregister_work(struct work_struct *work) { struct ib_device *ib_dev = container_of(work, struct ib_device, unregistration_work); __ib_unregister_device(ib_dev); put_device(&ib_dev->dev); } /** * ib_unregister_device_queued - Unregister a device using a work queue * @ib_dev: The device to unregister * * This schedules an asynchronous unregistration using a WQ for the device. A * driver should use this to avoid holding locks while doing unregistration, * such as holding the RTNL lock. * * Drivers using this API must use ib_unregister_driver before module unload * to ensure that all scheduled unregistrations have completed. */ void ib_unregister_device_queued(struct ib_device *ib_dev) { WARN_ON(!refcount_read(&ib_dev->refcount)); WARN_ON(!ib_dev->ops.dealloc_driver); get_device(&ib_dev->dev); if (!queue_work(ib_unreg_wq, &ib_dev->unregistration_work)) put_device(&ib_dev->dev); } EXPORT_SYMBOL(ib_unregister_device_queued); /* * The caller must pass in a device that has the kref held and the refcount * released. If the device is in cur_net and still registered then it is moved * into net. */ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net, struct net *net) { int ret2 = -EINVAL; int ret; mutex_lock(&device->unregistration_lock); /* * If a device not under ib_device_get() or if the unregistration_lock * is not held, the namespace can be changed, or it can be unregistered. * Check again under the lock. */ if (refcount_read(&device->refcount) == 0 || !net_eq(cur_net, read_pnet(&device->coredev.rdma_net))) { ret = -ENODEV; goto out; } kobject_uevent(&device->dev.kobj, KOBJ_REMOVE); disable_device(device); /* * At this point no one can be using the device, so it is safe to * change the namespace. */ write_pnet(&device->coredev.rdma_net, net); down_read(&devices_rwsem); /* * Currently rdma devices are system wide unique. So the device name * is guaranteed free in the new namespace. Publish the new namespace * at the sysfs level. */ ret = device_rename(&device->dev, dev_name(&device->dev)); up_read(&devices_rwsem); if (ret) { dev_warn(&device->dev, "%s: Couldn't rename device after namespace change\n", __func__); /* Try and put things back and re-enable the device */ write_pnet(&device->coredev.rdma_net, cur_net); } ret2 = enable_device_and_get(device); if (ret2) { /* * This shouldn't really happen, but if it does, let the user * retry at later point. So don't disable the device. */ dev_warn(&device->dev, "%s: Couldn't re-enable device after namespace change\n", __func__); } kobject_uevent(&device->dev.kobj, KOBJ_ADD); ib_device_put(device); out: mutex_unlock(&device->unregistration_lock); if (ret) return ret; return ret2; } int ib_device_set_netns_put(struct sk_buff *skb, struct ib_device *dev, u32 ns_fd) { struct net *net; int ret; net = get_net_ns_by_fd(ns_fd); if (IS_ERR(net)) { ret = PTR_ERR(net); goto net_err; } if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; goto ns_err; } /* * All the ib_clients, including uverbs, are reset when the namespace is * changed and this cannot be blocked waiting for userspace to do * something, so disassociation is mandatory. */ if (!dev->ops.disassociate_ucontext || ib_devices_shared_netns) { ret = -EOPNOTSUPP; goto ns_err; } get_device(&dev->dev); ib_device_put(dev); ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net); put_device(&dev->dev); put_net(net); return ret; ns_err: put_net(net); net_err: ib_device_put(dev); return ret; } static struct pernet_operations rdma_dev_net_ops = { .init = rdma_dev_init_net, .exit = rdma_dev_exit_net, .id = &rdma_dev_net_id, .size = sizeof(struct rdma_dev_net), }; static int assign_client_id(struct ib_client *client) { int ret; lockdep_assert_held(&clients_rwsem); /* * The add/remove callbacks must be called in FIFO/LIFO order. To * achieve this we assign client_ids so they are sorted in * registration order. */ client->client_id = highest_client_id; ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL); if (ret) return ret; highest_client_id++; xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED); return 0; } static void remove_client_id(struct ib_client *client) { down_write(&clients_rwsem); xa_erase(&clients, client->client_id); for (; highest_client_id; highest_client_id--) if (xa_load(&clients, highest_client_id - 1)) break; up_write(&clients_rwsem); } /** * ib_register_client - Register an IB client * @client:Client to register * * Upper level users of the IB drivers can use ib_register_client() to * register callbacks for IB device addition and removal. When an IB * device is added, each registered client's add method will be called * (in the order the clients were registered), and when a device is * removed, each client's remove method will be called (in the reverse * order that clients were registered). In addition, when * ib_register_client() is called, the client will receive an add * callback for all devices already registered. */ int ib_register_client(struct ib_client *client) { struct ib_device *device; unsigned long index; bool need_unreg = false; int ret; refcount_set(&client->uses, 1); init_completion(&client->uses_zero); /* * The devices_rwsem is held in write mode to ensure that a racing * ib_register_device() sees a consisent view of clients and devices. */ down_write(&devices_rwsem); down_write(&clients_rwsem); ret = assign_client_id(client); if (ret) goto out; need_unreg = true; xa_for_each_marked (&devices, index, device, DEVICE_REGISTERED) { ret = add_client_context(device, client); if (ret) goto out; } ret = 0; out: up_write(&clients_rwsem); up_write(&devices_rwsem); if (need_unreg && ret) ib_unregister_client(client); return ret; } EXPORT_SYMBOL(ib_register_client); /** * ib_unregister_client - Unregister an IB client * @client:Client to unregister * * Upper level users use ib_unregister_client() to remove their client * registration. When ib_unregister_client() is called, the client * will receive a remove callback for each IB device still registered. * * This is a full fence, once it returns no client callbacks will be called, * or are running in another thread. */ void ib_unregister_client(struct ib_client *client) { struct ib_device *device; unsigned long index; down_write(&clients_rwsem); ib_client_put(client); xa_clear_mark(&clients, client->client_id, CLIENT_REGISTERED); up_write(&clients_rwsem); /* We do not want to have locks while calling client->remove() */ rcu_read_lock(); xa_for_each (&devices, index, device) { if (!ib_device_try_get(device)) continue; rcu_read_unlock(); remove_client_context(device, client->client_id); ib_device_put(device); rcu_read_lock(); } rcu_read_unlock(); /* * remove_client_context() is not a fence, it can return even though a * removal is ongoing. Wait until all removals are completed. */ wait_for_completion(&client->uses_zero); remove_client_id(client); } EXPORT_SYMBOL(ib_unregister_client); static int __ib_get_global_client_nl_info(const char *client_name, struct ib_client_nl_info *res) { struct ib_client *client; unsigned long index; int ret = -ENOENT; down_read(&clients_rwsem); xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) { if (strcmp(client->name, client_name) != 0) continue; if (!client->get_global_nl_info) { ret = -EOPNOTSUPP; break; } ret = client->get_global_nl_info(res); if (WARN_ON(ret == -ENOENT)) ret = -EINVAL; if (!ret && res->cdev) get_device(res->cdev); break; } up_read(&clients_rwsem); return ret; } static int __ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name, struct ib_client_nl_info *res) { unsigned long index; void *client_data; int ret = -ENOENT; down_read(&ibdev->client_data_rwsem); xan_for_each_marked (&ibdev->client_data, index, client_data, CLIENT_DATA_REGISTERED) { struct ib_client *client = xa_load(&clients, index); if (!client || strcmp(client->name, client_name) != 0) continue; if (!client->get_nl_info) { ret = -EOPNOTSUPP; break; } ret = client->get_nl_info(ibdev, client_data, res); if (WARN_ON(ret == -ENOENT)) ret = -EINVAL; /* * The cdev is guaranteed valid as long as we are inside the * client_data_rwsem as remove_one can't be called. Keep it * valid for the caller. */ if (!ret && res->cdev) get_device(res->cdev); break; } up_read(&ibdev->client_data_rwsem); return ret; } /** * ib_get_client_nl_info - Fetch the nl_info from a client * @ibdev: IB device * @client_name: Name of the client * @res: Result of the query */ int ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name, struct ib_client_nl_info *res) { int ret; if (ibdev) ret = __ib_get_client_nl_info(ibdev, client_name, res); else ret = __ib_get_global_client_nl_info(client_name, res); #ifdef CONFIG_MODULES if (ret == -ENOENT) { request_module("rdma-client-%s", client_name); if (ibdev) ret = __ib_get_client_nl_info(ibdev, client_name, res); else ret = __ib_get_global_client_nl_info(client_name, res); } #endif if (ret) { if (ret == -ENOENT) return -EOPNOTSUPP; return ret; } if (WARN_ON(!res->cdev)) return -EINVAL; return 0; } /** * ib_set_client_data - Set IB client context * @device:Device to set context for * @client:Client to set context for * @data:Context to set * * ib_set_client_data() sets client context data that can be retrieved with * ib_get_client_data(). This can only be called while the client is * registered to the device, once the ib_client remove() callback returns this * cannot be called. */ void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data) { void *rc; if (WARN_ON(IS_ERR(data))) data = NULL; rc = xa_store(&device->client_data, client->client_id, data, GFP_KERNEL); WARN_ON(xa_is_err(rc)); } EXPORT_SYMBOL(ib_set_client_data); /** * ib_register_event_handler - Register an IB event handler * @event_handler:Handler to register * * ib_register_event_handler() registers an event handler that will be * called back when asynchronous IB events occur (as defined in * chapter 11 of the InfiniBand Architecture Specification). This * callback occurs in workqueue context. */ void ib_register_event_handler(struct ib_event_handler *event_handler) { down_write(&event_handler->device->event_handler_rwsem); list_add_tail(&event_handler->list, &event_handler->device->event_handler_list); up_write(&event_handler->device->event_handler_rwsem); } EXPORT_SYMBOL(ib_register_event_handler); /** * ib_unregister_event_handler - Unregister an event handler * @event_handler:Handler to unregister * * Unregister an event handler registered with * ib_register_event_handler(). */ void ib_unregister_event_handler(struct ib_event_handler *event_handler) { down_write(&event_handler->device->event_handler_rwsem); list_del(&event_handler->list); up_write(&event_handler->device->event_handler_rwsem); } EXPORT_SYMBOL(ib_unregister_event_handler); void ib_dispatch_event_clients(struct ib_event *event) { struct ib_event_handler *handler; down_read(&event->device->event_handler_rwsem); list_for_each_entry(handler, &event->device->event_handler_list, list) handler->handler(handler, event); up_read(&event->device->event_handler_rwsem); } static int iw_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { struct in_device *inetdev; struct net_device *netdev; memset(port_attr, 0, sizeof(*port_attr)); netdev = ib_device_get_netdev(device, port_num); if (!netdev) return -ENODEV; port_attr->max_mtu = IB_MTU_4096; port_attr->active_mtu = ib_mtu_int_to_enum(netdev->mtu); if (!netif_carrier_ok(netdev)) { port_attr->state = IB_PORT_DOWN; port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; } else { rcu_read_lock(); inetdev = __in_dev_get_rcu(netdev); if (inetdev && inetdev->ifa_list) { port_attr->state = IB_PORT_ACTIVE; port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; } else { port_attr->state = IB_PORT_INIT; port_attr->phys_state = IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING; } rcu_read_unlock(); } dev_put(netdev); return device->ops.query_port(device, port_num, port_attr); } static int __ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { int err; memset(port_attr, 0, sizeof(*port_attr)); err = device->ops.query_port(device, port_num, port_attr); if (err || port_attr->subnet_prefix) return err; if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND) return 0; ib_get_cached_subnet_prefix(device, port_num, &port_attr->subnet_prefix); return 0; } /** * ib_query_port - Query IB port attributes * @device:Device to query * @port_num:Port number to query * @port_attr:Port attributes * * ib_query_port() returns the attributes of a port through the * @port_attr pointer. */ int ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr) { if (!rdma_is_port_valid(device, port_num)) return -EINVAL; if (rdma_protocol_iwarp(device, port_num)) return iw_query_port(device, port_num, port_attr); else return __ib_query_port(device, port_num, port_attr); } EXPORT_SYMBOL(ib_query_port); static void add_ndev_hash(struct ib_port_data *pdata) { unsigned long flags; might_sleep(); spin_lock_irqsave(&ndev_hash_lock, flags); if (hash_hashed(&pdata->ndev_hash_link)) { hash_del_rcu(&pdata->ndev_hash_link); spin_unlock_irqrestore(&ndev_hash_lock, flags); /* * We cannot do hash_add_rcu after a hash_del_rcu until the * grace period */ synchronize_rcu(); spin_lock_irqsave(&ndev_hash_lock, flags); } if (pdata->netdev) hash_add_rcu(ndev_hash, &pdata->ndev_hash_link, (uintptr_t)pdata->netdev); spin_unlock_irqrestore(&ndev_hash_lock, flags); } /** * ib_device_set_netdev - Associate the ib_dev with an underlying net_device * @ib_dev: Device to modify * @ndev: net_device to affiliate, may be NULL * @port: IB port the net_device is connected to * * Drivers should use this to link the ib_device to a netdev so the netdev * shows up in interfaces like ib_enum_roce_netdev. Only one netdev may be * affiliated with any port. * * The caller must ensure that the given ndev is not unregistered or * unregistering, and that either the ib_device is unregistered or * ib_device_set_netdev() is called with NULL when the ndev sends a * NETDEV_UNREGISTER event. */ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, u32 port) { enum rdma_nl_notify_event_type etype; struct net_device *old_ndev; struct ib_port_data *pdata; unsigned long flags; int ret; if (!rdma_is_port_valid(ib_dev, port)) return -EINVAL; /* * Drivers wish to call this before ib_register_driver, so we have to * setup the port data early. */ ret = alloc_port_data(ib_dev); if (ret) return ret; pdata = &ib_dev->port_data[port]; spin_lock_irqsave(&pdata->netdev_lock, flags); old_ndev = rcu_dereference_protected( pdata->netdev, lockdep_is_held(&pdata->netdev_lock)); if (old_ndev == ndev) { spin_unlock_irqrestore(&pdata->netdev_lock, flags); return 0; } rcu_assign_pointer(pdata->netdev, ndev); netdev_put(old_ndev, &pdata->netdev_tracker); netdev_hold(ndev, &pdata->netdev_tracker, GFP_ATOMIC); spin_unlock_irqrestore(&pdata->netdev_lock, flags); add_ndev_hash(pdata); /* Make sure that the device is registered before we send events */ if (xa_load(&devices, ib_dev->index) != ib_dev) return 0; etype = ndev ? RDMA_NETDEV_ATTACH_EVENT : RDMA_NETDEV_DETACH_EVENT; rdma_nl_notify_event(ib_dev, port, etype); return 0; } EXPORT_SYMBOL(ib_device_set_netdev); static void free_netdevs(struct ib_device *ib_dev) { unsigned long flags; u32 port; if (!ib_dev->port_data) return; rdma_for_each_port (ib_dev, port) { struct ib_port_data *pdata = &ib_dev->port_data[port]; struct net_device *ndev; spin_lock_irqsave(&pdata->netdev_lock, flags); ndev = rcu_dereference_protected( pdata->netdev, lockdep_is_held(&pdata->netdev_lock)); if (ndev) { spin_lock(&ndev_hash_lock); hash_del_rcu(&pdata->ndev_hash_link); spin_unlock(&ndev_hash_lock); /* * If this is the last dev_put there is still a * synchronize_rcu before the netdev is kfreed, so we * can continue to rely on unlocked pointer * comparisons after the put */ rcu_assign_pointer(pdata->netdev, NULL); netdev_put(ndev, &pdata->netdev_tracker); } spin_unlock_irqrestore(&pdata->netdev_lock, flags); } } struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port) { struct ib_port_data *pdata; struct net_device *res; if (!rdma_is_port_valid(ib_dev, port)) return NULL; if (!ib_dev->port_data) return NULL; pdata = &ib_dev->port_data[port]; /* * New drivers should use ib_device_set_netdev() not the legacy * get_netdev(). */ if (ib_dev->ops.get_netdev) res = ib_dev->ops.get_netdev(ib_dev, port); else { spin_lock(&pdata->netdev_lock); res = rcu_dereference_protected( pdata->netdev, lockdep_is_held(&pdata->netdev_lock)); dev_hold(res); spin_unlock(&pdata->netdev_lock); } return res; } EXPORT_SYMBOL(ib_device_get_netdev); /** * ib_device_get_by_netdev - Find an IB device associated with a netdev * @ndev: netdev to locate * @driver_id: The driver ID that must match (RDMA_DRIVER_UNKNOWN matches all) * * Find and hold an ib_device that is associated with a netdev via * ib_device_set_netdev(). The caller must call ib_device_put() on the * returned pointer. */ struct ib_device *ib_device_get_by_netdev(struct net_device *ndev, enum rdma_driver_id driver_id) { struct ib_device *res = NULL; struct ib_port_data *cur; rcu_read_lock(); hash_for_each_possible_rcu (ndev_hash, cur, ndev_hash_link, (uintptr_t)ndev) { if (rcu_access_pointer(cur->netdev) == ndev && (driver_id == RDMA_DRIVER_UNKNOWN || cur->ib_dev->ops.driver_id == driver_id) && ib_device_try_get(cur->ib_dev)) { res = cur->ib_dev; break; } } rcu_read_unlock(); return res; } EXPORT_SYMBOL(ib_device_get_by_netdev); /** * ib_enum_roce_netdev - enumerate all RoCE ports * @ib_dev : IB device we want to query * @filter: Should we call the callback? * @filter_cookie: Cookie passed to filter * @cb: Callback to call for each found RoCE ports * @cookie: Cookie passed back to the callback * * Enumerates all of the physical RoCE ports of ib_dev * which are related to netdevice and calls callback() on each * device for which filter() function returns non zero. */ void ib_enum_roce_netdev(struct ib_device *ib_dev, roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie) { u32 port; rdma_for_each_port (ib_dev, port) if (rdma_protocol_roce(ib_dev, port)) { struct net_device *idev = ib_device_get_netdev(ib_dev, port); if (filter(ib_dev, port, idev, filter_cookie)) cb(ib_dev, port, idev, cookie); dev_put(idev); } } /** * ib_enum_all_roce_netdevs - enumerate all RoCE devices * @filter: Should we call the callback? * @filter_cookie: Cookie passed to filter * @cb: Callback to call for each found RoCE ports * @cookie: Cookie passed back to the callback * * Enumerates all RoCE devices' physical ports which are related * to netdevices and calls callback() on each device for which * filter() function returns non zero. */ void ib_enum_all_roce_netdevs(roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie) { struct ib_device *dev; unsigned long index; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) ib_enum_roce_netdev(dev, filter, filter_cookie, cb, cookie); up_read(&devices_rwsem); } /* * ib_enum_all_devs - enumerate all ib_devices * @cb: Callback to call for each found ib_device * * Enumerates all ib_devices and calls callback() on each device. */ int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb, struct netlink_callback *cb) { unsigned long index; struct ib_device *dev; unsigned int idx = 0; int ret = 0; down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { if (!rdma_dev_access_netns(dev, sock_net(skb->sk))) continue; ret = nldev_cb(dev, skb, cb, idx); if (ret) break; idx++; } up_read(&devices_rwsem); return ret; } /** * ib_query_pkey - Get P_Key table entry * @device:Device to query * @port_num:Port number to query * @index:P_Key table index to query * @pkey:Returned P_Key * * ib_query_pkey() fetches the specified P_Key table entry. */ int ib_query_pkey(struct ib_device *device, u32 port_num, u16 index, u16 *pkey) { if (!rdma_is_port_valid(device, port_num)) return -EINVAL; if (!device->ops.query_pkey) return -EOPNOTSUPP; return device->ops.query_pkey(device, port_num, index, pkey); } EXPORT_SYMBOL(ib_query_pkey); /** * ib_modify_device - Change IB device attributes * @device:Device to modify * @device_modify_mask:Mask of attributes to change * @device_modify:New attribute values * * ib_modify_device() changes a device's attributes as specified by * the @device_modify_mask and @device_modify structure. */ int ib_modify_device(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify) { if (!device->ops.modify_device) return -EOPNOTSUPP; return device->ops.modify_device(device, device_modify_mask, device_modify); } EXPORT_SYMBOL(ib_modify_device); /** * ib_modify_port - Modifies the attributes for the specified port. * @device: The device to modify. * @port_num: The number of the port to modify. * @port_modify_mask: Mask used to specify which attributes of the port * to change. * @port_modify: New attribute values for the port. * * ib_modify_port() changes a port's attributes as specified by the * @port_modify_mask and @port_modify structure. */ int ib_modify_port(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify) { int rc; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; if (device->ops.modify_port) rc = device->ops.modify_port(device, port_num, port_modify_mask, port_modify); else if (rdma_protocol_roce(device, port_num) && ((port_modify->set_port_cap_mask & ~IB_PORT_CM_SUP) == 0 || (port_modify->clr_port_cap_mask & ~IB_PORT_CM_SUP) == 0)) rc = 0; else rc = -EOPNOTSUPP; return rc; } EXPORT_SYMBOL(ib_modify_port); /** * ib_find_gid - Returns the port number and GID table index where * a specified GID value occurs. Its searches only for IB link layer. * @device: The device to query. * @gid: The GID value to search for. * @port_num: The port number of the device where the GID value was found. * @index: The index into the GID table where the GID was found. This * parameter may be NULL. */ int ib_find_gid(struct ib_device *device, union ib_gid *gid, u32 *port_num, u16 *index) { union ib_gid tmp_gid; u32 port; int ret, i; rdma_for_each_port (device, port) { if (!rdma_protocol_ib(device, port)) continue; for (i = 0; i < device->port_data[port].immutable.gid_tbl_len; ++i) { ret = rdma_query_gid(device, port, i, &tmp_gid); if (ret) continue; if (!memcmp(&tmp_gid, gid, sizeof *gid)) { *port_num = port; if (index) *index = i; return 0; } } } return -ENOENT; } EXPORT_SYMBOL(ib_find_gid); /** * ib_find_pkey - Returns the PKey table index where a specified * PKey value occurs. * @device: The device to query. * @port_num: The port number of the device to search for the PKey. * @pkey: The PKey value to search for. * @index: The index into the PKey table where the PKey was found. */ int ib_find_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index) { int ret, i; u16 tmp_pkey; int partial_ix = -1; for (i = 0; i < device->port_data[port_num].immutable.pkey_tbl_len; ++i) { ret = ib_query_pkey(device, port_num, i, &tmp_pkey); if (ret) return ret; if ((pkey & 0x7fff) == (tmp_pkey & 0x7fff)) { /* if there is full-member pkey take it.*/ if (tmp_pkey & 0x8000) { *index = i; return 0; } if (partial_ix < 0) partial_ix = i; } } /*no full-member, if exists take the limited*/ if (partial_ix >= 0) { *index = partial_ix; return 0; } return -ENOENT; } EXPORT_SYMBOL(ib_find_pkey); /** * ib_get_net_dev_by_params() - Return the appropriate net_dev * for a received CM request * @dev: An RDMA device on which the request has been received. * @port: Port number on the RDMA device. * @pkey: The Pkey the request came on. * @gid: A GID that the net_dev uses to communicate. * @addr: Contains the IP address that the request specified as its * destination. * */ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr) { struct net_device *net_dev = NULL; unsigned long index; void *client_data; if (!rdma_protocol_ib(dev, port)) return NULL; /* * Holding the read side guarantees that the client will not become * unregistered while we are calling get_net_dev_by_params() */ down_read(&dev->client_data_rwsem); xan_for_each_marked (&dev->client_data, index, client_data, CLIENT_DATA_REGISTERED) { struct ib_client *client = xa_load(&clients, index); if (!client || !client->get_net_dev_by_params) continue; net_dev = client->get_net_dev_by_params(dev, port, pkey, gid, addr, client_data); if (net_dev) break; } up_read(&dev->client_data_rwsem); return net_dev; } EXPORT_SYMBOL(ib_get_net_dev_by_params); void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) { struct ib_device_ops *dev_ops = &dev->ops; #define SET_DEVICE_OP(ptr, name) \ do { \ if (ops->name) \ if (!((ptr)->name)) \ (ptr)->name = ops->name; \ } while (0) #define SET_OBJ_SIZE(ptr, name) SET_DEVICE_OP(ptr, size_##name) if (ops->driver_id != RDMA_DRIVER_UNKNOWN) { WARN_ON(dev_ops->driver_id != RDMA_DRIVER_UNKNOWN && dev_ops->driver_id != ops->driver_id); dev_ops->driver_id = ops->driver_id; } if (ops->owner) { WARN_ON(dev_ops->owner && dev_ops->owner != ops->owner); dev_ops->owner = ops->owner; } if (ops->uverbs_abi_ver) dev_ops->uverbs_abi_ver = ops->uverbs_abi_ver; dev_ops->uverbs_no_driver_id_binding |= ops->uverbs_no_driver_id_binding; SET_DEVICE_OP(dev_ops, add_gid); SET_DEVICE_OP(dev_ops, add_sub_dev); SET_DEVICE_OP(dev_ops, advise_mr); SET_DEVICE_OP(dev_ops, alloc_dm); SET_DEVICE_OP(dev_ops, alloc_hw_device_stats); SET_DEVICE_OP(dev_ops, alloc_hw_port_stats); SET_DEVICE_OP(dev_ops, alloc_mr); SET_DEVICE_OP(dev_ops, alloc_mr_integrity); SET_DEVICE_OP(dev_ops, alloc_mw); SET_DEVICE_OP(dev_ops, alloc_pd); SET_DEVICE_OP(dev_ops, alloc_rdma_netdev); SET_DEVICE_OP(dev_ops, alloc_ucontext); SET_DEVICE_OP(dev_ops, alloc_xrcd); SET_DEVICE_OP(dev_ops, attach_mcast); SET_DEVICE_OP(dev_ops, check_mr_status); SET_DEVICE_OP(dev_ops, counter_alloc_stats); SET_DEVICE_OP(dev_ops, counter_bind_qp); SET_DEVICE_OP(dev_ops, counter_dealloc); SET_DEVICE_OP(dev_ops, counter_unbind_qp); SET_DEVICE_OP(dev_ops, counter_update_stats); SET_DEVICE_OP(dev_ops, create_ah); SET_DEVICE_OP(dev_ops, create_counters); SET_DEVICE_OP(dev_ops, create_cq); SET_DEVICE_OP(dev_ops, create_flow); SET_DEVICE_OP(dev_ops, create_qp); SET_DEVICE_OP(dev_ops, create_rwq_ind_table); SET_DEVICE_OP(dev_ops, create_srq); SET_DEVICE_OP(dev_ops, create_user_ah); SET_DEVICE_OP(dev_ops, create_wq); SET_DEVICE_OP(dev_ops, dealloc_dm); SET_DEVICE_OP(dev_ops, dealloc_driver); SET_DEVICE_OP(dev_ops, dealloc_mw); SET_DEVICE_OP(dev_ops, dealloc_pd); SET_DEVICE_OP(dev_ops, dealloc_ucontext); SET_DEVICE_OP(dev_ops, dealloc_xrcd); SET_DEVICE_OP(dev_ops, del_gid); SET_DEVICE_OP(dev_ops, del_sub_dev); SET_DEVICE_OP(dev_ops, dereg_mr); SET_DEVICE_OP(dev_ops, destroy_ah); SET_DEVICE_OP(dev_ops, destroy_counters); SET_DEVICE_OP(dev_ops, destroy_cq); SET_DEVICE_OP(dev_ops, destroy_flow); SET_DEVICE_OP(dev_ops, destroy_flow_action); SET_DEVICE_OP(dev_ops, destroy_qp); SET_DEVICE_OP(dev_ops, destroy_rwq_ind_table); SET_DEVICE_OP(dev_ops, destroy_srq); SET_DEVICE_OP(dev_ops, destroy_wq); SET_DEVICE_OP(dev_ops, device_group); SET_DEVICE_OP(dev_ops, detach_mcast); SET_DEVICE_OP(dev_ops, disassociate_ucontext); SET_DEVICE_OP(dev_ops, drain_rq); SET_DEVICE_OP(dev_ops, drain_sq); SET_DEVICE_OP(dev_ops, enable_driver); SET_DEVICE_OP(dev_ops, fill_res_cm_id_entry); SET_DEVICE_OP(dev_ops, fill_res_cq_entry); SET_DEVICE_OP(dev_ops, fill_res_cq_entry_raw); SET_DEVICE_OP(dev_ops, fill_res_mr_entry); SET_DEVICE_OP(dev_ops, fill_res_mr_entry_raw); SET_DEVICE_OP(dev_ops, fill_res_qp_entry); SET_DEVICE_OP(dev_ops, fill_res_qp_entry_raw); SET_DEVICE_OP(dev_ops, fill_res_srq_entry); SET_DEVICE_OP(dev_ops, fill_res_srq_entry_raw); SET_DEVICE_OP(dev_ops, fill_stat_mr_entry); SET_DEVICE_OP(dev_ops, get_dev_fw_str); SET_DEVICE_OP(dev_ops, get_dma_mr); SET_DEVICE_OP(dev_ops, get_hw_stats); SET_DEVICE_OP(dev_ops, get_link_layer); SET_DEVICE_OP(dev_ops, get_netdev); SET_DEVICE_OP(dev_ops, get_numa_node); SET_DEVICE_OP(dev_ops, get_port_immutable); SET_DEVICE_OP(dev_ops, get_vector_affinity); SET_DEVICE_OP(dev_ops, get_vf_config); SET_DEVICE_OP(dev_ops, get_vf_guid); SET_DEVICE_OP(dev_ops, get_vf_stats); SET_DEVICE_OP(dev_ops, iw_accept); SET_DEVICE_OP(dev_ops, iw_add_ref); SET_DEVICE_OP(dev_ops, iw_connect); SET_DEVICE_OP(dev_ops, iw_create_listen); SET_DEVICE_OP(dev_ops, iw_destroy_listen); SET_DEVICE_OP(dev_ops, iw_get_qp); SET_DEVICE_OP(dev_ops, iw_reject); SET_DEVICE_OP(dev_ops, iw_rem_ref); SET_DEVICE_OP(dev_ops, map_mr_sg); SET_DEVICE_OP(dev_ops, map_mr_sg_pi); SET_DEVICE_OP(dev_ops, mmap); SET_DEVICE_OP(dev_ops, mmap_free); SET_DEVICE_OP(dev_ops, modify_ah); SET_DEVICE_OP(dev_ops, modify_cq); SET_DEVICE_OP(dev_ops, modify_device); SET_DEVICE_OP(dev_ops, modify_hw_stat); SET_DEVICE_OP(dev_ops, modify_port); SET_DEVICE_OP(dev_ops, modify_qp); SET_DEVICE_OP(dev_ops, modify_srq); SET_DEVICE_OP(dev_ops, modify_wq); SET_DEVICE_OP(dev_ops, peek_cq); SET_DEVICE_OP(dev_ops, poll_cq); SET_DEVICE_OP(dev_ops, port_groups); SET_DEVICE_OP(dev_ops, post_recv); SET_DEVICE_OP(dev_ops, post_send); SET_DEVICE_OP(dev_ops, post_srq_recv); SET_DEVICE_OP(dev_ops, process_mad); SET_DEVICE_OP(dev_ops, query_ah); SET_DEVICE_OP(dev_ops, query_device); SET_DEVICE_OP(dev_ops, query_gid); SET_DEVICE_OP(dev_ops, query_pkey); SET_DEVICE_OP(dev_ops, query_port); SET_DEVICE_OP(dev_ops, query_qp); SET_DEVICE_OP(dev_ops, query_srq); SET_DEVICE_OP(dev_ops, query_ucontext); SET_DEVICE_OP(dev_ops, rdma_netdev_get_params); SET_DEVICE_OP(dev_ops, read_counters); SET_DEVICE_OP(dev_ops, reg_dm_mr); SET_DEVICE_OP(dev_ops, reg_user_mr); SET_DEVICE_OP(dev_ops, reg_user_mr_dmabuf); SET_DEVICE_OP(dev_ops, req_notify_cq); SET_DEVICE_OP(dev_ops, rereg_user_mr); SET_DEVICE_OP(dev_ops, resize_cq); SET_DEVICE_OP(dev_ops, set_vf_guid); SET_DEVICE_OP(dev_ops, set_vf_link_state); SET_OBJ_SIZE(dev_ops, ib_ah); SET_OBJ_SIZE(dev_ops, ib_counters); SET_OBJ_SIZE(dev_ops, ib_cq); SET_OBJ_SIZE(dev_ops, ib_mw); SET_OBJ_SIZE(dev_ops, ib_pd); SET_OBJ_SIZE(dev_ops, ib_qp); SET_OBJ_SIZE(dev_ops, ib_rwq_ind_table); SET_OBJ_SIZE(dev_ops, ib_srq); SET_OBJ_SIZE(dev_ops, ib_ucontext); SET_OBJ_SIZE(dev_ops, ib_xrcd); } EXPORT_SYMBOL(ib_set_device_ops); int ib_add_sub_device(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name) { struct ib_device *sub; int ret = 0; if (!parent->ops.add_sub_dev || !parent->ops.del_sub_dev) return -EOPNOTSUPP; if (!ib_device_try_get(parent)) return -EINVAL; sub = parent->ops.add_sub_dev(parent, type, name); if (IS_ERR(sub)) { ib_device_put(parent); return PTR_ERR(sub); } sub->type = type; sub->parent = parent; mutex_lock(&parent->subdev_lock); list_add_tail(&parent->subdev_list_head, &sub->subdev_list); mutex_unlock(&parent->subdev_lock); return ret; } EXPORT_SYMBOL(ib_add_sub_device); int ib_del_sub_device_and_put(struct ib_device *sub) { struct ib_device *parent = sub->parent; if (!parent) return -EOPNOTSUPP; mutex_lock(&parent->subdev_lock); list_del(&sub->subdev_list); mutex_unlock(&parent->subdev_lock); ib_device_put(sub); parent->ops.del_sub_dev(sub); ib_device_put(parent); return 0; } EXPORT_SYMBOL(ib_del_sub_device_and_put); #ifdef CONFIG_INFINIBAND_VIRT_DMA int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents) { struct scatterlist *s; int i; for_each_sg(sg, s, nents, i) { sg_dma_address(s) = (uintptr_t)sg_virt(s); sg_dma_len(s) = s->length; } return nents; } EXPORT_SYMBOL(ib_dma_virt_map_sg); #endif /* CONFIG_INFINIBAND_VIRT_DMA */ static const struct rdma_nl_cbs ibnl_ls_cb_table[RDMA_NL_LS_NUM_OPS] = { [RDMA_NL_LS_OP_RESOLVE] = { .doit = ib_nl_handle_resolve_resp, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NL_LS_OP_SET_TIMEOUT] = { .doit = ib_nl_handle_set_timeout, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NL_LS_OP_IP_RESOLVE] = { .doit = ib_nl_handle_ip_res_resp, .flags = RDMA_NL_ADMIN_PERM, }, }; static int __init ib_core_init(void) { int ret = -ENOMEM; ib_wq = alloc_workqueue("infiniband", 0, 0); if (!ib_wq) return -ENOMEM; ib_unreg_wq = alloc_workqueue("ib-unreg-wq", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); if (!ib_unreg_wq) goto err; ib_comp_wq = alloc_workqueue("ib-comp-wq", WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_SYSFS, 0); if (!ib_comp_wq) goto err_unbound; ib_comp_unbound_wq = alloc_workqueue("ib-comp-unb-wq", WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_SYSFS, WQ_UNBOUND_MAX_ACTIVE); if (!ib_comp_unbound_wq) goto err_comp; ret = class_register(&ib_class); if (ret) { pr_warn("Couldn't create InfiniBand device class\n"); goto err_comp_unbound; } rdma_nl_init(); ret = addr_init(); if (ret) { pr_warn("Couldn't init IB address resolution\n"); goto err_ibnl; } ret = ib_mad_init(); if (ret) { pr_warn("Couldn't init IB MAD\n"); goto err_addr; } ret = ib_sa_init(); if (ret) { pr_warn("Couldn't init SA\n"); goto err_mad; } ret = register_blocking_lsm_notifier(&ibdev_lsm_nb); if (ret) { pr_warn("Couldn't register LSM notifier. ret %d\n", ret); goto err_sa; } ret = register_pernet_device(&rdma_dev_net_ops); if (ret) { pr_warn("Couldn't init compat dev. ret %d\n", ret); goto err_compat; } nldev_init(); rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table); ret = roce_gid_mgmt_init(); if (ret) { pr_warn("Couldn't init RoCE GID management\n"); goto err_parent; } return 0; err_parent: rdma_nl_unregister(RDMA_NL_LS); nldev_exit(); unregister_pernet_device(&rdma_dev_net_ops); err_compat: unregister_blocking_lsm_notifier(&ibdev_lsm_nb); err_sa: ib_sa_cleanup(); err_mad: ib_mad_cleanup(); err_addr: addr_cleanup(); err_ibnl: class_unregister(&ib_class); err_comp_unbound: destroy_workqueue(ib_comp_unbound_wq); err_comp: destroy_workqueue(ib_comp_wq); err_unbound: destroy_workqueue(ib_unreg_wq); err: destroy_workqueue(ib_wq); return ret; } static void __exit ib_core_cleanup(void) { roce_gid_mgmt_cleanup(); rdma_nl_unregister(RDMA_NL_LS); nldev_exit(); unregister_pernet_device(&rdma_dev_net_ops); unregister_blocking_lsm_notifier(&ibdev_lsm_nb); ib_sa_cleanup(); ib_mad_cleanup(); addr_cleanup(); rdma_nl_exit(); class_unregister(&ib_class); destroy_workqueue(ib_comp_unbound_wq); destroy_workqueue(ib_comp_wq); /* Make sure that any pending umem accounting work is done. */ destroy_workqueue(ib_wq); destroy_workqueue(ib_unreg_wq); WARN_ON(!xa_empty(&clients)); WARN_ON(!xa_empty(&devices)); } MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_LS, 4); /* ib core relies on netdev stack to first register net_ns_type_operations * ns kobject type before ib_core initialization. */ fs_initcall(ib_core_init); module_exit(ib_core_cleanup); |
| 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 | /* SPDX-License-Identifier: GPL-2.0 */ /* Freezer declarations */ #ifndef FREEZER_H_INCLUDED #define FREEZER_H_INCLUDED #include <linux/debug_locks.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/atomic.h> #include <linux/jump_label.h> #ifdef CONFIG_FREEZER DECLARE_STATIC_KEY_FALSE(freezer_active); extern bool pm_freezing; /* PM freezing in effect */ extern bool pm_nosig_freezing; /* PM nosig freezing in effect */ /* * Timeout for stopping processes */ extern unsigned int freeze_timeout_msecs; /* * Check if a process has been frozen */ extern bool frozen(struct task_struct *p); extern bool freezing_slow_path(struct task_struct *p); /* * Check if there is a request to freeze a process */ static inline bool freezing(struct task_struct *p) { if (static_branch_unlikely(&freezer_active)) return freezing_slow_path(p); return false; } /* Takes and releases task alloc lock using task_lock() */ extern void __thaw_task(struct task_struct *t); extern bool __refrigerator(bool check_kthr_stop); extern int freeze_processes(void); extern int freeze_kernel_threads(void); extern void thaw_processes(void); extern void thaw_kernel_threads(void); static inline bool try_to_freeze(void) { might_sleep(); if (likely(!freezing(current))) return false; if (!(current->flags & PF_NOFREEZE)) debug_check_no_locks_held(); return __refrigerator(false); } extern bool freeze_task(struct task_struct *p); extern bool set_freezable(void); #ifdef CONFIG_CGROUP_FREEZER extern bool cgroup_freezing(struct task_struct *task); #else /* !CONFIG_CGROUP_FREEZER */ static inline bool cgroup_freezing(struct task_struct *task) { return false; } #endif /* !CONFIG_CGROUP_FREEZER */ #else /* !CONFIG_FREEZER */ static inline bool frozen(struct task_struct *p) { return false; } static inline bool freezing(struct task_struct *p) { return false; } static inline void __thaw_task(struct task_struct *t) {} static inline bool __refrigerator(bool check_kthr_stop) { return false; } static inline int freeze_processes(void) { return -ENOSYS; } static inline int freeze_kernel_threads(void) { return -ENOSYS; } static inline void thaw_processes(void) {} static inline void thaw_kernel_threads(void) {} static inline bool try_to_freeze(void) { return false; } static inline void set_freezable(void) {} #endif /* !CONFIG_FREEZER */ #endif /* FREEZER_H_INCLUDED */ |
| 24 1 3 22 2 1 1 26 26 24 1 3 14 1 1 1 2 17 2 30 1 22 17 1 1 15 1 16 2 4 2 24 5 9 19 6 10 6 16 16 8 5 1 2 5 2 1 2 7 4 35 7 30 16 10 6 15 11 1 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VGIC: KVM DEVICE API * * Copyright (C) 2015 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> #include <linux/uaccess.h> #include <asm/kvm_mmu.h> #include <asm/cputype.h> #include "vgic.h" /* common helpers */ int vgic_check_iorange(struct kvm *kvm, phys_addr_t ioaddr, phys_addr_t addr, phys_addr_t alignment, phys_addr_t size) { if (!IS_VGIC_ADDR_UNDEF(ioaddr)) return -EEXIST; if (!IS_ALIGNED(addr, alignment) || !IS_ALIGNED(size, alignment)) return -EINVAL; if (addr + size < addr) return -EINVAL; if (addr & ~kvm_phys_mask(&kvm->arch.mmu) || (addr + size) > kvm_phys_size(&kvm->arch.mmu)) return -E2BIG; return 0; } static int vgic_check_type(struct kvm *kvm, int type_needed) { if (kvm->arch.vgic.vgic_model != type_needed) return -ENODEV; else return 0; } int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr) { struct vgic_dist *vgic = &kvm->arch.vgic; int r; mutex_lock(&kvm->arch.config_lock); switch (FIELD_GET(KVM_ARM_DEVICE_TYPE_MASK, dev_addr->id)) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); if (!r) r = vgic_check_iorange(kvm, vgic->vgic_dist_base, dev_addr->addr, SZ_4K, KVM_VGIC_V2_DIST_SIZE); if (!r) vgic->vgic_dist_base = dev_addr->addr; break; case KVM_VGIC_V2_ADDR_TYPE_CPU: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); if (!r) r = vgic_check_iorange(kvm, vgic->vgic_cpu_base, dev_addr->addr, SZ_4K, KVM_VGIC_V2_CPU_SIZE); if (!r) vgic->vgic_cpu_base = dev_addr->addr; break; default: r = -ENODEV; } mutex_unlock(&kvm->arch.config_lock); return r; } /** * kvm_vgic_addr - set or get vgic VM base addresses * @kvm: pointer to the vm struct * @attr: pointer to the attribute being retrieved/updated * @write: if true set the address in the VM address space, if false read the * address * * Set or get the vgic base addresses for the distributor and the virtual CPU * interface in the VM physical address space. These addresses are properties * of the emulated core/SoC and therefore user space initially knows this * information. * Check them for sanity (alignment, double assignment). We can't check for * overlapping regions in case of a virtual GICv3 here, since we don't know * the number of VCPUs yet, so we defer this check to map_resources(). */ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool write) { u64 __user *uaddr = (u64 __user *)attr->addr; struct vgic_dist *vgic = &kvm->arch.vgic; phys_addr_t *addr_ptr, alignment, size; u64 undef_value = VGIC_ADDR_UNDEF; u64 addr; int r; /* Reading a redistributor region addr implies getting the index */ if (write || attr->attr == KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION) if (get_user(addr, uaddr)) return -EFAULT; /* * Since we can't hold config_lock while registering the redistributor * iodevs, take the slots_lock immediately. */ mutex_lock(&kvm->slots_lock); switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); addr_ptr = &vgic->vgic_dist_base; alignment = SZ_4K; size = KVM_VGIC_V2_DIST_SIZE; break; case KVM_VGIC_V2_ADDR_TYPE_CPU: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); addr_ptr = &vgic->vgic_cpu_base; alignment = SZ_4K; size = KVM_VGIC_V2_CPU_SIZE; break; case KVM_VGIC_V3_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); addr_ptr = &vgic->vgic_dist_base; alignment = SZ_64K; size = KVM_VGIC_V3_DIST_SIZE; break; case KVM_VGIC_V3_ADDR_TYPE_REDIST: { struct vgic_redist_region *rdreg; r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; if (write) { r = vgic_v3_set_redist_base(kvm, 0, addr, 0); goto out; } rdreg = list_first_entry_or_null(&vgic->rd_regions, struct vgic_redist_region, list); if (!rdreg) addr_ptr = &undef_value; else addr_ptr = &rdreg->base; break; } case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: { struct vgic_redist_region *rdreg; u8 index; r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; index = addr & KVM_VGIC_V3_RDIST_INDEX_MASK; if (write) { gpa_t base = addr & KVM_VGIC_V3_RDIST_BASE_MASK; u32 count = FIELD_GET(KVM_VGIC_V3_RDIST_COUNT_MASK, addr); u8 flags = FIELD_GET(KVM_VGIC_V3_RDIST_FLAGS_MASK, addr); if (!count || flags) r = -EINVAL; else r = vgic_v3_set_redist_base(kvm, index, base, count); goto out; } rdreg = vgic_v3_rdist_region_from_index(kvm, index); if (!rdreg) { r = -ENOENT; goto out; } addr = index; addr |= rdreg->base; addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT; goto out; } default: r = -ENODEV; } if (r) goto out; mutex_lock(&kvm->arch.config_lock); if (write) { r = vgic_check_iorange(kvm, *addr_ptr, addr, alignment, size); if (!r) *addr_ptr = addr; } else { addr = *addr_ptr; } mutex_unlock(&kvm->arch.config_lock); out: mutex_unlock(&kvm->slots_lock); if (!r && !write) r = put_user(addr, uaddr); return r; } static int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: r = kvm_vgic_addr(dev->kvm, attr, true); return (r == -ENODEV) ? -ENXIO : r; case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { u32 __user *uaddr = (u32 __user *)(long)attr->addr; u32 val; int ret = 0; if (get_user(val, uaddr)) return -EFAULT; /* * We require: * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs * - at most 1024 interrupts * - a multiple of 32 interrupts */ if (val < (VGIC_NR_PRIVATE_IRQS + 32) || val > VGIC_MAX_RESERVED || (val & 31)) return -EINVAL; mutex_lock(&dev->kvm->arch.config_lock); /* * Either userspace has already configured NR_IRQS or * the vgic has already been initialized and vgic_init() * supplied a default amount of SPIs. */ if (dev->kvm->arch.vgic.nr_spis) ret = -EBUSY; else dev->kvm->arch.vgic.nr_spis = val - VGIC_NR_PRIVATE_IRQS; mutex_unlock(&dev->kvm->arch.config_lock); return ret; } case KVM_DEV_ARM_VGIC_GRP_CTRL: { switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: mutex_lock(&dev->kvm->arch.config_lock); r = vgic_init(dev->kvm); mutex_unlock(&dev->kvm->arch.config_lock); return r; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: /* * OK, this one isn't common at all, but we * want to handle all control group attributes * in a single place. */ if (vgic_check_type(dev->kvm, KVM_DEV_TYPE_ARM_VGIC_V3)) return -ENXIO; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); r = vgic_v3_save_pending_tables(dev->kvm); mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return r; } break; } } return -ENXIO; } static int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r = -ENXIO; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: r = kvm_vgic_addr(dev->kvm, attr, false); return (r == -ENODEV) ? -ENXIO : r; case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { u32 __user *uaddr = (u32 __user *)(long)attr->addr; r = put_user(dev->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS, uaddr); break; } } return r; } static int vgic_create(struct kvm_device *dev, u32 type) { return kvm_vgic_create(dev->kvm, type); } static void vgic_destroy(struct kvm_device *dev) { kfree(dev); } int kvm_register_vgic_device(unsigned long type) { int ret = -ENODEV; switch (type) { case KVM_DEV_TYPE_ARM_VGIC_V2: ret = kvm_register_device_ops(&kvm_arm_vgic_v2_ops, KVM_DEV_TYPE_ARM_VGIC_V2); break; case KVM_DEV_TYPE_ARM_VGIC_V3: ret = kvm_register_device_ops(&kvm_arm_vgic_v3_ops, KVM_DEV_TYPE_ARM_VGIC_V3); if (ret) break; ret = kvm_vgic_register_its_device(); break; } return ret; } int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); if (!reg_attr->vcpu) return -EINVAL; return 0; } /** * vgic_v2_attr_regs_access - allows user space to access VGIC v2 state * * @dev: kvm device handle * @attr: kvm device attribute * @is_write: true if userspace is writing a register */ static int vgic_v2_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; struct vgic_reg_attr reg_attr; gpa_t addr; struct kvm_vcpu *vcpu; int ret; u32 val; ret = vgic_v2_parse_attr(dev, attr, ®_attr); if (ret) return ret; vcpu = reg_attr.vcpu; addr = reg_attr.addr; if (is_write) if (get_user(val, uaddr)) return -EFAULT; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); ret = vgic_init(dev->kvm); if (ret) goto out; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: ret = vgic_v2_dist_uaccess(vcpu, is_write, addr, &val); break; default: ret = -EINVAL; break; } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && !is_write) ret = put_user(val, uaddr); return ret; } static int vgic_v2_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_attr_regs_access(dev, attr, true); default: return vgic_set_common_attr(dev, attr); } } static int vgic_v2_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_attr_regs_access(dev, attr, false); default: return vgic_get_common_attr(dev, attr); } } static int vgic_v2_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: case KVM_VGIC_V2_ADDR_TYPE_CPU: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_has_attr_regs(dev, attr); case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: return 0; case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; } } return -ENXIO; } struct kvm_device_ops kvm_arm_vgic_v2_ops = { .name = "kvm-arm-vgic-v2", .create = vgic_create, .destroy = vgic_destroy, .set_attr = vgic_v2_set_attr, .get_attr = vgic_v2_get_attr, .has_attr = vgic_v2_has_attr, }; int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { unsigned long vgic_mpidr, mpidr_reg; /* * For KVM_DEV_ARM_VGIC_GRP_DIST_REGS group, * attr might not hold MPIDR. Hence assume vcpu0. */ if (attr->group != KVM_DEV_ARM_VGIC_GRP_DIST_REGS) { vgic_mpidr = (attr->attr & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) >> KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT; mpidr_reg = VGIC_TO_MPIDR(vgic_mpidr); reg_attr->vcpu = kvm_mpidr_to_vcpu(dev->kvm, mpidr_reg); } else { reg_attr->vcpu = kvm_get_vcpu(dev->kvm, 0); } if (!reg_attr->vcpu) return -EINVAL; reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; return 0; } /* * vgic_v3_attr_regs_access - allows user space to access VGIC v3 state * * @dev: kvm device handle * @attr: kvm device attribute * @is_write: true if userspace is writing a register */ static int vgic_v3_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { struct vgic_reg_attr reg_attr; gpa_t addr; struct kvm_vcpu *vcpu; bool uaccess; u32 val; int ret; ret = vgic_v3_parse_attr(dev, attr, ®_attr); if (ret) return ret; vcpu = reg_attr.vcpu; addr = reg_attr.addr; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: /* Sysregs uaccess is performed by the sysreg handling code */ uaccess = false; break; default: uaccess = true; } if (uaccess && is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; if (get_user(val, uaddr)) return -EFAULT; } mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); if (unlikely(!vgic_initialized(dev->kvm))) { ret = -EBUSY; goto out; } switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: ret = vgic_v3_dist_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: ret = vgic_v3_redist_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: ret = vgic_v3_cpu_sysregs_uaccess(vcpu, attr, is_write); break; case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { unsigned int info, intid; info = (attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT; if (info == VGIC_LEVEL_INFO_LINE_LEVEL) { intid = attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK; ret = vgic_v3_line_level_info_uaccess(vcpu, is_write, intid, &val); } else { ret = -EINVAL; } break; } default: ret = -EINVAL; break; } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && uaccess && !is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; ret = put_user(val, uaddr); } return ret; } static int vgic_v3_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: return vgic_v3_attr_regs_access(dev, attr, true); default: return vgic_set_common_attr(dev, attr); } } static int vgic_v3_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: return vgic_v3_attr_regs_access(dev, attr, false); default: return vgic_get_common_attr(dev, attr); } } static int vgic_v3_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_V3_ADDR_TYPE_DIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: return vgic_v3_has_attr_regs(dev, attr); case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: return 0; case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { if (((attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) == VGIC_LEVEL_INFO_LINE_LEVEL) return 0; break; } case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: return 0; } } return -ENXIO; } struct kvm_device_ops kvm_arm_vgic_v3_ops = { .name = "kvm-arm-vgic-v3", .create = vgic_create, .destroy = vgic_destroy, .set_attr = vgic_v3_set_attr, .get_attr = vgic_v3_get_attr, .has_attr = vgic_v3_has_attr, }; |
| 621 621 620 623 638 637 640 638 622 630 631 630 630 632 61 616 620 617 614 617 616 72 639 641 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0 /* * Lockless hierarchical page accounting & limiting * * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner */ #include <linux/page_counter.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/bug.h> #include <asm/page.h> static bool track_protection(struct page_counter *c) { return c->protection_support; } static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; long delta; if (!c->parent) return; protected = min(usage, READ_ONCE(c->min)); old_protected = atomic_long_read(&c->min_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } protected = min(usage, READ_ONCE(c->low)); old_protected = atomic_long_read(&c->low_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->low_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_low_usage); } } /** * page_counter_cancel - take pages out of the local counter * @counter: counter * @nr_pages: number of pages to cancel */ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) { long new; new = atomic_long_sub_return(nr_pages, &counter->usage); /* More uncharges than charges? */ if (WARN_ONCE(new < 0, "page_counter underflow: %ld nr_pages=%lu\n", new, nr_pages)) { new = 0; atomic_long_set(&counter->usage, new); } if (track_protection(counter)) propagate_protected_usage(counter, new); } /** * page_counter_charge - hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * * NOTE: This does not consider any configured counter limits. */ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; bool protection = track_protection(counter); for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); if (protection) propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. * * Notably, we have two watermarks to allow for both a globally * visible peak and one that can be reset at a smaller scope. * * Since we reset both watermarks when the global reset occurs, * we can guarantee that watermark >= local_watermark, so we * don't need to do both comparisons every time. * * On systems with branch predictors, the inner condition should * be almost free. */ if (new > READ_ONCE(c->local_watermark)) { WRITE_ONCE(c->local_watermark, new); if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } } /** * page_counter_try_charge - try to hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * @fail: points first counter to hit its limit, if any * * Returns %true on success, or %false and @fail if the counter or one * of its ancestors has hit its configured limit. */ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail) { struct page_counter *c; bool protection = track_protection(counter); for (c = counter; c; c = c->parent) { long new; /* * Charge speculatively to avoid an expensive CAS. If * a bigger charge fails, it might falsely lock out a * racing smaller charge and send it into reclaim * early, but the error is limited to the difference * between the two sizes, which is less than 2M/4M in * case of a THP locking out a regular page charge. * * The atomic_long_add_return() implies a full memory * barrier between incrementing the count and reading * the limit. When racing with page_counter_set_max(), * we either see the new limit or the setter sees the * counter has changed and retries. */ new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); /* * This is racy, but we can live with some * inaccuracy in the failcnt which is only used * to report stats. */ data_race(c->failcnt++); *fail = c; goto failed; } if (protection) propagate_protected_usage(c, new); /* see comment on page_counter_charge */ if (new > READ_ONCE(c->local_watermark)) { WRITE_ONCE(c->local_watermark, new); if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } return true; failed: for (c = counter; c != *fail; c = c->parent) page_counter_cancel(c, nr_pages); return false; } /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter * @nr_pages: number of pages to uncharge */ void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) page_counter_cancel(c, nr_pages); } /** * page_counter_set_max - set the maximum number of pages allowed * @counter: counter * @nr_pages: limit to set * * Returns 0 on success, -EBUSY if the current number of pages on the * counter already exceeds the specified limit. * * The caller must serialize invocations on the same counter. */ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) { for (;;) { unsigned long old; long usage; /* * Update the limit while making sure that it's not * below the concurrently-changing counter value. * * The xchg implies two full memory barriers before * and after, so the read-swap-read is ordered and * ensures coherency with page_counter_try_charge(): * that function modifies the count before checking * the limit, so if it sees the old limit, we see the * modified counter and retry. */ usage = page_counter_read(counter); if (usage > nr_pages) return -EBUSY; old = xchg(&counter->max, nr_pages); if (page_counter_read(counter) <= usage || nr_pages >= old) return 0; counter->max = old; cond_resched(); } } /** * page_counter_set_min - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->min, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_set_low - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->low, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages) { char *end; u64 bytes; if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } bytes = memparse(buf, &end); if (*end != '\0') return -EINVAL; *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); return 0; } #ifdef CONFIG_MEMCG /* * This function calculates an individual page counter's effective * protection which is derived from its own memory.min/low, its * parent's and siblings' settings, as well as the actual memory * distribution in the tree. * * The following rules apply to the effective protection values: * * 1. At the first level of reclaim, effective protection is equal to * the declared protection in memory.min and memory.low. * * 2. To enable safe delegation of the protection configuration, at * subsequent levels the effective protection is capped to the * parent's effective protection. * * 3. To make complex and dynamic subtrees easier to configure, the * user is allowed to overcommit the declared protection at a given * level. If that is the case, the parent's effective protection is * distributed to the children in proportion to how much protection * they have declared and how much of it they are utilizing. * * This makes distribution proportional, but also work-conserving: * if one counter claims much more protection than it uses memory, * the unused remainder is available to its siblings. * * 4. Conversely, when the declared protection is undercommitted at a * given level, the distribution of the larger parental protection * budget is NOT proportional. A counter's protection from a sibling * is capped to its own memory.min/low setting. * * 5. However, to allow protecting recursive subtrees from each other * without having to declare each individual counter's fixed share * of the ancestor's claim to protection, any unutilized - * "floating" - protection from up the tree is distributed in * proportion to each counter's *usage*. This makes the protection * neutral wrt sibling cgroups and lets them compete freely over * the shared parental protection budget, but it protects the * subtree as a whole from neighboring subtrees. * * Note that 4. and 5. are not in conflict: 4. is about protecting * against immediate siblings whereas 5. is about protecting against * neighboring subtrees. */ static unsigned long effective_protection(unsigned long usage, unsigned long parent_usage, unsigned long setting, unsigned long parent_effective, unsigned long siblings_protected, bool recursive_protection) { unsigned long protected; unsigned long ep; protected = min(usage, setting); /* * If all cgroups at this level combined claim and use more * protection than what the parent affords them, distribute * shares in proportion to utilization. * * We are using actual utilization rather than the statically * claimed protection in order to be work-conserving: claimed * but unused protection is available to siblings that would * otherwise get a smaller chunk than what they claimed. */ if (siblings_protected > parent_effective) return protected * parent_effective / siblings_protected; /* * Ok, utilized protection of all children is within what the * parent affords them, so we know whatever this child claims * and utilizes is effectively protected. * * If there is unprotected usage beyond this value, reclaim * will apply pressure in proportion to that amount. * * If there is unutilized protection, the cgroup will be fully * shielded from reclaim, but we do return a smaller value for * protection than what the group could enjoy in theory. This * is okay. With the overcommit distribution above, effective * protection is always dependent on how memory is actually * consumed among the siblings anyway. */ ep = protected; /* * If the children aren't claiming (all of) the protection * afforded to them by the parent, distribute the remainder in * proportion to the (unprotected) memory of each cgroup. That * way, cgroups that aren't explicitly prioritized wrt each * other compete freely over the allowance, but they are * collectively protected from neighboring trees. * * We're using unprotected memory for the weight so that if * some cgroups DO claim explicit protection, we don't protect * the same bytes twice. * * Check both usage and parent_usage against the respective * protected values. One should imply the other, but they * aren't read atomically - make sure the division is sane. */ if (!recursive_protection) return ep; if (parent_effective > siblings_protected && parent_usage > siblings_protected && usage > protected) { unsigned long unclaimed; unclaimed = parent_effective - siblings_protected; unclaimed *= usage - protected; unclaimed /= parent_usage - siblings_protected; ep += unclaimed; } return ep; } /** * page_counter_calculate_protection - check if memory consumption is in the normal range * @root: the top ancestor of the sub-tree being checked * @counter: the page_counter the counter to update * @recursive_protection: Whether to use memory_recursiveprot behavior. * * Calculates elow/emin thresholds for given page_counter. * * WARNING: This function is not stateless! It can only be used as part * of a top-down tree iteration, not for isolated queries. */ void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection) { unsigned long usage, parent_usage; struct page_counter *parent = counter->parent; /* * Effective values of the reclaim targets are ignored so they * can be stale. Have a look at mem_cgroup_protection for more * details. * TODO: calculation should be more robust so that we do not need * that special casing. */ if (root == counter) return; usage = page_counter_read(counter); if (!usage) return; if (parent == root) { counter->emin = READ_ONCE(counter->min); counter->elow = READ_ONCE(counter->low); return; } parent_usage = page_counter_read(parent); WRITE_ONCE(counter->emin, effective_protection(usage, parent_usage, READ_ONCE(counter->min), READ_ONCE(parent->emin), atomic_long_read(&parent->children_min_usage), recursive_protection)); WRITE_ONCE(counter->elow, effective_protection(usage, parent_usage, READ_ONCE(counter->low), READ_ONCE(parent->elow), atomic_long_read(&parent->children_low_usage), recursive_protection)); } #endif /* CONFIG_MEMCG */ |
| 7 7 7 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 | /* 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 { 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; __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); __printf(1, 0) int vprintk_deferred(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); 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) /* * 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 |
| 23 316 60 23 4 35 23 33 11 11 13 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGEMAP_H #define _LINUX_PAGEMAP_H /* * Copyright 1995 Linus Torvalds */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/list.h> #include <linux/highmem.h> #include <linux/compiler.h> #include <linux/uaccess.h> #include <linux/gfp.h> #include <linux/bitops.h> #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> struct folio_batch; unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); static inline void invalidate_remote_inode(struct inode *inode) { if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) invalidate_mapping_pages(inode->i_mapping, 0, -1); } int invalidate_inode_pages2(struct address_space *mapping); int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); int kiocb_invalidate_pages(struct kiocb *iocb, size_t count); void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count); int filemap_invalidate_pages(struct address_space *mapping, loff_t pos, loff_t end, bool nowait); int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); int filemap_flush(struct address_space *); int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); int filemap_invalidate_inode(struct inode *inode, bool flush, loff_t start, loff_t end); static inline int filemap_fdatawait(struct address_space *mapping) { return filemap_fdatawait_range(mapping, 0, LLONG_MAX); } bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); int filemap_check_errors(struct address_space *mapping); void __filemap_set_wb_err(struct address_space *mapping, int err); int filemap_fdatawrite_wbc(struct address_space *mapping, struct writeback_control *wbc); int kiocb_write_and_wait(struct kiocb *iocb, size_t count); static inline int filemap_write_and_wait(struct address_space *mapping) { return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); } /** * filemap_set_wb_err - set a writeback error on an address_space * @mapping: mapping in which to set writeback error * @err: error to be set in mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * filemap_set_wb_err to record the error in the mapping so that it will be * automatically reported whenever fsync is called on the file. */ static inline void filemap_set_wb_err(struct address_space *mapping, int err) { /* Fastpath for common case of no error */ if (unlikely(err)) __filemap_set_wb_err(mapping, err); } /** * filemap_check_wb_err - has an error occurred since the mark was sampled? * @mapping: mapping to check for writeback errors * @since: previously-sampled errseq_t * * Grab the errseq_t value from the mapping, and see if it has changed "since" * the given value was sampled. * * If it has then report the latest error set, otherwise return 0. */ static inline int filemap_check_wb_err(struct address_space *mapping, errseq_t since) { return errseq_check(&mapping->wb_err, since); } /** * filemap_sample_wb_err - sample the current errseq_t to test for later errors * @mapping: mapping to be sampled * * Writeback errors are always reported relative to a particular sample point * in the past. This function provides those sample points. */ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) { return errseq_sample(&mapping->wb_err); } /** * file_sample_sb_err - sample the current errseq_t to test for later errors * @file: file pointer to be sampled * * Grab the most current superblock-level errseq_t value for the given * struct file. */ static inline errseq_t file_sample_sb_err(struct file *file) { return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); } /* * Flush file data before changing attributes. Caller must hold any locks * required to prevent further writes to this file until we're done setting * flags. */ static inline int inode_drain_writes(struct inode *inode) { inode_dio_wait(inode); return filemap_write_and_wait(inode->i_mapping); } static inline bool mapping_empty(struct address_space *mapping) { return xa_empty(&mapping->i_pages); } /* * mapping_shrinkable - test if page cache state allows inode reclaim * @mapping: the page cache mapping * * This checks the mapping's cache state for the pupose of inode * reclaim and LRU management. * * The caller is expected to hold the i_lock, but is not required to * hold the i_pages lock, which usually protects cache state. That's * because the i_lock and the list_lru lock that protect the inode and * its LRU state don't nest inside the irq-safe i_pages lock. * * Cache deletions are performed under the i_lock, which ensures that * when an inode goes empty, it will reliably get queued on the LRU. * * Cache additions do not acquire the i_lock and may race with this * check, in which case we'll report the inode as shrinkable when it * has cache pages. This is okay: the shrinker also checks the * refcount and the referenced bit, which will be elevated or set in * the process of adding new cache pages to an inode. */ static inline bool mapping_shrinkable(struct address_space *mapping) { void *head; /* * On highmem systems, there could be lowmem pressure from the * inodes before there is highmem pressure from the page * cache. Make inodes shrinkable regardless of cache state. */ if (IS_ENABLED(CONFIG_HIGHMEM)) return true; /* Cache completely empty? Shrink away. */ head = rcu_access_pointer(mapping->i_pages.xa_head); if (!head) return true; /* * The xarray stores single offset-0 entries directly in the * head pointer, which allows non-resident page cache entries * to escape the shadow shrinker's list of xarray nodes. The * inode shrinker needs to pick them up under memory pressure. */ if (!xa_is_node(head) && xa_is_value(head)) return true; return false; } /* * Bits in mapping->flags. */ enum mapping_flags { AS_EIO = 0, /* IO error on async write */ AS_ENOSPC = 1, /* ENOSPC on async write */ AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */ AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ AS_STABLE_WRITES = 7, /* must wait for writeback before modifying folio contents */ AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS, }; #define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1) #define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN) #define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX) #define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK) /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set * @error: the error to set in the mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * mapping_set_error to record the error in the mapping so that it can be * reported when the application calls fsync(2). */ static inline void mapping_set_error(struct address_space *mapping, int error) { if (likely(!error)) return; /* Record in wb_err for checkers using errseq_t based tracking */ __filemap_set_wb_err(mapping, error); /* Record it in superblock */ if (mapping->host) errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) set_bit(AS_ENOSPC, &mapping->flags); else set_bit(AS_EIO, &mapping->flags); } static inline void mapping_set_unevictable(struct address_space *mapping) { set_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_clear_unevictable(struct address_space *mapping) { clear_bit(AS_UNEVICTABLE, &mapping->flags); } static inline bool mapping_unevictable(struct address_space *mapping) { return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_set_exiting(struct address_space *mapping) { set_bit(AS_EXITING, &mapping->flags); } static inline int mapping_exiting(struct address_space *mapping) { return test_bit(AS_EXITING, &mapping->flags); } static inline void mapping_set_no_writeback_tags(struct address_space *mapping) { set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline int mapping_use_writeback_tags(struct address_space *mapping) { return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline bool mapping_release_always(const struct address_space *mapping) { return test_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline void mapping_set_release_always(struct address_space *mapping) { set_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline void mapping_clear_release_always(struct address_space *mapping) { clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline bool mapping_stable_writes(const struct address_space *mapping) { return test_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_set_stable_writes(struct address_space *mapping) { set_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_clear_stable_writes(struct address_space *mapping) { clear_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_set_inaccessible(struct address_space *mapping) { /* * It's expected inaccessible mappings are also unevictable. Compaction * migrate scanner (isolate_migratepages_block()) relies on this to * reduce page locking. */ set_bit(AS_UNEVICTABLE, &mapping->flags); set_bit(AS_INACCESSIBLE, &mapping->flags); } static inline bool mapping_inaccessible(struct address_space *mapping) { return test_bit(AS_INACCESSIBLE, &mapping->flags); } static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; } /* Restricts the given gfp_mask to what the mapping allows. */ static inline gfp_t mapping_gfp_constraint(struct address_space *mapping, gfp_t gfp_mask) { return mapping_gfp_mask(mapping) & gfp_mask; } /* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... */ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) { m->gfp_mask = mask; } /* * There are some parts of the kernel which assume that PMD entries * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, * limit the maximum allocation order to PMD size. I'm not aware of any * assumptions about maximum order if THP are disabled, but 8 seems like * a good order (that's 1MB if you're using 4kB pages) */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define PREFERRED_MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER #else #define PREFERRED_MAX_PAGECACHE_ORDER 8 #endif /* * xas_split_alloc() does not support arbitrary orders. This implies no * 512MB THP on ARM64 with 64KB base page size. */ #define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) #define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) /* * mapping_max_folio_size_supported() - Check the max folio size supported * * The filesystem should call this function at mount time if there is a * requirement on the folio mapping size in the page cache. */ static inline size_t mapping_max_folio_size_supported(void) { if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER); return PAGE_SIZE; } /* * mapping_set_folio_order_range() - Set the orders supported by a file. * @mapping: The address space of the file. * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive). * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive). * * The filesystem should call this function in its inode constructor to * indicate which base size (min) and maximum size (max) of folio the VFS * can use to cache the contents of the file. This should only be used * if the filesystem needs special handling of folio sizes (ie there is * something the core cannot know). * Do not tune it based on, eg, i_size. * * Context: This should not be called while the inode is active as it * is non-atomic. */ static inline void mapping_set_folio_order_range(struct address_space *mapping, unsigned int min, unsigned int max) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; if (min > MAX_PAGECACHE_ORDER) min = MAX_PAGECACHE_ORDER; if (max > MAX_PAGECACHE_ORDER) max = MAX_PAGECACHE_ORDER; if (max < min) max = min; mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) | (min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX); } static inline void mapping_set_folio_min_order(struct address_space *mapping, unsigned int min) { mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER); } /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The address space of the file. * * The filesystem should call this function in its inode constructor to * indicate that the VFS can use large folios to cache the contents of * the file. * * Context: This should not be called while the inode is active as it * is non-atomic. */ static inline void mapping_set_large_folios(struct address_space *mapping) { mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER); } static inline unsigned int mapping_max_folio_order(const struct address_space *mapping) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 0; return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX; } static inline unsigned int mapping_min_folio_order(const struct address_space *mapping) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 0; return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; } static inline unsigned long mapping_min_folio_nrpages(struct address_space *mapping) { return 1UL << mapping_min_folio_order(mapping); } /** * mapping_align_index() - Align index for this mapping. * @mapping: The address_space. * @index: The page index. * * The index of a folio must be naturally aligned. If you are adding a * new folio to the page cache and need to know what index to give it, * call this function. */ static inline pgoff_t mapping_align_index(struct address_space *mapping, pgoff_t index) { return round_down(index, mapping_min_folio_nrpages(mapping)); } /* * Large folio support currently depends on THP. These dependencies are * being worked on but are not yet fixed. */ static inline bool mapping_large_folio_support(struct address_space *mapping) { /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, "Anonymous mapping always supports large folio"); return mapping_max_folio_order(mapping) > 0; } /* Return the maximum folio size for this pagecache mapping, in bytes. */ static inline size_t mapping_max_folio_size(const struct address_space *mapping) { return PAGE_SIZE << mapping_max_folio_order(mapping); } static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS return atomic_read(&mapping->nr_thps); #else return 0; #endif } static inline void filemap_nr_thps_inc(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } static inline void filemap_nr_thps_dec(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); /** * folio_file_mapping - Find the mapping this folio belongs to. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Folios in the swap cache return the mapping of the * swap file or swap device where the data is stored. This is different * from the mapping returned by folio_mapping(). The only reason to * use it is if, like NFS, you return 0 from ->activate_swapfile. * * Do not call this for folios which aren't in the page cache or swap cache. */ static inline struct address_space *folio_file_mapping(struct folio *folio) { if (unlikely(folio_test_swapcache(folio))) return swapcache_mapping(folio); return folio->mapping; } /** * folio_flush_mapping - Find the file mapping this folio belongs to. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Anonymous folios return NULL, even if they're in * the swap cache. Other kinds of folio also return NULL. * * This is ONLY used by architecture cache flushing code. If you aren't * writing cache flushing code, you want either folio_mapping() or * folio_file_mapping(). */ static inline struct address_space *folio_flush_mapping(struct folio *folio) { if (unlikely(folio_test_swapcache(folio))) return NULL; return folio_mapping(folio); } static inline struct address_space *page_file_mapping(struct page *page) { return folio_file_mapping(page_folio(page)); } /** * folio_inode - Get the host inode for this folio. * @folio: The folio. * * For folios which are in the page cache, return the inode that this folio * belongs to. * * Do not call this for folios which aren't in the page cache. */ static inline struct inode *folio_inode(struct folio *folio) { return folio->mapping->host; } /** * folio_attach_private - Attach private data to a folio. * @folio: Folio to attach data to. * @data: Data to attach to folio. * * Attaching private data to a folio increments the page's reference count. * The data must be detached before the folio will be freed. */ static inline void folio_attach_private(struct folio *folio, void *data) { folio_get(folio); folio->private = data; folio_set_private(folio); } /** * folio_change_private - Change private data on a folio. * @folio: Folio to change the data on. * @data: Data to set on the folio. * * Change the private data attached to a folio and return the old * data. The page must previously have had data attached and the data * must be detached before the folio will be freed. * * Return: Data that was previously attached to the folio. */ static inline void *folio_change_private(struct folio *folio, void *data) { void *old = folio_get_private(folio); folio->private = data; return old; } /** * folio_detach_private - Detach private data from a folio. * @folio: Folio to detach data from. * * Removes the data that was previously attached to the folio and decrements * the refcount on the page. * * Return: Data that was attached to the folio. */ static inline void *folio_detach_private(struct folio *folio) { void *data = folio_get_private(folio); if (!folio_test_private(folio)) return NULL; folio_clear_private(folio); folio->private = NULL; folio_put(folio); return data; } static inline void attach_page_private(struct page *page, void *data) { folio_attach_private(page_folio(page), data); } static inline void *detach_page_private(struct page *page) { return folio_detach_private(page_folio(page)); } #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order); #else static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { return folio_alloc_noprof(gfp, order); } #endif #define filemap_alloc_folio(...) \ alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__)) static inline struct page *__page_cache_alloc(gfp_t gfp) { return &filemap_alloc_folio(gfp, 0)->page; } static inline gfp_t readahead_gfp_mask(struct address_space *x) { return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } typedef int filler_t(struct file *, struct folio *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); /** * typedef fgf_t - Flags for getting folios from the page cache. * * Most users of the page cache will not need to use these flags; * there are convenience functions such as filemap_get_folio() and * filemap_lock_folio(). For users which need more control over exactly * what is done with the folios, these flags to __filemap_get_folio() * are available. * * * %FGP_ACCESSED - The folio will be marked accessed. * * %FGP_LOCK - The folio is returned locked. * * %FGP_CREAT - If no folio is present then a new folio is allocated, * added to the page cache and the VM's LRU list. The folio is * returned locked. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * folio is already in cache. If the folio was allocated, unlock it * before returning so the caller can do the same dance. * * %FGP_WRITE - The folio will be written to by the caller. * * %FGP_NOFS - __GFP_FS will get cleared in gfp. * * %FGP_NOWAIT - Don't block on the folio lock. * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin() * implementation. */ typedef unsigned int __bitwise fgf_t; #define FGP_ACCESSED ((__force fgf_t)0x00000001) #define FGP_LOCK ((__force fgf_t)0x00000002) #define FGP_CREAT ((__force fgf_t)0x00000004) #define FGP_WRITE ((__force fgf_t)0x00000008) #define FGP_NOFS ((__force fgf_t)0x00000010) #define FGP_NOWAIT ((__force fgf_t)0x00000020) #define FGP_FOR_MMAP ((__force fgf_t)0x00000040) #define FGP_STABLE ((__force fgf_t)0x00000080) #define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) /** * fgf_set_order - Encode a length in the fgf_t flags. * @size: The suggested size of the folio to create. * * The caller of __filemap_get_folio() can use this to suggest a preferred * size for the folio that is created. If there is already a folio at * the index, it will be returned, no matter what its size. If a folio * is freshly created, it may be of a different size than requested * due to alignment constraints, memory pressure, or the presence of * other folios at nearby indices. */ static inline fgf_t fgf_set_order(size_t size) { unsigned int shift = ilog2(size); if (shift <= PAGE_SHIFT) return 0; return (__force fgf_t)((shift - PAGE_SHIFT) << 26); } void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp); /** * filemap_get_folio - Find and get a folio. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned with an increased refcount. * * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_get_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, 0, 0); } /** * filemap_lock_folio - Find and lock a folio. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned locked with an increased refcount. * * Context: May sleep. * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_lock_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, FGP_LOCK, 0); } /** * filemap_grab_folio - grab a folio from the page cache * @mapping: The address space to search * @index: The page index * * Looks up the page cache entry at @mapping & @index. If no folio is found, * a new folio is created. The folio is locked, marked as accessed, and * returned. * * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found * and failed to create a folio. */ static inline struct folio *filemap_grab_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mapping_gfp_mask(mapping)); } /** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned with an increased refcount. * * Otherwise, %NULL is returned. */ static inline struct page *find_get_page(struct address_space *mapping, pgoff_t offset) { return pagecache_get_page(mapping, offset, 0, 0); } static inline struct page *find_get_page_flags(struct address_space *mapping, pgoff_t offset, fgf_t fgp_flags) { return pagecache_get_page(mapping, offset, fgp_flags, 0); } /** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search * @index: the page index * * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, it is returned locked and with an increased * refcount. * * Context: May sleep. * Return: A struct page or %NULL if there is no page in the cache for this * index. */ static inline struct page *find_lock_page(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK, 0); } /** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned locked and with an increased * refcount. * * If the page is not present, a new page is allocated using @gfp_mask * and added to the page cache and the VM's LRU list. The page is * returned locked and with an increased refcount. * * On memory exhaustion, %NULL is returned. * * find_or_create_page() may sleep, even if @gfp_flags specifies an * atomic allocation! */ static inline struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_ACCESSED|FGP_CREAT, gfp_mask); } /** * grab_cache_page_nowait - returns locked page at given index in given cache * @mapping: target address_space * @index: the page index * * Same as grab_cache_page(), but do not wait if the page is unavailable. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should * be safe to call while holding the lock for another page. * * Clear __GFP_FS when allocating the page to avoid recursion into the fs * and deadlock against the caller's locked page. */ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, mapping_gfp_mask(mapping)); } extern pgoff_t __folio_swap_cache_index(struct folio *folio); /** * folio_index - File index of a folio. * @folio: The folio. * * For a folio which is either in the page cache or the swap cache, * return its index within the address_space it belongs to. If you know * the page is definitely in the page cache, you can look at the folio's * index directly. * * Return: The index (offset in units of pages) of a folio in its file. */ static inline pgoff_t folio_index(struct folio *folio) { if (unlikely(folio_test_swapcache(folio))) return __folio_swap_cache_index(folio); return folio->index; } /** * folio_next_index - Get the index of the next folio. * @folio: The current folio. * * Return: The index of the folio which follows this folio in the file. */ static inline pgoff_t folio_next_index(struct folio *folio) { return folio->index + folio_nr_pages(folio); } /** * folio_file_page - The page for a particular index. * @folio: The folio which contains this index. * @index: The index we want to look up. * * Sometimes after looking up a folio in the page cache, we need to * obtain the specific page for an index (eg a page fault). * * Return: The page containing the file data for this index. */ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) { return folio_page(folio, index & (folio_nr_pages(folio) - 1)); } /** * folio_contains - Does this folio contain this index? * @folio: The folio. * @index: The page index within the file. * * Context: The caller should have the page locked in order to prevent * (eg) shmem from moving the page between the page cache and swap cache * and changing its index in the middle of the operation. * Return: true or false. */ static inline bool folio_contains(struct folio *folio, pgoff_t index) { return index - folio_index(folio) < folio_nr_pages(folio); } /* * Given the page we found in the page cache, return the page corresponding * to this index in the file */ static inline struct page *find_subpage(struct page *head, pgoff_t index) { /* HugeTLBfs wants the head page regardless */ if (PageHuge(head)) return head; return head + (index & (thp_nr_pages(head) - 1)); } unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index); /* * Returns locked page at given index in given cache, creating it if needed. */ static inline struct page *grab_cache_page(struct address_space *mapping, pgoff_t index) { return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } struct folio *read_cache_folio(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); struct folio *mapping_read_folio_gfp(struct address_space *, pgoff_t index, gfp_t flags); struct page *read_cache_page(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, struct file *file) { return read_cache_page(mapping, index, NULL, file); } static inline struct folio *read_mapping_folio(struct address_space *mapping, pgoff_t index, struct file *file) { return read_cache_folio(mapping, index, NULL, file); } /* * Get the offset in PAGE_SIZE (even for hugetlb pages). */ static inline pgoff_t page_to_pgoff(struct page *page) { struct page *head; if (likely(!PageTransTail(page))) return page->index; head = compound_head(page); /* * We don't initialize ->index for tail pages: calculate based on * head page */ return head->index + page - head; } /* * Return byte-offset into filesystem object for page. */ static inline loff_t page_offset(struct page *page) { return ((loff_t)page->index) << PAGE_SHIFT; } /** * folio_pos - Returns the byte position of this folio in its file. * @folio: The folio. */ static inline loff_t folio_pos(struct folio *folio) { return page_offset(&folio->page); } /* * Get the offset in PAGE_SIZE (even for hugetlb folios). */ static inline pgoff_t folio_pgoff(struct folio *folio) { return folio->index; } static inline pgoff_t linear_page_index(struct vm_area_struct *vma, unsigned long address) { pgoff_t pgoff; pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff; } struct wait_page_key { struct folio *folio; int bit_nr; int page_match; }; struct wait_page_queue { struct folio *folio; int bit_nr; wait_queue_entry_t wait; }; static inline bool wake_page_match(struct wait_page_queue *wait_page, struct wait_page_key *key) { if (wait_page->folio != key->folio) return false; key->page_match = 1; if (wait_page->bit_nr != key->bit_nr) return false; return true; } void __folio_lock(struct folio *folio); int __folio_lock_killable(struct folio *folio); vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf); void unlock_page(struct page *page); void folio_unlock(struct folio *folio); /** * folio_trylock() - Attempt to lock a folio. * @folio: The folio to attempt to lock. * * Sometimes it is undesirable to wait for a folio to be unlocked (eg * when the locks are being taken in the wrong order, or if making * progress through a batch of folios is more important than processing * them in order). Usually folio_lock() is the correct function to call. * * Context: Any context. * Return: Whether the lock was successfully acquired. */ static inline bool folio_trylock(struct folio *folio) { return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); } /* * Return true if the page was successfully locked */ static inline bool trylock_page(struct page *page) { return folio_trylock(page_folio(page)); } /** * folio_lock() - Lock this folio. * @folio: The folio to lock. * * The folio lock protects against many things, probably more than it * should. It is primarily held while a folio is being brought uptodate, * either from its backing file or from swap. It is also held while a * folio is being truncated from its address_space, so holding the lock * is sufficient to keep folio->mapping stable. * * The folio lock is also held while write() is modifying the page to * provide POSIX atomicity guarantees (as long as the write does not * cross a page boundary). Other modifications to the data in the folio * do not hold the folio lock and can race with writes, eg DMA and stores * to mapped pages. * * Context: May sleep. If you need to acquire the locks of two or * more folios, they must be in order of ascending index, if they are * in the same address_space. If they are in different address_spaces, * acquire the lock of the folio which belongs to the address_space which * has the lowest address in memory first. */ static inline void folio_lock(struct folio *folio) { might_sleep(); if (!folio_trylock(folio)) __folio_lock(folio); } /** * lock_page() - Lock the folio containing this page. * @page: The page to lock. * * See folio_lock() for a description of what the lock protects. * This is a legacy function and new code should probably use folio_lock() * instead. * * Context: May sleep. Pages in the same folio share a lock, so do not * attempt to lock two pages which share a folio. */ static inline void lock_page(struct page *page) { struct folio *folio; might_sleep(); folio = page_folio(page); if (!folio_trylock(folio)) __folio_lock(folio); } /** * folio_lock_killable() - Lock this folio, interruptible by a fatal signal. * @folio: The folio to lock. * * Attempts to lock the folio, like folio_lock(), except that the sleep * to acquire the lock is interruptible by a fatal signal. * * Context: May sleep; see folio_lock(). * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received. */ static inline int folio_lock_killable(struct folio *folio) { might_sleep(); if (!folio_trylock(folio)) return __folio_lock_killable(folio); return 0; } /* * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __folio_lock_or_retry(). */ static inline vm_fault_t folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { might_sleep(); if (!folio_trylock(folio)) return __folio_lock_or_retry(folio, vmf); return 0; } /* * This is exported only for folio_wait_locked/folio_wait_writeback, etc., * and should not be used directly. */ void folio_wait_bit(struct folio *folio, int bit_nr); int folio_wait_bit_killable(struct folio *folio, int bit_nr); /* * Wait for a folio to be unlocked. * * This must be called with the caller "holding" the folio, * ie with increased folio reference count so that the folio won't * go away during the wait. */ static inline void folio_wait_locked(struct folio *folio) { if (folio_test_locked(folio)) folio_wait_bit(folio, PG_locked); } static inline int folio_wait_locked_killable(struct folio *folio) { if (!folio_test_locked(folio)) return 0; return folio_wait_bit_killable(folio, PG_locked); } static inline void wait_on_page_locked(struct page *page) { folio_wait_locked(page_folio(page)); } void folio_end_read(struct folio *folio, bool success); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); void end_page_writeback(struct page *page); void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); void folio_wait_stable(struct folio *folio); void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { /* Avoid atomic ops, locking, etc. when not actually needed. */ if (folio_test_dirty(folio)) __folio_cancel_dirty(folio); } bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_MIGRATION int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); #else #define filemap_migrate_folio NULL #endif void folio_end_private_2(struct folio *folio); void folio_wait_private_2(struct folio *folio); int folio_wait_private_2_killable(struct folio *folio); /* * Add an arbitrary waiter to a page's wait queue */ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); /* * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp); void filemap_remove_folio(struct folio *folio); void __filemap_remove_folio(struct folio *folio, void *shadow); void replace_page_cache_folio(struct folio *old, struct folio *new); void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch); bool filemap_release_folio(struct folio *folio, gfp_t gfp); loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, int whence); /* Must be non-static for BPF error injection */ int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp); bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte); /** * filemap_range_needs_writeback - check if range potentially needs writeback * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. Used by O_DIRECT * read/write with IOCB_NOWAIT, to see if the caller needs to do * filemap_write_and_wait_range() before proceeding. * * Return: %true if the caller should do filemap_write_and_wait_range() before * doing O_DIRECT to a page in this range, %false otherwise. */ static inline bool filemap_range_needs_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { if (!mapping->nrpages) return false; if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) return false; return filemap_range_has_writeback(mapping, start_byte, end_byte); } /** * struct readahead_control - Describes a readahead request. * * A readahead request is for consecutive pages. Filesystems which * implement the ->readahead method should call readahead_page() or * readahead_page_batch() in a loop and attempt to start I/O against * each page in the request. * * Most of the fields in this struct are private and should be accessed * by the functions below. * * @file: The file, used primarily by network filesystems for authentication. * May be NULL if invoked internally by the filesystem. * @mapping: Readahead this filesystem object. * @ra: File readahead state. May be NULL. */ struct readahead_control { struct file *file; struct address_space *mapping; struct file_ra_state *ra; /* private: use the readahead_* accessors instead */ pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; bool _workingset; unsigned long _pflags; }; #define DEFINE_READAHEAD(ractl, f, r, m, i) \ struct readahead_control ractl = { \ .file = f, \ .mapping = m, \ .ra = r, \ ._index = i, \ } #define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, unsigned long req_count); void page_cache_async_ra(struct readahead_control *, struct folio *, unsigned long req_count); void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len); /** * page_cache_sync_readahead - generic file readahead * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * * page_cache_sync_readahead() should be called when a cache miss happened: * it will submit the read. The readahead logic may decide to piggyback more * pages onto the read request if access patterns suggest it will improve * performance. */ static inline void page_cache_sync_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); page_cache_sync_ra(&ractl, req_count); } /** * page_cache_async_readahead - file readahead for marked pages * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @folio: The folio which triggered the readahead call. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which * is marked as PageReadahead; this is a marker to suggest that the application * has used up enough of the readahead window that we should start pulling in * more pages. */ static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, struct folio *folio, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index); page_cache_async_ra(&ractl, folio, req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) { struct folio *folio; BUG_ON(ractl->_batch_count > ractl->_nr_pages); ractl->_nr_pages -= ractl->_batch_count; ractl->_index += ractl->_batch_count; if (!ractl->_nr_pages) { ractl->_batch_count = 0; return NULL; } folio = xa_load(&ractl->mapping->i_pages, ractl->_index); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); ractl->_batch_count = folio_nr_pages(folio); return folio; } /** * readahead_page - Get the next page to read. * @ractl: The current readahead request. * * Context: The page is locked and has an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: A pointer to the next page, or %NULL if we are done. */ static inline struct page *readahead_page(struct readahead_control *ractl) { struct folio *folio = __readahead_folio(ractl); return &folio->page; } /** * readahead_folio - Get the next folio to read. * @ractl: The current readahead request. * * Context: The folio is locked. The caller should unlock the folio once * all I/O to that folio has completed. * Return: A pointer to the next folio, or %NULL if we are done. */ static inline struct folio *readahead_folio(struct readahead_control *ractl) { struct folio *folio = __readahead_folio(ractl); if (folio) folio_put(folio); return folio; } static inline unsigned int __readahead_batch(struct readahead_control *rac, struct page **array, unsigned int array_sz) { unsigned int i = 0; XA_STATE(xas, &rac->mapping->i_pages, 0); struct page *page; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; rac->_index += rac->_batch_count; rac->_batch_count = 0; xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { if (xas_retry(&xas, page)) continue; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; rac->_batch_count += thp_nr_pages(page); if (i == array_sz) break; } rcu_read_unlock(); return i; } /** * readahead_page_batch - Get a batch of pages to read. * @rac: The current readahead request. * @array: An array of pointers to struct page. * * Context: The pages are locked and have an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: The number of pages placed in the array. 0 indicates the request * is complete. */ #define readahead_page_batch(rac, array) \ __readahead_batch(rac, array, ARRAY_SIZE(array)) /** * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */ static inline loff_t readahead_pos(struct readahead_control *rac) { return (loff_t)rac->_index * PAGE_SIZE; } /** * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ static inline size_t readahead_length(struct readahead_control *rac) { return rac->_nr_pages * PAGE_SIZE; } /** * readahead_index - The index of the first page in this readahead request. * @rac: The readahead request. */ static inline pgoff_t readahead_index(struct readahead_control *rac) { return rac->_index; } /** * readahead_count - The number of pages in this readahead request. * @rac: The readahead request. */ static inline unsigned int readahead_count(struct readahead_control *rac) { return rac->_nr_pages; } /** * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ static inline size_t readahead_batch_length(struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } static inline unsigned long dir_pages(struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; } /** * folio_mkwrite_check_truncate - check if folio was truncated * @folio: the folio to check * @inode: the inode to check the folio against * * Return: the number of bytes in the folio up to EOF, * or -EFAULT if the folio was truncated. */ static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio, struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; size_t offset = offset_in_folio(folio, size); if (!folio->mapping) return -EFAULT; /* folio is wholly inside EOF */ if (folio_next_index(folio) - 1 < index) return folio_size(folio); /* folio is wholly past EOF */ if (folio->index > index || !offset) return -EFAULT; /* folio is partially inside EOF */ return offset; } /** * page_mkwrite_check_truncate - check if page was truncated * @page: the page to check * @inode: the inode to check the page against * * Returns the number of bytes in the page up to EOF, * or -EFAULT if the page was truncated. */ static inline int page_mkwrite_check_truncate(struct page *page, struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; int offset = offset_in_page(size); if (page->mapping != inode->i_mapping) return -EFAULT; /* page is wholly inside EOF */ if (page->index < index) return PAGE_SIZE; /* page is wholly past EOF */ if (page->index > index || !offset) return -EFAULT; /* page is partially inside EOF */ return offset; } /** * i_blocks_per_folio - How many blocks fit in this folio. * @inode: The inode which contains the blocks. * @folio: The folio. * * If the block size is larger than the size of this folio, return zero. * * Context: The caller should hold a refcount on the folio to prevent it * from being split. * Return: The number of filesystem blocks covered by this folio. */ static inline unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio) { return folio_size(folio) >> inode->i_blkbits; } #endif /* _LINUX_PAGEMAP_H */ |
| 198 198 198 198 198 198 139 139 7 7 7 198 198 198 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.c - library routines for handling generic kernel objects * * Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2006-2007 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2007 Novell Inc. * * Please see the file Documentation/core-api/kobject.rst for critical information * about using the kobject interface. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/random.h> /** * kobject_namespace() - Return @kobj's namespace tag. * @kobj: kobject in question * * Returns namespace tag of @kobj if its parent has namespace ops enabled * and thus @kobj should have a namespace tag associated with it. Returns * %NULL otherwise. */ const void *kobject_namespace(const struct kobject *kobj) { const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj); if (!ns_ops || ns_ops->type == KOBJ_NS_TYPE_NONE) return NULL; return kobj->ktype->namespace(kobj); } /** * kobject_get_ownership() - Get sysfs ownership data for @kobj. * @kobj: kobject in question * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns initial uid/gid pair that should be used when creating sysfs * representation of given kobject. Normally used to adjust ownership of * objects in a container. */ void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; if (kobj->ktype->get_ownership) kobj->ktype->get_ownership(kobj, uid, gid); } static bool kobj_ns_type_is_valid(enum kobj_ns_type type) { if ((type <= KOBJ_NS_TYPE_NONE) || (type >= KOBJ_NS_TYPES)) return false; return true; } static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); const struct kobj_ns_type_operations *ops; int error; error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj)); if (error) return error; if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { sysfs_remove_dir(kobj); return error; } } /* * @kobj->sd may be deleted by an ancestor going away. Hold an * extra reference so that it stays until @kobj is gone. */ sysfs_get(kobj->sd); /* * If @kobj has ns_ops, its children need to be filtered based on * their namespace tags. Enable namespace support on @kobj->sd. */ ops = kobj_child_ns_ops(kobj); if (ops) { BUG_ON(!kobj_ns_type_is_valid(ops->type)); BUG_ON(!kobj_ns_type_registered(ops->type)); sysfs_enable_ns(kobj->sd); } return 0; } static int get_kobj_path_length(const struct kobject *kobj) { int length = 1; const struct kobject *parent = kobj; /* walk up the ancestors until we hit the one pointing to the * root. * Add 1 to strlen for leading '/' of each level. */ do { if (kobject_name(parent) == NULL) return 0; length += strlen(kobject_name(parent)) + 1; parent = parent->parent; } while (parent); return length; } static int fill_kobj_path(const struct kobject *kobj, char *path, int length) { const struct kobject *parent; --length; for (parent = kobj; parent; parent = parent->parent) { int cur = strlen(kobject_name(parent)); /* back up enough to print this name with '/' */ length -= cur; if (length <= 0) return -EINVAL; memcpy(path + length, kobject_name(parent), cur); *(path + --length) = '/'; } pr_debug("'%s' (%p): %s: path = '%s'\n", kobject_name(kobj), kobj, __func__, path); return 0; } /** * kobject_get_path() - Allocate memory and fill in the path for @kobj. * @kobj: kobject in question, with which to build the path * @gfp_mask: the allocation type used to allocate the path * * Return: The newly allocated memory, caller must free with kfree(). */ char *kobject_get_path(const struct kobject *kobj, gfp_t gfp_mask) { char *path; int len; retry: len = get_kobj_path_length(kobj); if (len == 0) return NULL; path = kzalloc(len, gfp_mask); if (!path) return NULL; if (fill_kobj_path(kobj, path, len)) { kfree(path); goto retry; } return path; } EXPORT_SYMBOL_GPL(kobject_get_path); /* add the kobject to its kset's list */ static void kobj_kset_join(struct kobject *kobj) { if (!kobj->kset) return; kset_get(kobj->kset); spin_lock(&kobj->kset->list_lock); list_add_tail(&kobj->entry, &kobj->kset->list); spin_unlock(&kobj->kset->list_lock); } /* remove the kobject from its kset's list */ static void kobj_kset_leave(struct kobject *kobj) { if (!kobj->kset) return; spin_lock(&kobj->kset->list_lock); list_del_init(&kobj->entry); spin_unlock(&kobj->kset->list_lock); kset_put(kobj->kset); } static void kobject_init_internal(struct kobject *kobj) { if (!kobj) return; kref_init(&kobj->kref); INIT_LIST_HEAD(&kobj->entry); kobj->state_in_sysfs = 0; kobj->state_add_uevent_sent = 0; kobj->state_remove_uevent_sent = 0; kobj->state_initialized = 1; } static int kobject_add_internal(struct kobject *kobj) { int error = 0; struct kobject *parent; if (!kobj) return -ENOENT; if (!kobj->name || !kobj->name[0]) { WARN(1, "kobject: (%p): attempted to be registered with empty name!\n", kobj); return -EINVAL; } parent = kobject_get(kobj->parent); /* join kset if set, use it as parent if we do not already have one */ if (kobj->kset) { if (!parent) parent = kobject_get(&kobj->kset->kobj); kobj_kset_join(kobj); kobj->parent = parent; } pr_debug("'%s' (%p): %s: parent: '%s', set: '%s'\n", kobject_name(kobj), kobj, __func__, parent ? kobject_name(parent) : "<NULL>", kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>"); error = create_dir(kobj); if (error) { kobj_kset_leave(kobj); kobject_put(parent); kobj->parent = NULL; /* be noisy on error issues */ if (error == -EEXIST) pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n", __func__, kobject_name(kobj)); else pr_err("%s failed for %s (error: %d parent: %s)\n", __func__, kobject_name(kobj), error, parent ? kobject_name(parent) : "'none'"); } else kobj->state_in_sysfs = 1; return error; } /** * kobject_set_name_vargs() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * @vargs: vargs to format the string. */ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { const char *s; if (kobj->name && !fmt) return 0; s = kvasprintf_const(GFP_KERNEL, fmt, vargs); if (!s) return -ENOMEM; /* * ewww... some of these buggers have '/' in the name ... If * that's the case, we need to make sure we have an actual * allocated copy to modify, since kvasprintf_const may have * returned something from .rodata. */ if (strchr(s, '/')) { char *t; t = kstrdup(s, GFP_KERNEL); kfree_const(s); if (!t) return -ENOMEM; s = strreplace(t, '/', '!'); } kfree_const(kobj->name); kobj->name = s; return 0; } /** * kobject_set_name() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * * This sets the name of the kobject. If you have already added the * kobject to the system, you must call kobject_rename() in order to * change the name of the kobject. */ int kobject_set_name(struct kobject *kobj, const char *fmt, ...) { va_list vargs; int retval; va_start(vargs, fmt); retval = kobject_set_name_vargs(kobj, fmt, vargs); va_end(vargs); return retval; } EXPORT_SYMBOL(kobject_set_name); /** * kobject_init() - Initialize a kobject structure. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * * This function will properly initialize a kobject such that it can then * be passed to the kobject_add() call. * * After this function is called, the kobject MUST be cleaned up by a call * to kobject_put(), not by a call to kfree directly to ensure that all of * the memory is cleaned up properly. */ void kobject_init(struct kobject *kobj, const struct kobj_type *ktype) { char *err_str; if (!kobj) { err_str = "invalid kobject pointer!"; goto error; } if (!ktype) { err_str = "must have a ktype to be initialized properly!\n"; goto error; } if (kobj->state_initialized) { /* do not error out as sometimes we can recover */ pr_err("kobject (%p): tried to init an initialized object, something is seriously wrong.\n", kobj); dump_stack_lvl(KERN_ERR); } kobject_init_internal(kobj); kobj->ktype = ktype; return; error: pr_err("kobject (%p): %s\n", kobj, err_str); dump_stack_lvl(KERN_ERR); } EXPORT_SYMBOL(kobject_init); static __printf(3, 0) int kobject_add_varg(struct kobject *kobj, struct kobject *parent, const char *fmt, va_list vargs) { int retval; retval = kobject_set_name_vargs(kobj, fmt, vargs); if (retval) { pr_err("can not set name properly!\n"); return retval; } kobj->parent = parent; return kobject_add_internal(kobj); } /** * kobject_add() - The main kobject add function. * @kobj: the kobject to add * @parent: pointer to the parent of the kobject. * @fmt: format to name the kobject with. * * The kobject name is set and added to the kobject hierarchy in this * function. * * If @parent is set, then the parent of the @kobj will be set to it. * If @parent is NULL, then the parent of the @kobj will be set to the * kobject associated with the kset assigned to this kobject. If no kset * is assigned to the kobject, then the kobject will be located in the * root of the sysfs tree. * * Note, no "add" uevent will be created with this call, the caller should set * up all of the necessary sysfs files for the object and then call * kobject_uevent() with the UEVENT_ADD parameter to ensure that * userspace is properly notified of this kobject's creation. * * Return: If this function returns an error, kobject_put() must be * called to properly clean up the memory associated with the * object. Under no instance should the kobject that is passed * to this function be directly freed with a call to kfree(), * that can leak memory. * * If this function returns success, kobject_put() must also be called * in order to properly clean up the memory associated with the object. * * In short, once this function is called, kobject_put() MUST be called * when the use of the object is finished in order to properly free * everything. */ int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; if (!kobj) return -EINVAL; if (!kobj->state_initialized) { pr_err("kobject '%s' (%p): tried to add an uninitialized object, something is seriously wrong.\n", kobject_name(kobj), kobj); dump_stack_lvl(KERN_ERR); return -EINVAL; } va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL(kobject_add); /** * kobject_init_and_add() - Initialize a kobject structure and add it to * the kobject hierarchy. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * @parent: pointer to the parent of this kobject. * @fmt: the name of the kobject. * * This function combines the call to kobject_init() and kobject_add(). * * If this function returns an error, kobject_put() must be called to * properly clean up the memory associated with the object. This is the * same type of error handling after a call to kobject_add() and kobject * lifetime rules are the same here. */ int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; kobject_init(kobj, ktype); va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL_GPL(kobject_init_and_add); /** * kobject_rename() - Change the name of an object. * @kobj: object in question. * @new_name: object's new name * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of kobject_rename * on the same kobject and to ensure that new_name is valid and * won't conflict with other kobjects. */ int kobject_rename(struct kobject *kobj, const char *new_name) { int error = 0; const char *devpath = NULL; const char *dup_name = NULL, *name; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; if (!kobj->parent) { kobject_put(kobj); return -EINVAL; } devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; name = dup_name = kstrdup_const(new_name, GFP_KERNEL); if (!name) { error = -ENOMEM; goto out; } error = sysfs_rename_dir_ns(kobj, new_name, kobject_namespace(kobj)); if (error) goto out; /* Install the new kobject name */ dup_name = kobj->name; kobj->name = name; /* This function is mostly/only used for network interface. * Some hotplug package track interfaces by their name and * therefore want to know when the name is changed by the user. */ kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kfree_const(dup_name); kfree(devpath_string); kfree(devpath); kobject_put(kobj); return error; } EXPORT_SYMBOL_GPL(kobject_rename); /** * kobject_move() - Move object to another parent. * @kobj: object in question. * @new_parent: object's new parent (can be NULL) */ int kobject_move(struct kobject *kobj, struct kobject *new_parent) { int error; struct kobject *old_parent; const char *devpath = NULL; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; new_parent = kobject_get(new_parent); if (!new_parent) { if (kobj->kset) new_parent = kobject_get(&kobj->kset->kobj); } /* old object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; error = sysfs_move_dir_ns(kobj, new_parent, kobject_namespace(kobj)); if (error) goto out; old_parent = kobj->parent; kobj->parent = new_parent; new_parent = NULL; kobject_put(old_parent); kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kobject_put(new_parent); kobject_put(kobj); kfree(devpath_string); kfree(devpath); return error; } EXPORT_SYMBOL_GPL(kobject_move); static void __kobject_del(struct kobject *kobj) { struct kernfs_node *sd; const struct kobj_type *ktype; sd = kobj->sd; ktype = get_ktype(kobj); if (ktype) sysfs_remove_groups(kobj, ktype->default_groups); /* send "remove" if the caller did not do it but sent "add" */ if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) { pr_debug("'%s' (%p): auto cleanup 'remove' event\n", kobject_name(kobj), kobj); kobject_uevent(kobj, KOBJ_REMOVE); } sysfs_remove_dir(kobj); sysfs_put(sd); kobj->state_in_sysfs = 0; kobj_kset_leave(kobj); kobj->parent = NULL; } /** * kobject_del() - Unlink kobject from hierarchy. * @kobj: object. * * This is the function that should be called to delete an object * successfully added via kobject_add(). */ void kobject_del(struct kobject *kobj) { struct kobject *parent; if (!kobj) return; parent = kobj->parent; __kobject_del(kobj); kobject_put(parent); } EXPORT_SYMBOL(kobject_del); /** * kobject_get() - Increment refcount for object. * @kobj: object. */ struct kobject *kobject_get(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_get() is being called.\n", kobject_name(kobj), kobj); kref_get(&kobj->kref); } return kobj; } EXPORT_SYMBOL(kobject_get); struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj) { if (!kobj) return NULL; if (!kref_get_unless_zero(&kobj->kref)) kobj = NULL; return kobj; } EXPORT_SYMBOL(kobject_get_unless_zero); /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup */ static void kobject_cleanup(struct kobject *kobj) { struct kobject *parent = kobj->parent; const struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; pr_debug("'%s' (%p): %s, parent %p\n", kobject_name(kobj), kobj, __func__, kobj->parent); if (t && !t->release) pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", kobject_name(kobj), kobj); /* remove from sysfs if the caller did not do it */ if (kobj->state_in_sysfs) { pr_debug("'%s' (%p): auto cleanup kobject_del\n", kobject_name(kobj), kobj); __kobject_del(kobj); } else { /* avoid dropping the parent reference unnecessarily */ parent = NULL; } if (t && t->release) { pr_debug("'%s' (%p): calling ktype release\n", kobject_name(kobj), kobj); t->release(kobj); } /* free name if we allocated it */ if (name) { pr_debug("'%s': free name\n", name); kfree_const(name); } kobject_put(parent); } #ifdef CONFIG_DEBUG_KOBJECT_RELEASE static void kobject_delayed_cleanup(struct work_struct *work) { kobject_cleanup(container_of(to_delayed_work(work), struct kobject, release)); } #endif static void kobject_release(struct kref *kref) { struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE unsigned long delay = HZ + HZ * get_random_u32_below(4); pr_info("'%s' (%p): %s, parent %p (delayed %ld)\n", kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); schedule_delayed_work(&kobj->release, delay); #else kobject_cleanup(kobj); #endif } /** * kobject_put() - Decrement refcount for object. * @kobj: object. * * Decrement the refcount, and if 0, call kobject_cleanup(). */ void kobject_put(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_put() is being called.\n", kobject_name(kobj), kobj); kref_put(&kobj->kref, kobject_release); } } EXPORT_SYMBOL(kobject_put); static void dynamic_kobj_release(struct kobject *kobj) { pr_debug("(%p): %s\n", kobj, __func__); kfree(kobj); } static const struct kobj_type dynamic_kobj_ktype = { .release = dynamic_kobj_release, .sysfs_ops = &kobj_sysfs_ops, }; /** * kobject_create() - Create a struct kobject dynamically. * * This function creates a kobject structure dynamically and sets it up * to be a "dynamic" kobject with a default release function set up. * * If the kobject was not able to be created, NULL will be returned. * The kobject structure returned from here must be cleaned up with a * call to kobject_put() and not kfree(), as kobject_init() has * already been called on this structure. */ static struct kobject *kobject_create(void) { struct kobject *kobj; kobj = kzalloc(sizeof(*kobj), GFP_KERNEL); if (!kobj) return NULL; kobject_init(kobj, &dynamic_kobj_ktype); return kobj; } /** * kobject_create_and_add() - Create a struct kobject dynamically and * register it with sysfs. * @name: the name for the kobject * @parent: the parent kobject of this kobject, if any. * * This function creates a kobject structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kobject_put() and the structure will be dynamically freed when * it is no longer being used. * * If the kobject was not able to be created, NULL will be returned. */ struct kobject *kobject_create_and_add(const char *name, struct kobject *parent) { struct kobject *kobj; int retval; kobj = kobject_create(); if (!kobj) return NULL; retval = kobject_add(kobj, parent, "%s", name); if (retval) { pr_warn("%s: kobject_add error: %d\n", __func__, retval); kobject_put(kobj); kobj = NULL; } return kobj; } EXPORT_SYMBOL_GPL(kobject_create_and_add); /** * kset_init() - Initialize a kset for use. * @k: kset */ void kset_init(struct kset *k) { kobject_init_internal(&k->kobj); INIT_LIST_HEAD(&k->list); spin_lock_init(&k->list_lock); } /* default kobject attribute operations */ static ssize_t kobj_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->show) ret = kattr->show(kobj, kattr, buf); return ret; } static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->store) ret = kattr->store(kobj, kattr, buf, count); return ret; } const struct sysfs_ops kobj_sysfs_ops = { .show = kobj_attr_show, .store = kobj_attr_store, }; EXPORT_SYMBOL_GPL(kobj_sysfs_ops); /** * kset_register() - Initialize and add a kset. * @k: kset. * * NOTE: On error, the kset.kobj.name allocated by() kobj_set_name() * is freed, it can not be used any more. */ int kset_register(struct kset *k) { int err; if (!k) return -EINVAL; if (!k->kobj.ktype) { pr_err("must have a ktype to be initialized properly!\n"); return -EINVAL; } kset_init(k); err = kobject_add_internal(&k->kobj); if (err) { kfree_const(k->kobj.name); /* Set it to NULL to avoid accessing bad pointer in callers. */ k->kobj.name = NULL; return err; } kobject_uevent(&k->kobj, KOBJ_ADD); return 0; } EXPORT_SYMBOL(kset_register); /** * kset_unregister() - Remove a kset. * @k: kset. */ void kset_unregister(struct kset *k) { if (!k) return; kobject_del(&k->kobj); kobject_put(&k->kobj); } EXPORT_SYMBOL(kset_unregister); /** * kset_find_obj() - Search for object in kset. * @kset: kset we're looking in. * @name: object's name. * * Lock kset via @kset->subsys, and iterate over @kset->list, * looking for a matching kobject. If matching object is found * take a reference and return the object. */ struct kobject *kset_find_obj(struct kset *kset, const char *name) { struct kobject *k; struct kobject *ret = NULL; spin_lock(&kset->list_lock); list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { ret = kobject_get_unless_zero(k); break; } } spin_unlock(&kset->list_lock); return ret; } EXPORT_SYMBOL_GPL(kset_find_obj); static void kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); pr_debug("'%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); kfree(kset); } static void kset_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { if (kobj->parent) kobject_get_ownership(kobj->parent, uid, gid); } static const struct kobj_type kset_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = kset_release, .get_ownership = kset_get_ownership, }; /** * kset_create() - Create a struct kset dynamically. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically. This structure can * then be registered with the system and show up in sysfs with a call to * kset_register(). When you are finished with this structure, if * kset_register() has been called, call kset_unregister() and the * structure will be dynamically freed when it is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ static struct kset *kset_create(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int retval; kset = kzalloc(sizeof(*kset), GFP_KERNEL); if (!kset) return NULL; retval = kobject_set_name(&kset->kobj, "%s", name); if (retval) { kfree(kset); return NULL; } kset->uevent_ops = uevent_ops; kset->kobj.parent = parent_kobj; /* * The kobject of this kset will have a type of kset_ktype and belong to * no kset itself. That way we can properly free it when it is * finished being used. */ kset->kobj.ktype = &kset_ktype; kset->kobj.kset = NULL; return kset; } /** * kset_create_and_add() - Create a struct kset dynamically and add it to sysfs. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kset_unregister() and the structure will be dynamically freed when it * is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ struct kset *kset_create_and_add(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int error; kset = kset_create(name, uevent_ops, parent_kobj); if (!kset) return NULL; error = kset_register(kset); if (error) { kfree(kset); return NULL; } return kset; } EXPORT_SYMBOL_GPL(kset_create_and_add); static DEFINE_SPINLOCK(kobj_ns_type_lock); static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES]; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops) { enum kobj_ns_type type = ops->type; int error; spin_lock(&kobj_ns_type_lock); error = -EINVAL; if (!kobj_ns_type_is_valid(type)) goto out; error = -EBUSY; if (kobj_ns_ops_tbl[type]) goto out; error = 0; kobj_ns_ops_tbl[type] = ops; out: spin_unlock(&kobj_ns_type_lock); return error; } int kobj_ns_type_registered(enum kobj_ns_type type) { int registered = 0; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type)) registered = kobj_ns_ops_tbl[type] != NULL; spin_unlock(&kobj_ns_type_lock); return registered; } const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *parent) { const struct kobj_ns_type_operations *ops = NULL; if (parent && parent->ktype && parent->ktype->child_ns_type) ops = parent->ktype->child_ns_type(parent); return ops; } const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj) { return kobj_child_ns_ops(kobj->parent); } bool kobj_ns_current_may_mount(enum kobj_ns_type type) { bool may_mount = true; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) may_mount = kobj_ns_ops_tbl[type]->current_may_mount(); spin_unlock(&kobj_ns_type_lock); return may_mount; } void *kobj_ns_grab_current(enum kobj_ns_type type) { void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->grab_current_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk) { const void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->netlink_ns(sk); spin_unlock(&kobj_ns_type_lock); return ns; } const void *kobj_ns_initial(enum kobj_ns_type type) { const void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->initial_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } void kobj_ns_drop(enum kobj_ns_type type, void *ns) { spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns) kobj_ns_ops_tbl[type]->drop_ns(ns); spin_unlock(&kobj_ns_type_lock); } EXPORT_SYMBOL_GPL(kobj_ns_drop); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2014-2015, The Linux Foundation. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM clk #if !defined(_TRACE_CLK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CLK_H #include <linux/tracepoint.h> struct clk_core; DECLARE_EVENT_CLASS(clk, TP_PROTO(struct clk_core *core), TP_ARGS(core), TP_STRUCT__entry( __string( name, core->name ) ), TP_fast_assign( __assign_str(name); ), TP_printk("%s", __get_str(name)) ); DEFINE_EVENT(clk, clk_enable, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_enable_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_disable, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_disable_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_prepare, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_prepare_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_unprepare, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_unprepare_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DECLARE_EVENT_CLASS(clk_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate), TP_STRUCT__entry( __string( name, core->name ) __field(unsigned long, rate ) ), TP_fast_assign( __assign_str(name); __entry->rate = rate; ), TP_printk("%s %lu", __get_str(name), (unsigned long)__entry->rate) ); DEFINE_EVENT(clk_rate, clk_set_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_rate_complete, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_min_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_max_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DECLARE_EVENT_CLASS(clk_rate_range, TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max), TP_ARGS(core, min, max), TP_STRUCT__entry( __string( name, core->name ) __field(unsigned long, min ) __field(unsigned long, max ) ), TP_fast_assign( __assign_str(name); __entry->min = min; __entry->max = max; ), TP_printk("%s min %lu max %lu", __get_str(name), (unsigned long)__entry->min, (unsigned long)__entry->max) ); DEFINE_EVENT(clk_rate_range, clk_set_rate_range, TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max), TP_ARGS(core, min, max) ); DECLARE_EVENT_CLASS(clk_parent, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent), TP_STRUCT__entry( __string( name, core->name ) __string( pname, parent ? parent->name : "none" ) ), TP_fast_assign( __assign_str(name); __assign_str(pname); ), TP_printk("%s %s", __get_str(name), __get_str(pname)) ); DEFINE_EVENT(clk_parent, clk_set_parent, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent) ); DEFINE_EVENT(clk_parent, clk_set_parent_complete, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent) ); DECLARE_EVENT_CLASS(clk_phase, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase), TP_STRUCT__entry( __string( name, core->name ) __field( int, phase ) ), TP_fast_assign( __assign_str(name); __entry->phase = phase; ), TP_printk("%s %d", __get_str(name), (int)__entry->phase) ); DEFINE_EVENT(clk_phase, clk_set_phase, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase) ); DEFINE_EVENT(clk_phase, clk_set_phase_complete, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase) ); DECLARE_EVENT_CLASS(clk_duty_cycle, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty), TP_STRUCT__entry( __string( name, core->name ) __field( unsigned int, num ) __field( unsigned int, den ) ), TP_fast_assign( __assign_str(name); __entry->num = duty->num; __entry->den = duty->den; ), TP_printk("%s %u/%u", __get_str(name), (unsigned int)__entry->num, (unsigned int)__entry->den) ); DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty) ); DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle_complete, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty) ); DECLARE_EVENT_CLASS(clk_rate_request, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req), TP_STRUCT__entry( __string( name, req->core ? req->core->name : "none") __string( pname, req->best_parent_hw ? clk_hw_get_name(req->best_parent_hw) : "none" ) __field(unsigned long, min ) __field(unsigned long, max ) __field(unsigned long, prate ) ), TP_fast_assign( __assign_str(name); __assign_str(pname); __entry->min = req->min_rate; __entry->max = req->max_rate; __entry->prate = req->best_parent_rate; ), TP_printk("%s min %lu max %lu, parent %s (%lu)", __get_str(name), (unsigned long)__entry->min, (unsigned long)__entry->max, __get_str(pname), (unsigned long)__entry->prate) ); DEFINE_EVENT(clk_rate_request, clk_rate_request_start, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req) ); DEFINE_EVENT(clk_rate_request, clk_rate_request_done, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req) ); #endif /* _TRACE_CLK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 86 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Parameters used to convert the timespec values: */ #define PSEC_PER_NSEC 1000L /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) #define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow / underflow */ if (ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; if (ts->tv_sec <= KTIME_SEC_MIN) return KTIME_MIN; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */ |
| 23 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filemap #if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILEMAP_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <linux/device.h> #include <linux/kdev_t.h> #include <linux/errseq.h> DECLARE_EVENT_CLASS(mm_filemap_op_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(unsigned long, pfn) __field(unsigned long, i_ino) __field(unsigned long, index) __field(dev_t, s_dev) __field(unsigned char, order) ), TP_fast_assign( __entry->pfn = folio_pfn(folio); __entry->i_ino = folio->mapping->host->i_ino; __entry->index = folio->index; if (folio->mapping->host->i_sb) __entry->s_dev = folio->mapping->host->i_sb->s_dev; else __entry->s_dev = folio->mapping->host->i_rdev; __entry->order = folio_order(folio); ), TP_printk("dev %d:%d ino %lx pfn=0x%lx ofs=%lu order=%u", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->pfn, __entry->index << PAGE_SHIFT, __entry->order) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio) ); DECLARE_EVENT_CLASS(mm_filemap_op_page_cache_range, TP_PROTO( struct address_space *mapping, pgoff_t index, pgoff_t last_index ), TP_ARGS(mapping, index, last_index), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(unsigned long, index) __field(unsigned long, last_index) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; __entry->index = index; __entry->last_index = last_index; ), TP_printk( "dev=%d:%d ino=%lx ofs=%lld-%lld", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, ((loff_t)__entry->index) << PAGE_SHIFT, ((((loff_t)__entry->last_index + 1) << PAGE_SHIFT) - 1) ) ); DEFINE_EVENT(mm_filemap_op_page_cache_range, mm_filemap_get_pages, TP_PROTO( struct address_space *mapping, pgoff_t index, pgoff_t last_index ), TP_ARGS(mapping, index, last_index) ); DEFINE_EVENT(mm_filemap_op_page_cache_range, mm_filemap_map_pages, TP_PROTO( struct address_space *mapping, pgoff_t index, pgoff_t last_index ), TP_ARGS(mapping, index, last_index) ); TRACE_EVENT(mm_filemap_fault, TP_PROTO(struct address_space *mapping, pgoff_t index), TP_ARGS(mapping, index), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(unsigned long, index) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; __entry->index = index; ), TP_printk( "dev=%d:%d ino=%lx ofs=%lld", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, ((loff_t)__entry->index) << PAGE_SHIFT ) ); TRACE_EVENT(filemap_set_wb_err, TP_PROTO(struct address_space *mapping, errseq_t eseq), TP_ARGS(mapping, eseq), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, errseq) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; __entry->errseq = eseq; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; ), TP_printk("dev=%d:%d ino=0x%lx errseq=0x%x", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->errseq) ); TRACE_EVENT(file_check_and_advance_wb_err, TP_PROTO(struct file *file, errseq_t old), TP_ARGS(file, old), TP_STRUCT__entry( __field(struct file *, file) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, old) __field(errseq_t, new) ), TP_fast_assign( __entry->file = file; __entry->i_ino = file->f_mapping->host->i_ino; if (file->f_mapping->host->i_sb) __entry->s_dev = file->f_mapping->host->i_sb->s_dev; else __entry->s_dev = file->f_mapping->host->i_rdev; __entry->old = old; __entry->new = file->f_wb_err; ), TP_printk("file=%p dev=%d:%d ino=0x%lx old=0x%x new=0x%x", __entry->file, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->old, __entry->new) ); #endif /* _TRACE_FILEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 256 260 156 288 207 36 41 17 52 54 195 22 221 311 311 278 63 217 238 271 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> (C) 2002 David Woodhouse <dwmw2@infradead.org> (C) 2012 Michel Lespinasse <walken@google.com> linux/include/linux/rbtree_augmented.h */ #ifndef _LINUX_RBTREE_AUGMENTED_H #define _LINUX_RBTREE_AUGMENTED_H #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> /* * Please note - only struct rb_augment_callbacks and the prototypes for * rb_insert_augmented() and rb_erase_augmented() are intended to be public. * The rest are implementation details you are not expected to depend on. * * See Documentation/core-api/rbtree.rst for documentation and samples. */ struct rb_augment_callbacks { void (*propagate)(struct rb_node *node, struct rb_node *stop); void (*copy)(struct rb_node *old, struct rb_node *new); void (*rotate)(struct rb_node *old, struct rb_node *new); }; extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and * rb_insert_augmented() instead of the usual rb_insert_color() call. * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { __rb_insert_augmented(node, root, augment->rotate); } static inline void rb_insert_augmented_cached(struct rb_node *node, struct rb_root_cached *root, bool newleft, const struct rb_augment_callbacks *augment) { if (newleft) root->rb_leftmost = node; rb_insert_augmented(node, &root->rb_root, augment); } static __always_inline struct rb_node * rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *), const struct rb_augment_callbacks *augment) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); augment->propagate(parent, NULL); /* suboptimal */ rb_insert_augmented_cached(node, tree, leftmost, augment); return leftmost ? node : NULL; } /* * Template for declaring augmented rbtree callbacks (generic case) * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data */ #define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ if (RBCOMPUTE(node, true)) \ break; \ rb = rb_parent(&node->RBFIELD); \ } \ } \ static inline void \ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ RBCOMPUTE(old, false); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .propagate = RBNAME ## _propagate, \ .copy = RBNAME ## _copy, \ .rotate = RBNAME ## _rotate \ }; /* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBTYPE: type of the RBAUGMENTED field * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar */ #define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ RBTYPE, RBAUGMENTED, RBCOMPUTE) \ static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ { \ RBSTRUCT *child; \ RBTYPE max = RBCOMPUTE(node); \ if (node->RBFIELD.rb_left) { \ child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (node->RBFIELD.rb_right) { \ child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (exit && node->RBAUGMENTED == max) \ return true; \ node->RBAUGMENTED = max; \ return false; \ } \ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) #define RB_RED 0 #define RB_BLACK 1 #define __rb_parent(pc) ((struct rb_node *)(pc & ~3)) #define __rb_color(pc) ((pc) & 1) #define __rb_is_black(pc) __rb_color(pc) #define __rb_is_red(pc) (!__rb_color(pc)) #define rb_color(rb) __rb_color((rb)->__rb_parent_color) #define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color) #define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color) static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { rb->__rb_parent_color = (unsigned long)p + color; } static inline void __rb_change_child(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) WRITE_ONCE(parent->rb_left, new); else WRITE_ONCE(parent->rb_right, new); } else WRITE_ONCE(root->rb_node, new); } static inline void __rb_change_child_rcu(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) rcu_assign_pointer(parent->rb_left, new); else rcu_assign_pointer(parent->rb_right, new); } else rcu_assign_pointer(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) * * Note that if there is one child it must be red due to 5) * and node must be black due to 4). We adjust colors locally * so as to bypass __rb_erase_color() later on. */ pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, child, parent, root); if (child) { child->__rb_parent_color = pc; rebalance = NULL; } else rebalance = __rb_is_black(pc) ? parent : NULL; tmp = parent; } else if (!child) { /* Still case 1, but this time the child is node->rb_left */ tmp->__rb_parent_color = pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, tmp, parent, root); rebalance = NULL; tmp = parent; } else { struct rb_node *successor = child, *child2; tmp = child->rb_left; if (!tmp) { /* * Case 2: node's successor is its right child * * (n) (s) * / \ / \ * (x) (s) -> (x) (c) * \ * (c) */ parent = successor; child2 = successor->rb_right; augment->copy(node, successor); } else { /* * Case 3: node's successor is leftmost under * node's right child subtree * * (n) (s) * / \ / \ * (x) (y) -> (x) (y) * / / * (p) (p) * / / * (s) (c) * \ * (c) */ do { parent = successor; successor = tmp; tmp = tmp->rb_left; } while (tmp); child2 = successor->rb_right; WRITE_ONCE(parent->rb_left, child2); WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); augment->copy(node, successor); augment->propagate(parent, successor); } tmp = node->rb_left; WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); if (child2) { rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { rebalance = rb_is_black(successor) ? parent : NULL; } successor->__rb_parent_color = pc; tmp = successor; } augment->propagate(tmp, NULL); return rebalance; } static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } static __always_inline void rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, const struct rb_augment_callbacks *augment) { if (root->rb_leftmost == node) root->rb_leftmost = rb_next(node); rb_erase_augmented(node, &root->rb_root, augment); } #endif /* _LINUX_RBTREE_AUGMENTED_H */ |
| 9 9 9 9 82 20 63 9 9 9 86 2 85 86 48 82 81 2 71 22 82 82 82 81 82 48 48 61 84 27 116 114 124 124 124 124 44 81 127 127 57 54 3 51 48 123 127 125 127 6 124 124 124 86 123 81 63 20 82 127 27 8 27 8 27 8 20 8 27 27 196 195 105 195 195 196 145 61 196 7 8 27 27 9 9 7 4 23 18 21 9 9 9 9 8 23 23 3 23 23 9 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/memfd.h> #include <linux/memremap.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/secretmem.h> #include <linux/sched/signal.h> #include <linux/rwsem.h> #include <linux/hugetlb.h> #include <linux/migrate.h> #include <linux/mm_inline.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <linux/shmem_fs.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include "internal.h" struct follow_page_context { struct dev_pagemap *pgmap; unsigned int page_mask; }; static inline void sanity_check_pinned_pages(struct page **pages, unsigned long npages) { if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; /* * We only pin anonymous pages if they are exclusive. Once pinned, we * can no longer turn them possibly shared and PageAnonExclusive() will * stick around until the page is freed. * * We'd like to verify that our pinned anonymous pages are still mapped * exclusively. The issue with anon THP is that we don't know how * they are/were mapped when pinning them. However, for anon * THP we can assume that either the given page (PTE-mapped THP) or * the head page (PMD-mapped THP) should be PageAnonExclusive(). If * neither is the case, there is certainly something wrong. */ for (; npages; npages--, pages++) { struct page *page = *pages; struct folio *folio = page_folio(page); if (is_zero_page(page) || !folio_test_anon(folio)) continue; if (!folio_test_large(folio) || folio_test_hugetlb(folio)) VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); else /* Either a PTE-mapped or a PMD-mapped THP. */ VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) && !PageAnonExclusive(page), page); } } /* * Return the folio with ref appropriately incremented, * or NULL if that failed. */ static inline struct folio *try_get_folio(struct page *page, int refs) { struct folio *folio; retry: folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) < 0)) return NULL; if (unlikely(!folio_ref_try_add(folio, refs))) return NULL; /* * At this point we have a stable reference to the folio; but it * could be that between calling page_folio() and the refcount * increment, the folio was split, in which case we'd end up * holding a reference on a folio that has nothing to do with the page * we were given anymore. * So now that the folio is stable, recheck that the page still * belongs to this folio. */ if (unlikely(page_folio(page) != folio)) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); goto retry; } return folio; } static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { if (is_zero_folio(folio)) return; node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) atomic_sub(refs, &folio->_pincount); else refs *= GUP_PIN_COUNTING_BIAS; } if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); } /** * try_grab_folio() - add a folio's refcount by a flag-dependent amount * @folio: pointer to folio to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values * * This might not do anything at all, depending on the flags argument. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same * time. * * Return: 0 for success, or if no action was required (if neither FOLL_PIN * nor FOLL_GET was set, nothing is done). A negative error code for failure: * * -ENOMEM FOLL_GET or FOLL_PIN was set, but the folio could not * be grabbed. * * It is called when we have a stable reference for the folio, typically in * GUP slow path. */ int __must_check try_grab_folio(struct folio *folio, int refs, unsigned int flags) { if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page))) return -EREMOTEIO; if (flags & FOLL_GET) folio_ref_add(folio, refs); else if (flags & FOLL_PIN) { /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_folio(folio)) return 0; /* * Increment the normal page refcount field at least once, * so that the page really is pinned. */ if (folio_test_large(folio)) { folio_ref_add(folio, refs); atomic_add(refs, &folio->_pincount); } else { folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS); } node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); } return 0; } /** * unpin_user_page() - release a dma-pinned page * @page: pointer to page to be released * * Pages that were pinned via pin_user_pages*() must be released via either * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so * that such pages can be separately tracked and uniquely handled. In * particular, interactions with RDMA and filesystems need special handling. */ void unpin_user_page(struct page *page) { sanity_check_pinned_pages(&page, 1); gup_put_folio(page_folio(page), 1, FOLL_PIN); } EXPORT_SYMBOL(unpin_user_page); /** * unpin_folio() - release a dma-pinned folio * @folio: pointer to folio to be released * * Folios that were pinned via memfd_pin_folios() or other similar routines * must be released either using unpin_folio() or unpin_folios(). */ void unpin_folio(struct folio *folio) { gup_put_folio(folio, 1, FOLL_PIN); } EXPORT_SYMBOL_GPL(unpin_folio); /** * folio_add_pin - Try to get an additional pin on a pinned folio * @folio: The folio to be pinned * * Get an additional pin on a folio we already have a pin on. Makes no change * if the folio is a zero_page. */ void folio_add_pin(struct folio *folio) { if (is_zero_folio(folio)) return; /* * Similar to try_grab_folio(): be sure to *also* increment the normal * page refcount field at least once, so that the page really is * pinned. */ if (folio_test_large(folio)) { WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1); folio_ref_inc(folio); atomic_inc(&folio->_pincount); } else { WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS); folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); } } static inline struct folio *gup_folio_range_next(struct page *start, unsigned long npages, unsigned long i, unsigned int *ntails) { struct page *next = nth_page(start, i); struct folio *folio = page_folio(next); unsigned int nr = 1; if (folio_test_large(folio)) nr = min_t(unsigned int, npages - i, folio_nr_pages(folio) - folio_page_idx(folio, next)); *ntails = nr; return folio; } static inline struct folio *gup_folio_next(struct page **list, unsigned long npages, unsigned long i, unsigned int *ntails) { struct folio *folio = page_folio(list[i]); unsigned int nr; for (nr = i + 1; nr < npages; nr++) { if (page_folio(list[nr]) != folio) break; } *ntails = nr - i; return folio; } /** * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages * @pages: array of pages to be maybe marked dirty, and definitely released. * @npages: number of pages in the @pages array. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page" refers to a page that has had one of the get_user_pages() * variants called on that page. * * For each page in the @pages array, make that page (or its head page, if a * compound page) dirty, if @make_dirty is true, and if the page was previously * listed as clean. In any case, releases all pages using unpin_user_page(), * possibly via unpin_user_pages(), for the non-dirty case. * * Please see the unpin_user_page() documentation for details. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; if (!make_dirty) { unpin_user_pages(pages, npages); return; } sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); /* * Checking PageDirty at this point may race with * clear_page_dirty_for_io(), but that's OK. Two key * cases: * * 1) This code sees the page as already dirty, so it * skips the call to set_page_dirty(). That could happen * because clear_page_dirty_for_io() called * folio_mkclean(), followed by set_page_dirty(). * However, now the page is going to get written back, * which meets the original intention of setting it * dirty, so all is well: clear_page_dirty_for_io() goes * on to call TestClearPageDirty(), and write the page * back. * * 2) This code sees the page as clean, so it calls * set_page_dirty(). The page stays dirty, despite being * written back, so it gets written back again in the * next writeback cycle. This is harmless. */ if (!folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages_dirty_lock); /** * unpin_user_page_range_dirty_lock() - release and optionally dirty * gup-pinned page range * * @page: the starting page of a range maybe marked dirty, and definitely released. * @npages: number of consecutive pages to release. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page range" refers to a range of pages that has had one of the * pin_user_pages() variants called on that page. * * For the page ranges defined by [page .. page+npages], make that range (or * its head pages, if a compound page) dirty, if @make_dirty is true, and if the * page range was previously listed as clean. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; for (i = 0; i < npages; i += nr) { folio = gup_folio_range_next(page, npages, i, &nr); if (make_dirty && !folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_page_range_dirty_lock); static void gup_fast_unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * Don't perform any sanity checks because we might have raced with * fork() and some anonymous pages might now actually be shared -- * which is why we're unpinning after all. */ for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } /** * unpin_user_pages() - release an array of gup-pinned pages. * @pages: array of pages to be marked dirty and released. * @npages: number of pages in the @pages array. * * For each page in the @pages array, release the page using unpin_user_page(). * * Please see the unpin_user_page() documentation for details. */ void unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * If this WARN_ON() fires, then the system *might* be leaking pages (by * leaving them pinned), but probably not. More likely, gup/pup returned * a hard -ERRNO error to the caller, who erroneously passed it here. */ if (WARN_ON(IS_ERR_VALUE(npages))) return; sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages); /** * unpin_user_folio() - release pages of a folio * @folio: pointer to folio to be released * @npages: number of pages of same folio * * Release npages of the folio */ void unpin_user_folio(struct folio *folio, unsigned long npages) { gup_put_folio(folio, npages, FOLL_PIN); } EXPORT_SYMBOL(unpin_user_folio); /** * unpin_folios() - release an array of gup-pinned folios. * @folios: array of folios to be marked dirty and released. * @nfolios: number of folios in the @folios array. * * For each folio in the @folios array, release the folio using gup_put_folio. * * Please see the unpin_folio() documentation for details. */ void unpin_folios(struct folio **folios, unsigned long nfolios) { unsigned long i = 0, j; /* * If this WARN_ON() fires, then the system *might* be leaking folios * (by leaving them pinned), but probably not. More likely, gup/pup * returned a hard -ERRNO error to the caller, who erroneously passed * it here. */ if (WARN_ON(IS_ERR_VALUE(nfolios))) return; while (i < nfolios) { for (j = i + 1; j < nfolios; j++) if (folios[i] != folios[j]) break; if (folios[i]) gup_put_folio(folios[i], j - i, FOLL_PIN); i = j; } } EXPORT_SYMBOL_GPL(unpin_folios); /* * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's * lifecycle. Avoid setting the bit unless necessary, or it might cause write * cache bouncing on large SMP machines for concurrent pinned gups. */ static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) { if (!test_bit(MMF_HAS_PINNED, mm_flags)) set_bit(MMF_HAS_PINNED, mm_flags); } #ifdef CONFIG_MMU #ifdef CONFIG_HAVE_GUP_FAST static int record_subpages(struct page *page, unsigned long sz, unsigned long addr, unsigned long end, struct page **pages) { struct page *start_page; int nr; start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT); for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) pages[nr] = nth_page(start_page, nr); return nr; } /** * try_grab_folio_fast() - Attempt to get or pin a folio in fast path. * @page: pointer to page to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the * same time. (That's true throughout the get_user_pages*() and * pin_user_pages*() APIs.) Cases: * * FOLL_GET: folio's refcount will be incremented by @refs. * * FOLL_PIN on large folios: folio's refcount will be incremented by * @refs, and its pincount will be incremented by @refs. * * FOLL_PIN on single-page folios: folio's refcount will be incremented by * @refs * GUP_PIN_COUNTING_BIAS. * * Return: The folio containing @page (with refcount appropriately * incremented) for success, or NULL upon failure. If neither FOLL_GET * nor FOLL_PIN was set, that's considered failure, and furthermore, * a likely bug in the caller, so a warning is also emitted. * * It uses add ref unless zero to elevate the folio refcount and must be called * in fast path only. */ static struct folio *try_grab_folio_fast(struct page *page, int refs, unsigned int flags) { struct folio *folio; /* Raise warn if it is not called in fast GUP */ VM_WARN_ON_ONCE(!irqs_disabled()); if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) return NULL; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return NULL; if (flags & FOLL_GET) return try_get_folio(page, refs); /* FOLL_PIN is set */ /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_page(page)) return page_folio(page); folio = try_get_folio(page, refs); if (!folio) return NULL; /* * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a * right zone, so fail and let the caller fall back to the slow * path. */ if (unlikely((flags & FOLL_LONGTERM) && !folio_is_longterm_pinnable(folio))) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); return NULL; } /* * When pinning a large folio, use an exact count to track it. * * However, be sure to *also* increment the normal folio * refcount field at least once, so that the folio really * is pinned. That's why the refcount from the earlier * try_get_folio() is left intact. */ if (folio_test_large(folio)) atomic_add(refs, &folio->_pincount); else folio_ref_add(folio, refs * (GUP_PIN_COUNTING_BIAS - 1)); /* * Adjust the pincount before re-checking the PTE for changes. * This is essentially a smp_mb() and is paired with a memory * barrier in folio_try_share_anon_rmap_*(). */ smp_mb__after_atomic(); node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); return folio; } #endif /* CONFIG_HAVE_GUP_FAST */ static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags, unsigned long address) { if (!(flags & FOLL_DUMP)) return NULL; /* * When core dumping, we don't want to allocate unnecessary pages or * page tables. Return error instead of NULL to skip handle_mm_fault, * then get_dump_page() will return NULL to leave a hole in the dump. * But we can only make this optimization where a hole would surely * be zero-filled if handle_mm_fault() actually did handle it. */ if (is_vm_hugetlb_page(vma)) { struct hstate *h = hstate_vma(vma); if (!hugetlbfs_pagecache_present(h, vma, address)) return ERR_PTR(-EFAULT); } else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) { return ERR_PTR(-EFAULT); } return NULL; } #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; struct page *page; pud_t pud = *pudp; unsigned long pfn = pud_pfn(pud); int ret; assert_spin_locked(pud_lockptr(mm, pudp)); if ((flags & FOLL_WRITE) && !pud_write(pud)) return NULL; if (!pud_present(pud)) return NULL; pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && pud_devmap(pud)) { /* * device mapped pages can only be returned if the caller * will manage the page reference count. * * At least one of FOLL_GET | FOLL_PIN must be set, so * assert that here: */ if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST); if (flags & FOLL_TOUCH) touch_pud(vma, addr, pudp, flags & FOLL_WRITE); ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap); if (!ctx->pgmap) return ERR_PTR(-EFAULT); } page = pfn_to_page(pfn); if (!pud_devmap(pud) && !pud_write(pud) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); ret = try_grab_folio(page_folio(page), 1, flags); if (ret) page = ERR_PTR(ret); else ctx->page_mask = HPAGE_PUD_NR - 1; return page; } /* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pmd is writable, we can write to the page. */ if (pmd_write(pmd)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (pmd_needs_soft_dirty_wp(vma, pmd)) return false; return !userfaultfd_huge_pmd_wp(vma, pmd); } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; pmd_t pmdval = *pmd; struct page *page; int ret; assert_spin_locked(pmd_lockptr(mm, pmd)); page = pmd_page(pmdval); if ((flags & FOLL_WRITE) && !can_follow_write_pmd(pmdval, page, vma, flags)) return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval)) return ERR_PTR(-EFAULT); if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) return NULL; if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); ret = try_grab_folio(page_folio(page), 1, flags); if (ret) return ERR_PTR(ret); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH)) touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; ctx->page_mask = HPAGE_PMD_NR - 1; return page; } #else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { return NULL; } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { return NULL; } #endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, pte_t *pte, unsigned int flags) { if (flags & FOLL_TOUCH) { pte_t orig_entry = ptep_get(pte); pte_t entry = orig_entry; if (flags & FOLL_WRITE) entry = pte_mkdirty(entry); entry = pte_mkyoung(entry); if (!pte_same(orig_entry, entry)) { set_pte_at(vma->vm_mm, address, pte, entry); update_mmu_cache(vma, address, pte); } } /* Proper page table entry exists, but no corresponding struct page */ return -EEXIST; } /* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ static inline bool can_follow_write_pte(pte_t pte, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pte is writable, we can write to the page. */ if (pte_write(pte)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (pte_needs_soft_dirty_wp(vma, pte)) return false; return !userfaultfd_pte_wp(vma, pte); } static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags, struct dev_pagemap **pgmap) { struct mm_struct *mm = vma->vm_mm; struct folio *folio; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; int ret; /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) return no_page_table(vma, flags, address); pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags)) goto no_page; page = vm_normal_page(vma, address, pte); /* * We only care about anon pages in can_follow_write_pte() and don't * have to worry about pte_devmap() because they are never anon. */ if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, page, vma, flags)) { page = NULL; goto out; } if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN * case since they are only valid while holding the pgmap * reference. */ *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); if (*pgmap) page = pte_page(pte); else goto no_page; } else if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */ page = ERR_PTR(-EFAULT); goto out; } if (is_zero_pfn(pte_pfn(pte))) { page = pte_page(pte); } else { ret = follow_pfn_pte(vma, address, ptep, flags); page = ERR_PTR(ret); goto out; } } folio = page_folio(page); if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) { page = ERR_PTR(-EMLINK); goto out; } VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); /* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */ ret = try_grab_folio(folio, 1, flags); if (unlikely(ret)) { page = ERR_PTR(ret); goto out; } /* * We need to make the page accessible if and only if we are going * to access its content (the FOLL_PIN case). Please see * Documentation/core-api/pin_user_pages.rst for details. */ if (flags & FOLL_PIN) { ret = arch_make_folio_accessible(folio); if (ret) { unpin_user_page(page); page = ERR_PTR(ret); goto out; } } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) set_page_dirty(page); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use * mark_page_accessed(). */ mark_page_accessed(page); } out: pte_unmap_unlock(ptep, ptl); return page; no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; return no_page_table(vma, flags, address); } static struct page *follow_pmd_mask(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, unsigned int flags, struct follow_page_context *ctx) { pmd_t *pmd, pmdval; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pmd = pmd_offset(pudp, address); pmdval = pmdp_get_lockless(pmd); if (pmd_none(pmdval)) return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) return no_page_table(vma, flags, address); if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (likely(!pmd_leaf(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) return no_page_table(vma, flags, address); ptl = pmd_lock(mm, pmd); pmdval = *pmd; if (unlikely(!pmd_present(pmdval))) { spin_unlock(ptl); return no_page_table(vma, flags, address); } if (unlikely(!pmd_leaf(pmdval))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) { spin_unlock(ptl); split_huge_pmd(vma, pmd, address); /* If pmd was left empty, stuff a page table in there quickly */ return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) : follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } page = follow_huge_pmd(vma, address, pmd, flags, ctx); spin_unlock(ptl); return page; } static struct page *follow_pud_mask(struct vm_area_struct *vma, unsigned long address, p4d_t *p4dp, unsigned int flags, struct follow_page_context *ctx) { pud_t *pudp, pud; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pudp = pud_offset(p4dp, address); pud = READ_ONCE(*pudp); if (!pud_present(pud)) return no_page_table(vma, flags, address); if (pud_leaf(pud)) { ptl = pud_lock(mm, pudp); page = follow_huge_pud(vma, address, pudp, flags, ctx); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (unlikely(pud_bad(pud))) return no_page_table(vma, flags, address); return follow_pmd_mask(vma, address, pudp, flags, ctx); } static struct page *follow_p4d_mask(struct vm_area_struct *vma, unsigned long address, pgd_t *pgdp, unsigned int flags, struct follow_page_context *ctx) { p4d_t *p4dp, p4d; p4dp = p4d_offset(pgdp, address); p4d = READ_ONCE(*p4dp); BUILD_BUG_ON(p4d_leaf(p4d)); if (!p4d_present(p4d) || p4d_bad(p4d)) return no_page_table(vma, flags, address); return follow_pud_mask(vma, address, p4dp, flags, ctx); } /** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a * pointer to output page_mask * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches * the device's dev_pagemap metadata to avoid repeating expensive lookups. * * When getting an anonymous page and the caller has to trigger unsharing * of a shared anonymous page first, -EMLINK is returned. The caller should * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only * relevant with FOLL_PIN and !FOLL_WRITE. * * On output, the @ctx->page_mask is set according to the size of the page. * * Return: the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ static struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct follow_page_context *ctx) { pgd_t *pgd; struct mm_struct *mm = vma->vm_mm; struct page *page; vma_pgtable_walk_begin(vma); ctx->page_mask = 0; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) page = no_page_table(vma, flags, address); else page = follow_p4d_mask(vma, address, pgd, flags, ctx); vma_pgtable_walk_end(vma); return page; } static int get_gate_page(struct mm_struct *mm, unsigned long address, unsigned int gup_flags, struct vm_area_struct **vma, struct page **page) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; pte_t entry; int ret = -EFAULT; /* user gate pages are read-only */ if (gup_flags & FOLL_WRITE) return -EFAULT; if (address > TASK_SIZE) pgd = pgd_offset_k(address); else pgd = pgd_offset_gate(mm, address); if (pgd_none(*pgd)) return -EFAULT; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return -EFAULT; pud = pud_offset(p4d, address); if (pud_none(*pud)) return -EFAULT; pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return -EFAULT; pte = pte_offset_map(pmd, address); if (!pte) return -EFAULT; entry = ptep_get(pte); if (pte_none(entry)) goto unmap; *vma = get_gate_vma(mm); if (!page) goto out; *page = vm_normal_page(*vma, address, entry); if (!*page) { if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(entry))) goto unmap; *page = pte_page(entry); } ret = try_grab_folio(page_folio(*page), 1, gup_flags); if (unlikely(ret)) goto unmap; out: ret = 0; unmap: pte_unmap(pte); return ret; } /* * mmap_lock must be held on entry. If @flags has FOLL_UNLOCKABLE but not * FOLL_NOWAIT, the mmap_lock may be released. If it is, *@locked will be set * to 0 and -EBUSY returned. */ static int faultin_page(struct vm_area_struct *vma, unsigned long address, unsigned int flags, bool unshare, int *locked) { unsigned int fault_flags = 0; vm_fault_t ret; if (flags & FOLL_NOFAULT) return -EFAULT; if (flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (flags & FOLL_REMOTE) fault_flags |= FAULT_FLAG_REMOTE; if (flags & FOLL_UNLOCKABLE) { fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set * FOLL_INTERRUPTIBLE to enable FAULT_FLAG_INTERRUPTIBLE. * That's because some callers may not be prepared to * handle early exits caused by non-fatal signals. */ if (flags & FOLL_INTERRUPTIBLE) fault_flags |= FAULT_FLAG_INTERRUPTIBLE; } if (flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (flags & FOLL_TRIED) { /* * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED * can co-exist */ fault_flags |= FAULT_FLAG_TRIED; } if (unshare) { fault_flags |= FAULT_FLAG_UNSHARE; /* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */ VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE); } ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * With FAULT_FLAG_RETRY_NOWAIT we'll never release the * mmap lock in the page fault handler. Sanity check this. */ WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); *locked = 0; /* * We should do the same as VM_FAULT_RETRY, but let's not * return -EBUSY since that's not reflecting the reality of * what has happened - we've just fully completed a page * fault, with the mmap lock released. Use -EAGAIN to show * that we want to take the mmap lock _again_. */ return -EAGAIN; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, flags); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { if (!(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; return -EBUSY; } return 0; } /* * Writing to file-backed mappings which require folio dirty tracking using GUP * is a fundamentally broken operation, as kernel write access to GUP mappings * do not adhere to the semantics expected by a file system. * * Consider the following scenario:- * * 1. A folio is written to via GUP which write-faults the memory, notifying * the file system and dirtying the folio. * 2. Later, writeback is triggered, resulting in the folio being cleaned and * the PTE being marked read-only. * 3. The GUP caller writes to the folio, as it is mapped read/write via the * direct mapping. * 4. The GUP caller, now done with the page, unpins it and sets it dirty * (though it does not have to). * * This results in both data being written to a folio without writenotify, and * the folio being dirtied unexpectedly (if the caller decides to do so). */ static bool writable_file_mapping_allowed(struct vm_area_struct *vma, unsigned long gup_flags) { /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the case we disallow. */ if ((gup_flags & (FOLL_PIN | FOLL_LONGTERM)) != (FOLL_PIN | FOLL_LONGTERM)) return true; /* * If the VMA does not require dirty tracking then no problematic write * can occur either. */ return !vma_needs_dirty_tracking(vma); } static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) { vm_flags_t vm_flags = vma->vm_flags; int write = (gup_flags & FOLL_WRITE); int foreign = (gup_flags & FOLL_REMOTE); bool vma_anon = vma_is_anonymous(vma); if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT; if ((gup_flags & FOLL_ANON) && !vma_anon) return -EFAULT; if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma)) return -EOPNOTSUPP; if (vma_is_secretmem(vma)) return -EFAULT; if (write) { if (!vma_anon && !writable_file_mapping_allowed(vma, gup_flags)) return -EFAULT; if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */ if (is_vm_hugetlb_page(vma)) return -EFAULT; /* * We used to let the write,force case do COW in a * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could * set a breakpoint in a read-only mapping of an * executable, without corrupting the file (yet only * when that file had been opened for writing!). * Anon pages in shared mappings are surprising: now * just reject it. */ if (!is_cow_mapping(vm_flags)) return -EFAULT; } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* * Is there actually any vma we can reach here which does not * have VM_MAYREAD set? */ if (!(vm_flags & VM_MAYREAD)) return -EFAULT; } /* * gups are always data accesses, not instruction * fetches, so execute=false here */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return -EFAULT; return 0; } /* * This is "vma_lookup()", but with a warning if we would have * historically expanded the stack in the GUP code. */ static struct vm_area_struct *gup_vma_lookup(struct mm_struct *mm, unsigned long addr) { #ifdef CONFIG_STACK_GROWSUP return vma_lookup(mm, addr); #else static volatile unsigned long next_warn; struct vm_area_struct *vma; unsigned long now, next; vma = find_vma(mm, addr); if (!vma || (addr >= vma->vm_start)) return vma; /* Only warn for half-way relevant accesses */ if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; if (vma->vm_start - addr > 65536) return NULL; /* Let's not warn more than once an hour.. */ now = jiffies; next = next_warn; if (next && time_before(now, next)) return NULL; next_warn = now + 60*60*HZ; /* Let people know things may have changed. */ pr_warn("GUP no longer grows the stack in %s (%d): %lx-%lx (%lx)\n", current->comm, task_pid_nr(current), vma->vm_start, vma->vm_end, addr); dump_stack(); return NULL; #endif } /** * __get_user_pages() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: whether we're still with the mmap_lock held * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * -- 0 return value is possible when the fault would need to be retried. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held. It may be released. See below. * * __get_user_pages walks a process's page tables and takes a reference to * each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * __get_user_pages returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If * the page is written to, set_page_dirty (or set_page_dirty_lock, as * appropriate) must be called after the page is finished with, and * before put_page is called. * * If FOLL_UNLOCKABLE is set without FOLL_NOWAIT then the mmap_lock may * be released. If this happens *@locked will be set to 0 on return. * * A caller using such a combination of @gup_flags must therefore hold the * mmap_lock for reading only, and recognize when it's been released. Otherwise, * it must be held for either reading or writing and will not be released. * * In most cases, get_user_pages or get_user_pages_fast should be used * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags. */ static long __get_user_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { long ret = 0, i = 0; struct vm_area_struct *vma = NULL; struct follow_page_context ctx = { NULL }; if (!nr_pages) return 0; start = untagged_addr_remote(mm, start); VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN))); do { struct page *page; unsigned int page_increm; /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { /* * MADV_POPULATE_(READ|WRITE) wants to handle VMA * lookups+error reporting differently. */ if (gup_flags & FOLL_MADV_POPULATE) { vma = vma_lookup(mm, start); if (!vma) { ret = -ENOMEM; goto out; } if (check_vma_flags(vma, gup_flags)) { ret = -EINVAL; goto out; } goto retry; } vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, gup_flags, &vma, pages ? &page : NULL); if (ret) goto out; ctx.page_mask = 0; goto next_page; } if (!vma) { ret = -EFAULT; goto out; } ret = check_vma_flags(vma, gup_flags); if (ret) goto out; } retry: /* * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory. */ if (fatal_signal_pending(current)) { ret = -EINTR; goto out; } cond_resched(); page = follow_page_mask(vma, start, gup_flags, &ctx); if (!page || PTR_ERR(page) == -EMLINK) { ret = faultin_page(vma, start, gup_flags, PTR_ERR(page) == -EMLINK, locked); switch (ret) { case 0: goto retry; case -EBUSY: case -EAGAIN: ret = 0; fallthrough; case -EFAULT: case -ENOMEM: case -EHWPOISON: goto out; } BUG(); } else if (PTR_ERR(page) == -EEXIST) { /* * Proper page table entry exists, but no corresponding * struct page. If the caller expects **pages to be * filled in, bail out now, because that can't be done * for this page. */ if (pages) { ret = PTR_ERR(page); goto out; } } else if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } next_page: page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); if (page_increm > nr_pages) page_increm = nr_pages; if (pages) { struct page *subpage; unsigned int j; /* * This must be a large folio (and doesn't need to * be the whole folio; it can be part of it), do * the refcount work for all the subpages too. * * NOTE: here the page may not be the head page * e.g. when start addr is not thp-size aligned. * try_grab_folio() should have taken care of tail * pages. */ if (page_increm > 1) { struct folio *folio = page_folio(page); /* * Since we already hold refcount on the * large folio, this should never fail. */ if (try_grab_folio(folio, page_increm - 1, gup_flags)) { /* * Release the 1st page ref if the * folio is problematic, fail hard. */ gup_put_folio(folio, 1, gup_flags); ret = -EFAULT; goto out; } } for (j = 0; j < page_increm; j++) { subpage = nth_page(page, j); pages[i + j] = subpage; flush_anon_page(vma, subpage, start + j * PAGE_SIZE); flush_dcache_page(subpage); } } i += page_increm; start += page_increm * PAGE_SIZE; nr_pages -= page_increm; } while (nr_pages); out: if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); return i ? i : ret; } static bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags) { bool write = !!(fault_flags & FAULT_FLAG_WRITE); bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE); vm_flags_t vm_flags = write ? VM_WRITE : VM_READ; if (!(vm_flags & vma->vm_flags)) return false; /* * The architecture might have a hardware protection * mechanism other than read/write that can deny access. * * gup always represents data access, not instruction * fetches, so execute=false here: */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return false; return true; } /** * fixup_user_fault() - manually resolve a user page fault * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() * @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller * does not allow retry. If NULL, the caller must guarantee * that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY. * * This is meant to be called in the specific scenario where for locking reasons * we try to access user memory in atomic context (within a pagefault_disable() * section), this returns -EFAULT, and we want to resolve the user fault before * trying again. * * Typically this is meant to be used by the futex code. * * The main difference with get_user_pages() is that this function will * unconditionally call handle_mm_fault() which will in turn perform all the * necessary SW fixup of the dirty and young bits in the PTE, while * get_user_pages() only guarantees to update these in the struct page. * * This is important for some architectures where those bits also gate the * access permission to the page because they are maintained in software. On * such architectures, gup() will not be enough to make a subsequent access * succeed. * * This function will not return with an unlocked mmap_lock. So it has not the * same semantics wrt the @mm->mmap_lock as does filemap_fault(). */ int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { struct vm_area_struct *vma; vm_fault_t ret; address = untagged_addr_remote(mm, address); if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; retry: vma = gup_vma_lookup(mm, address); if (!vma) return -EFAULT; if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; if ((fault_flags & FAULT_FLAG_KILLABLE) && fatal_signal_pending(current)) return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * NOTE: it's a pity that we need to retake the lock here * to pair with the unlock() in the callers. Ideally we * could tell the callers so they do not need to unlock. */ mmap_read_lock(mm); *unlocked = true; return 0; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { mmap_read_lock(mm); *unlocked = true; fault_flags |= FAULT_FLAG_TRIED; goto retry; } return 0; } EXPORT_SYMBOL_GPL(fixup_user_fault); /* * GUP always responds to fatal signals. When FOLL_INTERRUPTIBLE is * specified, it'll also respond to generic signals. The caller of GUP * that has FOLL_INTERRUPTIBLE should take care of the GUP interruption. */ static bool gup_signal_pending(unsigned int flags) { if (fatal_signal_pending(current)) return true; if (!(flags & FOLL_INTERRUPTIBLE)) return false; return signal_pending(current); } /* * Locking: (*locked == 1) means that the mmap_lock has already been acquired by * the caller. This function may drop the mmap_lock. If it does so, then it will * set (*locked = 0). * * (*locked == 0) means that the caller expects this function to acquire and * drop the mmap_lock. Therefore, the value of *locked will still be zero when * the function returns, even though it may have changed temporarily during * function execution. * * Please note that this function, unlike __get_user_pages(), will not return 0 * for nr_pages > 0, unless FOLL_NOWAIT is used. */ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int flags) { long ret, pages_done; bool must_unlock = false; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } else mmap_assert_locked(mm); if (flags & FOLL_PIN) mm_set_has_pinned_flag(&mm->flags); /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior * is to set FOLL_GET if the caller wants pages[] filled in (but has * carelessly failed to specify FOLL_GET), so keep doing that, but only * for FOLL_GET, not for the newer FOLL_PIN. * * FOLL_PIN always expects pages to be non-null, but no need to assert * that here, as any failures will be obvious enough. */ if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET; pages_done = 0; for (;;) { ret = __get_user_pages(mm, start, nr_pages, flags, pages, locked); if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */ pages_done = ret; break; } /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); } if (ret > 0) { nr_pages -= ret; pages_done += ret; if (!nr_pages) break; } if (*locked) { /* * VM_FAULT_RETRY didn't trigger or it was a * FOLL_NOWAIT. */ if (!pages_done) pages_done = ret; break; } /* * VM_FAULT_RETRY triggered, so seek to the faulting offset. * For the prefault case (!pages) we only update counts. */ if (likely(pages)) pages += ret; start += ret << PAGE_SHIFT; /* The lock was temporarily dropped, so we must unlock later */ must_unlock = true; retry: /* * Repeat on the address that fired VM_FAULT_RETRY * with both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_TRIED. Note that GUP can be interrupted * by fatal signals of even common signals, depending on * the caller's request. So we need to check it before we * start trying again otherwise it can loop forever. */ if (gup_signal_pending(flags)) { if (!pages_done) pages_done = -EINTR; break; } ret = mmap_read_lock_killable(mm); if (ret) { BUG_ON(ret > 0); if (!pages_done) pages_done = ret; break; } *locked = 1; ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, pages, locked); if (!*locked) { /* Continue to retry until we succeeded */ BUG_ON(ret != 0); goto retry; } if (ret != 1) { BUG_ON(ret > 1); if (!pages_done) pages_done = ret; break; } nr_pages--; pages_done++; if (!nr_pages) break; if (likely(pages)) pages++; start += PAGE_SIZE; } if (must_unlock && *locked) { /* * We either temporarily dropped the lock, or the caller * requested that we both acquire and drop the lock. Either way, * we must now unlock, and notify the caller of that state. */ mmap_read_unlock(mm); *locked = 0; } /* * Failing to pin anything implies something has gone wrong (except when * FOLL_NOWAIT is specified). */ if (WARN_ON_ONCE(pages_done == 0 && !(flags & FOLL_NOWAIT))) return -EFAULT; return pages_done; } /** * populate_vma_page_range() - populate a range of pages in the vma. * @vma: target vma * @start: start address * @end: end address * @locked: whether the mmap_lock is still held * * This takes care of mlocking the pages too if VM_LOCKED is set. * * Return either number of pages pinned in the vma, or a negative error * code on error. * * vma->vm_mm->mmap_lock must be held. * * If @locked is NULL, it may be held for read or write and will * be unperturbed. * * If @locked is non-NULL, it must held for read only and may be * released. If it's released, *@locked will be set to 0. */ long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked) { struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int local_locked = 1; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); VM_BUG_ON_VMA(start < vma->vm_start, vma); VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* * Rightly or wrongly, the VM_LOCKONFAULT case has never used * faultin_page() to break COW, so it has no work to do here. */ if (vma->vm_flags & VM_LOCKONFAULT) return nr_pages; /* ... similarly, we've never faulted in PROT_NONE pages */ if (!vma_is_accessible(vma)) return -EFAULT; gup_flags = FOLL_TOUCH; /* * We want to touch writable mappings with a write fault in order * to break COW, except for shared mappings because these don't COW * and we would not want to dirty them for nothing. * * Otherwise, do a read fault, and use FOLL_FORCE in case it's not * readable (ie write-only or executable). */ if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) gup_flags |= FOLL_WRITE; else gup_flags |= FOLL_FORCE; if (locked) gup_flags |= FOLL_UNLOCKABLE; /* * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, locked ? locked : &local_locked); lru_add_drain(); return ret; } /* * faultin_page_range() - populate (prefault) page tables inside the * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * * Returns either number of processed pages in the MM, or a negative error * code on error (see __get_user_pages()). Note that this function reports * errors related to VMAs, such as incompatible mappings, as expected by * MADV_POPULATE_(READ|WRITE). * * The range must be page-aligned. * * mm->mmap_lock must be held. If it's released, *@locked will be set to 0. */ long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked) { unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); mmap_assert_locked(mm); /* * FOLL_TOUCH: Mark page accessed and thereby young; will also mark * the page dirty with FOLL_WRITE -- which doesn't make a * difference with !FOLL_FORCE, because the page is writable * in the page table. * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE | FOLL_MADV_POPULATE; if (write) gup_flags |= FOLL_WRITE; ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked, gup_flags); lru_add_drain(); return ret; } /* * __mm_populate - populate and/or mlock pages within a range of address space. * * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap * flags. VMAs must be already marked with the desired vm_flags, and * mmap_lock must not be held. */ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) { struct mm_struct *mm = current->mm; unsigned long end, nstart, nend; struct vm_area_struct *vma = NULL; int locked = 0; long ret = 0; end = start + len; for (nstart = start; nstart < end; nstart = nend) { /* * We want to fault in pages for [nstart; end) address range. * Find first corresponding VMA. */ if (!locked) { locked = 1; mmap_read_lock(mm); vma = find_vma_intersection(mm, nstart, end); } else if (nstart >= vma->vm_end) vma = find_vma_intersection(mm, vma->vm_end, end); if (!vma) break; /* * Set [nstart; nend) to intersection of desired address * range with the first VMA. Also, skip undesirable VMA types. */ nend = min(end, vma->vm_end); if (vma->vm_flags & (VM_IO | VM_PFNMAP)) continue; if (nstart < vma->vm_start) nstart = vma->vm_start; /* * Now fault in a range of pages. populate_vma_page_range() * double checks the vma flags, so that it won't mlock pages * if the vma was already munlocked. */ ret = populate_vma_page_range(vma, nstart, nend, &locked); if (ret < 0) { if (ignore_errors) { ret = 0; continue; /* continue at next VMA */ } break; } nend = nstart + ret * PAGE_SIZE; ret = 0; } if (locked) mmap_read_unlock(mm); return ret; /* 0 or negative error code */ } #else /* CONFIG_MMU */ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int foll_flags) { struct vm_area_struct *vma; bool must_unlock = false; unsigned long vm_flags; long i; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } /* calculate required read or write permissions. * If FOLL_FORCE is set, we only require the "MAY" flags. */ vm_flags = (foll_flags & FOLL_WRITE) ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); vm_flags &= (foll_flags & FOLL_FORCE) ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); for (i = 0; i < nr_pages; i++) { vma = find_vma(mm, start); if (!vma) break; /* protect what we can, including chardevs */ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) || !(vm_flags & vma->vm_flags)) break; if (pages) { pages[i] = virt_to_page((void *)start); if (pages[i]) get_page(pages[i]); } start = (start + PAGE_SIZE) & PAGE_MASK; } if (must_unlock && *locked) { mmap_read_unlock(mm); *locked = 0; } return i ? : -EFAULT; } #endif /* !CONFIG_MMU */ /** * fault_in_writeable - fault in userspace address range for writing * @uaddr: start of address range * @size: size of address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_writeable(char __user *uaddr, size_t size) { char __user *start = uaddr, *end; if (unlikely(size == 0)) return 0; if (!user_write_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_put_user(0, uaddr, out); uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_put_user(0, uaddr, out); uaddr += PAGE_SIZE; } out: user_write_access_end(); if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_writeable); /** * fault_in_subpage_writeable - fault in an address range for writing * @uaddr: start of address range * @size: size of address range * * Fault in a user address range for writing while checking for permissions at * sub-page granularity (e.g. arm64 MTE). This function should be used when * the caller cannot guarantee forward progress of a copy_to_user() loop. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_subpage_writeable(char __user *uaddr, size_t size) { size_t faulted_in; /* * Attempt faulting in at page granularity first for page table * permission checking. The arch-specific probe_subpage_writeable() * functions may not check for this. */ faulted_in = size - fault_in_writeable(uaddr, size); if (faulted_in) faulted_in -= probe_subpage_writeable(uaddr, faulted_in); return size - faulted_in; } EXPORT_SYMBOL(fault_in_subpage_writeable); /* * fault_in_safe_writeable - fault in an address range for writing * @uaddr: start of address range * @size: length of address range * * Faults in an address range for writing. This is primarily useful when we * already know that some or all of the pages in the address range aren't in * memory. * * Unlike fault_in_writeable(), this function is non-destructive. * * Note that we don't pin or otherwise hold the pages referenced that we fault * in. There's no guarantee that they'll stay in memory for any duration of * time. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user(). */ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) { unsigned long start = (unsigned long)uaddr, end; struct mm_struct *mm = current->mm; bool unlocked = false; if (unlikely(size == 0)) return 0; end = PAGE_ALIGN(start + size); if (end < start) end = 0; mmap_read_lock(mm); do { if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked)) break; start = (start + PAGE_SIZE) & PAGE_MASK; } while (start != end); mmap_read_unlock(mm); if (size > (unsigned long)uaddr - start) return size - ((unsigned long)uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_safe_writeable); /** * fault_in_readable - fault in userspace address range for reading * @uaddr: start of user address range * @size: size of user address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_readable(const char __user *uaddr, size_t size) { const char __user *start = uaddr, *end; volatile char c; if (unlikely(size == 0)) return 0; if (!user_read_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_get_user(c, uaddr, out); uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (const char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_get_user(c, uaddr, out); uaddr += PAGE_SIZE; } out: user_read_access_end(); (void)c; if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_readable); /** * get_dump_page() - pin user page in memory while writing it to core dump * @addr: user address * * Returns struct page pointer of user page pinned for dump, * to be freed afterwards by put_page(). * * Returns NULL on any kind of failure - a hole must then be inserted into * the corefile, to preserve alignment with its headers; and also returns * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - * allowing a hole to be left in the corefile to save disk space. * * Called without mmap_lock (takes and releases the mmap_lock by itself). */ #ifdef CONFIG_ELF_CORE struct page *get_dump_page(unsigned long addr) { struct page *page; int locked = 0; int ret; ret = __get_user_pages_locked(current->mm, addr, 1, &page, &locked, FOLL_FORCE | FOLL_DUMP | FOLL_GET); return (ret == 1) ? page : NULL; } #endif /* CONFIG_ELF_CORE */ #ifdef CONFIG_MIGRATION /* * Returns the number of collected folios. Return value is always >= 0. */ static unsigned long collect_longterm_unpinnable_folios( struct list_head *movable_folio_list, unsigned long nr_folios, struct folio **folios) { unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; for (i = 0; i < nr_folios; i++) { struct folio *folio = folios[i]; if (folio == prev_folio) continue; prev_folio = folio; if (folio_is_longterm_pinnable(folio)) continue; collected++; if (folio_is_device_coherent(folio)) continue; if (folio_test_hugetlb(folio)) { isolate_hugetlb(folio, movable_folio_list); continue; } if (!folio_test_lru(folio) && drain_allow) { lru_add_drain_all(); drain_allow = false; } if (!folio_isolate_lru(folio)) continue; list_add_tail(&folio->lru, movable_folio_list); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } return collected; } /* * Unpins all folios and migrates device coherent folios and movable_folio_list. * Returns -EAGAIN if all folios were successfully migrated or -errno for * failure (or partial success). */ static int migrate_longterm_unpinnable_folios( struct list_head *movable_folio_list, unsigned long nr_folios, struct folio **folios) { int ret; unsigned long i; for (i = 0; i < nr_folios; i++) { struct folio *folio = folios[i]; if (folio_is_device_coherent(folio)) { /* * Migration will fail if the folio is pinned, so * convert the pin on the source folio to a normal * reference. */ folios[i] = NULL; folio_get(folio); gup_put_folio(folio, 1, FOLL_PIN); if (migrate_device_coherent_folio(folio)) { ret = -EBUSY; goto err; } continue; } /* * We can't migrate folios with unexpected references, so drop * the reference obtained by __get_user_pages_locked(). * Migrating folios have been added to movable_folio_list after * calling folio_isolate_lru() which takes a reference so the * folio won't be freed if it's migrating. */ unpin_folio(folios[i]); folios[i] = NULL; } if (!list_empty(movable_folio_list)) { struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_NOWARN, .reason = MR_LONGTERM_PIN, }; if (migrate_pages(movable_folio_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_LONGTERM_PIN, NULL)) { ret = -ENOMEM; goto err; } } putback_movable_pages(movable_folio_list); return -EAGAIN; err: unpin_folios(folios, nr_folios); putback_movable_pages(movable_folio_list); return ret; } /* * Check whether all folios are *allowed* to be pinned indefinitely (longterm). * Rather confusingly, all folios in the range are required to be pinned via * FOLL_PIN, before calling this routine. * * If any folios in the range are not allowed to be pinned, then this routine * will migrate those folios away, unpin all the folios in the range and return * -EAGAIN. The caller should re-pin the entire range with FOLL_PIN and then * call this routine again. * * If an error other than -EAGAIN occurs, this indicates a migration failure. * The caller should give up, and propagate the error back up the call stack. * * If everything is OK and all folios in the range are allowed to be pinned, * then this routine leaves all folios pinned and returns zero for success. */ static long check_and_migrate_movable_folios(unsigned long nr_folios, struct folio **folios) { unsigned long collected; LIST_HEAD(movable_folio_list); collected = collect_longterm_unpinnable_folios(&movable_folio_list, nr_folios, folios); if (!collected) return 0; return migrate_longterm_unpinnable_folios(&movable_folio_list, nr_folios, folios); } /* * This routine just converts all the pages in the @pages array to folios and * calls check_and_migrate_movable_folios() to do the heavy lifting. * * Please see the check_and_migrate_movable_folios() documentation for details. */ static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { struct folio **folios; long i, ret; folios = kmalloc_array(nr_pages, sizeof(*folios), GFP_KERNEL); if (!folios) return -ENOMEM; for (i = 0; i < nr_pages; i++) folios[i] = page_folio(pages[i]); ret = check_and_migrate_movable_folios(nr_pages, folios); kfree(folios); return ret; } #else static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { return 0; } static long check_and_migrate_movable_folios(unsigned long nr_folios, struct folio **folios) { return 0; } #endif /* CONFIG_MIGRATION */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which * allows us to process the FOLL_LONGTERM flag. */ static long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int gup_flags) { unsigned int flags; long rc, nr_pinned_pages; if (!(gup_flags & FOLL_LONGTERM)) return __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); flags = memalloc_pin_save(); do { nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); if (nr_pinned_pages <= 0) { rc = nr_pinned_pages; break; } /* FOLL_LONGTERM implies FOLL_PIN */ rc = check_and_migrate_movable_pages(nr_pinned_pages, pages); } while (rc == -EAGAIN); memalloc_pin_restore(flags); return rc ? rc : nr_pinned_pages; } /* * Check that the given flags are valid for the exported gup/pup interface, and * update them with the required flags that the caller must have set. */ static bool is_valid_gup_args(struct page **pages, int *locked, unsigned int *gup_flags_p, unsigned int to_set) { unsigned int gup_flags = *gup_flags_p; /* * These flags not allowed to be specified externally to the gup * interfaces: * - FOLL_TOUCH/FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only * - FOLL_REMOTE is internal only, set in (get|pin)_user_pages_remote() * - FOLL_UNLOCKABLE is internal only and used if locked is !NULL */ if (WARN_ON_ONCE(gup_flags & INTERNAL_GUP_FLAGS)) return false; gup_flags |= to_set; if (locked) { /* At the external interface locked must be set */ if (WARN_ON_ONCE(*locked != 1)) return false; gup_flags |= FOLL_UNLOCKABLE; } /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return false; /* LONGTERM can only be specified when pinning */ if (WARN_ON_ONCE(!(gup_flags & FOLL_PIN) && (gup_flags & FOLL_LONGTERM))) return false; /* Pages input must be given if using GET/PIN */ if (WARN_ON_ONCE((gup_flags & (FOLL_GET | FOLL_PIN)) && !pages)) return false; /* We want to allow the pgmap to be hot-unplugged at all times */ if (WARN_ON_ONCE((gup_flags & FOLL_LONGTERM) && (gup_flags & FOLL_PCI_P2PDMA))) return false; *gup_flags_p = gup_flags; return true; } #ifdef CONFIG_MMU /** * get_user_pages_remote() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held for read or write. * * get_user_pages_remote walks a process's page tables and takes a reference * to each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * get_user_pages_remote returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must * be called after the page is finished with, and before put_page is called. * * get_user_pages_remote is typically used for fewer-copy IO operations, * to get a handle on the memory by some means other than accesses * via the user virtual addresses. The pages may be submitted for * DMA to devices or accessed via their kernel linear mapping (via the * kmap APIs). Care should be taken to use the correct cache flushing APIs. * * See also get_user_pages_fast, for performance critical applications. * * get_user_pages_remote should be phased out in favor of * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing * should use get_user_pages_remote because it cannot pass * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_TOUCH | FOLL_REMOTE)) return -EINVAL; return __get_user_pages_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_remote); #else /* CONFIG_MMU */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { return 0; } #endif /* !CONFIG_MMU */ /** * get_user_pages() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * * This is the same as get_user_pages_remote(), just with a less-flexible * calling convention where we assume that the mm being operated on belongs to * the current task, and doesn't allow passing of a locked parameter. We also * obviously don't pass FOLL_REMOTE in here. */ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages); /* * get_user_pages_unlocked() is suitable to replace the form: * * mmap_read_lock(mm); * get_user_pages(mm, ..., pages, NULL); * mmap_read_unlock(mm); * * with: * * get_user_pages_unlocked(mm, ..., pages); * * It is functionally equivalent to get_user_pages_fast so * get_user_pages_fast should be used instead if specific gup_flags * (e.g. FOLL_FORCE) are not required. */ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH | FOLL_UNLOCKABLE)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_unlocked); /* * GUP-fast * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be * protected from page table pages being freed from under it, and should * block any THP splits. * * One way to achieve this is to have the walker disable interrupts, and * rely on IPIs from the TLB flushing code blocking before the page table * pages are freed. This is unsuitable for architectures that do not need * to broadcast an IPI when invalidating TLBs. * * Another way to achieve this is to batch up page table containing pages * belonging to more than one mm_user, then rcu_sched a callback to free those * pages. Disabling interrupts will allow the gup_fast() walker to both block * the rcu_sched callback, and an IPI that we broadcast for splitting THPs * (which is a relatively rare event). The code below adopts this strategy. * * Before activating this code, please be aware that the following assumptions * are currently made: * * *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to * free pages containing page tables or TLB flushing requires IPI broadcast. * * *) ptes can be read atomically by the architecture. * * *) access_ok is sufficient to validate userspace address ranges. * * The last two assumptions can be relaxed by the addition of helper functions. * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ #ifdef CONFIG_HAVE_GUP_FAST /* * Used in the GUP-fast path to determine whether GUP is permitted to work on * a specific folio. * * This call assumes the caller has pinned the folio, that the lowest page table * level still points to this folio, and that interrupts have been disabled. * * GUP-fast must reject all secretmem folios. * * Writing to pinned file-backed dirty tracked folios is inherently problematic * (see comment describing the writable_file_mapping_allowed() function). We * therefore try to avoid the most egregious case of a long-term mapping doing * so. * * This function cannot be as thorough as that one as the VMA is not available * in the fast path, so instead we whitelist known good cases and if in doubt, * fall back to the slow path. */ static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags) { bool reject_file_backed = false; struct address_space *mapping; bool check_secretmem = false; unsigned long mapping_flags; /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the one we disallow. */ if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) == (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) reject_file_backed = true; /* We hold a folio reference, so we can safely access folio fields. */ /* secretmem folios are always order-0 folios. */ if (IS_ENABLED(CONFIG_SECRETMEM) && !folio_test_large(folio)) check_secretmem = true; if (!reject_file_backed && !check_secretmem) return true; if (WARN_ON_ONCE(folio_test_slab(folio))) return false; /* hugetlb neither requires dirty-tracking nor can be secretmem. */ if (folio_test_hugetlb(folio)) return true; /* * GUP-fast disables IRQs. When IRQS are disabled, RCU grace periods * cannot proceed, which means no actions performed under RCU can * proceed either. * * inodes and thus their mappings are freed under RCU, which means the * mapping cannot be freed beneath us and thus we can safely dereference * it. */ lockdep_assert_irqs_disabled(); /* * However, there may be operations which _alter_ the mapping, so ensure * we read it once and only once. */ mapping = READ_ONCE(folio->mapping); /* * The mapping may have been truncated, in any case we cannot determine * if this mapping is safe - fall back to slow path to determine how to * proceed. */ if (!mapping) return false; /* Anonymous folios pose no problem. */ mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS; if (mapping_flags) return mapping_flags & PAGE_MAPPING_ANON; /* * At this point, we know the mapping is non-null and points to an * address_space object. */ if (check_secretmem && secretmem_mapping(mapping)) return false; /* The only remaining allowed file system is shmem. */ return !reject_file_backed || shmem_mapping(mapping); } static void __maybe_unused gup_fast_undo_dev_pagemap(int *nr, int nr_start, unsigned int flags, struct page **pages) { while ((*nr) - nr_start) { struct folio *folio = page_folio(pages[--(*nr)]); folio_clear_referenced(folio); gup_put_folio(folio, 1, flags); } } #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL /* * GUP-fast relies on pte change detection to avoid concurrent pgtable * operations. * * To pin the page, GUP-fast needs to do below in order: * (1) pin the page (by prefetching pte), then (2) check pte not changed. * * For the rest of pgtable operations where pgtable updates can be racy * with GUP-fast, we need to do (1) clear pte, then (2) check whether page * is pinned. * * Above will work for all pte-level operations, including THP split. * * For THP collapse, it's a bit more complicated because GUP-fast may be * walking a pgtable page that is being freed (pte is still valid but pmd * can be cleared already). To avoid race in such condition, we need to * also check pmd here to make sure pmd doesn't change (corresponds to * pmdp_collapse_flush() in the THP collapse code path). */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct dev_pagemap *pgmap = NULL; int nr_start = *nr, ret = 0; pte_t *ptep, *ptem; ptem = ptep = pte_offset_map(&pmd, addr); if (!ptep) return 0; do { pte_t pte = ptep_get_lockless(ptep); struct page *page; struct folio *folio; /* * Always fallback to ordinary GUP on PROT_NONE-mapped pages: * pte_access_permitted() better should reject these pages * either way: otherwise, GUP-fast might succeed in * cases where ordinary GUP would fail due to VMA access * permissions. */ if (pte_protnone(pte)) goto pte_unmap; if (!pte_access_permitted(pte, flags & FOLL_WRITE)) goto pte_unmap; if (pte_devmap(pte)) { if (unlikely(flags & FOLL_LONGTERM)) goto pte_unmap; pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); goto pte_unmap; } } else if (pte_special(pte)) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); folio = try_grab_folio_fast(page, 1, flags); if (!folio) goto pte_unmap; if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } /* * We need to make the page accessible if and only if we are * going to access its content (the FOLL_PIN case). Please * see Documentation/core-api/pin_user_pages.rst for * details. */ if (flags & FOLL_PIN) { ret = arch_make_folio_accessible(folio); if (ret) { gup_put_folio(folio, 1, flags); goto pte_unmap; } } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; } while (ptep++, addr += PAGE_SIZE, addr != end); ret = 1; pte_unmap: if (pgmap) put_dev_pagemap(pgmap); pte_unmap(ptem); return ret; } #else /* * If we can't determine whether or not a pte is special, then fail immediately * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not * to be special. * * For a futex to be placed on a THP tail page, get_futex_key requires a * get_user_pages_fast_only implementation that can pin pages. Thus it's still * useful to have gup_fast_pmd_leaf even if we can't operate on ptes. */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int nr_start = *nr; struct dev_pagemap *pgmap = NULL; do { struct folio *folio; struct page *page = pfn_to_page(pfn); pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio = try_grab_folio_fast(page, 1, flags); if (!folio) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); put_dev_pagemap(pgmap); return addr == end; } static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } #else static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } #endif static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pmd_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pmd_special(orig)) return 0; if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags, pages, nr); } page = pmd_page(orig); refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr); folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pud_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pud_special(orig)) return 0; if (pud_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags, pages, nr); } page = pud_page(orig); refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr); folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int refs; struct page *page; struct folio *folio; if (!pgd_access_permitted(orig, flags & FOLL_WRITE)) return 0; BUILD_BUG_ON(pgd_devmap(orig)); page = pgd_page(orig); refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); folio = try_grab_folio_fast(page, refs, flags); if (!folio) return 0; if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!pgd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = pmdp_get_lockless(pmdp); next = pmd_addr_end(addr, end); if (!pmd_present(pmd)) return 0; if (unlikely(pmd_leaf(pmd))) { /* See gup_fast_pte_range() */ if (pmd_protnone(pmd)) return 0; if (!gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); return 1; } static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; if (unlikely(pud_leaf(pud))) { if (!gup_fast_pud_leaf(pud, pudp, addr, next, flags, pages, nr)) return 0; } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); next = p4d_addr_end(addr, end); if (!p4d_present(p4d)) return 0; BUILD_BUG_ON(p4d_leaf(p4d)); if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); return 1; } static void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pgd_t *pgdp; pgdp = pgd_offset(current->mm, addr); do { pgd_t pgd = READ_ONCE(*pgdp); next = pgd_addr_end(addr, end); if (pgd_none(pgd)) return; if (unlikely(pgd_leaf(pgd))) { if (!gup_fast_pgd_leaf(pgd, pgdp, addr, next, flags, pages, nr)) return; } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } #else static inline void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { } #endif /* CONFIG_HAVE_GUP_FAST */ #ifndef gup_fast_permitted /* * Check if it's allowed to use get_user_pages_fast_only() for the range, or * we need to fall back to the slow version: */ static bool gup_fast_permitted(unsigned long start, unsigned long end) { return true; } #endif static unsigned long gup_fast(unsigned long start, unsigned long end, unsigned int gup_flags, struct page **pages) { unsigned long flags; int nr_pinned = 0; unsigned seq; if (!IS_ENABLED(CONFIG_HAVE_GUP_FAST) || !gup_fast_permitted(start, end)) return 0; if (gup_flags & FOLL_PIN) { seq = raw_read_seqcount(¤t->mm->write_protect_seq); if (seq & 1) return 0; } /* * Disable interrupts. The nested form is used, in order to allow full, * general purpose use of this routine. * * With interrupts disabled, we block page table pages from being freed * from under us. See struct mmu_table_batch comments in * include/asm-generic/tlb.h for more details. * * We do not adopt an rcu_read_lock() here as we also want to block IPIs * that come from THPs splitting. */ local_irq_save(flags); gup_fast_pgd_range(start, end, gup_flags, pages, &nr_pinned); local_irq_restore(flags); /* * When pinning pages for DMA there could be a concurrent write protect * from fork() via copy_page_range(), in this case always fail GUP-fast. */ if (gup_flags & FOLL_PIN) { if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { gup_fast_unpin_user_pages(pages, nr_pinned); return 0; } else { sanity_check_pinned_pages(pages, nr_pinned); } } return nr_pinned; } static int gup_fast_fallback(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { unsigned long len, end; unsigned long nr_pinned; int locked = 0; int ret; if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_FORCE | FOLL_PIN | FOLL_GET | FOLL_FAST_ONLY | FOLL_NOFAULT | FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT))) return -EINVAL; if (gup_flags & FOLL_PIN) mm_set_has_pinned_flag(¤t->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); start = untagged_addr(start) & PAGE_MASK; len = nr_pages << PAGE_SHIFT; if (check_add_overflow(start, len, &end)) return -EOVERFLOW; if (end > TASK_SIZE_MAX) return -EFAULT; if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; nr_pinned = gup_fast(start, end, gup_flags, pages); if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY) return nr_pinned; /* Slow path: try to get the remaining pages with get_user_pages */ start += nr_pinned << PAGE_SHIFT; pages += nr_pinned; ret = __gup_longterm_locked(current->mm, start, nr_pages - nr_pinned, pages, &locked, gup_flags | FOLL_TOUCH | FOLL_UNLOCKABLE); if (ret < 0) { /* * The caller has to unpin the pages we already pinned so * returning -errno is not an option */ if (nr_pinned) return nr_pinned; return ret; } return ret + nr_pinned; } /** * get_user_pages_fast_only() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. * * If the architecture does not support this function, simply return with no * pages pinned. * * Careful, careful! COW breaking can go either way, so a non-write * access can get ambiguous page results. If you call this function without * 'write' set, you'd better be sure that you're ok with that ambiguity. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * Internally (within mm/gup.c), gup fast variants must set FOLL_GET, * because gup fast is always a "pin with a +1 page refcount" request. * * FOLL_FAST_ONLY is required in order to match the API description of * this routine: no fall back to regular ("slow") GUP. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET | FOLL_FAST_ONLY)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast_only); /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Attempt to pin user pages in memory without taking mm->mmap_lock. * If not successful, it will fall back to taking the lock and * calling get_user_pages(). * * Returns number of pages pinned. This may be fewer than the number requested. * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns * -errno. */ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * The caller may or may not have explicitly set FOLL_GET; either way is * OK. However, internally (within mm/gup.c), gup fast variants must set * FOLL_GET, because gup fast is always a "pin with a +1 page refcount" * request. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast); /** * pin_user_pages_fast() - pin user pages in memory without taking locks * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See * get_user_pages_fast() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for further details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page() will not remove pins from it. */ int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(pin_user_pages_fast); /** * pin_user_pages_remote() - pin pages of a remote process * * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See * get_user_pages_remote() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_REMOTE)) return 0; return __gup_longterm_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_remote); /** * pin_user_pages() - pin user pages in memory for use by other devices * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and * FOLL_PIN is set. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages); /* * pin_user_pages_unlocked() is the FOLL_PIN variant of * get_user_pages_unlocked(). Behavior is the same, except that this one sets * FOLL_PIN and rejects FOLL_GET. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_unlocked); /** * memfd_pin_folios() - pin folios associated with a memfd * @memfd: the memfd whose folios are to be pinned * @start: the first memfd offset * @end: the last memfd offset (inclusive) * @folios: array that receives pointers to the folios pinned * @max_folios: maximum number of entries in @folios * @offset: the offset into the first folio * * Attempt to pin folios associated with a memfd in the contiguous range * [start, end]. Given that a memfd is either backed by shmem or hugetlb, * the folios can either be found in the page cache or need to be allocated * if necessary. Once the folios are located, they are all pinned via * FOLL_PIN and @offset is populatedwith the offset into the first folio. * And, eventually, these pinned folios must be released either using * unpin_folios() or unpin_folio(). * * It must be noted that the folios may be pinned for an indefinite amount * of time. And, in most cases, the duration of time they may stay pinned * would be controlled by the userspace. This behavior is effectively the * same as using FOLL_LONGTERM with other GUP APIs. * * Returns number of folios pinned, which could be less than @max_folios * as it depends on the folio sizes that cover the range [start, end]. * If no folios were pinned, it returns -errno. */ long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, struct folio **folios, unsigned int max_folios, pgoff_t *offset) { unsigned int flags, nr_folios, nr_found; unsigned int i, pgshift = PAGE_SHIFT; pgoff_t start_idx, end_idx, next_idx; struct folio *folio = NULL; struct folio_batch fbatch; struct hstate *h; long ret = -EINVAL; if (start < 0 || start > end || !max_folios) return -EINVAL; if (!memfd) return -EINVAL; if (!shmem_file(memfd) && !is_file_hugepages(memfd)) return -EINVAL; if (end >= i_size_read(file_inode(memfd))) return -EINVAL; if (is_file_hugepages(memfd)) { h = hstate_file(memfd); pgshift = huge_page_shift(h); } flags = memalloc_pin_save(); do { nr_folios = 0; start_idx = start >> pgshift; end_idx = end >> pgshift; if (is_file_hugepages(memfd)) { start_idx <<= huge_page_order(h); end_idx <<= huge_page_order(h); } folio_batch_init(&fbatch); while (start_idx <= end_idx && nr_folios < max_folios) { /* * In most cases, we should be able to find the folios * in the page cache. If we cannot find them for some * reason, we try to allocate them and add them to the * page cache. */ nr_found = filemap_get_folios_contig(memfd->f_mapping, &start_idx, end_idx, &fbatch); if (folio) { folio_put(folio); folio = NULL; } next_idx = 0; for (i = 0; i < nr_found; i++) { /* * As there can be multiple entries for a * given folio in the batch returned by * filemap_get_folios_contig(), the below * check is to ensure that we pin and return a * unique set of folios between start and end. */ if (next_idx && next_idx != folio_index(fbatch.folios[i])) continue; folio = page_folio(&fbatch.folios[i]->page); if (try_grab_folio(folio, 1, FOLL_PIN)) { folio_batch_release(&fbatch); ret = -EINVAL; goto err; } if (nr_folios == 0) *offset = offset_in_folio(folio, start); folios[nr_folios] = folio; next_idx = folio_next_index(folio); if (++nr_folios == max_folios) break; } folio = NULL; folio_batch_release(&fbatch); if (!nr_found) { folio = memfd_alloc_folio(memfd, start_idx); if (IS_ERR(folio)) { ret = PTR_ERR(folio); if (ret != -EEXIST) goto err; folio = NULL; } } } ret = check_and_migrate_movable_folios(nr_folios, folios); } while (ret == -EAGAIN); memalloc_pin_restore(flags); return ret ? ret : nr_folios; err: memalloc_pin_restore(flags); unpin_folios(folios, nr_folios); return ret; } EXPORT_SYMBOL_GPL(memfd_pin_folios); |
| 372 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * RCU-based infrastructure for lightweight reader-writer locking * * Copyright (c) 2015, Red Hat, Inc. * * Author: Oleg Nesterov <oleg@redhat.com> */ #ifndef _LINUX_RCU_SYNC_H_ #define _LINUX_RCU_SYNC_H_ #include <linux/wait.h> #include <linux/rcupdate.h> /* Structure to mediate between updaters and fastpath-using readers. */ struct rcu_sync { int gp_state; int gp_count; wait_queue_head_t gp_wait; struct rcu_head cb_head; }; /** * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? * @rsp: Pointer to rcu_sync structure to use for synchronization * * Returns true if readers are permitted to use their fastpaths. Must be * invoked within some flavor of RCU read-side critical section. */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), "suspicious rcu_sync_is_idle() usage"); return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } extern void rcu_sync_init(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); #define __RCU_SYNC_INITIALIZER(name) { \ .gp_state = 0, \ .gp_count = 0, \ .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ } #define DEFINE_RCU_SYNC(name) \ struct rcu_sync name = __RCU_SYNC_INITIALIZER(name) #endif /* _LINUX_RCU_SYNC_H_ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ERR_H #define _LINUX_ERR_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/errno.h> /* * Kernel pointers have redundant information, so we can use a * scheme where we can return either an error code or a normal * pointer with the same return value. * * This should be a per-architecture thing, to allow different * error and pointer decisions. */ #define MAX_ERRNO 4095 #ifndef __ASSEMBLY__ /** * IS_ERR_VALUE - Detect an error pointer. * @x: The pointer to check. * * Like IS_ERR(), but does not generate a compiler warning if result is unused. */ #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) /** * ERR_PTR - Create an error pointer. * @error: A negative error code. * * Encodes @error into a pointer value. Users should consider the result * opaque and not assume anything about how the error is encoded. * * Return: A pointer with @error encoded within its value. */ static inline void * __must_check ERR_PTR(long error) { return (void *) error; } /* Return the pointer in the percpu address space. */ #define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error)) /** * PTR_ERR - Extract the error code from an error pointer. * @ptr: An error pointer. * Return: The error code within @ptr. */ static inline long __must_check PTR_ERR(__force const void *ptr) { return (long) ptr; } /* Read an error pointer from the percpu address space. */ #define PTR_ERR_PCPU(ptr) (PTR_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR - Detect an error pointer. * @ptr: The pointer to check. * Return: true if @ptr is an error pointer, false otherwise. */ static inline bool __must_check IS_ERR(__force const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } /* Read an error pointer from the percpu address space. */ #define IS_ERR_PCPU(ptr) (IS_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR_OR_NULL - Detect an error pointer or a null pointer. * @ptr: The pointer to check. * * Like IS_ERR(), but also returns true for a null pointer. */ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type * @ptr: The pointer to cast. * * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ static inline void * __must_check ERR_CAST(__force const void *ptr) { /* cast away the const */ return (void *) ptr; } /** * PTR_ERR_OR_ZERO - Extract the error code from a pointer if it has one. * @ptr: A potential error pointer. * * Convenience function that can be used inside a function that returns * an error code to propagate errors received as error pointers. * For example, ``return PTR_ERR_OR_ZERO(ptr);`` replaces: * * .. code-block:: c * * if (IS_ERR(ptr)) * return PTR_ERR(ptr); * else * return 0; * * Return: The error code within @ptr if it is an error pointer; 0 otherwise. */ static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0; } #endif #endif /* _LINUX_ERR_H */ |
| 45 44 1 45 46 46 48 37 37 37 37 37 37 37 37 37 43 43 25 25 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Debug and Guest Debug support * * Copyright (C) 2015 - Linaro Ltd * Author: Alex Bennée <alex.bennee@linaro.org> */ #include <linux/kvm_host.h> #include <linux/hw_breakpoint.h> #include <asm/debug-monitors.h> #include <asm/kvm_asm.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> #include "trace.h" /* These are the bits of MDSCR_EL1 we may manipulate */ #define MDSCR_EL1_DEBUG_MASK (DBG_MDSCR_SS | \ DBG_MDSCR_KDE | \ DBG_MDSCR_MDE) static DEFINE_PER_CPU(u64, mdcr_el2); /* * save/restore_guest_debug_regs * * For some debug operations we need to tweak some guest registers. As * a result we need to save the state of those registers before we * make those modifications. * * Guest access to MDSCR_EL1 is trapped by the hypervisor and handled * after we have restored the preserved value to the main context. * * When single-step is enabled by userspace, we tweak PSTATE.SS on every * guest entry. Preserve PSTATE.SS so we can restore the original value * for the vcpu after the single-step is disabled. */ static void save_guest_debug_regs(struct kvm_vcpu *vcpu) { u64 val = vcpu_read_sys_reg(vcpu, MDSCR_EL1); vcpu->arch.guest_debug_preserved.mdscr_el1 = val; trace_kvm_arm_set_dreg32("Saved MDSCR_EL1", vcpu->arch.guest_debug_preserved.mdscr_el1); vcpu->arch.guest_debug_preserved.pstate_ss = (*vcpu_cpsr(vcpu) & DBG_SPSR_SS); } static void restore_guest_debug_regs(struct kvm_vcpu *vcpu) { u64 val = vcpu->arch.guest_debug_preserved.mdscr_el1; vcpu_write_sys_reg(vcpu, val, MDSCR_EL1); trace_kvm_arm_set_dreg32("Restored MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1)); if (vcpu->arch.guest_debug_preserved.pstate_ss) *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; else *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } /** * kvm_arm_init_debug - grab what we need for debug * * Currently the sole task of this function is to retrieve the initial * value of mdcr_el2 so we can preserve MDCR_EL2.HPMN which has * presumably been set-up by some knowledgeable bootcode. * * It is called once per-cpu during CPU hyp initialisation. */ void kvm_arm_init_debug(void) { __this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2)); } /** * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value * * @vcpu: the vcpu pointer * * This ensures we will trap access to: * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * - Self-hosted Trace (MDCR_EL2_TTRF/MDCR_EL2_E2TB) */ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) { /* * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK * to disable guest access to the profiling and trace buffers */ vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); /* Is the VM being debugged by userspace? */ if (vcpu->guest_debug) /* Route all software debug exceptions to EL2 */ vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; /* * Trap debug register access when one of the following is true: * - Userspace is using the hardware to debug the guest * (KVM_GUESTDBG_USE_HW is set). * - The guest is not using debug (DEBUG_DIRTY clear). * - The guest has enabled the OS Lock (debug exceptions are blocked). */ if ((vcpu->guest_debug & KVM_GUESTDBG_USE_HW) || !vcpu_get_flag(vcpu, DEBUG_DIRTY) || kvm_vcpu_os_lock_enabled(vcpu)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); } /** * kvm_arm_vcpu_init_debug - setup vcpu debug traps * * @vcpu: the vcpu pointer * * Set vcpu initial mdcr_el2 value. */ void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu) { preempt_disable(); kvm_arm_setup_mdcr_el2(vcpu); preempt_enable(); } /** * kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state * @vcpu: the vcpu pointer */ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) { vcpu->arch.debug_ptr = &vcpu->arch.vcpu_debug_state; } /** * kvm_arm_setup_debug - set up debug related stuff * * @vcpu: the vcpu pointer * * This is called before each entry into the hypervisor to setup any * debug related registers. * * Additionally, KVM only traps guest accesses to the debug registers if * the guest is not actively using them (see the DEBUG_DIRTY * flag on vcpu->arch.iflags). Since the guest must not interfere * with the hardware state when debugging the guest, we must ensure that * trapping is enabled whenever we are debugging the guest using the * debug registers. */ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) { unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2; trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug); kvm_arm_setup_mdcr_el2(vcpu); /* Check if we need to use the debug registers. */ if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { /* Save guest debug state */ save_guest_debug_regs(vcpu); /* * Single Step (ARM ARM D2.12.3 The software step state * machine) * * If we are doing Single Step we need to manipulate * the guest's MDSCR_EL1.SS and PSTATE.SS. Once the * step has occurred the hypervisor will trap the * debug exception and we return to userspace. * * If the guest attempts to single step its userspace * we would have to deal with a trapped exception * while in the guest kernel. Because this would be * hard to unwind we suppress the guest's ability to * do so by masking MDSCR_EL.SS. * * This confuses guest debuggers which use * single-step behind the scenes but everything * returns to normal once the host is no longer * debugging the system. */ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { /* * If the software step state at the last guest exit * was Active-pending, we don't set DBG_SPSR_SS so * that the state is maintained (to not run another * single-step until the pending Software Step * exception is taken). */ if (!vcpu_get_flag(vcpu, DBG_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; else *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); mdscr |= DBG_MDSCR_SS; vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); } else { mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); mdscr &= ~DBG_MDSCR_SS; vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); } trace_kvm_arm_set_dreg32("SPSR_EL2", *vcpu_cpsr(vcpu)); /* * HW Breakpoints and watchpoints * * We simply switch the debug_ptr to point to our new * external_debug_state which has been populated by the * debug ioctl. The existing DEBUG_DIRTY mechanism ensures * the registers are updated on the world switch. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { /* Enable breakpoints/watchpoints */ mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); mdscr |= DBG_MDSCR_MDE; vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state; vcpu_set_flag(vcpu, DEBUG_DIRTY); trace_kvm_arm_set_regset("BKPTS", get_num_brps(), &vcpu->arch.debug_ptr->dbg_bcr[0], &vcpu->arch.debug_ptr->dbg_bvr[0]); trace_kvm_arm_set_regset("WAPTS", get_num_wrps(), &vcpu->arch.debug_ptr->dbg_wcr[0], &vcpu->arch.debug_ptr->dbg_wvr[0]); /* * The OS Lock blocks debug exceptions in all ELs when it is * enabled. If the guest has enabled the OS Lock, constrain its * effects to the guest. Emulate the behavior by clearing * MDSCR_EL1.MDE. In so doing, we ensure that host debug * exceptions are unaffected by guest configuration of the OS * Lock. */ } else if (kvm_vcpu_os_lock_enabled(vcpu)) { mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); mdscr &= ~DBG_MDSCR_MDE; vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); } } BUG_ON(!vcpu->guest_debug && vcpu->arch.debug_ptr != &vcpu->arch.vcpu_debug_state); /* If KDE or MDE are set, perform a full save/restore cycle. */ if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE)) vcpu_set_flag(vcpu, DEBUG_DIRTY); /* Write mdcr_el2 changes since vcpu_load on VHE systems */ if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2) write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1)); } void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) { trace_kvm_arm_clear_debug(vcpu->guest_debug); /* * Restore the guest's debug registers if we were using them. */ if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)) /* * Mark the vcpu as ACTIVE_PENDING * until Software Step exception is taken. */ vcpu_set_flag(vcpu, DBG_SS_ACTIVE_PENDING); } restore_guest_debug_regs(vcpu); /* * If we were using HW debug we need to restore the * debug_ptr to the guest debug state. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { kvm_arm_reset_debug_ptr(vcpu); trace_kvm_arm_set_regset("BKPTS", get_num_brps(), &vcpu->arch.debug_ptr->dbg_bcr[0], &vcpu->arch.debug_ptr->dbg_bvr[0]); trace_kvm_arm_set_regset("WAPTS", get_num_wrps(), &vcpu->arch.debug_ptr->dbg_wcr[0], &vcpu->arch.debug_ptr->dbg_wvr[0]); } } } void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu) { u64 dfr0; /* For VHE, there is nothing to do */ if (has_vhe()) return; dfr0 = read_sysreg(id_aa64dfr0_el1); /* * If SPE is present on this CPU and is available at current EL, * we may need to check if the host state needs to be saved. */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && !(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(PMBIDR_EL1_P_SHIFT))) vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_SPE); /* Check if we have TRBE implemented and available at the host */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_TRBE); } void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu) { vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_SPE); vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_TRBE); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/xarray.h> #include <net/net_debug.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> #include <net/page_pool/types.h> #include <net/sock.h> #include "devmem.h" #include "page_pool_priv.h" #include "netdev-genl-gen.h" static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1); /* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user. * Ordering: inside rtnl_lock */ static DEFINE_MUTEX(page_pools_lock); /* Page pools are only reachable from user space (via netlink) if they are * linked to a netdev at creation time. Following page pool "visibility" * states are possible: * - normal * - user.list: linked to real netdev, netdev: real netdev * - orphaned - real netdev has disappeared * - user.list: linked to lo, netdev: lo * - invisible - either (a) created without netdev linking, (b) unlisted due * to error, or (c) the entire namespace which owned this pool disappeared * - user.list: unhashed, netdev: unknown */ typedef int (*pp_nl_fill_cb)(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info); static int netdev_nl_page_pool_get_do(struct genl_info *info, u32 id, pp_nl_fill_cb fill) { struct page_pool *pool; struct sk_buff *rsp; int err; mutex_lock(&page_pools_lock); pool = xa_load(&page_pools, id); if (!pool || hlist_unhashed(&pool->user.list) || !net_eq(dev_net(pool->slow.netdev), genl_info_net(info))) { err = -ENOENT; goto err_unlock; } rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) { err = -ENOMEM; goto err_unlock; } err = fill(rsp, pool, info); if (err) goto err_free_msg; mutex_unlock(&page_pools_lock); return genlmsg_reply(rsp, info); err_free_msg: nlmsg_free(rsp); err_unlock: mutex_unlock(&page_pools_lock); return err; } struct page_pool_dump_cb { unsigned long ifindex; u32 pp_id; }; static int netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, pp_nl_fill_cb fill) { struct page_pool_dump_cb *state = (void *)cb->ctx; const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; struct page_pool *pool; int err = 0; rtnl_lock(); mutex_lock(&page_pools_lock); for_each_netdev_dump(net, netdev, state->ifindex) { hlist_for_each_entry(pool, &netdev->page_pools, user.list) { if (state->pp_id && state->pp_id < pool->user.id) continue; state->pp_id = pool->user.id; err = fill(skb, pool, info); if (err) goto out; } state->pp_id = 0; } out: mutex_unlock(&page_pools_lock); rtnl_unlock(); return err; } static int page_pool_nl_stats_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { #ifdef CONFIG_PAGE_POOL_STATS struct page_pool_stats stats = {}; struct nlattr *nest; void *hdr; if (!page_pool_get_stats(pool, &stats)) return 0; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; nest = nla_nest_start(rsp, NETDEV_A_PAGE_POOL_STATS_INFO); if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id) || (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, pool->slow.netdev->ifindex))) goto err_cancel_nest; nla_nest_end(rsp, nest); if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST, stats.alloc_stats.fast) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW, stats.alloc_stats.slow) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER, stats.alloc_stats.slow_high_order) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY, stats.alloc_stats.empty) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL, stats.alloc_stats.refill) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE, stats.alloc_stats.waive) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED, stats.recycle_stats.cached) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL, stats.recycle_stats.cache_full) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING, stats.recycle_stats.ring) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL, stats.recycle_stats.ring_full) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT, stats.recycle_stats.released_refcnt)) goto err_cancel_msg; genlmsg_end(rsp, hdr); return 0; err_cancel_nest: nla_nest_cancel(rsp, nest); err_cancel_msg: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; #else GENL_SET_ERR_MSG(info, "kernel built without CONFIG_PAGE_POOL_STATS"); return -EOPNOTSUPP; #endif } int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[ARRAY_SIZE(netdev_page_pool_info_nl_policy)]; struct nlattr *nest; int err; u32 id; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_STATS_INFO)) return -EINVAL; nest = info->attrs[NETDEV_A_PAGE_POOL_STATS_INFO]; err = nla_parse_nested(tb, ARRAY_SIZE(tb) - 1, nest, netdev_page_pool_info_nl_policy, info->extack); if (err) return err; if (NL_REQ_ATTR_CHECK(info->extack, nest, tb, NETDEV_A_PAGE_POOL_ID)) return -EINVAL; if (tb[NETDEV_A_PAGE_POOL_IFINDEX]) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NETDEV_A_PAGE_POOL_IFINDEX], "selecting by ifindex not supported"); return -EINVAL; } id = nla_get_uint(tb[NETDEV_A_PAGE_POOL_ID]); return netdev_nl_page_pool_get_do(info, id, page_pool_nl_stats_fill); } int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_stats_fill); } static int page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { struct net_devmem_dmabuf_binding *binding = pool->mp_priv; size_t inflight, refsz; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id)) goto err_cancel; if (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, pool->slow.netdev->ifindex)) goto err_cancel; if (pool->user.napi_id && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id)) goto err_cancel; inflight = page_pool_inflight(pool, false); refsz = PAGE_SIZE << pool->p.order; if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT, inflight) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, inflight * refsz)) goto err_cancel; if (pool->user.detach_time && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME, pool->user.detach_time)) goto err_cancel; if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id)) goto err_cancel; genlmsg_end(rsp, hdr); return 0; err_cancel: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static void netdev_nl_page_pool_event(const struct page_pool *pool, u32 cmd) { struct genl_info info; struct sk_buff *ntf; struct net *net; lockdep_assert_held(&page_pools_lock); /* 'invisible' page pools don't matter */ if (hlist_unhashed(&pool->user.list)) return; net = dev_net(pool->slow.netdev); if (!genl_has_listeners(&netdev_nl_family, net, NETDEV_NLGRP_PAGE_POOL)) return; genl_info_init_ntf(&info, &netdev_nl_family, cmd); ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ntf) return; if (page_pool_nl_fill(ntf, pool, &info)) { nlmsg_free(ntf); return; } genlmsg_multicast_netns(&netdev_nl_family, net, ntf, 0, NETDEV_NLGRP_PAGE_POOL, GFP_KERNEL); } int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info) { u32 id; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_ID)) return -EINVAL; id = nla_get_uint(info->attrs[NETDEV_A_PAGE_POOL_ID]); return netdev_nl_page_pool_get_do(info, id, page_pool_nl_fill); } int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_fill); } int page_pool_list(struct page_pool *pool) { static u32 id_alloc_next; int err; mutex_lock(&page_pools_lock); err = xa_alloc_cyclic(&page_pools, &pool->user.id, pool, xa_limit_32b, &id_alloc_next, GFP_KERNEL); if (err < 0) goto err_unlock; INIT_HLIST_NODE(&pool->user.list); if (pool->slow.netdev) { hlist_add_head(&pool->user.list, &pool->slow.netdev->page_pools); pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0; netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF); } mutex_unlock(&page_pools_lock); return 0; err_unlock: mutex_unlock(&page_pools_lock); return err; } void page_pool_detached(struct page_pool *pool) { mutex_lock(&page_pools_lock); pool->user.detach_time = ktime_get_boottime_seconds(); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); mutex_unlock(&page_pools_lock); } void page_pool_unlist(struct page_pool *pool) { mutex_lock(&page_pools_lock); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_DEL_NTF); xa_erase(&page_pools, pool->user.id); if (!hlist_unhashed(&pool->user.list)) hlist_del(&pool->user.list); mutex_unlock(&page_pools_lock); } int page_pool_check_memory_provider(struct net_device *dev, struct netdev_rx_queue *rxq) { struct net_devmem_dmabuf_binding *binding = rxq->mp_params.mp_priv; struct page_pool *pool; struct hlist_node *n; if (!binding) return 0; mutex_lock(&page_pools_lock); hlist_for_each_entry_safe(pool, n, &dev->page_pools, user.list) { if (pool->mp_priv != binding) continue; if (pool->slow.queue_idx == get_netdev_rx_queue_index(rxq)) { mutex_unlock(&page_pools_lock); return 0; } } mutex_unlock(&page_pools_lock); return -ENODATA; } static void page_pool_unreg_netdev_wipe(struct net_device *netdev) { struct page_pool *pool; struct hlist_node *n; mutex_lock(&page_pools_lock); hlist_for_each_entry_safe(pool, n, &netdev->page_pools, user.list) { hlist_del_init(&pool->user.list); pool->slow.netdev = NET_PTR_POISON; } mutex_unlock(&page_pools_lock); } static void page_pool_unreg_netdev(struct net_device *netdev) { struct page_pool *pool, *last; struct net_device *lo; lo = dev_net(netdev)->loopback_dev; mutex_lock(&page_pools_lock); last = NULL; hlist_for_each_entry(pool, &netdev->page_pools, user.list) { pool->slow.netdev = lo; netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); last = pool; } if (last) hlist_splice_init(&netdev->page_pools, &last->user.list, &lo->page_pools); mutex_unlock(&page_pools_lock); } static int page_pool_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; if (hlist_empty(&netdev->page_pools)) return NOTIFY_OK; if (netdev->ifindex != LOOPBACK_IFINDEX) page_pool_unreg_netdev(netdev); else page_pool_unreg_netdev_wipe(netdev); return NOTIFY_OK; } static struct notifier_block page_pool_netdevice_nb = { .notifier_call = page_pool_netdevice_event, }; static int __init page_pool_user_init(void) { return register_netdevice_notifier(&page_pool_netdevice_nb); } subsys_initcall(page_pool_user_init); |
| 162 162 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/zswap.h> #include <linux/plist.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "internal.h" #include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry, unsigned int nr_pages); static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries); static bool folio_swapcache_freeable(struct folio *folio); static struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset); static void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); static struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full */ #define TTRS_FULL 0x4 /* Reclaim directly, bypass the slot cache and don't touch device lock */ #define TTRS_DIRECT 0x8 static bool swap_is_has_cache(struct swap_info_struct *si, unsigned long offset, int nr_pages) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; do { VM_BUG_ON(!(*map & SWAP_HAS_CACHE)); if (*map != SWAP_HAS_CACHE) return false; } while (++map < map_end); return true; } static bool swap_is_last_map(struct swap_info_struct *si, unsigned long offset, int nr_pages, bool *has_cache) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; unsigned char count = *map; if (swap_count(count) != 1) return false; while (++map < map_end) { if (*map != count) return false; } *has_cache = !!(count & SWAP_HAS_CACHE); return true; } /* * returns number of pages in the folio that backs the swap entry. If positive, * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no * folio was associated with the swap entry. */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct address_space *address_space = swap_address_space(entry); struct swap_cluster_info *ci; struct folio *folio; int ret, nr_pages; bool need_reclaim; folio = filemap_get_folio(address_space, swap_cache_index(entry)); if (IS_ERR(folio)) return 0; /* offset could point to the middle of a large folio */ entry = folio->swap; offset = swp_offset(entry); nr_pages = folio_nr_pages(folio); ret = -nr_pages; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (!folio_trylock(folio)) goto out; need_reclaim = ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); if (!need_reclaim || !folio_swapcache_freeable(folio)) goto out_unlock; /* * It's safe to delete the folio from swap cache only if the folio's * swap_map is HAS_CACHE only, which means the slots have no page table * reference or pending writeback, and can't be allocated to others. */ ci = lock_cluster_or_swap_info(si, offset); need_reclaim = swap_is_has_cache(si, offset, nr_pages); unlock_cluster_or_swap_info(si, ci); if (!need_reclaim) goto out_unlock; if (!(flags & TTRS_DIRECT)) { /* Free through slot cache */ delete_from_swap_cache(folio); folio_set_dirty(folio); ret = nr_pages; goto out_unlock; } xa_lock_irq(&address_space->i_pages); __delete_from_swap_cache(folio, entry, NULL); xa_unlock_irq(&address_space->i_pages); folio_ref_sub(folio, nr_pages); folio_set_dirty(folio); spin_lock(&si->lock); /* Only sinple page folio can be backed by zswap */ if (nr_pages == 1) zswap_invalidate(entry); swap_entry_range_free(si, entry, nr_pages); spin_unlock(&si->lock); ret = nr_pages; out_unlock: folio_unlock(folio); out: folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_folio_sector(struct folio *folio) { struct swap_info_struct *sis = swp_swap_info(folio->swap); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = swp_offset(folio->swap); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_order(order) (order) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_order() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_order(order) 0 #endif #define LATENCY_LIMIT 256 static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } static inline unsigned int cluster_index(struct swap_info_struct *si, struct swap_cluster_info *ci) { return ci - si->cluster_info; } static inline unsigned int cluster_offset(struct swap_info_struct *si, struct swap_cluster_info *ci) { return cluster_index(si, ci) * SWAPFILE_CLUSTER; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); } /* * Determine the locking method in use for this device. Return * swap_cluster_info if SSD-style cluster-based locking is in place. */ static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; /* Try to use fine-grained SSD-style locking if available: */ ci = lock_cluster(si, offset); /* Otherwise, fall back to traditional, coarse locking: */ if (!ci) spin_lock(&si->lock); return ci; } static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, struct swap_cluster_info *ci) { unsigned int idx = cluster_index(si, ci); /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); list_move_tail(&ci->list, &si->discard_clusters); ci->flags = 0; schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); if (ci->flags) list_move_tail(&ci->list, &si->free_clusters); else list_add_tail(&ci->list, &si->free_clusters); ci->flags = CLUSTER_FLAG_FREE; ci->order = 0; } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *ci; unsigned int idx; while (!list_empty(&si->discard_clusters)) { ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); list_del(&ci->list); idx = cluster_index(si, ci); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); spin_lock(&ci->lock); __free_cluster(si, ci); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); spin_unlock(&ci->lock); } } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->count != 0); lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, ci); return; } __free_cluster(si, ci); } /* * The cluster corresponding to page_nr will be used. The cluster will not be * added to free cluster list and its usage counter will be increased by 1. * Only used for initialization. */ static void inc_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; if (!cluster_info) return; ci = cluster_info + idx; ci->count++; VM_BUG_ON(ci->count > SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags); } /* * The cluster ci decreases @nr_pages usage. If the usage counter becomes 0, * which means no page in the cluster is in use, we can optionally discard * the cluster and add it to free cluster list. */ static void dec_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *ci, int nr_pages) { if (!si->cluster_info) return; VM_BUG_ON(ci->count < nr_pages); VM_BUG_ON(cluster_is_free(ci)); lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); ci->count -= nr_pages; if (!ci->count) { free_cluster(si, ci); return; } if (!(ci->flags & CLUSTER_FLAG_NONFULL)) { VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; list_move_tail(&ci->list, &si->nonfull_clusters[ci->order]); ci->flags = CLUSTER_FLAG_NONFULL; } } static bool cluster_reclaim_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned long end) { unsigned char *map = si->swap_map; unsigned long offset; spin_unlock(&ci->lock); spin_unlock(&si->lock); for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT) > 0) continue; goto out; default: goto out; } } out: spin_lock(&si->lock); spin_lock(&ci->lock); /* * Recheck the range no matter reclaim succeeded or not, the slot * could have been be freed while we are not holding the lock. */ for (offset = start; offset < end; offset++) if (READ_ONCE(map[offset])) return false; return true; } static bool cluster_scan_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned int nr_pages) { unsigned long offset, end = start + nr_pages; unsigned char *map = si->swap_map; bool need_reclaim = false; for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (!vm_swap_full()) return false; need_reclaim = true; continue; default: return false; } } if (need_reclaim) return cluster_reclaim_range(si, ci, start, end); return true; } static void cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int start, unsigned char usage, unsigned int order) { unsigned int nr_pages = 1 << order; if (cluster_is_free(ci)) { if (nr_pages < SWAPFILE_CLUSTER) { list_move_tail(&ci->list, &si->nonfull_clusters[order]); ci->flags = CLUSTER_FLAG_NONFULL; } ci->order = order; } memset(si->swap_map + start, usage, nr_pages); swap_range_alloc(si, start, nr_pages); ci->count += nr_pages; if (ci->count == SWAPFILE_CLUSTER) { VM_BUG_ON(!(ci->flags & (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG))); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; list_move_tail(&ci->list, &si->full_clusters); ci->flags = CLUSTER_FLAG_FULL; } } static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigned long offset, unsigned int *foundp, unsigned int order, unsigned char usage) { unsigned long start = offset & ~(SWAPFILE_CLUSTER - 1); unsigned long end = min(start + SWAPFILE_CLUSTER, si->max); unsigned int nr_pages = 1 << order; struct swap_cluster_info *ci; if (end < nr_pages) return SWAP_NEXT_INVALID; end -= nr_pages; ci = lock_cluster(si, offset); if (ci->count + nr_pages > SWAPFILE_CLUSTER) { offset = SWAP_NEXT_INVALID; goto done; } while (offset <= end) { if (cluster_scan_range(si, ci, offset, nr_pages)) { cluster_alloc_range(si, ci, offset, usage, order); *foundp = offset; if (ci->count == SWAPFILE_CLUSTER) { offset = SWAP_NEXT_INVALID; goto done; } offset += nr_pages; break; } offset += nr_pages; } if (offset > end) offset = SWAP_NEXT_INVALID; done: unlock_cluster(ci); return offset; } static void swap_reclaim_full_clusters(struct swap_info_struct *si) { long to_scan = 1; unsigned long offset, end; struct swap_cluster_info *ci; unsigned char *map = si->swap_map; int nr_reclaim, total_reclaimed = 0; if (atomic_long_read(&nr_swap_pages) <= SWAPFILE_CLUSTER) to_scan = si->inuse_pages / SWAPFILE_CLUSTER; while (!list_empty(&si->full_clusters)) { ci = list_first_entry(&si->full_clusters, struct swap_cluster_info, list); list_move_tail(&ci->list, &si->full_clusters); offset = cluster_offset(si, ci); end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; while (offset < end) { if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { spin_unlock(&si->lock); nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); spin_lock(&si->lock); if (nr_reclaim > 0) { offset += nr_reclaim; total_reclaimed += nr_reclaim; continue; } else if (nr_reclaim < 0) { offset += -nr_reclaim; continue; } } offset++; } if (to_scan <= 0 || total_reclaimed) break; } } /* * Try to get swap entries with specified order from current cpu's swap entry * pool (a cluster). This might involve allocating a new cluster for current CPU * too. */ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order, unsigned char usage) { struct percpu_cluster *cluster; struct swap_cluster_info *ci; unsigned int offset, found = 0; new_cluster: lockdep_assert_held(&si->lock); cluster = this_cpu_ptr(si->percpu_cluster); offset = cluster->next[order]; if (offset) { offset = alloc_swap_scan_cluster(si, offset, &found, order, usage); if (found) goto done; } if (!list_empty(&si->free_clusters)) { ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); VM_BUG_ON(!found); goto done; } if (order < PMD_ORDER) { unsigned int frags = 0; while (!list_empty(&si->nonfull_clusters[order])) { ci = list_first_entry(&si->nonfull_clusters[order], struct swap_cluster_info, list); list_move_tail(&ci->list, &si->frag_clusters[order]); ci->flags = CLUSTER_FLAG_FRAG; si->frag_cluster_nr[order]++; offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); frags++; if (found) break; } if (!found) { /* * Nonfull clusters are moved to frag tail if we reached * here, count them too, don't over scan the frag list. */ while (frags < si->frag_cluster_nr[order]) { ci = list_first_entry(&si->frag_clusters[order], struct swap_cluster_info, list); /* * Rotate the frag list to iterate, they were all failing * high order allocation or moved here due to per-CPU usage, * this help keeping usable cluster ahead. */ list_move_tail(&ci->list, &si->frag_clusters[order]); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); frags++; if (found) break; } } } if (found) goto done; if (!list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); goto new_cluster; } if (order) goto done; /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { /* * Clusters here have at least one usable slots and can't fail order 0 * allocation, but reclaim may drop si->lock and race with another user. */ while (!list_empty(&si->frag_clusters[o])) { ci = list_first_entry(&si->frag_clusters[o], struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, 0, usage); if (found) goto done; } while (!list_empty(&si->nonfull_clusters[o])) { ci = list_first_entry(&si->nonfull_clusters[o], struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, 0, usage); if (found) goto done; } } done: /* Try reclaim from full clusters if device is nearfull */ if (vm_swap_full() && (!found || (si->pages - si->inuse_pages) < SWAPFILE_CLUSTER)) { swap_reclaim_full_clusters(si); if (!found && !order && si->pages != si->inuse_pages) goto new_cluster; } cluster->next[order] = offset; return found; } static void __del_from_avail_list(struct swap_info_struct *si) { int nid; assert_spin_locked(&si->lock); for_each_node(nid) plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]); } static void del_from_avail_list(struct swap_info_struct *si) { spin_lock(&swap_avail_lock); __del_from_avail_list(si); spin_unlock(&swap_avail_lock); } static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned int end = offset + nr_entries - 1; if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries); if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); } } static void add_to_avail_list(struct swap_info_struct *si) { int nid; spin_lock(&swap_avail_lock); for_each_node(nid) plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]); spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); unsigned int i; /* * Use atomic clear_bit operations only on zeromap instead of non-atomic * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. */ for (i = 0; i < nr_entries; i++) clear_bit(offset + i, si->zeromap); if (offset < si->lowest_bit) si->lowest_bit = offset; if (end > si->highest_bit) { bool was_full = !si->highest_bit; WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); /* * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 * only after the above cleanups are done. */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); } static void set_cluster_next(struct swap_info_struct *si, unsigned long next) { unsigned long prev; if (!(si->flags & SWP_SOLIDSTATE)) { si->cluster_next = next; return; } prev = this_cpu_read(*si->cluster_next_cpu); /* * Cross the swap address space size aligned trunk, choose * another trunk randomly to avoid lock contention on swap * address space if possible. */ if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != (next >> SWAP_ADDRESS_SPACE_SHIFT)) { /* No free swap slots available */ if (si->highest_bit <= si->lowest_bit) return; next = get_random_u32_inclusive(si->lowest_bit, si->highest_bit); next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); next = max_t(unsigned int, next, si->lowest_bit); } this_cpu_write(*si->cluster_next_cpu, next); } static bool swap_offset_available_and_locked(struct swap_info_struct *si, unsigned long offset) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); return true; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); return true; } return false; } static int cluster_alloc_swap(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { int n_ret = 0; VM_BUG_ON(!si->cluster_info); while (n_ret < nr) { unsigned long offset = cluster_alloc_swap_entry(si, order, usage); if (!offset) break; slots[n_ret++] = swp_entry(si->type, offset); } return n_ret; } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; unsigned int nr_pages = 1 << order; int n_ret = 0; bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ if (order > 0) { /* * Should not even be attempting large allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP) || nr_pages > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); return 0; } /* * Swapfile is not block device or not using clusters so unable * to allocate large entries. */ if (!(si->flags & SWP_BLKDEV) || !si->cluster_info) return 0; } if (si->cluster_info) return cluster_alloc_swap(si, usage, nr, slots, order); si->flags += SWP_SCANNING; /* For HDD, sequential access is more important. */ scan_base = si->cluster_next; offset = scan_base; if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= READ_ONCE(si->highest_bit); offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed > 0) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { if (!n_ret) goto scan; else goto done; } memset(si->swap_map + offset, usage, nr_pages); swap_range_alloc(si, offset, nr_pages); slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } if (si->cluster_nr && !si->swap_map[++offset]) { /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; goto checks; } /* * Even if there's no free clusters available (fragmented), * try to scan a little more quickly with lock held unless we * have scanned too many slots already. */ if (!scanned_many) { unsigned long scan_limit; if (offset < scan_base) scan_limit = scan_base; else scan_limit = si->highest_bit; for (; offset <= scan_limit && --latency_ration > 0; offset++) { if (!si->swap_map[offset]) goto checks; } } done: if (order == 0) set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: VM_WARN_ON(order > 0); spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; } offset = si->lowest_bit; while (offset < scan_base) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order) { int order = swap_entry_order(entry_order); unsigned long size = 1 << order; struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) { spin_unlock(&swap_avail_lock); goto noswap; } n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries, order); spin_unlock(&si->lock); if (n_ret || size > 1) goto check_out; cond_resched(); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (data_race(!(si->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= si->max) goto bad_offset; if (data_race(!si->swap_map[swp_offset(entry)])) goto bad_free; return si; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *si, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = si->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(si, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(si->swap_map[offset], usage); else WRITE_ONCE(si->swap_map[offset], SWAP_HAS_CACHE); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, RCU * reader side is locked, etc., the swap entry may become invalid * because of swapoff. Then, we need to enclose all swap related * functions with get_swap_device() and put_swap_device(), unless the * swap functions call get/put_swap_device() by themselves. * * RCU reader side lock (including any spinlock) is sufficient to * prevent swapoff, because synchronize_rcu() is called in swapoff() * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!percpu_ref_tryget_live(&si->users)) goto out; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(). */ smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(si, offset); usage = __swap_entry_free_locked(si, offset, 1); unlock_cluster_or_swap_info(si, ci); if (!usage) free_swap_slot(entry); return usage; } static bool __swap_entries_free(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); unsigned int type = swp_type(entry); struct swap_cluster_info *ci; bool has_cache = false; unsigned char count; int i; if (nr <= 1 || swap_count(data_race(si->swap_map[offset])) != 1) goto fallback; /* cross into another cluster */ if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER) goto fallback; ci = lock_cluster_or_swap_info(si, offset); if (!swap_is_last_map(si, offset, nr, &has_cache)) { unlock_cluster_or_swap_info(si, ci); goto fallback; } for (i = 0; i < nr; i++) WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE); unlock_cluster_or_swap_info(si, ci); if (!has_cache) { for (i = 0; i < nr; i++) zswap_invalidate(swp_entry(si->type, offset + i)); spin_lock(&si->lock); swap_entry_range_free(si, entry, nr); spin_unlock(&si->lock); } return has_cache; fallback: for (i = 0; i < nr; i++) { if (data_race(si->swap_map[offset + i])) { count = __swap_entry_free(si, swp_entry(type, offset + i)); if (count == SWAP_HAS_CACHE) has_cache = true; } else { WARN_ON_ONCE(1); } } return has_cache; } /* * Drop the last HAS_CACHE flag of swap entries, caller have to * ensure all entries belong to the same cgroup. */ static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry, unsigned int nr_pages) { unsigned long offset = swp_offset(entry); unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; struct swap_cluster_info *ci; ci = lock_cluster(si, offset); do { VM_BUG_ON(*map != SWAP_HAS_CACHE); *map = 0; } while (++map < map_end); dec_cluster_info_page(si, ci, nr_pages); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, nr_pages); swap_range_free(si, offset, nr_pages); } static void cluster_swap_free_nr(struct swap_info_struct *si, unsigned long offset, int nr_pages, unsigned char usage) { struct swap_cluster_info *ci; DECLARE_BITMAP(to_free, BITS_PER_LONG) = { 0 }; int i, nr; ci = lock_cluster_or_swap_info(si, offset); while (nr_pages) { nr = min(BITS_PER_LONG, nr_pages); for (i = 0; i < nr; i++) { if (!__swap_entry_free_locked(si, offset + i, usage)) bitmap_set(to_free, i, 1); } if (!bitmap_empty(to_free, BITS_PER_LONG)) { unlock_cluster_or_swap_info(si, ci); for_each_set_bit(i, to_free, BITS_PER_LONG) free_swap_slot(swp_entry(si->type, offset + i)); if (nr == nr_pages) return; bitmap_clear(to_free, 0, BITS_PER_LONG); ci = lock_cluster_or_swap_info(si, offset); } offset += nr; nr_pages -= nr; } unlock_cluster_or_swap_info(si, ci); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free_nr(swp_entry_t entry, int nr_pages) { int nr; struct swap_info_struct *sis; unsigned long offset = swp_offset(entry); sis = _swap_info_get(entry); if (!sis) return; while (nr_pages) { nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); cluster_swap_free_nr(sis, offset, nr, 1); offset += nr; nr_pages -= nr; } } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; struct swap_info_struct *si; int size = 1 << swap_entry_order(folio_order(folio)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster_or_swap_info(si, offset); if (size > 1 && swap_is_has_cache(si, offset, size)) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); swap_entry_range_free(si, entry, size); spin_unlock(&si->lock); return; } for (int i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { unlock_cluster_or_swap_info(si, ci); free_swap_slot(entry); if (i == size - 1) return; lock_cluster_or_swap_info(si, offset); } } unlock_cluster_or_swap_info(si, ci); } static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; return (int)swp_type(*e1) - (int)swp_type(*e2); } void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; /* * Sort swap entries by swap device, so each lock is only taken once. * nr_swapfiles isn't absolutely correct, but the overhead of sort() is * so low that it isn't necessary to optimize further. */ if (nr_swapfiles > 1) sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_range_free(p, entries[i], 1); prev = p; } if (p) spin_unlock(&p->lock); } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si = swp_swap_info(entry); pgoff_t offset = swp_offset(entry); return swap_count(si->swap_map[offset]); } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster_or_swap_info(si, ci); return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; si = _swap_info_get(entry); if (!si) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_local_page(page); tmp_count = map[offset]; kunmap_local(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(si, ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry, int order) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned int nr_pages = 1 << order; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, nr_pages); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); if (!ci || nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < nr_pages; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster_or_swap_info(si, ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio->swap; struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_swapcount(si, entry) != 0; return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); } static bool folio_swapcache_freeable(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; return true; } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { if (!folio_swapcache_freeable(folio)) return false; if (folio_swapped(folio)) return false; delete_from_swap_cache(folio); folio_set_dirty(folio); return true; } /** * free_swap_and_cache_nr() - Release reference on range of swap entries and * reclaim their cache if no more references remain. * @entry: First entry of range. * @nr: Number of entries in range. * * For each swap entry in the contiguous range, release a reference. If any swap * entries become free, try to reclaim their underlying folios, if present. The * offset range is defined by [entry.offset, entry.offset + nr). */ void free_swap_and_cache_nr(swp_entry_t entry, int nr) { const unsigned long start_offset = swp_offset(entry); const unsigned long end_offset = start_offset + nr; struct swap_info_struct *si; bool any_only_cache = false; unsigned long offset; if (non_swap_entry(entry)) return; si = get_swap_device(entry); if (!si) return; if (WARN_ON(end_offset > si->max)) goto out; /* * First free all entries in the range. */ any_only_cache = __swap_entries_free(si, entry, nr); /* * Short-circuit the below loop if none of the entries had their * reference drop to zero. */ if (!any_only_cache) goto out; /* * Now go back over the range trying to reclaim the swap cache. This is * more efficient for large folios because we will only try to reclaim * the swap once per folio in the common case. If we do * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the * latter will get a reference and lock the folio for every individual * page but will only succeed once the swap slot for every subpage is * zero. */ for (offset = start_offset; offset < end_offset; offset += nr) { nr = 1; if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { /* * Folios are always naturally aligned in swap so * advance forward to the next boundary. Zero means no * folio was found for the swap entry, so advance by 1 * in this case. Negative value means folio was found * but could not be reclaimed. Here we can still advance * to the next boundary. */ nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); if (nr == 0) nr = 1; else if (nr < 0) nr = -nr; nr = ALIGN(offset + 1, nr) - offset; } } out: put_swap_device(si); } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ spin_lock(&si->lock); if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0)) atomic_long_dec(&nr_swap_pages); spin_unlock(&si->lock); fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page; struct folio *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; bool hwpoisoned = false; int ret = 1; swapcache = folio; folio = ksm_might_need_to_copy(folio, vma, addr); if (unlikely(!folio)) return -ENOMEM; else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { hwpoisoned = true; folio = swapcache; } page = folio_file_page(folio, swp_offset(entry)); if (PageHWPoison(page)) hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), swp_entry_to_pte(entry)))) { ret = 0; goto out; } old_pte = ptep_get(pte); if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); if (hwpoisoned) { swp_entry = make_hwpoison_entry(page); } else { swp_entry = make_poisoned_swp_entry(); } new_pte = swp_entry_to_pte(swp_entry); ret = 0; goto setpte; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); folio_get(folio); if (folio == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): writeback would be problematic. * However, we do a folio_wait_writeback() just before this * call and have the folio locked. */ VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; /* * We currently only expect small !anon folios, which are either * fully exclusive or fully shared. If we ever get large folios * here, we have to be careful. */ if (!folio_test_anon(folio)) { VM_WARN_ON_ONCE(folio_test_large(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); } else { folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } } else { /* ksm created a completely new copy */ folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(old_pte)) new_pte = pte_mkuffd_wp(new_pte); setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: if (pte) pte_unmap_unlock(pte, ptl); if (folio != swapcache) { folio_unlock(folio); folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { pte_t *pte = NULL; struct swap_info_struct *si; si = swap_info[type]; do { struct folio *folio; unsigned long offset; unsigned char swp_count; swp_entry_t entry; int ret; pte_t ptent; if (!pte++) { pte = pte_offset_map(pmd, addr); if (!pte) break; } ptent = ptep_get_lockless(pte); if (!is_swap_pte(ptent)) continue; entry = pte_to_swp_entry(ptent); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); pte = NULL; folio = swap_cache_get_folio(entry, vma, addr); if (!folio) { struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!folio) { swp_count = READ_ONCE(si->swap_map[offset]); if (swp_count == 0 || swp_count == SWAP_MAP_BAD) continue; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); return ret; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } while (addr += PAGE_SIZE, addr != end); if (pte) pte_unmap(pte); return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (vma->anon_vma) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!READ_ONCE(si->inuse_pages)) goto success; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry)); if (IS_ERR(folio)) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writepage() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; return -EINTR; } success: /* * Make sure that further cleanups after try_to_unuse() returns happen * after swap_range_free() reduces si->inuse_pages to 0. */ smp_mb(); return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *si) { struct block_device *bdev; if (si->bdev) bdev = si->bdev; else bdev = si->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { int i; if (prio >= 0) si->prio = prio; else si->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ si->list.prio = -si->prio; for_each_node(i) { if (si->prio >= 0) si->avail_lists[i].prio = -si->prio; else { if (swap_node(si) == i) si->avail_lists[i].prio = 1; else si->avail_lists[i].prio = -si->prio; } } si->swap_map = swap_map; si->cluster_info = cluster_info; si->zeromap = zeromap; } static void _enable_swap_info(struct swap_info_struct *si) { si->flags |= SWP_WRITEOK; atomic_long_add(si->pages, &nr_swap_pages); total_swap_pages += si->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&si->list, &swap_active_head); /* add to available list iff swap device is not full */ if (si->highest_bit) add_to_avail_list(si); } static void enable_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, prio, swap_map, cluster_info, zeromap); spin_unlock(&si->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&si->users); spin_lock(&swap_lock); spin_lock(&si->lock); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static bool __has_usable_swap(void) { return !plist_head_empty(&swap_active_head); } bool has_usable_swap(void) { bool ret; spin_lock(&swap_lock); ret = __has_usable_swap(); spin_unlock(&swap_lock); return ret; } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; unsigned long *zeromap; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); /* * Wait for swap operations protected by get/put_swap_device() * to complete. Because of synchronize_rcu() here, all swap * operations protected by RCU reader side lock (including any * spinlock) will be waited too. This makes it easy to * prevent folio_test_swapcache() and the following swap cache * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; zeromap = p->zeromap; p->zeromap = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = K(si->pages); inuse = K(READ_ONCE(si->inuse_pages)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *si, struct inode *inode) { if (S_ISBLK(inode->i_mode)) { si->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(si->bdev)) return -EINVAL; si->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { si->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *si, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } si->lowest_bit = 1; si->cluster_next = 1; si->cluster_nr = 0; maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", K(maxpages), K(last_page)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } si->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *si, union swap_header *swap_header, unsigned char *swap_map, unsigned long maxpages, sector_t *span) { unsigned int nr_good_pages; unsigned long i; int nr_extents; nr_good_pages = maxpages - 1; /* omit header page */ for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; } } if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; si->max = maxpages; si->pages = nr_good_pages; nr_extents = setup_swap_extents(si, span); if (nr_extents < 0) return nr_extents; nr_good_pages = si->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } return nr_extents; } static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, union swap_header *swap_header, unsigned long maxpages) { unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = si->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; struct swap_cluster_info *cluster_info; unsigned long i, j, k, idx; int cpu, err = -ENOMEM; cluster_info = kvcalloc(nr_clusters, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) goto err; for (i = 0; i < nr_clusters; i++) spin_lock_init(&cluster_info[i].lock); si->cluster_next_cpu = alloc_percpu(unsigned int); if (!si->cluster_next_cpu) goto err_free; /* Random start position to help with wear leveling */ for_each_possible_cpu(cpu) per_cpu(*si->cluster_next_cpu, cpu) = get_random_u32_inclusive(1, si->highest_bit); si->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!si->percpu_cluster) goto err_free; for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(si->percpu_cluster, cpu); for (i = 0; i < SWAP_NR_ORDERS; i++) cluster->next[i] = SWAP_NEXT_INVALID; } /* * Mark unusable pages as unavailable. The clusters aren't * marked free yet, so no list operations are involved yet. * * See setup_swap_map_and_extents(): header page, bad pages, * and the EOF part of the last cluster. */ inc_cluster_info_page(si, cluster_info, 0); for (i = 0; i < swap_header->info.nr_badpages; i++) inc_cluster_info_page(si, cluster_info, swap_header->info.badpages[i]); for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(si, cluster_info, i); INIT_LIST_HEAD(&si->free_clusters); INIT_LIST_HEAD(&si->full_clusters); INIT_LIST_HEAD(&si->discard_clusters); for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&si->nonfull_clusters[i]); INIT_LIST_HEAD(&si->frag_clusters[i]); si->frag_cluster_nr[i] = 0; } /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { struct swap_cluster_info *ci; idx = i * SWAP_CLUSTER_COLS + j; ci = cluster_info + idx; if (idx >= nr_clusters) continue; if (ci->count) { ci->flags = CLUSTER_FLAG_NONFULL; list_add_tail(&ci->list, &si->nonfull_clusters[0]); continue; } ci->flags = CLUSTER_FLAG_FREE; list_add_tail(&ci->list, &si->free_clusters); } } return cluster_info; err_free: kvfree(cluster_info); err: return ERR_PTR(err); } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *si; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; unsigned long *zeromap = NULL; struct swap_cluster_info *cluster_info = NULL; struct folio *folio = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; si = alloc_swap_info(); if (IS_ERR(si)) return PTR_ERR(si); INIT_WORK(&si->discard_work, swap_discard_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } si->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(si, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } folio = read_mapping_folio(mapping, 0, swap_file); if (IS_ERR(folio)) { error = PTR_ERR(folio); goto bad_swap_unlock_inode; } swap_header = kmap_local_folio(folio, 0); maxpages = read_swap_header(si, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } error = swap_cgroup_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might * be above MAX_PAGE_ORDER incase of a large swap file. */ zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!zeromap) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (si->bdev && bdev_stable_writes(si->bdev)) si->flags |= SWP_STABLE_WRITES; if (si->bdev && bdev_synchronous(si->bdev)) si->flags |= SWP_SYNCHRONOUS_IO; if (si->bdev && bdev_nonrot(si->bdev)) { si->flags |= SWP_SOLIDSTATE; cluster_info = setup_clusters(si, swap_header, maxpages); if (IS_ERR(cluster_info)) { error = PTR_ERR(cluster_info); cluster_info = NULL; goto bad_swap_unlock_inode; } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } if ((swap_flags & SWAP_FLAG_DISCARD) && si->bdev && bdev_max_discard_sectors(si->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) si->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) si->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (si->flags & SWP_AREA_DISCARD) { int err = discard_swap(si); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", si, err); } } error = init_swap_address_space(si->type, maxpages); if (error) goto bad_swap_unlock_inode; error = zswap_swapon(si->type, maxpages); if (error) goto free_swap_address_space; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_zswap; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(si, prio, swap_map, cluster_info, zeromap); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(si->pages), name->name, si->prio, nr_extents, K((unsigned long long)span), (si->flags & SWP_SOLIDSTATE) ? "SS" : "", (si->flags & SWP_DISCARDABLE) ? "D" : "", (si->flags & SWP_AREA_DISCARD) ? "s" : "", (si->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_zswap: zswap_swapoff(si->type); free_swap_address_space: exit_swap_address_space(si->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(si->percpu_cluster); si->percpu_cluster = NULL; free_percpu(si->cluster_next_cpu); si->cluster_next_cpu = NULL; inode = NULL; destroy_swap_extents(si); swap_cgroup_swapoff(si->type); spin_lock(&swap_lock); si->swap_file = NULL; si->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (!IS_ERR_OR_NULL(folio)) folio_release_kmap(folio, swap_header); if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += READ_ONCE(si->inuse_pages); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that nr swap entries are valid and increment their swap map counts. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err, i; si = swp_swap_info(entry); offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); VM_WARN_ON(usage == 1 && nr > 1); ci = lock_cluster_or_swap_info(si, offset); err = 0; for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (!count && !has_cache) { err = -ENOENT; } else if (usage == SWAP_HAS_CACHE) { if (has_cache) err = -EEXIST; } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { err = -EINVAL; } if (err) goto unlock_out; } for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) has_cache = SWAP_HAS_CACHE; else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if (swap_count_continued(si, offset + i, count)) count = COUNT_CONTINUED; else { /* * Don't need to rollback changes, because if * usage == 1, there must be nr == 1. */ err = -ENOMEM; goto unlock_out; } WRITE_ONCE(si->swap_map[offset + i], count | has_cache); } unlock_out: unlock_cluster_or_swap_info(si, ci); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry, int nr) { __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: first swap entry from which we allocate nr swap cache. * * Called when allocating swap cache for existing swap entries, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry, int nr) { return __swap_duplicate(entry, SWAP_HAS_CACHE, nr); } void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); cluster_swap_free_nr(si, offset, nr, SWAP_HAS_CACHE); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } /* * out-of-line methods to avoid include hell. */ struct address_space *swapcache_mapping(struct folio *folio) { return swp_swap_info(folio->swap)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __folio_swap_cache_index(struct folio *folio) { return swap_cache_index(folio->swap); } EXPORT_SYMBOL_GPL(__folio_swap_cache_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } spin_lock(&si->lock); offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_local_page(list_page) + offset; count = *map; kunmap_local(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); spin_unlock(&si->lock); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_local(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; kunmap_local(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_local(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si, *next; int nid = folio_nid(folio); if (!(gfp & __GFP_IO)) return; if (!__has_usable_swap()) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_disk) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 32 552 527 141 460 283 197 22 22 15 15 191 31 115 202 9 119 387 231 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H #include <linux/container_of.h> #include <linux/types.h> #include <linux/stddef.h> #include <linux/poison.h> #include <linux/const.h> #include <asm/barrier.h> /* * Circular doubly linked list implementation. * * Some of the internal functions ("__xxx") are useful when * manipulating whole lists rather than single entries, as * sometimes we already know the next/prev entries and we can * generate better code by using them directly rather than * using the generic single-entry routines. */ #define LIST_HEAD_INIT(name) { &(name), &(name) } #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) /** * INIT_LIST_HEAD - Initialize a list_head structure * @list: list_head structure to be initialized. * * Initializes the list_head to point to itself. If it is a list header, * the result is an empty list. */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } #ifdef CONFIG_LIST_HARDENED #ifdef CONFIG_DEBUG_LIST # define __list_valid_slowpath #else # define __list_valid_slowpath __cold __preserve_most #endif /* * Performs the full set of list corruption checks before __list_add(). * On list corruption reports a warning, and returns false. */ extern bool __list_valid_slowpath __list_add_valid_or_report(struct list_head *new, struct list_head *prev, struct list_head *next); /* * Performs list corruption checks before __list_add(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_add_valid_or_report(). */ static __always_inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { /* * With the hardening version, elide checking if next and prev * are NULL, since the immediate dereference of them below would * result in a fault if NULL. * * With the reduced set of checks, we can afford to inline the * checks, which also gives the compiler a chance to elide some * of them completely if they can be proven at compile-time. If * one of the pre-conditions does not hold, the slow-path will * show a report which pre-condition failed. */ if (likely(next->prev == prev && prev->next == next && new != prev && new != next)) return true; ret = false; } ret &= __list_add_valid_or_report(new, prev, next); return ret; } /* * Performs the full set of list corruption checks before __list_del_entry(). * On list corruption reports a warning, and returns false. */ extern bool __list_valid_slowpath __list_del_entry_valid_or_report(struct list_head *entry); /* * Performs list corruption checks before __list_del_entry(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_del_entry_valid_or_report(). */ static __always_inline bool __list_del_entry_valid(struct list_head *entry) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { struct list_head *prev = entry->prev; struct list_head *next = entry->next; /* * With the hardening version, elide checking if next and prev * are NULL, LIST_POISON1 or LIST_POISON2, since the immediate * dereference of them below would result in a fault. */ if (likely(prev->next == entry && next->prev == entry)) return true; ret = false; } ret &= __list_del_entry_valid_or_report(entry); return ret; } #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { return true; } static inline bool __list_del_entry_valid(struct list_head *entry) { return true; } #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } /** * list_add - add a new entry * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } /** * list_add_tail - add a new entry * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. */ static inline void list_add_tail(struct list_head *new, struct list_head *head) { __list_add(new, head->prev, head); } /* * Delete a list entry by making the prev/next entries * point to each other. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; WRITE_ONCE(prev->next, next); } /* * Delete a list entry and clear the 'prev' pointer. * * This is a special-purpose list clearing method used in the networking code * for lists allocated as per-cpu, where we don't want to incur the extra * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this * needs to check the node 'prev' pointer instead of calling list_empty(). */ static inline void __list_del_clearprev(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->prev = NULL; } static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) return; __list_del(entry->prev, entry->next); } /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } /** * list_replace - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace(struct list_head *old, struct list_head *new) { new->next = old->next; new->next->prev = new; new->prev = old->prev; new->prev->next = new; } /** * list_replace_init - replace old entry by new one and initialize the old one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace_init(struct list_head *old, struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); } /** * list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position * @entry1: the location to place entry2 * @entry2: the location to place entry1 */ static inline void list_swap(struct list_head *entry1, struct list_head *entry2) { struct list_head *pos = entry2->prev; list_del(entry2); list_replace(entry1, entry2); if (pos == entry1) pos = entry2; list_add(entry1, pos); } /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. */ static inline void list_del_init(struct list_head *entry) { __list_del_entry(entry); INIT_LIST_HEAD(entry); } /** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry */ static inline void list_move(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add(list, head); } /** * list_move_tail - delete from one list and add as another's tail * @list: the entry to move * @head: the head that will follow our entry */ static inline void list_move_tail(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add_tail(list, head); } /** * list_bulk_move_tail - move a subsection of a list to its tail * @head: the head that will follow our entry * @first: first entry to move * @last: last entry to move, can be the same as first * * Move all entries between @first and including @last before @head. * All three entries must belong to the same linked list. */ static inline void list_bulk_move_tail(struct list_head *head, struct list_head *first, struct list_head *last) { first->prev->next = last->next; last->next->prev = first->prev; head->prev->next = first; first->prev = head->prev; last->next = head; head->prev = last; } /** * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** * list_is_head - tests whether @list is the list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_head(const struct list_head *list, const struct list_head *head) { return list == head; } /** * list_empty - tests whether a list is empty * @head: the list to test. */ static inline int list_empty(const struct list_head *head) { return READ_ONCE(head->next) == head; } /** * list_del_init_careful - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. * * This is the same as list_del_init(), except designed to be used * together with list_empty_careful() in a way to guarantee ordering * of other memory operations. * * Any memory operations done before a list_del_init_careful() are * guaranteed to be visible after a list_empty_careful() test. */ static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); WRITE_ONCE(entry->prev, entry); smp_store_release(&entry->next, entry); } /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * * Description: * tests whether a list is empty _and_ checks that no other CPU might be * in the process of modifying either member (next or prev) * * NOTE: using list_empty_careful() without synchronization * can only be safe if the only activity that can happen * to the list entry is list_del_init(). Eg. it cannot be used * if another CPU could re-list_add() it. */ static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); return list_is_head(next, head) && (next == READ_ONCE(head->prev)); } /** * list_rotate_left - rotate the list to the left * @head: the head of the list */ static inline void list_rotate_left(struct list_head *head) { struct list_head *first; if (!list_empty(head)) { first = head->next; list_move_tail(first, head); } } /** * list_rotate_to_front() - Rotate list to specific item. * @list: The desired new front of the list. * @head: The head of the list. * * Rotates list so that @list becomes the new front of the list. */ static inline void list_rotate_to_front(struct list_head *list, struct list_head *head) { /* * Deletes the list head from the list denoted by @head and * places it as the tail of @list, this effectively rotates the * list so that @list is at the front. */ list_move_tail(head, list); } /** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ static inline int list_is_singular(const struct list_head *head) { return !list_empty(head) && (head->next == head->prev); } static inline void __list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { struct list_head *new_first = entry->next; list->next = head->next; list->next->prev = list; list->prev = entry; entry->next = list; head->next = new_first; new_first->prev = head; } /** * list_cut_position - cut a list into two * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * and if so we won't cut the list * * This helper moves the initial part of @head, up to and * including @entry, from @head to @list. You should * pass on @entry an element you know is on @head. @list * should be an empty list or a list you do not care about * losing its data. * */ static inline void list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { if (list_empty(head)) return; if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next)) return; if (list_is_head(entry, head)) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); } /** * list_cut_before - cut a list into two, before given entry * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * * This helper moves the initial part of @head, up to but * excluding @entry, from @head to @list. You should pass * in @entry an element you know is on @head. @list should * be an empty list or a list you do not care about losing * its data. * If @entry == @head, all entries on @head are moved to * @list. */ static inline void list_cut_before(struct list_head *list, struct list_head *head, struct list_head *entry) { if (head->next == entry) { INIT_LIST_HEAD(list); return; } list->next = head->next; list->next->prev = list; list->prev = entry->prev; list->prev->next = list; head->next = entry; entry->prev = head; } static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; first->prev = prev; prev->next = first; last->next = next; next->prev = last; } /** * list_splice - join two lists, this is designed for stacks * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head, head->next); } /** * list_splice_tail - join two lists, each list being a queue * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice_tail(struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head->prev, head); } /** * list_splice_init - join two lists and reinitialise the emptied list. * @list: the new list to add. * @head: the place to add it in the first list. * * The list at @list is reinitialised */ static inline void list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head, head->next); INIT_LIST_HEAD(list); } } /** * list_splice_tail_init - join two lists and reinitialise the emptied list * @list: the new list to add. * @head: the place to add it in the first list. * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void list_splice_tail_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. */ #define list_entry(ptr, type, member) \ container_of(ptr, type, member) /** * list_first_entry - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) /** * list_last_entry - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_last_entry(ptr, type, member) \ list_entry((ptr)->prev, type, member) /** * list_first_entry_or_null - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_first_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->next); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) /** * list_next_entry_circular - get the next element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the last element (return the first element). * Note, that list is expected to be not empty. */ #define list_next_entry_circular(pos, head, member) \ (list_is_last(&(pos)->member, head) ? \ list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member)) /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) /** * list_prev_entry_circular - get the prev element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the first element (return the last element). * Note, that list is expected to be not empty. */ #define list_prev_entry_circular(pos, head, member) \ (list_is_first(&(pos)->member, head) ? \ list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member)) /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_reverse - iterate backwards over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_reverse(pos, head) \ for (pos = (head)->prev; pos != (head); pos = pos->prev) /** * list_for_each_rcu - Iterate over a list in an RCU-safe fashion * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_rcu(pos, head) \ for (pos = rcu_dereference((head)->next); \ !list_is_head(pos, (head)); \ pos = rcu_dereference(pos->next)) /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ for (pos = (head)->next, n = pos->next; \ !list_is_head(pos, (head)); \ pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ !list_is_head(pos, (head)); \ pos = n, n = pos->prev) /** * list_count_nodes - count nodes in the list * @head: the head for your list. */ static inline size_t list_count_nodes(struct list_head *head) { struct list_head *pos; size_t count = 0; list_for_each(pos, head) count++; return count; } /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ list_is_head(&pos->member, (head)) /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_reverse - iterate backwards over list of given type. * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() * @pos: the type * to use as a start point * @head: the head of the list * @member: the name of the list_head within the struct. * * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). */ #define list_prepare_entry(pos, head, member) \ ((pos) ? : list_entry(head, typeof(*pos), member)) /** * list_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position. */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_continue_reverse - iterate backwards from the given point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Start to iterate over list of given type backwards, continuing after * the current position. */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_from - iterate over list of given type from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_from_reverse - iterate backwards over list of given type * from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_continue - continue list iteration safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing after current point, * safe against removal of list entry. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_from - iterate over list from current point safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type from current point, safe against * removal of list entry. */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, safe against removal * of list entry. */ #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** * list_safe_reset_next - reset a stale list_for_each_entry_safe loop * @pos: the loop cursor used in the list_for_each_entry_safe loop * @n: temporary storage used in list_for_each_entry_safe * @member: the name of the list_head within the struct. * * list_safe_reset_next is not safe to use in general if the list may be * modified concurrently (eg. the lock is dropped in the loop body). An * exception to this is if the cursor element (pos) is pinned in the list, * and list_safe_reset_next is called after re-taking the lock and before * completing the current iteration of the loop body. */ #define list_safe_reset_next(pos, n, member) \ n = list_next_entry(pos, member) /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is * too wasteful. * You lose the ability to access the tail in O(1). */ #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) static inline void INIT_HLIST_NODE(struct hlist_node *h) { h->next = NULL; h->pprev = NULL; } /** * hlist_unhashed - Has node been removed from list and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed * state. For example, hlist_nulls_del_init_rcu() does leave the * node in unhashed state, but hlist_nulls_del() does not. */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } /** * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use * @h: Node to be checked * * This variant of hlist_unhashed() must be used in lockless contexts * to avoid potential load-tearing. The READ_ONCE() is paired with the * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } /** * hlist_empty - Is the specified hlist_head structure an empty hlist? * @h: Structure to check. */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (next) WRITE_ONCE(next->pprev, pprev); } /** * hlist_del - Delete the specified hlist_node from its list * @n: Node to delete. * * Note that this function leaves the node in hashed state. Use * hlist_del_init() or similar instead to unhash @n. */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } /** * hlist_del_init - Delete the specified hlist_node from its list and initialize * @n: Node to delete. * * Note that this function leaves the node in unhashed state. */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); INIT_HLIST_NODE(n); } } /** * hlist_add_head - add a new entry at the beginning of the hlist * @n: new entry to be added * @h: hlist head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; WRITE_ONCE(n->next, first); if (first) WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); WRITE_ONCE(n->pprev, &h->first); } /** * hlist_add_before - add a new entry before the one specified * @n: new entry to be added * @next: hlist node to add it before, which must be non-NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } /** * hlist_add_behind - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { WRITE_ONCE(n->next, prev->next); WRITE_ONCE(prev->next, n); WRITE_ONCE(n->pprev, &prev->next); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } /** * hlist_add_fake - create a fake hlist consisting of a single headless node * @n: Node to make a fake list out of * * This makes @n appear to be its own predecessor on a headless hlist. * The point of this is to allow things like hlist_del() to work correctly * in cases where there is no list. */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } /** * hlist_fake: Is this node a fake hlist? * @h: Node to check for being a self-referential fake hlist. */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } /** * hlist_is_singular_node - is node the only element of the specified hlist? * @n: Node to check for singularity. * @h: Header for potentially singular list. * * Check whether the node is the only node of the head without * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) { return !n->next && n->pprev == &h->first; } /** * hlist_move_list - Move an hlist * @old: hlist_head for old list. * @new: hlist_head for new list. * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ static inline void hlist_move_list(struct hlist_head *old, struct hlist_head *new) { new->first = old->first; if (new->first) new->first->pprev = &new->first; old->first = NULL; } /** * hlist_splice_init() - move all entries from one list to another * @from: hlist_head from which entries will be moved * @last: last entry on the @from list * @to: hlist_head to which entries will be moved * * @to can be empty, @from must contain at least @last. */ static inline void hlist_splice_init(struct hlist_head *from, struct hlist_node *last, struct hlist_head *to) { if (to->first) to->first->pprev = &last->next; last->next = to->first; to->first = from->first; from->first->pprev = &to->first; from->first = NULL; } #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) #define hlist_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ }) /** * hlist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry(pos, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue(pos, member) \ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(pos, member) \ for (; pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: a &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_safe(pos, n, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) /** * hlist_count_nodes - count nodes in the hlist * @head: the head for your hlist. */ static inline size_t hlist_count_nodes(struct hlist_head *head) { struct hlist_node *pos; size_t count = 0; hlist_for_each(pos, head) count++; return count; } #endif |
| 187 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_PERCPU_INTERNAL_H #define _MM_PERCPU_INTERNAL_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/memcontrol.h> /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. * * The scan hint is the largest known contiguous area before the contig hint. * It is not necessarily the actual largest contig hint though. There is an * invariant that the scan_hint_start > contig_hint_start iff * scan_hint == contig_hint. This is necessary because when scanning forward, * we don't know if a new contig hint would be better than the current one. */ struct pcpu_block_md { int scan_hint; /* scan hint for block */ int scan_hint_start; /* block relative starting position of the scan hint */ int contig_hint; /* contig hint for block */ int contig_hint_start; /* block relative starting position of the contig hint */ int left_free; /* size of free space along the left side of the block */ int right_free; /* size of free space along the right side of the block */ int first_free; /* block position of first free */ int nr_bits; /* total bits responsible for */ }; struct pcpuobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *cgroup; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref tag; #endif }; #if defined(CONFIG_MEMCG) || defined(CONFIG_MEM_ALLOC_PROFILING) #define NEED_PCPUOBJ_EXT #endif struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ size_t max_alloc_size; /* largest allocation size */ #endif struct list_head list; /* linked to pcpu_slot lists */ int free_bytes; /* free bytes in the chunk */ struct pcpu_block_md chunk_md; unsigned long *bound_map; /* boundary map */ /* * base_addr is the base address of this chunk. * To reduce false sharing, current layout is optimized to make sure * base_addr locate in the different cacheline with free_bytes and * chunk_md. */ void *base_addr ____cacheline_aligned_in_smp; unsigned long *alloc_map; /* allocation map */ struct pcpu_block_md *md_blocks; /* metadata blocks */ void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ bool isolated; /* isolated from active chunk slots */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ int end_offset; /* additional area required to have the region end page aligned */ #ifdef NEED_PCPUOBJ_EXT struct pcpuobj_ext *obj_exts; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ int nr_populated; /* # of populated pages */ int nr_empty_pop_pages; /* # of empty populated pages */ unsigned long populated[]; /* populated bitmap */ }; static inline bool need_pcpuobj_ext(void) { if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING)) return true; if (!mem_cgroup_kmem_disabled()) return true; return false; } extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_sidelined_slot; extern int pcpu_to_depopulate_slot; extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; /** * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bitmap blocks used. */ static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) { return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; } /** * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap * @pages: number of physical pages * * This conversion is from physical pages to the number of bits * required in the bitmap. */ static inline int pcpu_nr_pages_to_map_bits(int pages) { return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; } /** * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bits in the bitmap. */ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) { return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } /** * pcpu_obj_full_size - helper to calculate size of each accounted object * @size: size of area to allocate in bytes * * For each accounted object there is an extra space which is used to store * obj_cgroup membership if kmemcg is not disabled. Charge it too. */ static inline size_t pcpu_obj_full_size(size_t size) { size_t extra_size = 0; #ifdef CONFIG_MEMCG if (!mem_cgroup_kmem_disabled()) extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); #endif return size * num_possible_cpus() + extra_size; } #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> struct percpu_stats { u64 nr_alloc; /* lifetime # of allocations */ u64 nr_dealloc; /* lifetime # of deallocations */ u64 nr_cur_alloc; /* current # of allocations */ u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ size_t min_alloc_size; /* min allocation size */ size_t max_alloc_size; /* max allocation size */ }; extern struct percpu_stats pcpu_stats; extern struct pcpu_alloc_info pcpu_stats_ai; /* * For debug purposes. We don't care about the flexible array. */ static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); /* initialize min_alloc_size to unit_size */ pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; } /* * pcpu_stats_area_alloc - increment area allocation stats * @chunk: the location of the area being allocated * @size: size of area to allocate in bytes * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_alloc++; pcpu_stats.nr_cur_alloc++; pcpu_stats.nr_max_alloc = max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); pcpu_stats.min_alloc_size = min(pcpu_stats.min_alloc_size, size); pcpu_stats.max_alloc_size = max(pcpu_stats.max_alloc_size, size); chunk->nr_alloc++; chunk->max_alloc_size = max(chunk->max_alloc_size, size); } /* * pcpu_stats_area_dealloc - decrement allocation stats * @chunk: the location of the area being deallocated * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_dealloc++; pcpu_stats.nr_cur_alloc--; chunk->nr_alloc--; } /* * pcpu_stats_chunk_alloc - increment chunk stats */ static inline void pcpu_stats_chunk_alloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks++; pcpu_stats.nr_max_chunks = max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); spin_unlock_irqrestore(&pcpu_lock, flags); } /* * pcpu_stats_chunk_dealloc - decrement chunk stats */ static inline void pcpu_stats_chunk_dealloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks--; spin_unlock_irqrestore(&pcpu_lock, flags); } #else static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { } static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { } static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { } static inline void pcpu_stats_chunk_alloc(void) { } static inline void pcpu_stats_chunk_dealloc(void) { } #endif /* !CONFIG_PERCPU_STATS */ #endif |
| 548 117 346 809 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for atomic bit * operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #include <linux/instrumented.h> /** * set_bit - Atomically set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void set_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_set_bit(nr, addr); } /** * clear_bit - Clears a bit in memory * @nr: Bit to clear * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). */ static __always_inline void clear_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_clear_bit(nr, addr); } /** * change_bit - Toggle a bit in memory * @nr: Bit to change * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void change_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_change_bit(nr, addr); } /** * test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_set_bit(nr, addr); } /** * test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_clear_bit(nr, addr); } /** * test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_change_bit(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ |
| 168 168 168 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM writeback #if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WRITEBACK_H #include <linux/tracepoint.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #define show_inode_state(state) \ __print_flags(state, "|", \ {I_DIRTY_SYNC, "I_DIRTY_SYNC"}, \ {I_DIRTY_DATASYNC, "I_DIRTY_DATASYNC"}, \ {I_DIRTY_PAGES, "I_DIRTY_PAGES"}, \ {I_NEW, "I_NEW"}, \ {I_WILL_FREE, "I_WILL_FREE"}, \ {I_FREEING, "I_FREEING"}, \ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ {I_REFERENCED, "I_REFERENCED"}, \ {I_LINKABLE, "I_LINKABLE"}, \ {I_WB_SWITCH, "I_WB_SWITCH"}, \ {I_OVL_INUSE, "I_OVL_INUSE"}, \ {I_CREATING, "I_CREATING"}, \ {I_DONTCACHE, "I_DONTCACHE"}, \ {I_SYNC_QUEUED, "I_SYNC_QUEUED"}, \ {I_PINNING_NETFS_WB, "I_PINNING_NETFS_WB"}, \ {I_LRU_ISOLATING, "I_LRU_ISOLATING"} \ ) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); #define WB_WORK_REASON \ EM( WB_REASON_BACKGROUND, "background") \ EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EM( WB_REASON_FORKER_THREAD, "forker_thread") \ EMe(WB_REASON_FOREIGN_FLUSH, "foreign_flush") WB_WORK_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } struct wb_writeback_work; DECLARE_EVENT_CLASS(writeback_folio_template, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(pgoff_t, index) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = folio->index; ), TP_printk("bdi %s: ino=%lu index=%lu", __entry->name, (unsigned long)__entry->ino, __entry->index ) ); DEFINE_EVENT(writeback_folio_template, writeback_dirty_folio, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping) ); DEFINE_EVENT(writeback_folio_template, folio_wait_writeback, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping) ); DECLARE_EVENT_CLASS(writeback_dirty_inode_template, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, flags) ), TP_fast_assign( struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; ), TP_printk("bdi %s: ino=%lu state=%s flags=%s", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), show_inode_state(__entry->flags) ) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); #ifdef CREATE_TRACE_POINTS #ifdef CONFIG_CGROUP_WRITEBACK static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return cgroup_ino(wb->memcg_css->cgroup); } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { if (wbc->wb) return __trace_wb_assign_cgroup(wbc->wb); else return 1; } #else /* CONFIG_CGROUP_WRITEBACK */ static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return 1; } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { return 1; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* CREATE_TRACE_POINTS */ #ifdef CONFIG_CGROUP_WRITEBACK TRACE_EVENT(inode_foreign_history, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned int history), TP_ARGS(inode, wbc, history), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, cgroup_ino) __field(unsigned int, history) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; ), TP_printk("bdi %s: ino=%lu cgroup_ino=%lu history=0x%x", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->cgroup_ino, __entry->history ) ); TRACE_EVENT(inode_switch_wbs, TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb), TP_ARGS(inode, old_wb, new_wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, old_cgroup_ino) __field(ino_t, new_cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); ), TP_printk("bdi %s: ino=%lu old_cgroup_ino=%lu new_cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->old_cgroup_ino, (unsigned long)__entry->new_cgroup_ino ) ); TRACE_EVENT(track_foreign_dirty, TP_PROTO(struct folio *folio, struct bdi_writeback *wb), TP_ARGS(folio, wb), TP_STRUCT__entry( __array(char, name, 32) __field(u64, bdi_id) __field(ino_t, ino) __field(unsigned int, memcg_id) __field(ino_t, cgroup_ino) __field(ino_t, page_cgroup_ino) ), TP_fast_assign( struct address_space *mapping = folio_mapping(folio); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->page_cgroup_ino = cgroup_ino(folio_memcg(folio)->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", __entry->name, __entry->bdi_id, (unsigned long)__entry->ino, __entry->memcg_id, (unsigned long)__entry->cgroup_ino, (unsigned long)__entry->page_cgroup_ino ) ); TRACE_EVENT(flush_foreign, TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id, unsigned int frn_memcg_id), TP_ARGS(wb, frn_bdi_id, frn_memcg_id), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) __field(unsigned int, frn_bdi_id) __field(unsigned int, frn_memcg_id) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; ), TP_printk("bdi %s: cgroup_ino=%lu frn_bdi_id=%u frn_memcg_id=%u", __entry->name, (unsigned long)__entry->cgroup_ino, __entry->frn_bdi_id, __entry->frn_memcg_id ) ); #endif DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(int, sync_mode) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, __entry->sync_mode, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DECLARE_EVENT_CLASS(writeback_work_class, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), TP_ARGS(wb, work), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_pages) __field(dev_t, sb_dev) __field(int, sync_mode) __field(int, for_kupdate) __field(int, range_cyclic) __field(int, for_background) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; __entry->for_kupdate = work->for_kupdate; __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%lu", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), \ TP_ARGS(wb, work)) DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); DEFINE_WRITEBACK_WORK_EVENT(writeback_written); DEFINE_WRITEBACK_WORK_EVENT(writeback_wait); TRACE_EVENT(writeback_pages_written, TP_PROTO(long pages_written), TP_ARGS(pages_written), TP_STRUCT__entry( __field(long, pages) ), TP_fast_assign( __entry->pages = pages_written; ), TP_printk("%ld", __entry->pages) ); DECLARE_EVENT_CLASS(writeback_class, TP_PROTO(struct bdi_writeback *wb), TP_ARGS(wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%lu", __entry->name, (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_EVENT(name) \ DEFINE_EVENT(writeback_class, name, \ TP_PROTO(struct bdi_writeback *wb), \ TP_ARGS(wb)) DEFINE_WRITEBACK_EVENT(writeback_wake_background); TRACE_EVENT(writeback_bdi_register, TP_PROTO(struct backing_dev_info *bdi), TP_ARGS(bdi), TP_STRUCT__entry( __array(char, name, 32) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); ), TP_printk("bdi %s", __entry->name ) ); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), TP_ARGS(wbc, bdi), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_to_write) __field(long, pages_skipped) __field(int, sync_mode) __field(int, for_kupdate) __field(int, for_background) __field(int, for_reclaim) __field(int, range_cyclic) __field(long, range_start) __field(long, range_end) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->for_background = wbc->for_background; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->range_start = (long)wbc->range_start; __entry->range_end = (long)wbc->range_end; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " "bgrd=%d reclm=%d cyclic=%d " "start=0x%lx end=0x%lx cgroup_ino=%lu", __entry->name, __entry->nr_to_write, __entry->pages_skipped, __entry->sync_mode, __entry->for_kupdate, __entry->for_background, __entry->for_reclaim, __entry->range_cyclic, __entry->range_start, __entry->range_end, (unsigned long)__entry->cgroup_ino ) ) #define DEFINE_WBC_EVENT(name) \ DEFINE_EVENT(wbc_class, name, \ TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \ TP_ARGS(wbc, bdi)) DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before, int moved), TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) __field(long, age) __field(int, moved) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->older = dirtied_before; __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, __entry->older, /* dirtied_before in jiffies */ __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(global_dirty_state, TP_PROTO(unsigned long background_thresh, unsigned long dirty_thresh ), TP_ARGS(background_thresh, dirty_thresh ), TP_STRUCT__entry( __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, background_thresh) __field(unsigned long, dirty_thresh) __field(unsigned long, dirty_limit) __field(unsigned long, nr_dirtied) __field(unsigned long, nr_written) ), TP_fast_assign( __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu " "bg_thresh=%lu thresh=%lu limit=%lu " "dirtied=%lu written=%lu", __entry->nr_dirty, __entry->nr_writeback, __entry->background_thresh, __entry->dirty_thresh, __entry->dirty_limit, __entry->nr_dirtied, __entry->nr_written ) ); #define KBps(x) ((x) << (PAGE_SHIFT - 10)) TRACE_EVENT(bdi_dirty_ratelimit, TP_PROTO(struct bdi_writeback *wb, unsigned long dirty_rate, unsigned long task_ratelimit), TP_ARGS(wb, dirty_rate, task_ratelimit), TP_STRUCT__entry( __array(char, bdi, 32) __field(unsigned long, write_bw) __field(unsigned long, avg_write_bw) __field(unsigned long, dirty_rate) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned long, balanced_dirty_ratelimit) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); __entry->dirty_ratelimit = KBps(wb->dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = KBps(wb->balanced_dirty_ratelimit); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "balanced_dirty_ratelimit=%lu cgroup_ino=%lu", __entry->bdi, __entry->write_bw, /* write bandwidth */ __entry->avg_write_bw, /* avg write bandwidth */ __entry->dirty_rate, /* bdi dirty rate */ __entry->dirty_ratelimit, /* base ratelimit */ __entry->task_ratelimit, /* ratelimit with position control */ __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(balance_dirty_pages, TP_PROTO(struct bdi_writeback *wb, unsigned long thresh, unsigned long bg_thresh, unsigned long dirty, unsigned long bdi_thresh, unsigned long bdi_dirty, unsigned long dirty_ratelimit, unsigned long task_ratelimit, unsigned long dirtied, unsigned long period, long pause, unsigned long start_time), TP_ARGS(wb, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty, dirty_ratelimit, task_ratelimit, dirtied, period, pause, start_time), TP_STRUCT__entry( __array( char, bdi, 32) __field(unsigned long, limit) __field(unsigned long, setpoint) __field(unsigned long, dirty) __field(unsigned long, bdi_setpoint) __field(unsigned long, bdi_dirty) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned int, dirtied) __field(unsigned int, dirtied_pause) __field(unsigned long, paused) __field( long, pause) __field(unsigned long, period) __field( long, think) __field(ino_t, cgroup_ino) ), TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + freerun) / 2; __entry->dirty = dirty; __entry->bdi_setpoint = __entry->setpoint * bdi_thresh / (thresh + 1); __entry->bdi_dirty = bdi_dirty; __entry->dirty_ratelimit = KBps(dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->dirtied = dirtied; __entry->dirtied_pause = current->nr_dirtied_pause; __entry->think = current->dirty_paused_when == 0 ? 0 : (long)(jiffies - current->dirty_paused_when) * 1000/HZ; __entry->period = period * 1000 / HZ; __entry->pause = pause * 1000 / HZ; __entry->paused = (jiffies - start_time) * 1000 / HZ; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "limit=%lu setpoint=%lu dirty=%lu " "bdi_setpoint=%lu bdi_dirty=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "dirtied=%u dirtied_pause=%u " "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%lu", __entry->bdi, __entry->limit, __entry->setpoint, __entry->dirty, __entry->bdi_setpoint, __entry->bdi_dirty, __entry->dirty_ratelimit, __entry->task_ratelimit, __entry->dirtied, __entry->dirtied_pause, __entry->paused, /* ms */ __entry->pause, /* ms */ __entry->period, /* ms */ __entry->think, /* ms */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(writeback_sb_inodes_requeue, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, (unsigned long)__entry->cgroup_ino ) ); DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write ), TP_ARGS(inode, wbc, nr_to_write), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(unsigned long, writeback_index) __field(long, nr_to_write) __field(unsigned long, wrote) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; __entry->wrote = nr_to_write - wbc->nr_to_write; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " "index=%lu to_write=%ld wrote=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, __entry->writeback_index, __entry->nr_to_write, __entry->wrote, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DECLARE_EVENT_CLASS(writeback_inode_template, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, state ) __field( __u16, mode ) __field(unsigned long, dirtied_when ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, __entry->dirtied_when, show_inode_state(__entry->state), __entry->mode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime_iput, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_dirty_inode_enqueue, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* * Inode writeback list tracking. */ DEFINE_EVENT(writeback_inode_template, sb_mark_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, sb_clear_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 187 25 187 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_MM_H #define _LINUX_SCHED_MM_H #include <linux/kernel.h> #include <linux/atomic.h> #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> #include <linux/sched/coredump.h> /* * Routines for handling mm_structs */ extern struct mm_struct *mm_alloc(void); /** * mmgrab() - Pin a &struct mm_struct. * @mm: The &struct mm_struct to pin. * * Make sure that @mm will not get freed even after the owning task * exits. This doesn't guarantee that the associated address space * will still exist later on and mmget_not_zero() has to be used before * accessing it. * * This is a preferred way to pin @mm for a longer/unbounded amount * of time. * * Use mmdrop() to release the reference acquired by mmgrab(). * * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) { atomic_inc(&mm->mm_count); } static inline void smp_mb__after_mmgrab(void) { smp_mb__after_atomic(); } extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) { /* * The implicit full barrier implied by atomic_dec_and_test() is * required by the membarrier system call before returning to * user-space, after storing to rq->curr. */ if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } #ifdef CONFIG_PREEMPT_RT /* * RCU callback for delayed mm drop. Not strictly RCU, but call_rcu() is * by far the least expensive way to do that. */ static inline void __mmdrop_delayed(struct rcu_head *rhp) { struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); __mmdrop(mm); } /* * Invoked from finish_task_switch(). Delegates the heavy lifting on RT * kernels via RCU. */ static inline void mmdrop_sched(struct mm_struct *mm) { /* Provides a full memory barrier. See mmdrop() */ if (atomic_dec_and_test(&mm->mm_count)) call_rcu(&mm->delayed_drop, __mmdrop_delayed); } #else static inline void mmdrop_sched(struct mm_struct *mm) { mmdrop(mm); } #endif /* Helpers for lazy TLB mm refcounting */ static inline void mmgrab_lazy_tlb(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) mmgrab(mm); } static inline void mmdrop_lazy_tlb(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) { mmdrop(mm); } else { /* * mmdrop_lazy_tlb must provide a full memory barrier, see the * membarrier comment finish_task_switch which relies on this. */ smp_mb(); } } static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) mmdrop_sched(mm); else smp_mb(); /* see mmdrop_lazy_tlb() above */ } /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. * * Make sure that the address space of the given &struct mm_struct doesn't * go away. This does not protect against parts of the address space being * modified or freed, however. * * Never use this function to pin this address space for an * unbounded/indefinite amount of time. * * Use mmput() to release the reference acquired by mmget(). * * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) { atomic_inc(&mm->mm_users); } static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); } /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); #ifdef CONFIG_MMU /* same as above but performs the slow path from the async context. Can * be called from the atomic context as well */ void mmput_async(struct mm_struct *); #endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); /* * Grab a reference to a task's mm, if it is not already going away * and ptrace_may_access with the mode parameter passed to it * succeeds. */ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); /* Remove the current tasks stale references to the old mm_struct on exit() */ extern void exit_mm_release(struct task_struct *, struct mm_struct *); /* Remove the current tasks stale references to the old mm_struct on exec() */ extern void exec_mm_release(struct task_struct *, struct mm_struct *); #ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); #else static inline void mm_update_next_owner(struct mm_struct *mm) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU #ifndef arch_get_mmap_end #define arch_get_mmap_end(addr, len, flags) (TASK_SIZE) #endif #ifndef arch_get_mmap_base #define arch_get_mmap_base(addr, base) (base) #endif extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t); unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} #endif static inline bool in_vfork(struct task_struct *tsk) { bool ret; /* * need RCU to access ->real_parent if CLONE_VM was used along with * CLONE_PARENT. * * We check real_parent->mm == tsk->mm because CLONE_VFORK does not * imply CLONE_VM * * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus * ->real_parent is not necessarily the task doing vfork(), so in * theory we can't rely on task_lock() if we want to dereference it. * * And in this case we can't trust the real_parent->mm == tsk->mm * check, it can be false negative. But we do not care, if init or * another oom-unkillable task does this it should blame itself. */ rcu_read_lock(); ret = tsk->vfork_done && rcu_dereference(tsk->real_parent)->mm == tsk->mm; rcu_read_unlock(); return ret; } /* * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS * PF_MEMALLOC_PIN implies !GFP_MOVABLE */ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence */ if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; if (pflags & PF_MEMALLOC_PIN) flags &= ~__GFP_MOVABLE; } return flags; } #ifdef CONFIG_LOCKDEP extern void __fs_reclaim_acquire(unsigned long ip); extern void __fs_reclaim_release(unsigned long ip); extern void fs_reclaim_acquire(gfp_t gfp_mask); extern void fs_reclaim_release(gfp_t gfp_mask); #else static inline void __fs_reclaim_acquire(unsigned long ip) { } static inline void __fs_reclaim_release(unsigned long ip) { } static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif /* Any memory-allocation retry loop should use * memalloc_retry_wait(), and pass the flags for the most * constrained allocation attempt that might have failed. * This provides useful documentation of where loops are, * and a central place to fine tune the waiting as the MM * implementation changes. */ static inline void memalloc_retry_wait(gfp_t gfp_flags) { /* We use io_schedule_timeout because waiting for memory * typically included waiting for dirty pages to be * written out, which requires IO. */ __set_current_state(TASK_UNINTERRUPTIBLE); gfp_flags = current_gfp_context(gfp_flags); if (gfpflags_allow_blocking(gfp_flags) && !(gfp_flags & __GFP_NORETRY)) /* Probably waited already, no need for much more */ io_schedule_timeout(1); else /* Probably didn't wait, and has now released a lock, * so now is a good time to wait */ io_schedule_timeout(HZ/50); } /** * might_alloc - Mark possible allocation sites * @gfp_mask: gfp_t flags that would be used to allocate * * Similar to might_sleep() and other annotations, this can be used in functions * that might allocate, but often don't. Compiles to nothing without * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking. */ static inline void might_alloc(gfp_t gfp_mask) { fs_reclaim_acquire(gfp_mask); fs_reclaim_release(gfp_mask); might_sleep_if(gfpflags_allow_blocking(gfp_mask)); } /** * memalloc_flags_save - Add a PF_* flag to current->flags, save old value * * This allows PF_* flags to be conveniently added, irrespective of current * value, and then the old version restored with memalloc_flags_restore(). */ static inline unsigned memalloc_flags_save(unsigned flags) { unsigned oldflags = ~current->flags & flags; current->flags |= flags; return oldflags; } static inline void memalloc_flags_restore(unsigned flags) { current->flags &= ~flags; } /** * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. * * This functions marks the beginning of the GFP_NOIO allocation scope. * All further allocations will implicitly drop __GFP_IO flag and so * they are safe for the IO critical section from the allocation recursion * point of view. Use memalloc_noio_restore to end the scope with flags * returned by this function. * * Context: This function is safe to be used from any context. * Return: The saved flags to be passed to memalloc_noio_restore. */ static inline unsigned int memalloc_noio_save(void) { return memalloc_flags_save(PF_MEMALLOC_NOIO); } /** * memalloc_noio_restore - Ends the implicit GFP_NOIO scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_noio_save call. */ static inline void memalloc_noio_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope. * * This functions marks the beginning of the GFP_NOFS allocation scope. * All further allocations will implicitly drop __GFP_FS flag and so * they are safe for the FS critical section from the allocation recursion * point of view. Use memalloc_nofs_restore to end the scope with flags * returned by this function. * * Context: This function is safe to be used from any context. * Return: The saved flags to be passed to memalloc_nofs_restore. */ static inline unsigned int memalloc_nofs_save(void) { return memalloc_flags_save(PF_MEMALLOC_NOFS); } /** * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_nofs_save call. */ static inline void memalloc_nofs_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_noreclaim_save - Marks implicit __GFP_MEMALLOC scope. * * This function marks the beginning of the __GFP_MEMALLOC allocation scope. * All further allocations will implicitly add the __GFP_MEMALLOC flag, which * prevents entering reclaim and allows access to all memory reserves. This * should only be used when the caller guarantees the allocation will allow more * memory to be freed very shortly, i.e. it needs to allocate some memory in * the process of freeing memory, and cannot reclaim due to potential recursion. * * Users of this scope have to be extremely careful to not deplete the reserves * completely and implement a throttling mechanism which controls the * consumption of the reserve based on the amount of freed memory. Usage of a * pre-allocated pool (e.g. mempool) should be always considered before using * this scope. * * Individual allocations under the scope can opt out using __GFP_NOMEMALLOC * * Context: This function should not be used in an interrupt context as that one * does not give PF_MEMALLOC access to reserves. * See __gfp_pfmemalloc_flags(). * Return: The saved flags to be passed to memalloc_noreclaim_restore. */ static inline unsigned int memalloc_noreclaim_save(void) { return memalloc_flags_save(PF_MEMALLOC); } /** * memalloc_noreclaim_restore - Ends the implicit __GFP_MEMALLOC scope. * @flags: Flags to restore. * * Ends the implicit __GFP_MEMALLOC scope started by memalloc_noreclaim_save * function. Always make sure that the given flags is the return value from the * pairing memalloc_noreclaim_save call. */ static inline void memalloc_noreclaim_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_pin_save - Marks implicit ~__GFP_MOVABLE scope. * * This function marks the beginning of the ~__GFP_MOVABLE allocation scope. * All further allocations will implicitly remove the __GFP_MOVABLE flag, which * will constraint the allocations to zones that allow long term pinning, i.e. * not ZONE_MOVABLE zones. * * Return: The saved flags to be passed to memalloc_pin_restore. */ static inline unsigned int memalloc_pin_save(void) { return memalloc_flags_save(PF_MEMALLOC_PIN); } /** * memalloc_pin_restore - Ends the implicit ~__GFP_MOVABLE scope. * @flags: Flags to restore. * * Ends the implicit ~__GFP_MOVABLE scope started by memalloc_pin_save function. * Always make sure that the given flags is the return value from the pairing * memalloc_pin_save call. */ static inline void memalloc_pin_restore(unsigned int flags) { memalloc_flags_restore(flags); } #ifdef CONFIG_MEMCG DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); /** * set_active_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. * * This function marks the beginning of the remote memcg charging scope. All the * __GFP_ACCOUNT allocations till the end of the scope will be charged to the * given memcg. * * Please, make sure that caller has a reference to the passed memcg structure, * so its lifetime is guaranteed to exceed the scope between two * set_active_memcg() calls. * * NOTE: This function can nest. Users must save the return value and * reset the previous value after their own charging scope is over. */ static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { struct mem_cgroup *old; if (!in_task()) { old = this_cpu_read(int_active_memcg); this_cpu_write(int_active_memcg, memcg); } else { old = current->active_memcg; current->active_memcg = memcg; } return old; } #else static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { return NULL; } #endif #ifdef CONFIG_MEMBARRIER enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1), MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2), MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7), }; enum { MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), MEMBARRIER_FLAG_RSEQ = (1U << 1), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS #include <asm/membarrier.h> #endif static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { if (current->mm != mm) return; if (likely(!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE))) return; sync_core_before_usermode(); } extern void membarrier_exec_mmap(struct mm_struct *mm); extern void membarrier_update_current_mm(struct mm_struct *next_mm); #else #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS static inline void membarrier_arch_switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { } #endif static inline void membarrier_exec_mmap(struct mm_struct *mm) { } static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { } static inline void membarrier_update_current_mm(struct mm_struct *next_mm) { } #endif #endif /* _LINUX_SCHED_MM_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_MTE_H #define __ASM_MTE_H #include <asm/compiler.h> #include <asm/mte-def.h> #ifndef __ASSEMBLY__ #include <linux/bitfield.h> #include <linux/kasan-enabled.h> #include <linux/page-flags.h> #include <linux/sched.h> #include <linux/types.h> #include <asm/pgtable-types.h> void mte_clear_page_tags(void *addr); unsigned long mte_copy_tags_from_user(void *to, const void __user *from, unsigned long n); unsigned long mte_copy_tags_to_user(void __user *to, void *from, unsigned long n); int mte_save_tags(struct page *page); void mte_save_page_tags(const void *page_addr, void *tag_storage); void mte_restore_tags(swp_entry_t entry, struct page *page); void mte_restore_page_tags(void *page_addr, const void *tag_storage); void mte_invalidate_tags(int type, pgoff_t offset); void mte_invalidate_tags_area(int type); void *mte_allocate_tag_storage(void); void mte_free_tag_storage(char *storage); #ifdef CONFIG_ARM64_MTE /* track which pages have valid allocation tags */ #define PG_mte_tagged PG_arch_2 /* simple lock to avoid multiple threads tagging the same page */ #define PG_mte_lock PG_arch_3 static inline void set_page_mte_tagged(struct page *page) { /* * Ensure that the tags written prior to this function are visible * before the page flags update. */ smp_wmb(); set_bit(PG_mte_tagged, &page->flags); } static inline bool page_mte_tagged(struct page *page) { bool ret = test_bit(PG_mte_tagged, &page->flags); /* * If the page is tagged, ensure ordering with a likely subsequent * read of the tags. */ if (ret) smp_rmb(); return ret; } /* * Lock the page for tagging and return 'true' if the page can be tagged, * 'false' if already tagged. PG_mte_tagged is never cleared and therefore the * locking only happens once for page initialisation. * * The page MTE lock state: * * Locked: PG_mte_lock && !PG_mte_tagged * Unlocked: !PG_mte_lock || PG_mte_tagged * * Acquire semantics only if the page is tagged (returning 'false'). */ static inline bool try_page_mte_tagging(struct page *page) { if (!test_and_set_bit(PG_mte_lock, &page->flags)) return true; /* * The tags are either being initialised or may have been initialised * already. Check if the PG_mte_tagged flag has been set or wait * otherwise. */ smp_cond_load_acquire(&page->flags, VAL & (1UL << PG_mte_tagged)); return false; } void mte_zero_clear_page_tags(void *addr); void mte_sync_tags(pte_t pte, unsigned int nr_pages); void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); void mte_cpu_setup(void); void mte_suspend_enter(void); void mte_suspend_exit(void); long set_mte_ctrl(struct task_struct *task, unsigned long arg); long get_mte_ctrl(struct task_struct *task); int mte_ptrace_copy_tags(struct task_struct *child, long request, unsigned long addr, unsigned long data); size_t mte_probe_user_range(const char __user *uaddr, size_t size); #else /* CONFIG_ARM64_MTE */ /* unused if !CONFIG_ARM64_MTE, silence the compiler */ #define PG_mte_tagged 0 static inline void set_page_mte_tagged(struct page *page) { } static inline bool page_mte_tagged(struct page *page) { return false; } static inline bool try_page_mte_tagging(struct page *page) { return false; } static inline void mte_zero_clear_page_tags(void *addr) { } static inline void mte_sync_tags(pte_t pte, unsigned int nr_pages) { } static inline void mte_copy_page_tags(void *kto, const void *kfrom) { } static inline void mte_thread_init_user(void) { } static inline void mte_thread_switch(struct task_struct *next) { } static inline void mte_suspend_enter(void) { } static inline void mte_suspend_exit(void) { } static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg) { return 0; } static inline long get_mte_ctrl(struct task_struct *task) { return 0; } static inline int mte_ptrace_copy_tags(struct task_struct *child, long request, unsigned long addr, unsigned long data) { return -EIO; } #endif /* CONFIG_ARM64_MTE */ static inline void mte_disable_tco_entry(struct task_struct *task) { if (!system_supports_mte()) return; /* * Re-enable tag checking (TCO set on exception entry). This is only * necessary if MTE is enabled in either the kernel or the userspace * task in synchronous or asymmetric mode (SCTLR_EL1.TCF0 bit 0 is set * for both). With MTE disabled in the kernel and disabled or * asynchronous in userspace, tag check faults (including in uaccesses) * are not reported, therefore there is no need to re-enable checking. * This is beneficial on microarchitectures where re-enabling TCO is * expensive. */ if (kasan_hw_tags_enabled() || (task->thread.sctlr_user & (1UL << SCTLR_EL1_TCF0_SHIFT))) asm volatile(SET_PSTATE_TCO(0)); } #ifdef CONFIG_KASAN_HW_TAGS void mte_check_tfsr_el1(void); static inline void mte_check_tfsr_entry(void) { if (!kasan_hw_tags_enabled()) return; mte_check_tfsr_el1(); } static inline void mte_check_tfsr_exit(void) { if (!kasan_hw_tags_enabled()) return; /* * The asynchronous faults are sync'ed automatically with * TFSR_EL1 on kernel entry but for exit an explicit dsb() * is required. */ dsb(nsh); isb(); mte_check_tfsr_el1(); } #else static inline void mte_check_tfsr_el1(void) { } static inline void mte_check_tfsr_entry(void) { } static inline void mte_check_tfsr_exit(void) { } #endif /* CONFIG_KASAN_HW_TAGS */ #endif /* __ASSEMBLY__ */ #endif /* __ASM_MTE_H */ |
| 558 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2016 ARM Ltd. */ #ifndef __ASM_PGTABLE_PROT_H #define __ASM_PGTABLE_PROT_H #include <asm/memory.h> #include <asm/pgtable-hwdef.h> #include <linux/const.h> /* * Software defined PTE bits definition. */ #define PTE_WRITE (PTE_DBM) /* same as DBM (51) */ #define PTE_SWP_EXCLUSIVE (_AT(pteval_t, 1) << 2) /* only for swp ptes */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) #define PTE_DEVMAP (_AT(pteval_t, 1) << 57) /* * PTE_PRESENT_INVALID=1 & PTE_VALID=0 indicates that the pte's fields should be * interpreted according to the HW layout by SW but any attempted HW access to * the address will result in a fault. pte_present() returns true. */ #define PTE_PRESENT_INVALID (PTE_NG) /* only when !PTE_VALID */ #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP #define PTE_UFFD_WP (_AT(pteval_t, 1) << 58) /* uffd-wp tracking */ #define PTE_SWP_UFFD_WP (_AT(pteval_t, 1) << 3) /* only for swp ptes */ #else #define PTE_UFFD_WP (_AT(pteval_t, 0)) #define PTE_SWP_UFFD_WP (_AT(pteval_t, 0)) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_MAYBE_NG | PTE_MAYBE_SHARED | PTE_AF) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_MAYBE_NG | PMD_MAYBE_SHARED | PMD_SECT_AF) #define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) #define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_NORMAL_TAGGED (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PTE_WRITE | PMD_ATTRINDX(MT_NORMAL)) #define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) #define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) #define _PAGE_KERNEL (PROT_NORMAL) #define _PAGE_KERNEL_RO ((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY) #define _PAGE_KERNEL_ROX ((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY) #define _PAGE_KERNEL_EXEC (PROT_NORMAL & ~PTE_PXN) #define _PAGE_KERNEL_EXEC_CONT ((PROT_NORMAL & ~PTE_PXN) | PTE_CONT) #define _PAGE_SHARED (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) #define _PAGE_SHARED_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) #define _PAGE_READONLY (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define _PAGE_READONLY_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define _PAGE_EXECONLY (_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) #ifndef __ASSEMBLY__ #include <asm/cpufeature.h> #include <asm/pgtable-types.h> extern bool arm64_use_ng_mappings; #define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0) #define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0) #ifndef CONFIG_ARM64_LPA2 #define lpa2_is_enabled() false #define PTE_MAYBE_SHARED PTE_SHARED #define PMD_MAYBE_SHARED PMD_SECT_S #else static inline bool __pure lpa2_is_enabled(void) { return read_tcr() & TCR_DS; } #define PTE_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PTE_SHARED) #define PMD_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PMD_SECT_S) #endif /* * If we have userspace only BTI we don't want to mark kernel pages * guarded even if the system does support BTI. */ #define PTE_MAYBE_GP (system_supports_bti_kernel() ? PTE_GP : 0) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) #define PAGE_KERNEL_RO __pgprot(_PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_KERNEL_ROX) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL_EXEC) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_KERNEL_EXEC_CONT) #define PAGE_S2_MEMATTR(attr, has_fwb) \ ({ \ u64 __val; \ if (has_fwb) \ __val = PTE_S2_MEMATTR(MT_S2_FWB_ ## attr); \ else \ __val = PTE_S2_MEMATTR(MT_S2_ ## attr); \ __val; \ }) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PRESENT_INVALID | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) /* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */ #define PAGE_SHARED __pgprot(_PAGE_SHARED) #define PAGE_SHARED_EXEC __pgprot(_PAGE_SHARED_EXEC) #define PAGE_READONLY __pgprot(_PAGE_READONLY) #define PAGE_READONLY_EXEC __pgprot(_PAGE_READONLY_EXEC) #define PAGE_EXECONLY __pgprot(_PAGE_EXECONLY) #endif /* __ASSEMBLY__ */ #define pte_pi_index(pte) ( \ ((pte & BIT(PTE_PI_IDX_3)) >> (PTE_PI_IDX_3 - 3)) | \ ((pte & BIT(PTE_PI_IDX_2)) >> (PTE_PI_IDX_2 - 2)) | \ ((pte & BIT(PTE_PI_IDX_1)) >> (PTE_PI_IDX_1 - 1)) | \ ((pte & BIT(PTE_PI_IDX_0)) >> (PTE_PI_IDX_0 - 0))) /* * Page types used via Permission Indirection Extension (PIE). PIE uses * the USER, DBM, PXN and UXN bits to to generate an index which is used * to look up the actual permission in PIR_ELx and PIRE0_EL1. We define * combinations we use on non-PIE systems with the same encoding, for * convenience these are listed here as comments as are the unallocated * encodings. */ /* 0: PAGE_DEFAULT */ /* 1: PTE_USER */ /* 2: PTE_WRITE */ /* 3: PTE_WRITE | PTE_USER */ /* 4: PAGE_EXECONLY PTE_PXN */ /* 5: PAGE_READONLY_EXEC PTE_PXN | PTE_USER */ /* 6: PTE_PXN | PTE_WRITE */ /* 7: PAGE_SHARED_EXEC PTE_PXN | PTE_WRITE | PTE_USER */ /* 8: PAGE_KERNEL_ROX PTE_UXN */ /* 9: PTE_UXN | PTE_USER */ /* a: PAGE_KERNEL_EXEC PTE_UXN | PTE_WRITE */ /* b: PTE_UXN | PTE_WRITE | PTE_USER */ /* c: PAGE_KERNEL_RO PTE_UXN | PTE_PXN */ /* d: PAGE_READONLY PTE_UXN | PTE_PXN | PTE_USER */ /* e: PAGE_KERNEL PTE_UXN | PTE_PXN | PTE_WRITE */ /* f: PAGE_SHARED PTE_UXN | PTE_PXN | PTE_WRITE | PTE_USER */ #define PIE_E0 ( \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_X_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RWX_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY), PIE_R_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW_O)) #define PIE_E1 ( \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_NONE_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RW) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_ROX), PIE_RX) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_EXEC), PIE_RWX) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_RO), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL), PIE_RW)) #endif /* __ASM_PGTABLE_PROT_H */ |
| 156 156 1 156 156 158 1 1 1 1 158 1 169 1 158 170 168 170 170 170 20 155 155 1 1 1 19 20 20 5 5 5 20 20 20 5 20 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the SID table type. * * Original author: Stephen Smalley, <stephen.smalley.work@gmail.com> * Author: Ondrej Mosnacek, <omosnacek@gmail.com> * * Copyright (C) 2018 Red Hat, Inc. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <asm/barrier.h> #include "flask.h" #include "security.h" #include "sidtab.h" #include "services.h" struct sidtab_str_cache { struct rcu_head rcu_member; struct list_head lru_member; struct sidtab_entry *parent; u32 len; char str[] __counted_by(len); }; #define index_to_sid(index) ((index) + SECINITSID_NUM + 1) #define sid_to_index(sid) ((sid) - (SECINITSID_NUM + 1)) int sidtab_init(struct sidtab *s) { u32 i; memset(s->roots, 0, sizeof(s->roots)); for (i = 0; i < SECINITSID_NUM; i++) s->isids[i].set = 0; s->frozen = false; s->count = 0; s->convert = NULL; hash_init(s->context_to_sid); spin_lock_init(&s->lock); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 s->cache_free_slots = CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE; INIT_LIST_HEAD(&s->cache_lru_list); spin_lock_init(&s->cache_lock); #endif return 0; } static u32 context_to_sid(struct sidtab *s, struct context *context, u32 hash) { struct sidtab_entry *entry; u32 sid = 0; rcu_read_lock(); hash_for_each_possible_rcu(s->context_to_sid, entry, list, hash) { if (entry->hash != hash) continue; if (context_cmp(&entry->context, context)) { sid = entry->sid; break; } } rcu_read_unlock(); return sid; } int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context) { struct sidtab_isid_entry *isid; u32 hash; int rc; if (sid == 0 || sid > SECINITSID_NUM) return -EINVAL; isid = &s->isids[sid - 1]; rc = context_cpy(&isid->entry.context, context); if (rc) return rc; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 isid->entry.cache = NULL; #endif isid->set = 1; hash = context_compute_hash(context); /* * Multiple initial sids may map to the same context. Check that this * context is not already represented in the context_to_sid hashtable * to avoid duplicate entries and long linked lists upon hash * collision. */ if (!context_to_sid(s, context, hash)) { isid->entry.sid = sid; isid->entry.hash = hash; hash_add(s->context_to_sid, &isid->entry.list, hash); } return 0; } int sidtab_hash_stats(struct sidtab *sidtab, char *page) { int i; int chain_len = 0; int slots_used = 0; int entries = 0; int max_chain_len = 0; int cur_bucket = 0; struct sidtab_entry *entry; rcu_read_lock(); hash_for_each_rcu(sidtab->context_to_sid, i, entry, list) { entries++; if (i == cur_bucket) { chain_len++; if (chain_len == 1) slots_used++; } else { cur_bucket = i; if (chain_len > max_chain_len) max_chain_len = chain_len; chain_len = 0; } } rcu_read_unlock(); if (chain_len > max_chain_len) max_chain_len = chain_len; return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", entries, slots_used, SIDTAB_HASH_BUCKETS, max_chain_len); } static u32 sidtab_level_from_count(u32 count) { u32 capacity = SIDTAB_LEAF_ENTRIES; u32 level = 0; while (count > capacity) { capacity <<= SIDTAB_INNER_SHIFT; ++level; } return level; } static int sidtab_alloc_roots(struct sidtab *s, u32 level) { u32 l; if (!s->roots[0].ptr_leaf) { s->roots[0].ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[0].ptr_leaf) return -ENOMEM; } for (l = 1; l <= level; ++l) if (!s->roots[l].ptr_inner) { s->roots[l].ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[l].ptr_inner) return -ENOMEM; s->roots[l].ptr_inner->entries[0] = s->roots[l - 1]; } return 0; } static struct sidtab_entry *sidtab_do_lookup(struct sidtab *s, u32 index, int alloc) { union sidtab_entry_inner *entry; u32 level, capacity_shift, leaf_index = index / SIDTAB_LEAF_ENTRIES; /* find the level of the subtree we need */ level = sidtab_level_from_count(index + 1); capacity_shift = level * SIDTAB_INNER_SHIFT; /* allocate roots if needed */ if (alloc && sidtab_alloc_roots(s, level) != 0) return NULL; /* lookup inside the subtree */ entry = &s->roots[level]; while (level != 0) { capacity_shift -= SIDTAB_INNER_SHIFT; --level; entry = &entry->ptr_inner->entries[leaf_index >> capacity_shift]; leaf_index &= ((u32)1 << capacity_shift) - 1; if (!entry->ptr_inner) { if (alloc) entry->ptr_inner = kzalloc( SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_inner) return NULL; } } if (!entry->ptr_leaf) { if (alloc) entry->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_leaf) return NULL; } return &entry->ptr_leaf->entries[index % SIDTAB_LEAF_ENTRIES]; } static struct sidtab_entry *sidtab_lookup(struct sidtab *s, u32 index) { /* read entries only after reading count */ u32 count = smp_load_acquire(&s->count); if (index >= count) return NULL; return sidtab_do_lookup(s, index, 0); } static struct sidtab_entry *sidtab_lookup_initial(struct sidtab *s, u32 sid) { return s->isids[sid - 1].set ? &s->isids[sid - 1].entry : NULL; } static struct sidtab_entry *sidtab_search_core(struct sidtab *s, u32 sid, int force) { if (sid != 0) { struct sidtab_entry *entry; if (sid > SECINITSID_NUM) entry = sidtab_lookup(s, sid_to_index(sid)); else entry = sidtab_lookup_initial(s, sid); if (entry && (!entry->context.len || force)) return entry; } return sidtab_lookup_initial(s, SECINITSID_UNLABELED); } struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 0); } struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 1); } int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid) { unsigned long flags; u32 count, hash = context_compute_hash(context); struct sidtab_convert_params *convert; struct sidtab_entry *dst, *dst_convert; int rc; *sid = context_to_sid(s, context, hash); if (*sid) return 0; /* lock-free search failed: lock, re-search, and insert if not found */ spin_lock_irqsave(&s->lock, flags); rc = 0; *sid = context_to_sid(s, context, hash); if (*sid) goto out_unlock; if (unlikely(s->frozen)) { /* * This sidtab is now frozen - tell the caller to abort and * get the new one. */ rc = -ESTALE; goto out_unlock; } count = s->count; /* bail out if we already reached max entries */ rc = -EOVERFLOW; if (count >= SIDTAB_MAX) goto out_unlock; /* insert context into new entry */ rc = -ENOMEM; dst = sidtab_do_lookup(s, count, 1); if (!dst) goto out_unlock; dst->sid = index_to_sid(count); dst->hash = hash; rc = context_cpy(&dst->context, context); if (rc) goto out_unlock; /* * if we are building a new sidtab, we need to convert the context * and insert it there as well */ convert = s->convert; if (convert) { struct sidtab *target = convert->target; rc = -ENOMEM; dst_convert = sidtab_do_lookup(target, count, 1); if (!dst_convert) { context_destroy(&dst->context); goto out_unlock; } rc = services_convert_context(convert->args, context, &dst_convert->context, GFP_ATOMIC); if (rc) { context_destroy(&dst->context); goto out_unlock; } dst_convert->sid = index_to_sid(count); dst_convert->hash = context_compute_hash(&dst_convert->context); target->count = count + 1; hash_add_rcu(target->context_to_sid, &dst_convert->list, dst_convert->hash); } if (context->len) pr_info("SELinux: Context %s is not valid (left unmapped).\n", context->str); *sid = index_to_sid(count); /* write entries before updating count */ smp_store_release(&s->count, count + 1); hash_add_rcu(s->context_to_sid, &dst->list, dst->hash); rc = 0; out_unlock: spin_unlock_irqrestore(&s->lock, flags); return rc; } static void sidtab_convert_hashtable(struct sidtab *s, u32 count) { struct sidtab_entry *entry; u32 i; for (i = 0; i < count; i++) { entry = sidtab_do_lookup(s, i, 0); entry->sid = index_to_sid(i); entry->hash = context_compute_hash(&entry->context); hash_add_rcu(s->context_to_sid, &entry->list, entry->hash); } } static int sidtab_convert_tree(union sidtab_entry_inner *edst, union sidtab_entry_inner *esrc, u32 *pos, u32 count, u32 level, struct sidtab_convert_params *convert) { int rc; u32 i; if (level != 0) { if (!edst->ptr_inner) { edst->ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_inner) return -ENOMEM; } i = 0; while (i < SIDTAB_INNER_ENTRIES && *pos < count) { rc = sidtab_convert_tree(&edst->ptr_inner->entries[i], &esrc->ptr_inner->entries[i], pos, count, level - 1, convert); if (rc) return rc; i++; } } else { if (!edst->ptr_leaf) { edst->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_leaf) return -ENOMEM; } i = 0; while (i < SIDTAB_LEAF_ENTRIES && *pos < count) { rc = services_convert_context( convert->args, &esrc->ptr_leaf->entries[i].context, &edst->ptr_leaf->entries[i].context, GFP_KERNEL); if (rc) return rc; (*pos)++; i++; } cond_resched(); } return 0; } int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params) { unsigned long flags; u32 count, level, pos; int rc; spin_lock_irqsave(&s->lock, flags); /* concurrent policy loads are not allowed */ if (s->convert) { spin_unlock_irqrestore(&s->lock, flags); return -EBUSY; } count = s->count; level = sidtab_level_from_count(count); /* allocate last leaf in the new sidtab (to avoid race with * live convert) */ rc = sidtab_do_lookup(params->target, count - 1, 1) ? 0 : -ENOMEM; if (rc) { spin_unlock_irqrestore(&s->lock, flags); return rc; } /* set count in case no new entries are added during conversion */ params->target->count = count; /* enable live convert of new entries */ s->convert = params; /* we can safely convert the tree outside the lock */ spin_unlock_irqrestore(&s->lock, flags); pr_info("SELinux: Converting %u SID table entries...\n", count); /* convert all entries not covered by live convert */ pos = 0; rc = sidtab_convert_tree(¶ms->target->roots[level], &s->roots[level], &pos, count, level, params); if (rc) { /* we need to keep the old table - disable live convert */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); return rc; } /* * The hashtable can also be modified in sidtab_context_to_sid() * so we must re-acquire the lock here. */ spin_lock_irqsave(&s->lock, flags); sidtab_convert_hashtable(params->target, count); spin_unlock_irqrestore(&s->lock, flags); return 0; } void sidtab_cancel_convert(struct sidtab *s) { unsigned long flags; /* cancelling policy load - disable live convert of sidtab */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); } void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock) { spin_lock_irqsave(&s->lock, *flags); s->frozen = true; s->convert = NULL; } void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock) { spin_unlock_irqrestore(&s->lock, *flags); } static void sidtab_destroy_entry(struct sidtab_entry *entry) { context_destroy(&entry->context); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 kfree(rcu_dereference_raw(entry->cache)); #endif } static void sidtab_destroy_tree(union sidtab_entry_inner entry, u32 level) { u32 i; if (level != 0) { struct sidtab_node_inner *node = entry.ptr_inner; if (!node) return; for (i = 0; i < SIDTAB_INNER_ENTRIES; i++) sidtab_destroy_tree(node->entries[i], level - 1); kfree(node); } else { struct sidtab_node_leaf *node = entry.ptr_leaf; if (!node) return; for (i = 0; i < SIDTAB_LEAF_ENTRIES; i++) sidtab_destroy_entry(&node->entries[i]); kfree(node); } } void sidtab_destroy(struct sidtab *s) { u32 i, level; for (i = 0; i < SECINITSID_NUM; i++) if (s->isids[i].set) sidtab_destroy_entry(&s->isids[i].entry); level = SIDTAB_MAX_LEVEL; while (level && !s->roots[level].ptr_inner) --level; sidtab_destroy_tree(s->roots[level], level); /* * The context_to_sid hashtable's objects are all shared * with the isids array and context tree, and so don't need * to be cleaned up here. */ } #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, const char *str, u32 str_len) { struct sidtab_str_cache *cache, *victim = NULL; unsigned long flags; /* do not cache invalid contexts */ if (entry->context.len) return; spin_lock_irqsave(&s->cache_lock, flags); cache = rcu_dereference_protected(entry->cache, lockdep_is_held(&s->cache_lock)); if (cache) { /* entry in cache - just bump to the head of LRU list */ list_move(&cache->lru_member, &s->cache_lru_list); goto out_unlock; } cache = kmalloc(struct_size(cache, str, str_len), GFP_ATOMIC); if (!cache) goto out_unlock; if (s->cache_free_slots == 0) { /* pop a cache entry from the tail and free it */ victim = container_of(s->cache_lru_list.prev, struct sidtab_str_cache, lru_member); list_del(&victim->lru_member); rcu_assign_pointer(victim->parent->cache, NULL); } else { s->cache_free_slots--; } cache->parent = entry; cache->len = str_len; memcpy(cache->str, str, str_len); list_add(&cache->lru_member, &s->cache_lru_list); rcu_assign_pointer(entry->cache, cache); out_unlock: spin_unlock_irqrestore(&s->cache_lock, flags); kfree_rcu(victim, rcu_member); } int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out, u32 *out_len) { struct sidtab_str_cache *cache; int rc = 0; if (entry->context.len) return -ENOENT; /* do not cache invalid contexts */ rcu_read_lock(); cache = rcu_dereference(entry->cache); if (!cache) { rc = -ENOENT; } else { *out_len = cache->len; if (out) { *out = kmemdup(cache->str, cache->len, GFP_ATOMIC); if (!*out) rc = -ENOMEM; } } rcu_read_unlock(); if (!rc && out) sidtab_sid2str_put(s, entry, *out, *out_len); return rc; } #endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov */ #ifndef _LINUX_RADIX_TREE_H #define _LINUX_RADIX_TREE_H #include <linux/bitops.h> #include <linux/gfp_types.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/math.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/xarray.h> #include <linux/local_lock.h> /* Keep unconverted code working */ #define radix_tree_root xarray #define radix_tree_node xa_node struct radix_tree_preload { local_lock_t lock; unsigned nr; /* nodes->parent points to next preallocated node */ struct radix_tree_node *nodes; }; DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads); /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: * * 00 - data pointer * 10 - internal entry * x1 - value entry * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved * to another location in the tree and the lookup should be restarted. While * NULL fits the 'data pointer' pattern, it means that there is no entry in * the tree for this index (no matter what level of the tree it is found at). * This means that storing a NULL entry in the tree is the same as deleting * the entry from the tree. */ #define RADIX_TREE_ENTRY_MASK 3UL #define RADIX_TREE_INTERNAL_NODE 2UL static inline bool radix_tree_is_internal_node(void *ptr) { return ((unsigned long)ptr & RADIX_TREE_ENTRY_MASK) == RADIX_TREE_INTERNAL_NODE; } /*** radix-tree API starts here ***/ #define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) #define RADIX_TREE_MAX_TAGS XA_MAX_MARKS #define RADIX_TREE_TAG_LONGS XA_MARK_LONGS #define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) /* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) /* The top bits of xa_flags are used to store the root tags */ #define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) #define RADIX_TREE_INIT(name, mask) XARRAY_INIT(name, mask) #define RADIX_TREE(name, mask) \ struct radix_tree_root name = RADIX_TREE_INIT(name, mask) #define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask) static inline bool radix_tree_empty(const struct radix_tree_root *root) { return root->xa_head == NULL; } /** * struct radix_tree_iter - radix tree iterator state * * @index: index of current slot * @next_index: one beyond the last index for this chunk * @tags: bit-mask for tag-iterating * @node: node that contains current slot * * This radix tree iterator works in terms of "chunks" of slots. A chunk is a * subinterval of slots contained within one radix tree leaf node. It is * described by a pointer to its first slot and a struct radix_tree_iter * which holds the chunk's position in the tree and its size. For tagged * iteration radix_tree_iter also holds the slots' bit-mask for one chosen * radix tree tag. */ struct radix_tree_iter { unsigned long index; unsigned long next_index; unsigned long tags; struct radix_tree_node *node; }; /** * Radix-tree synchronization * * The radix-tree API requires that users provide all synchronisation (with * specific exceptions, noted below). * * Synchronization of access to the data items being stored in the tree, and * management of their lifetimes must be completely managed by API users. * * For API usage, in general, * - any function _modifying_ the tree or tags (inserting or deleting * items, setting or clearing tags) must exclude other modifications, and * exclude any functions reading the tree. * - any function _reading_ the tree or tags (looking up items or tags, * gang lookups) must exclude modifications to the tree, but may occur * concurrently with other readers. * * The notable exceptions to this rule are the following functions: * __radix_tree_lookup * radix_tree_lookup * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup * radix_tree_gang_lookup_tag * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. * * It is still required that the caller manage the synchronization and lifetimes * of the items. So if RCU lock-free lookups are used, typically this would mean * that the items have their own locks, or are amenable to lock-free access; and * that the items are freed by RCU (or only freed after having been deleted from * the radix tree *and* a synchronize_rcu() grace period). * * (Note, rcu_assign_pointer and rcu_dereference are not needed to control * access to data items when inserting into or looking up from the radix tree) * * Note that the value returned by radix_tree_tag_get() may not be relied upon * if only the RCU read lock is held. Functions to set/clear tags and to * delete nodes running concurrently with it may affect its result such that * two consecutive reads in the same locked section may return different * values. If reliability is required, modification functions must also be * excluded from concurrency. * * radix_tree_tagged is able to be called without locking or RCU. */ /** * radix_tree_deref_slot - dereference a slot * @slot: slot pointer, returned by radix_tree_lookup_slot * * For use with radix_tree_lookup_slot(). Caller must hold tree at least read * locked across slot lookup and dereference. Not required if write lock is * held (ie. items cannot be concurrently inserted). * * radix_tree_deref_retry must be used to confirm validity of the pointer if * only the read lock is held. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot(void __rcu **slot) { return rcu_dereference(*slot); } /** * radix_tree_deref_slot_protected - dereference a slot with tree lock held * @slot: slot pointer, returned by radix_tree_lookup_slot * * Similar to radix_tree_deref_slot. The caller does not hold the RCU read * lock but it must hold the tree lock to prevent parallel updates. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot_protected(void __rcu **slot, spinlock_t *treelock) { return rcu_dereference_protected(*slot, lockdep_is_held(treelock)); } /** * radix_tree_deref_retry - check radix_tree_deref_slot * @arg: pointer returned by radix_tree_deref_slot * Returns: 0 if retry is not required, otherwise retry is required * * radix_tree_deref_retry must be used with radix_tree_deref_slot. */ static inline int radix_tree_deref_retry(void *arg) { return unlikely(radix_tree_is_internal_node(arg)); } /** * radix_tree_exception - radix_tree_deref_slot returned either exception? * @arg: value returned by radix_tree_deref_slot * Returns: 0 if well-aligned pointer, non-0 if either kind of exception. */ static inline int radix_tree_exception(void *arg) { return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } int radix_tree_insert(struct radix_tree_root *, unsigned long index, void *); void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp); void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, unsigned long index); void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, void __rcu **slot, void *entry); void radix_tree_iter_replace(struct radix_tree_root *, const struct radix_tree_iter *, void __rcu **slot, void *entry); void radix_tree_replace_slot(struct radix_tree_root *, void __rcu **slot, void *entry); void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag); unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag); int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { local_unlock(&radix_tree_preloads.lock); } void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max); enum { RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ RADIX_TREE_ITER_TAGGED = 0x10, /* lookup tagged slots */ RADIX_TREE_ITER_CONTIG = 0x20, /* stop at first hole */ }; /** * radix_tree_iter_init - initialize radix tree iterator * * @iter: pointer to iterator state * @start: iteration starting index * Returns: NULL */ static __always_inline void __rcu ** radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) { /* * Leave iter->tags uninitialized. radix_tree_next_chunk() will fill it * in the case of a successful tagged chunk lookup. If the lookup was * unsuccessful or non-tagged then nobody cares about ->tags. * * Set index to zero to bypass next_index overflow protection. * See the comment in radix_tree_next_chunk() for details. */ iter->index = 0; iter->next_index = start; return NULL; } /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if there no more left * * This function looks up the next chunk in the radix tree starting from * @iter->next_index. It returns a pointer to the chunk's first slot. * Also it fills @iter with data about chunk: position in the tree (index), * its end (next_index), and constructs a bit mask for tagged iterating (tags). */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *, struct radix_tree_iter *iter, unsigned flags); /** * radix_tree_iter_lookup - look up an index in the radix tree * @root: radix tree root * @iter: iterator state * @index: key to look up * * If @index is present in the radix tree, this function returns the slot * containing it and updates @iter to describe the entry. If @index is not * present, it returns NULL. */ static inline void __rcu ** radix_tree_iter_lookup(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned long index) { radix_tree_iter_init(iter, index); return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG); } /** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * * If we iterate over a tree protected only by the RCU lock, a race * against deletion or creation may result in seeing a slot for which * radix_tree_deref_retry() returns true. If so, call this function * and continue the iteration. */ static inline __must_check void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; iter->tags = 0; return NULL; } static inline unsigned long __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) { return iter->index + slots; } /** * radix_tree_iter_resume - resume iterating when the chunk may be invalid * @slot: pointer to current slot * @iter: iterator state * Returns: New slot pointer * * If the iterator needs to release then reacquire a lock, the chunk may * have been invalidated by an insertion or deletion. Call this function * before releasing the lock to continue the iteration from the next index. */ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter); /** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator * Returns: current chunk size */ static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; } /** * radix_tree_next_slot - find next slot in chunk * * @slot: pointer to current slot * @iter: pointer to iterator state * @flags: RADIX_TREE_ITER_*, should be constant * Returns: pointer to next slot, or NULL if there no more left * * This function updates @iter->index in the case of a successful lookup. * For tagged lookup it also eats @iter->tags. * * There are several cases where 'slot' can be passed in as NULL to this * function. These cases result from the use of radix_tree_iter_resume() or * radix_tree_iter_retry(). In these cases we don't end up dereferencing * 'slot' because either: * a) we are doing tagged iteration and iter->tags has been set to 0, or * b) we are doing non-tagged iteration, and iter->index and iter->next_index * have been set up so that radix_tree_chunk_size() returns 1 or 0. */ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { if (flags & RADIX_TREE_ITER_TAGGED) { iter->tags >>= 1; if (unlikely(!iter->tags)) return NULL; if (likely(iter->tags & 1ul)) { iter->index = __radix_tree_iter_add(iter, 1); slot++; goto found; } if (!(flags & RADIX_TREE_ITER_CONTIG)) { unsigned offset = __ffs(iter->tags); iter->tags >>= offset++; iter->index = __radix_tree_iter_add(iter, offset); slot += offset; goto found; } } else { long count = radix_tree_chunk_size(iter); while (--count > 0) { slot++; iter->index = __radix_tree_iter_add(iter, 1); if (likely(*slot)) goto found; if (flags & RADIX_TREE_ITER_CONTIG) { /* forbid switching to the next chunk */ iter->next_index = 0; break; } } } return NULL; found: return slot; } /** * radix_tree_for_each_slot - iterate over non-empty slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_slot(slot, root, iter, start) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \ slot = radix_tree_next_slot(slot, iter, 0)) /** * radix_tree_for_each_tagged - iterate over tagged slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * @tag: tag index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_tagged(slot, root, iter, start, tag) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, \ RADIX_TREE_ITER_TAGGED | tag)) ; \ slot = radix_tree_next_slot(slot, iter, \ RADIX_TREE_ITER_TAGGED | tag)) #endif /* _LINUX_RADIX_TREE_H */ |
| 742 140 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * security/tomoyo/common.h * * Header file for TOMOYO. * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #ifndef _SECURITY_TOMOYO_COMMON_H #define _SECURITY_TOMOYO_COMMON_H #define pr_fmt(fmt) fmt #include <linux/ctype.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/kmod.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/list.h> #include <linux/cred.h> #include <linux/poll.h> #include <linux/binfmts.h> #include <linux/highmem.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/un.h> #include <linux/lsm_hooks.h> #include <net/sock.h> #include <net/af_unix.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> /********** Constants definitions. **********/ /* * TOMOYO uses this hash only when appending a string into the string * table. Frequency of appending strings is very low. So we don't need * large (e.g. 64k) hash size. 256 will be sufficient. */ #define TOMOYO_HASH_BITS 8 #define TOMOYO_MAX_HASH (1u<<TOMOYO_HASH_BITS) /* * TOMOYO checks only SOCK_STREAM, SOCK_DGRAM, SOCK_RAW, SOCK_SEQPACKET. * Therefore, we don't need SOCK_MAX. */ #define TOMOYO_SOCK_MAX 6 #define TOMOYO_EXEC_TMPSIZE 4096 /* Garbage collector is trying to kfree() this element. */ #define TOMOYO_GC_IN_PROGRESS -1 /* Profile number is an integer between 0 and 255. */ #define TOMOYO_MAX_PROFILES 256 /* Group number is an integer between 0 and 255. */ #define TOMOYO_MAX_ACL_GROUPS 256 /* Index numbers for "struct tomoyo_condition". */ enum tomoyo_conditions_index { TOMOYO_TASK_UID, /* current_uid() */ TOMOYO_TASK_EUID, /* current_euid() */ TOMOYO_TASK_SUID, /* current_suid() */ TOMOYO_TASK_FSUID, /* current_fsuid() */ TOMOYO_TASK_GID, /* current_gid() */ TOMOYO_TASK_EGID, /* current_egid() */ TOMOYO_TASK_SGID, /* current_sgid() */ TOMOYO_TASK_FSGID, /* current_fsgid() */ TOMOYO_TASK_PID, /* sys_getpid() */ TOMOYO_TASK_PPID, /* sys_getppid() */ TOMOYO_EXEC_ARGC, /* "struct linux_binprm *"->argc */ TOMOYO_EXEC_ENVC, /* "struct linux_binprm *"->envc */ TOMOYO_TYPE_IS_SOCKET, /* S_IFSOCK */ TOMOYO_TYPE_IS_SYMLINK, /* S_IFLNK */ TOMOYO_TYPE_IS_FILE, /* S_IFREG */ TOMOYO_TYPE_IS_BLOCK_DEV, /* S_IFBLK */ TOMOYO_TYPE_IS_DIRECTORY, /* S_IFDIR */ TOMOYO_TYPE_IS_CHAR_DEV, /* S_IFCHR */ TOMOYO_TYPE_IS_FIFO, /* S_IFIFO */ TOMOYO_MODE_SETUID, /* S_ISUID */ TOMOYO_MODE_SETGID, /* S_ISGID */ TOMOYO_MODE_STICKY, /* S_ISVTX */ TOMOYO_MODE_OWNER_READ, /* S_IRUSR */ TOMOYO_MODE_OWNER_WRITE, /* S_IWUSR */ TOMOYO_MODE_OWNER_EXECUTE, /* S_IXUSR */ TOMOYO_MODE_GROUP_READ, /* S_IRGRP */ TOMOYO_MODE_GROUP_WRITE, /* S_IWGRP */ TOMOYO_MODE_GROUP_EXECUTE, /* S_IXGRP */ TOMOYO_MODE_OTHERS_READ, /* S_IROTH */ TOMOYO_MODE_OTHERS_WRITE, /* S_IWOTH */ TOMOYO_MODE_OTHERS_EXECUTE, /* S_IXOTH */ TOMOYO_EXEC_REALPATH, TOMOYO_SYMLINK_TARGET, TOMOYO_PATH1_UID, TOMOYO_PATH1_GID, TOMOYO_PATH1_INO, TOMOYO_PATH1_MAJOR, TOMOYO_PATH1_MINOR, TOMOYO_PATH1_PERM, TOMOYO_PATH1_TYPE, TOMOYO_PATH1_DEV_MAJOR, TOMOYO_PATH1_DEV_MINOR, TOMOYO_PATH2_UID, TOMOYO_PATH2_GID, TOMOYO_PATH2_INO, TOMOYO_PATH2_MAJOR, TOMOYO_PATH2_MINOR, TOMOYO_PATH2_PERM, TOMOYO_PATH2_TYPE, TOMOYO_PATH2_DEV_MAJOR, TOMOYO_PATH2_DEV_MINOR, TOMOYO_PATH1_PARENT_UID, TOMOYO_PATH1_PARENT_GID, TOMOYO_PATH1_PARENT_INO, TOMOYO_PATH1_PARENT_PERM, TOMOYO_PATH2_PARENT_UID, TOMOYO_PATH2_PARENT_GID, TOMOYO_PATH2_PARENT_INO, TOMOYO_PATH2_PARENT_PERM, TOMOYO_MAX_CONDITION_KEYWORD, TOMOYO_NUMBER_UNION, TOMOYO_NAME_UNION, TOMOYO_ARGV_ENTRY, TOMOYO_ENVP_ENTRY, }; /* Index numbers for stat(). */ enum tomoyo_path_stat_index { /* Do not change this order. */ TOMOYO_PATH1, TOMOYO_PATH1_PARENT, TOMOYO_PATH2, TOMOYO_PATH2_PARENT, TOMOYO_MAX_PATH_STAT }; /* Index numbers for operation mode. */ enum tomoyo_mode_index { TOMOYO_CONFIG_DISABLED, TOMOYO_CONFIG_LEARNING, TOMOYO_CONFIG_PERMISSIVE, TOMOYO_CONFIG_ENFORCING, TOMOYO_CONFIG_MAX_MODE, TOMOYO_CONFIG_WANT_REJECT_LOG = 64, TOMOYO_CONFIG_WANT_GRANT_LOG = 128, TOMOYO_CONFIG_USE_DEFAULT = 255, }; /* Index numbers for entry type. */ enum tomoyo_policy_id { TOMOYO_ID_GROUP, TOMOYO_ID_ADDRESS_GROUP, TOMOYO_ID_PATH_GROUP, TOMOYO_ID_NUMBER_GROUP, TOMOYO_ID_TRANSITION_CONTROL, TOMOYO_ID_AGGREGATOR, TOMOYO_ID_MANAGER, TOMOYO_ID_CONDITION, TOMOYO_ID_NAME, TOMOYO_ID_ACL, TOMOYO_ID_DOMAIN, TOMOYO_MAX_POLICY }; /* Index numbers for domain's attributes. */ enum tomoyo_domain_info_flags_index { /* Quota warnning flag. */ TOMOYO_DIF_QUOTA_WARNED, /* * This domain was unable to create a new domain at * tomoyo_find_next_domain() because the name of the domain to be * created was too long or it could not allocate memory. * More than one process continued execve() without domain transition. */ TOMOYO_DIF_TRANSITION_FAILED, TOMOYO_MAX_DOMAIN_INFO_FLAGS }; /* Index numbers for audit type. */ enum tomoyo_grant_log { /* Follow profile's configuration. */ TOMOYO_GRANTLOG_AUTO, /* Do not generate grant log. */ TOMOYO_GRANTLOG_NO, /* Generate grant_log. */ TOMOYO_GRANTLOG_YES, }; /* Index numbers for group entries. */ enum tomoyo_group_id { TOMOYO_PATH_GROUP, TOMOYO_NUMBER_GROUP, TOMOYO_ADDRESS_GROUP, TOMOYO_MAX_GROUP }; /* Index numbers for type of numeric values. */ enum tomoyo_value_type { TOMOYO_VALUE_TYPE_INVALID, TOMOYO_VALUE_TYPE_DECIMAL, TOMOYO_VALUE_TYPE_OCTAL, TOMOYO_VALUE_TYPE_HEXADECIMAL, }; /* Index numbers for domain transition control keywords. */ enum tomoyo_transition_type { /* Do not change this order, */ TOMOYO_TRANSITION_CONTROL_NO_RESET, TOMOYO_TRANSITION_CONTROL_RESET, TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE, TOMOYO_TRANSITION_CONTROL_INITIALIZE, TOMOYO_TRANSITION_CONTROL_NO_KEEP, TOMOYO_TRANSITION_CONTROL_KEEP, TOMOYO_MAX_TRANSITION_TYPE }; /* Index numbers for Access Controls. */ enum tomoyo_acl_entry_type_index { TOMOYO_TYPE_PATH_ACL, TOMOYO_TYPE_PATH2_ACL, TOMOYO_TYPE_PATH_NUMBER_ACL, TOMOYO_TYPE_MKDEV_ACL, TOMOYO_TYPE_MOUNT_ACL, TOMOYO_TYPE_INET_ACL, TOMOYO_TYPE_UNIX_ACL, TOMOYO_TYPE_ENV_ACL, TOMOYO_TYPE_MANUAL_TASK_ACL, }; /* Index numbers for access controls with one pathname. */ enum tomoyo_path_acl_index { TOMOYO_TYPE_EXECUTE, TOMOYO_TYPE_READ, TOMOYO_TYPE_WRITE, TOMOYO_TYPE_APPEND, TOMOYO_TYPE_UNLINK, TOMOYO_TYPE_GETATTR, TOMOYO_TYPE_RMDIR, TOMOYO_TYPE_TRUNCATE, TOMOYO_TYPE_SYMLINK, TOMOYO_TYPE_CHROOT, TOMOYO_TYPE_UMOUNT, TOMOYO_MAX_PATH_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_memory_stat_type { TOMOYO_MEMORY_POLICY, TOMOYO_MEMORY_AUDIT, TOMOYO_MEMORY_QUERY, TOMOYO_MAX_MEMORY_STAT }; enum tomoyo_mkdev_acl_index { TOMOYO_TYPE_MKBLOCK, TOMOYO_TYPE_MKCHAR, TOMOYO_MAX_MKDEV_OPERATION }; /* Index numbers for socket operations. */ enum tomoyo_network_acl_index { TOMOYO_NETWORK_BIND, /* bind() operation. */ TOMOYO_NETWORK_LISTEN, /* listen() operation. */ TOMOYO_NETWORK_CONNECT, /* connect() operation. */ TOMOYO_NETWORK_SEND, /* send() operation. */ TOMOYO_MAX_NETWORK_OPERATION }; /* Index numbers for access controls with two pathnames. */ enum tomoyo_path2_acl_index { TOMOYO_TYPE_LINK, TOMOYO_TYPE_RENAME, TOMOYO_TYPE_PIVOT_ROOT, TOMOYO_MAX_PATH2_OPERATION }; /* Index numbers for access controls with one pathname and one number. */ enum tomoyo_path_number_acl_index { TOMOYO_TYPE_CREATE, TOMOYO_TYPE_MKDIR, TOMOYO_TYPE_MKFIFO, TOMOYO_TYPE_MKSOCK, TOMOYO_TYPE_IOCTL, TOMOYO_TYPE_CHMOD, TOMOYO_TYPE_CHOWN, TOMOYO_TYPE_CHGRP, TOMOYO_MAX_PATH_NUMBER_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/ interfaces. */ enum tomoyo_securityfs_interface_index { TOMOYO_DOMAINPOLICY, TOMOYO_EXCEPTIONPOLICY, TOMOYO_PROCESS_STATUS, TOMOYO_STAT, TOMOYO_AUDIT, TOMOYO_VERSION, TOMOYO_PROFILE, TOMOYO_QUERY, TOMOYO_MANAGER }; /* Index numbers for special mount operations. */ enum tomoyo_special_mount { TOMOYO_MOUNT_BIND, /* mount --bind /source /dest */ TOMOYO_MOUNT_MOVE, /* mount --move /old /new */ TOMOYO_MOUNT_REMOUNT, /* mount -o remount /dir */ TOMOYO_MOUNT_MAKE_UNBINDABLE, /* mount --make-unbindable /dir */ TOMOYO_MOUNT_MAKE_PRIVATE, /* mount --make-private /dir */ TOMOYO_MOUNT_MAKE_SLAVE, /* mount --make-slave /dir */ TOMOYO_MOUNT_MAKE_SHARED, /* mount --make-shared /dir */ TOMOYO_MAX_SPECIAL_MOUNT }; /* Index numbers for functionality. */ enum tomoyo_mac_index { TOMOYO_MAC_FILE_EXECUTE, TOMOYO_MAC_FILE_OPEN, TOMOYO_MAC_FILE_CREATE, TOMOYO_MAC_FILE_UNLINK, TOMOYO_MAC_FILE_GETATTR, TOMOYO_MAC_FILE_MKDIR, TOMOYO_MAC_FILE_RMDIR, TOMOYO_MAC_FILE_MKFIFO, TOMOYO_MAC_FILE_MKSOCK, TOMOYO_MAC_FILE_TRUNCATE, TOMOYO_MAC_FILE_SYMLINK, TOMOYO_MAC_FILE_MKBLOCK, TOMOYO_MAC_FILE_MKCHAR, TOMOYO_MAC_FILE_LINK, TOMOYO_MAC_FILE_RENAME, TOMOYO_MAC_FILE_CHMOD, TOMOYO_MAC_FILE_CHOWN, TOMOYO_MAC_FILE_CHGRP, TOMOYO_MAC_FILE_IOCTL, TOMOYO_MAC_FILE_CHROOT, TOMOYO_MAC_FILE_MOUNT, TOMOYO_MAC_FILE_UMOUNT, TOMOYO_MAC_FILE_PIVOT_ROOT, TOMOYO_MAC_NETWORK_INET_STREAM_BIND, TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN, TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT, TOMOYO_MAC_NETWORK_INET_DGRAM_BIND, TOMOYO_MAC_NETWORK_INET_DGRAM_SEND, TOMOYO_MAC_NETWORK_INET_RAW_BIND, TOMOYO_MAC_NETWORK_INET_RAW_SEND, TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND, TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN, TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT, TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND, TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT, TOMOYO_MAC_ENVIRON, TOMOYO_MAX_MAC_INDEX }; /* Index numbers for category of functionality. */ enum tomoyo_mac_category_index { TOMOYO_MAC_CATEGORY_FILE, TOMOYO_MAC_CATEGORY_NETWORK, TOMOYO_MAC_CATEGORY_MISC, TOMOYO_MAX_MAC_CATEGORY_INDEX }; /* * Retry this request. Returned by tomoyo_supervisor() if policy violation has * occurred in enforcing mode and the userspace daemon decided to retry. * * We must choose a positive value in order to distinguish "granted" (which is * 0) and "rejected" (which is a negative value) and "retry". */ #define TOMOYO_RETRY_REQUEST 1 /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_policy_stat_type { /* Do not change this order. */ TOMOYO_STAT_POLICY_UPDATES, TOMOYO_STAT_POLICY_LEARNING, /* == TOMOYO_CONFIG_LEARNING */ TOMOYO_STAT_POLICY_PERMISSIVE, /* == TOMOYO_CONFIG_PERMISSIVE */ TOMOYO_STAT_POLICY_ENFORCING, /* == TOMOYO_CONFIG_ENFORCING */ TOMOYO_MAX_POLICY_STAT }; /* Index numbers for profile's PREFERENCE values. */ enum tomoyo_pref_index { TOMOYO_PREF_MAX_AUDIT_LOG, TOMOYO_PREF_MAX_LEARNING_ENTRY, TOMOYO_MAX_PREF }; /********** Structure definitions. **********/ /* Common header for holding ACL entries. */ struct tomoyo_acl_head { struct list_head list; s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ } __packed; /* Common header for shared entries. */ struct tomoyo_shared_acl_head { struct list_head list; atomic_t users; } __packed; struct tomoyo_policy_namespace; /* Structure for request info. */ struct tomoyo_request_info { /* * For holding parameters specific to operations which deal files. * NULL if not dealing files. */ struct tomoyo_obj_info *obj; /* * For holding parameters specific to execve() request. * NULL if not dealing execve(). */ struct tomoyo_execve *ee; struct tomoyo_domain_info *domain; /* For holding parameters. */ union { struct { const struct tomoyo_path_info *filename; /* For using wildcards at tomoyo_find_next_domain(). */ const struct tomoyo_path_info *matched_path; /* One of values in "enum tomoyo_path_acl_index". */ u8 operation; } path; struct { const struct tomoyo_path_info *filename1; const struct tomoyo_path_info *filename2; /* One of values in "enum tomoyo_path2_acl_index". */ u8 operation; } path2; struct { const struct tomoyo_path_info *filename; unsigned int mode; unsigned int major; unsigned int minor; /* One of values in "enum tomoyo_mkdev_acl_index". */ u8 operation; } mkdev; struct { const struct tomoyo_path_info *filename; unsigned long number; /* * One of values in * "enum tomoyo_path_number_acl_index". */ u8 operation; } path_number; struct { const struct tomoyo_path_info *name; } environ; struct { const __be32 *address; u16 port; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; bool is_ipv6; } inet_network; struct { const struct tomoyo_path_info *address; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; } unix_network; struct { const struct tomoyo_path_info *type; const struct tomoyo_path_info *dir; const struct tomoyo_path_info *dev; unsigned long flags; int need_dev; } mount; struct { const struct tomoyo_path_info *domainname; } task; } param; struct tomoyo_acl_info *matched_acl; u8 param_type; bool granted; u8 retry; u8 profile; u8 mode; /* One of tomoyo_mode_index . */ u8 type; }; /* Structure for holding a token. */ struct tomoyo_path_info { const char *name; u32 hash; /* = full_name_hash(name, strlen(name)) */ u16 const_len; /* = tomoyo_const_part_length(name) */ bool is_dir; /* = tomoyo_strendswith(name, "/") */ bool is_patterned; /* = tomoyo_path_contains_pattern(name) */ }; /* Structure for holding string data. */ struct tomoyo_name { struct tomoyo_shared_acl_head head; struct tomoyo_path_info entry; }; /* Structure for holding a word. */ struct tomoyo_name_union { /* Either @filename or @group is NULL. */ const struct tomoyo_path_info *filename; struct tomoyo_group *group; }; /* Structure for holding a number. */ struct tomoyo_number_union { unsigned long values[2]; struct tomoyo_group *group; /* Maybe NULL. */ /* One of values in "enum tomoyo_value_type". */ u8 value_type[2]; }; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union { struct in6_addr ip[2]; /* Big endian. */ struct tomoyo_group *group; /* Pointer to address group. */ bool is_ipv6; /* Valid only if @group == NULL. */ }; /* Structure for "path_group"/"number_group"/"address_group" directive. */ struct tomoyo_group { struct tomoyo_shared_acl_head head; const struct tomoyo_path_info *group_name; struct list_head member_list; }; /* Structure for "path_group" directive. */ struct tomoyo_path_group { struct tomoyo_acl_head head; const struct tomoyo_path_info *member_name; }; /* Structure for "number_group" directive. */ struct tomoyo_number_group { struct tomoyo_acl_head head; struct tomoyo_number_union number; }; /* Structure for "address_group" directive. */ struct tomoyo_address_group { struct tomoyo_acl_head head; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union address; }; /* Subset of "struct stat". Used by conditional ACL and audit logs. */ struct tomoyo_mini_stat { kuid_t uid; kgid_t gid; ino_t ino; umode_t mode; dev_t dev; dev_t rdev; }; /* Structure for dumping argv[] and envp[] of "struct linux_binprm". */ struct tomoyo_page_dump { struct page *page; /* Previously dumped page. */ char *data; /* Contents of "page". Size is PAGE_SIZE. */ }; /* Structure for attribute checks in addition to pathname checks. */ struct tomoyo_obj_info { /* * True if tomoyo_get_attributes() was already called, false otherwise. */ bool validate_done; /* True if @stat[] is valid. */ bool stat_valid[TOMOYO_MAX_PATH_STAT]; /* First pathname. Initialized with { NULL, NULL } if no path. */ struct path path1; /* Second pathname. Initialized with { NULL, NULL } if no path. */ struct path path2; /* * Information on @path1, @path1's parent directory, @path2, @path2's * parent directory. */ struct tomoyo_mini_stat stat[TOMOYO_MAX_PATH_STAT]; /* * Content of symbolic link to be created. NULL for operations other * than symlink(). */ struct tomoyo_path_info *symlink_target; }; /* Structure for argv[]. */ struct tomoyo_argv { unsigned long index; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for envp[]. */ struct tomoyo_envp { const struct tomoyo_path_info *name; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for execve() operation. */ struct tomoyo_execve { struct tomoyo_request_info r; struct tomoyo_obj_info obj; struct linux_binprm *bprm; const struct tomoyo_path_info *transition; /* For dumping argv[] and envp[]. */ struct tomoyo_page_dump dump; /* For temporary use. */ char *tmp; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ }; /* Structure for entries which follows "struct tomoyo_condition". */ struct tomoyo_condition_element { /* * Left hand operand. A "struct tomoyo_argv" for TOMOYO_ARGV_ENTRY, a * "struct tomoyo_envp" for TOMOYO_ENVP_ENTRY is attached to the tail * of the array of this struct. */ u8 left; /* * Right hand operand. A "struct tomoyo_number_union" for * TOMOYO_NUMBER_UNION, a "struct tomoyo_name_union" for * TOMOYO_NAME_UNION is attached to the tail of the array of this * struct. */ u8 right; /* Equation operator. True if equals or overlaps, false otherwise. */ bool equals; }; /* Structure for optional arguments. */ struct tomoyo_condition { struct tomoyo_shared_acl_head head; u32 size; /* Memory size allocated for this entry. */ u16 condc; /* Number of conditions in this struct. */ u16 numbers_count; /* Number of "struct tomoyo_number_union values". */ u16 names_count; /* Number of "struct tomoyo_name_union names". */ u16 argc; /* Number of "struct tomoyo_argv". */ u16 envc; /* Number of "struct tomoyo_envp". */ u8 grant_log; /* One of values in "enum tomoyo_grant_log". */ const struct tomoyo_path_info *transit; /* Maybe NULL. */ /* * struct tomoyo_condition_element condition[condc]; * struct tomoyo_number_union values[numbers_count]; * struct tomoyo_name_union names[names_count]; * struct tomoyo_argv argv[argc]; * struct tomoyo_envp envp[envc]; */ }; /* Common header for individual entries. */ struct tomoyo_acl_info { struct list_head list; struct tomoyo_condition *cond; /* Maybe NULL. */ s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ u8 type; /* One of values in "enum tomoyo_acl_entry_type_index". */ } __packed; /* Structure for domain information. */ struct tomoyo_domain_info { struct list_head list; struct list_head acl_info_list; /* Name of this domain. Never NULL. */ const struct tomoyo_path_info *domainname; /* Namespace for this domain. Never NULL. */ struct tomoyo_policy_namespace *ns; /* Group numbers to use. */ unsigned long group[TOMOYO_MAX_ACL_GROUPS / BITS_PER_LONG]; u8 profile; /* Profile number to use. */ bool is_deleted; /* Delete flag. */ bool flags[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; atomic_t users; /* Number of referring tasks. */ }; /* * Structure for "task manual_domain_transition" directive. */ struct tomoyo_task_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MANUAL_TASK_ACL */ /* Pointer to domainname. */ const struct tomoyo_path_info *domainname; }; /* * Structure for "file execute", "file read", "file write", "file append", * "file unlink", "file getattr", "file rmdir", "file truncate", * "file symlink", "file chroot" and "file unmount" directive. */ struct tomoyo_path_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_ACL */ u16 perm; /* Bitmask of values in "enum tomoyo_path_acl_index". */ struct tomoyo_name_union name; }; /* * Structure for "file create", "file mkdir", "file mkfifo", "file mksock", * "file ioctl", "file chmod", "file chown" and "file chgrp" directive. */ struct tomoyo_path_number_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_NUMBER_ACL */ /* Bitmask of values in "enum tomoyo_path_number_acl_index". */ u8 perm; struct tomoyo_name_union name; struct tomoyo_number_union number; }; /* Structure for "file mkblock" and "file mkchar" directive. */ struct tomoyo_mkdev_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MKDEV_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_mkdev_acl_index". */ struct tomoyo_name_union name; struct tomoyo_number_union mode; struct tomoyo_number_union major; struct tomoyo_number_union minor; }; /* * Structure for "file rename", "file link" and "file pivot_root" directive. */ struct tomoyo_path2_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH2_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_path2_acl_index". */ struct tomoyo_name_union name1; struct tomoyo_name_union name2; }; /* Structure for "file mount" directive. */ struct tomoyo_mount_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MOUNT_ACL */ struct tomoyo_name_union dev_name; struct tomoyo_name_union dir_name; struct tomoyo_name_union fs_type; struct tomoyo_number_union flags; }; /* Structure for "misc env" directive in domain policy. */ struct tomoyo_env_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_ENV_ACL */ const struct tomoyo_path_info *env; /* environment variable */ }; /* Structure for "network inet" directive. */ struct tomoyo_inet_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_INET_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_ipaddr_union address; struct tomoyo_number_union port; }; /* Structure for "network unix" directive. */ struct tomoyo_unix_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_UNIX_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_name_union name; }; /* Structure for holding a line from /sys/kernel/security/tomoyo/ interface. */ struct tomoyo_acl_param { char *data; struct list_head *list; struct tomoyo_policy_namespace *ns; bool is_delete; }; #define TOMOYO_MAX_IO_READ_QUEUE 64 /* * Structure for reading/writing policy via /sys/kernel/security/tomoyo * interfaces. */ struct tomoyo_io_buffer { void (*read)(struct tomoyo_io_buffer *head); int (*write)(struct tomoyo_io_buffer *head); __poll_t (*poll)(struct file *file, poll_table *wait); /* Exclusive lock for this structure. */ struct mutex io_sem; char __user *read_user_buf; size_t read_user_buf_avail; struct { struct list_head *ns; struct list_head *domain; struct list_head *group; struct list_head *acl; size_t avail; unsigned int step; unsigned int query_index; u16 index; u16 cond_index; u8 acl_group_index; u8 cond_step; u8 bit; u8 w_pos; bool eof; bool print_this_domain_only; bool print_transition_related_only; bool print_cond_part; const char *w[TOMOYO_MAX_IO_READ_QUEUE]; } r; struct { struct tomoyo_policy_namespace *ns; /* The position currently writing to. */ struct tomoyo_domain_info *domain; /* Bytes available for writing. */ size_t avail; bool is_delete; } w; /* Buffer for reading. */ char *read_buf; /* Size of read buffer. */ size_t readbuf_size; /* Buffer for writing. */ char *write_buf; /* Size of write buffer. */ size_t writebuf_size; /* Type of this interface. */ enum tomoyo_securityfs_interface_index type; /* Users counter protected by tomoyo_io_buffer_list_lock. */ u8 users; /* List for telling GC not to kfree() elements. */ struct list_head list; }; /* * Structure for "initialize_domain"/"no_initialize_domain"/"keep_domain"/ * "no_keep_domain" keyword. */ struct tomoyo_transition_control { struct tomoyo_acl_head head; u8 type; /* One of values in "enum tomoyo_transition_type". */ /* True if the domainname is tomoyo_get_last_name(). */ bool is_last_name; const struct tomoyo_path_info *domainname; /* Maybe NULL */ const struct tomoyo_path_info *program; /* Maybe NULL */ }; /* Structure for "aggregator" keyword. */ struct tomoyo_aggregator { struct tomoyo_acl_head head; const struct tomoyo_path_info *original_name; const struct tomoyo_path_info *aggregated_name; }; /* Structure for policy manager. */ struct tomoyo_manager { struct tomoyo_acl_head head; /* A path to program or a domainname. */ const struct tomoyo_path_info *manager; }; struct tomoyo_preference { unsigned int learning_max_entry; bool enforcing_verbose; bool learning_verbose; bool permissive_verbose; }; /* Structure for /sys/kernel/security/tomnoyo/profile interface. */ struct tomoyo_profile { const struct tomoyo_path_info *comment; struct tomoyo_preference *learning; struct tomoyo_preference *permissive; struct tomoyo_preference *enforcing; struct tomoyo_preference preference; u8 default_config; u8 config[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; unsigned int pref[TOMOYO_MAX_PREF]; }; /* Structure for representing YYYY/MM/DD hh/mm/ss. */ struct tomoyo_time { u16 year; u8 month; u8 day; u8 hour; u8 min; u8 sec; }; /* Structure for policy namespace. */ struct tomoyo_policy_namespace { /* Profile table. Memory is allocated as needed. */ struct tomoyo_profile *profile_ptr[TOMOYO_MAX_PROFILES]; /* List of "struct tomoyo_group". */ struct list_head group_list[TOMOYO_MAX_GROUP]; /* List of policy. */ struct list_head policy_list[TOMOYO_MAX_POLICY]; /* The global ACL referred by "use_group" keyword. */ struct list_head acl_group[TOMOYO_MAX_ACL_GROUPS]; /* List for connecting to tomoyo_namespace_list list. */ struct list_head namespace_list; /* Profile version. Currently only 20150505 is defined. */ unsigned int profile_version; /* Name of this namespace (e.g. "<kernel>", "</usr/sbin/httpd>" ). */ const char *name; }; /* Structure for "struct task_struct"->security. */ struct tomoyo_task { struct tomoyo_domain_info *domain_info; struct tomoyo_domain_info *old_domain_info; }; /********** Function prototypes. **********/ bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, const struct tomoyo_group *group); bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr); bool tomoyo_condition(struct tomoyo_request_info *r, const struct tomoyo_condition *cond); bool tomoyo_correct_domain(const unsigned char *domainname); bool tomoyo_correct_path(const char *filename); bool tomoyo_correct_word(const char *string); bool tomoyo_domain_def(const unsigned char *buffer); bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r); bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump); bool tomoyo_memory_ok(void *ptr); bool tomoyo_number_matches_group(const unsigned long min, const unsigned long max, const struct tomoyo_group *group); bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param, struct tomoyo_ipaddr_union *ptr); bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr); bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr); bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern); bool tomoyo_permstr(const char *string, const char *keyword); bool tomoyo_str_starts(char **src, const char *find); char *tomoyo_encode(const char *str); char *tomoyo_encode2(const char *str, int str_len); char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); char *tomoyo_read_token(struct tomoyo_acl_param *param); char *tomoyo_realpath_from_path(const struct path *path); char *tomoyo_realpath_nofollow(const char *pathname); const char *tomoyo_get_exe(void); const struct tomoyo_path_info *tomoyo_compare_name_union (const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr); const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param); const struct tomoyo_path_info *tomoyo_get_name(const char *name); const struct tomoyo_path_info *tomoyo_path_matches_group (const struct tomoyo_path_info *pathname, const struct tomoyo_group *group); int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, const struct path *path, const int flag); void tomoyo_close_control(struct tomoyo_io_buffer *head); int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env); int tomoyo_execute_permission(struct tomoyo_request_info *r, const struct tomoyo_path_info *filename); int tomoyo_find_next_domain(struct linux_binprm *bprm); int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index); int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index); int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev); int tomoyo_mount_permission(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data_page); int tomoyo_open_control(const u8 type, struct file *file); int tomoyo_path2_perm(const u8 operation, const struct path *path1, const struct path *path2); int tomoyo_path_number_perm(const u8 operation, const struct path *path, unsigned long number); int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target); __poll_t tomoyo_poll_control(struct file *file, poll_table *wait); __poll_t tomoyo_poll_log(struct file *file, poll_table *wait); int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_connect_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_listen_permission(struct socket *sock); int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg, int size); int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate) (struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)); int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)); int tomoyo_write_aggregator(struct tomoyo_acl_param *param); int tomoyo_write_file(struct tomoyo_acl_param *param); int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_misc(struct tomoyo_acl_param *param); int tomoyo_write_inet_network(struct tomoyo_acl_param *param); int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_unix_network(struct tomoyo_acl_param *param); ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len); ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len); struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param); struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit); struct tomoyo_domain_info *tomoyo_domain(void); struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname); struct tomoyo_group *tomoyo_get_group(struct tomoyo_acl_param *param, const u8 idx); struct tomoyo_policy_namespace *tomoyo_assign_namespace (const char *domainname); struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile); u8 tomoyo_parse_ulong(unsigned long *result, char **str); void *tomoyo_commit_ok(void *data, const unsigned int size); void __init tomoyo_load_builtin_policy(void); void __init tomoyo_mm_init(void); void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)); void tomoyo_check_profile(void); void tomoyo_convert_time(time64_t time, struct tomoyo_time *stamp); void tomoyo_del_condition(struct list_head *element); void tomoyo_fill_path_info(struct tomoyo_path_info *ptr); void tomoyo_get_attributes(struct tomoyo_obj_info *obj); void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns); void tomoyo_load_policy(const char *filename); void tomoyo_normalize_line(unsigned char *buffer); void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register); void tomoyo_print_ip(char *buf, const unsigned int size, const struct tomoyo_ipaddr_union *ptr); void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type); void tomoyo_put_name_union(struct tomoyo_name_union *ptr); void tomoyo_put_number_union(struct tomoyo_number_union *ptr); void tomoyo_read_log(struct tomoyo_io_buffer *head); void tomoyo_update_stat(const u8 index); void tomoyo_warn_oom(const char *function); void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); /********** External variable definitions. **********/ extern bool tomoyo_policy_loaded; extern int tomoyo_enabled; extern const char * const tomoyo_condition_keyword [TOMOYO_MAX_CONDITION_KEYWORD]; extern const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; extern const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; extern const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE]; extern const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION]; extern const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX]; extern const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION]; extern const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX]; extern const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION]; extern const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION]; extern const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION]; extern struct list_head tomoyo_condition_list; extern struct list_head tomoyo_domain_list; extern struct list_head tomoyo_name_list[TOMOYO_MAX_HASH]; extern struct list_head tomoyo_namespace_list; extern struct mutex tomoyo_policy_lock; extern struct srcu_struct tomoyo_ss; extern struct tomoyo_domain_info tomoyo_kernel_domain; extern struct tomoyo_policy_namespace tomoyo_kernel_namespace; extern unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT]; extern unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT]; extern struct lsm_blob_sizes tomoyo_blob_sizes; /********** Inlined functions. **********/ /** * tomoyo_read_lock - Take lock for protecting policy. * * Returns index number for tomoyo_read_unlock(). */ static inline int tomoyo_read_lock(void) { return srcu_read_lock(&tomoyo_ss); } /** * tomoyo_read_unlock - Release lock for protecting policy. * * @idx: Index number returned by tomoyo_read_lock(). * * Returns nothing. */ static inline void tomoyo_read_unlock(int idx) { srcu_read_unlock(&tomoyo_ss, idx); } /** * tomoyo_sys_getppid - Copy of getppid(). * * Returns parent process's PID. * * Alpha does not have getppid() defined. To be able to build this module on * Alpha, I have to copy getppid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getppid(void) { pid_t pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } /** * tomoyo_sys_getpid - Copy of getpid(). * * Returns current thread's PID. * * Alpha does not have getpid() defined. To be able to build this module on * Alpha, I have to copy getpid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getpid(void) { return task_tgid_vnr(current); } /** * tomoyo_pathcmp - strcmp() for "struct tomoyo_path_info" structure. * * @a: Pointer to "struct tomoyo_path_info". * @b: Pointer to "struct tomoyo_path_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_pathcmp(const struct tomoyo_path_info *a, const struct tomoyo_path_info *b) { return a->hash != b->hash || strcmp(a->name, b->name); } /** * tomoyo_put_name - Drop reference on "struct tomoyo_name". * * @name: Pointer to "struct tomoyo_path_info". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_name(const struct tomoyo_path_info *name) { if (name) { struct tomoyo_name *ptr = container_of(name, typeof(*ptr), entry); atomic_dec(&ptr->head.users); } } /** * tomoyo_put_condition - Drop reference on "struct tomoyo_condition". * * @cond: Pointer to "struct tomoyo_condition". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_condition(struct tomoyo_condition *cond) { if (cond) atomic_dec(&cond->head.users); } /** * tomoyo_put_group - Drop reference on "struct tomoyo_group". * * @group: Pointer to "struct tomoyo_group". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_group(struct tomoyo_group *group) { if (group) atomic_dec(&group->head.users); } /** * tomoyo_task - Get "struct tomoyo_task" for specified thread. * * @task - Pointer to "struct task_struct". * * Returns pointer to "struct tomoyo_task" for specified thread. */ static inline struct tomoyo_task *tomoyo_task(struct task_struct *task) { return task->security + tomoyo_blob_sizes.lbs_task; } /** * tomoyo_same_name_union - Check for duplicated "struct tomoyo_name_union" entry. * * @a: Pointer to "struct tomoyo_name_union". * @b: Pointer to "struct tomoyo_name_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_name_union (const struct tomoyo_name_union *a, const struct tomoyo_name_union *b) { return a->filename == b->filename && a->group == b->group; } /** * tomoyo_same_number_union - Check for duplicated "struct tomoyo_number_union" entry. * * @a: Pointer to "struct tomoyo_number_union". * @b: Pointer to "struct tomoyo_number_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_number_union (const struct tomoyo_number_union *a, const struct tomoyo_number_union *b) { return a->values[0] == b->values[0] && a->values[1] == b->values[1] && a->group == b->group && a->value_type[0] == b->value_type[0] && a->value_type[1] == b->value_type[1]; } /** * tomoyo_same_ipaddr_union - Check for duplicated "struct tomoyo_ipaddr_union" entry. * * @a: Pointer to "struct tomoyo_ipaddr_union". * @b: Pointer to "struct tomoyo_ipaddr_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_ipaddr_union (const struct tomoyo_ipaddr_union *a, const struct tomoyo_ipaddr_union *b) { return !memcmp(a->ip, b->ip, sizeof(a->ip)) && a->group == b->group && a->is_ipv6 == b->is_ipv6; } /** * tomoyo_current_namespace - Get "struct tomoyo_policy_namespace" for current thread. * * Returns pointer to "struct tomoyo_policy_namespace" for current thread. */ static inline struct tomoyo_policy_namespace *tomoyo_current_namespace(void) { return tomoyo_domain()->ns; } /** * list_for_each_cookie - iterate over a list with cookie. * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_cookie(pos, head) \ if (!pos) \ pos = srcu_dereference((head)->next, &tomoyo_ss); \ for ( ; pos != (head); pos = srcu_dereference(pos->next, &tomoyo_ss)) #endif /* !defined(_SECURITY_TOMOYO_COMMON_H) */ |
| 198 198 197 198 198 198 198 198 198 198 198 198 198 198 198 198 198 198 198 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/core.c - core driver model code (device registration, etc) * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2006 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2006 Novell, Inc. */ #include <linux/acpi.h> #include <linux/blkdev.h> #include <linux/cleanup.h> #include <linux/cpufreq.h> #include <linux/device.h> #include <linux/dma-map-ops.h> /* for dma_default_coherent */ #include <linux/err.h> #include <linux/fwnode.h> #include <linux/init.h> #include <linux/kdev_t.h> #include <linux/kstrtox.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/pm_runtime.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/string_helpers.h> #include <linux/swiotlb.h> #include <linux/sysfs.h> #include "base.h" #include "physical_location.h" #include "power/power.h" /* Device links support. */ static LIST_HEAD(deferred_sync); static unsigned int defer_sync_state_count = 1; static DEFINE_MUTEX(fwnode_link_lock); static bool fw_devlink_is_permissive(void); static void __fw_devlink_link_to_consumers(struct device *dev); static bool fw_devlink_drv_reg_done; static bool fw_devlink_best_effort; static struct workqueue_struct *device_link_wq; /** * __fwnode_link_add - Create a link between two fwnode_handles. * @con: Consumer end of the link. * @sup: Supplier end of the link. * @flags: Link flags. * * Create a fwnode link between fwnode handles @con and @sup. The fwnode link * represents the detail that the firmware lists @sup fwnode as supplying a * resource to @con. * * The driver core will use the fwnode link to create a device link between the * two device objects corresponding to @con and @sup when they are created. The * driver core will automatically delete the fwnode link between @con and @sup * after doing that. * * Attempts to create duplicate links between the same pair of fwnode handles * are ignored and there is no reference counting. */ static int __fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup, u8 flags) { struct fwnode_link *link; list_for_each_entry(link, &sup->consumers, s_hook) if (link->consumer == con) { link->flags |= flags; return 0; } link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) return -ENOMEM; link->supplier = sup; INIT_LIST_HEAD(&link->s_hook); link->consumer = con; INIT_LIST_HEAD(&link->c_hook); link->flags = flags; list_add(&link->s_hook, &sup->consumers); list_add(&link->c_hook, &con->suppliers); pr_debug("%pfwf Linked as a fwnode consumer to %pfwf\n", con, sup); return 0; } int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup, u8 flags) { guard(mutex)(&fwnode_link_lock); return __fwnode_link_add(con, sup, flags); } /** * __fwnode_link_del - Delete a link between two fwnode_handles. * @link: the fwnode_link to be deleted * * The fwnode_link_lock needs to be held when this function is called. */ static void __fwnode_link_del(struct fwnode_link *link) { pr_debug("%pfwf Dropping the fwnode link to %pfwf\n", link->consumer, link->supplier); list_del(&link->s_hook); list_del(&link->c_hook); kfree(link); } /** * __fwnode_link_cycle - Mark a fwnode link as being part of a cycle. * @link: the fwnode_link to be marked * * The fwnode_link_lock needs to be held when this function is called. */ static void __fwnode_link_cycle(struct fwnode_link *link) { pr_debug("%pfwf: cycle: depends on %pfwf\n", link->consumer, link->supplier); link->flags |= FWLINK_FLAG_CYCLE; } /** * fwnode_links_purge_suppliers - Delete all supplier links of fwnode_handle. * @fwnode: fwnode whose supplier links need to be deleted * * Deletes all supplier links connecting directly to @fwnode. */ static void fwnode_links_purge_suppliers(struct fwnode_handle *fwnode) { struct fwnode_link *link, *tmp; guard(mutex)(&fwnode_link_lock); list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) __fwnode_link_del(link); } /** * fwnode_links_purge_consumers - Delete all consumer links of fwnode_handle. * @fwnode: fwnode whose consumer links need to be deleted * * Deletes all consumer links connecting directly to @fwnode. */ static void fwnode_links_purge_consumers(struct fwnode_handle *fwnode) { struct fwnode_link *link, *tmp; guard(mutex)(&fwnode_link_lock); list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) __fwnode_link_del(link); } /** * fwnode_links_purge - Delete all links connected to a fwnode_handle. * @fwnode: fwnode whose links needs to be deleted * * Deletes all links connecting directly to a fwnode. */ void fwnode_links_purge(struct fwnode_handle *fwnode) { fwnode_links_purge_suppliers(fwnode); fwnode_links_purge_consumers(fwnode); } void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode) { struct fwnode_handle *child; /* Don't purge consumer links of an added child */ if (fwnode->dev) return; fwnode->flags |= FWNODE_FLAG_NOT_DEVICE; fwnode_links_purge_consumers(fwnode); fwnode_for_each_available_child_node(fwnode, child) fw_devlink_purge_absent_suppliers(child); } EXPORT_SYMBOL_GPL(fw_devlink_purge_absent_suppliers); /** * __fwnode_links_move_consumers - Move consumer from @from to @to fwnode_handle * @from: move consumers away from this fwnode * @to: move consumers to this fwnode * * Move all consumer links from @from fwnode to @to fwnode. */ static void __fwnode_links_move_consumers(struct fwnode_handle *from, struct fwnode_handle *to) { struct fwnode_link *link, *tmp; list_for_each_entry_safe(link, tmp, &from->consumers, s_hook) { __fwnode_link_add(link->consumer, to, link->flags); __fwnode_link_del(link); } } /** * __fw_devlink_pickup_dangling_consumers - Pick up dangling consumers * @fwnode: fwnode from which to pick up dangling consumers * @new_sup: fwnode of new supplier * * If the @fwnode has a corresponding struct device and the device supports * probing (that is, added to a bus), then we want to let fw_devlink create * MANAGED device links to this device, so leave @fwnode and its descendant's * fwnode links alone. * * Otherwise, move its consumers to the new supplier @new_sup. */ static void __fw_devlink_pickup_dangling_consumers(struct fwnode_handle *fwnode, struct fwnode_handle *new_sup) { struct fwnode_handle *child; if (fwnode->dev && fwnode->dev->bus) return; fwnode->flags |= FWNODE_FLAG_NOT_DEVICE; __fwnode_links_move_consumers(fwnode, new_sup); fwnode_for_each_available_child_node(fwnode, child) __fw_devlink_pickup_dangling_consumers(child, new_sup); } static DEFINE_MUTEX(device_links_lock); DEFINE_STATIC_SRCU(device_links_srcu); static inline void device_links_write_lock(void) { mutex_lock(&device_links_lock); } static inline void device_links_write_unlock(void) { mutex_unlock(&device_links_lock); } int device_links_read_lock(void) __acquires(&device_links_srcu) { return srcu_read_lock(&device_links_srcu); } void device_links_read_unlock(int idx) __releases(&device_links_srcu) { srcu_read_unlock(&device_links_srcu, idx); } int device_links_read_lock_held(void) { return srcu_read_lock_held(&device_links_srcu); } static void device_link_synchronize_removal(void) { synchronize_srcu(&device_links_srcu); } static void device_link_remove_from_lists(struct device_link *link) { list_del_rcu(&link->s_node); list_del_rcu(&link->c_node); } static bool device_is_ancestor(struct device *dev, struct device *target) { while (target->parent) { target = target->parent; if (dev == target) return true; } return false; } #define DL_MARKER_FLAGS (DL_FLAG_INFERRED | \ DL_FLAG_CYCLE | \ DL_FLAG_MANAGED) static inline bool device_link_flag_is_sync_state_only(u32 flags) { return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY; } /** * device_is_dependent - Check if one device depends on another one * @dev: Device to check dependencies for. * @target: Device to check against. * * Check if @target depends on @dev or any device dependent on it (its child or * its consumer etc). Return 1 if that is the case or 0 otherwise. */ static int device_is_dependent(struct device *dev, void *target) { struct device_link *link; int ret; /* * The "ancestors" check is needed to catch the case when the target * device has not been completely initialized yet and it is still * missing from the list of children of its parent device. */ if (dev == target || device_is_ancestor(dev, target)) return 1; ret = device_for_each_child(dev, target, device_is_dependent); if (ret) return ret; list_for_each_entry(link, &dev->links.consumers, s_node) { if (device_link_flag_is_sync_state_only(link->flags)) continue; if (link->consumer == target) return 1; ret = device_is_dependent(link->consumer, target); if (ret) break; } return ret; } static void device_link_init_status(struct device_link *link, struct device *consumer, struct device *supplier) { switch (supplier->links.status) { case DL_DEV_PROBING: switch (consumer->links.status) { case DL_DEV_PROBING: /* * A consumer driver can create a link to a supplier * that has not completed its probing yet as long as it * knows that the supplier is already functional (for * example, it has just acquired some resources from the * supplier). */ link->status = DL_STATE_CONSUMER_PROBE; break; default: link->status = DL_STATE_DORMANT; break; } break; case DL_DEV_DRIVER_BOUND: switch (consumer->links.status) { case DL_DEV_PROBING: link->status = DL_STATE_CONSUMER_PROBE; break; case DL_DEV_DRIVER_BOUND: link->status = DL_STATE_ACTIVE; break; default: link->status = DL_STATE_AVAILABLE; break; } break; case DL_DEV_UNBINDING: link->status = DL_STATE_SUPPLIER_UNBIND; break; default: link->status = DL_STATE_DORMANT; break; } } static int device_reorder_to_tail(struct device *dev, void *not_used) { struct device_link *link; /* * Devices that have not been registered yet will be put to the ends * of the lists during the registration, so skip them here. */ if (device_is_registered(dev)) devices_kset_move_last(dev); if (device_pm_initialized(dev)) device_pm_move_last(dev); device_for_each_child(dev, NULL, device_reorder_to_tail); list_for_each_entry(link, &dev->links.consumers, s_node) { if (device_link_flag_is_sync_state_only(link->flags)) continue; device_reorder_to_tail(link->consumer, NULL); } return 0; } /** * device_pm_move_to_tail - Move set of devices to the end of device lists * @dev: Device to move * * This is a device_reorder_to_tail() wrapper taking the requisite locks. * * It moves the @dev along with all of its children and all of its consumers * to the ends of the device_kset and dpm_list, recursively. */ void device_pm_move_to_tail(struct device *dev) { int idx; idx = device_links_read_lock(); device_pm_lock(); device_reorder_to_tail(dev, NULL); device_pm_unlock(); device_links_read_unlock(idx); } #define to_devlink(dev) container_of((dev), struct device_link, link_dev) static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *output; switch (to_devlink(dev)->status) { case DL_STATE_NONE: output = "not tracked"; break; case DL_STATE_DORMANT: output = "dormant"; break; case DL_STATE_AVAILABLE: output = "available"; break; case DL_STATE_CONSUMER_PROBE: output = "consumer probing"; break; case DL_STATE_ACTIVE: output = "active"; break; case DL_STATE_SUPPLIER_UNBIND: output = "supplier unbinding"; break; default: output = "unknown"; break; } return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(status); static ssize_t auto_remove_on_show(struct device *dev, struct device_attribute *attr, char *buf) { struct device_link *link = to_devlink(dev); const char *output; if (link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) output = "supplier unbind"; else if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) output = "consumer unbind"; else output = "never"; return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(auto_remove_on); static ssize_t runtime_pm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct device_link *link = to_devlink(dev); return sysfs_emit(buf, "%d\n", !!(link->flags & DL_FLAG_PM_RUNTIME)); } static DEVICE_ATTR_RO(runtime_pm); static ssize_t sync_state_only_show(struct device *dev, struct device_attribute *attr, char *buf) { struct device_link *link = to_devlink(dev); return sysfs_emit(buf, "%d\n", !!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); } static DEVICE_ATTR_RO(sync_state_only); static struct attribute *devlink_attrs[] = { &dev_attr_status.attr, &dev_attr_auto_remove_on.attr, &dev_attr_runtime_pm.attr, &dev_attr_sync_state_only.attr, NULL, }; ATTRIBUTE_GROUPS(devlink); static void device_link_release_fn(struct work_struct *work) { struct device_link *link = container_of(work, struct device_link, rm_work); /* Ensure that all references to the link object have been dropped. */ device_link_synchronize_removal(); pm_runtime_release_supplier(link); /* * If supplier_preactivated is set, the link has been dropped between * the pm_runtime_get_suppliers() and pm_runtime_put_suppliers() calls * in __driver_probe_device(). In that case, drop the supplier's * PM-runtime usage counter to remove the reference taken by * pm_runtime_get_suppliers(). */ if (link->supplier_preactivated) pm_runtime_put_noidle(link->supplier); pm_request_idle(link->supplier); put_device(link->consumer); put_device(link->supplier); kfree(link); } static void devlink_dev_release(struct device *dev) { struct device_link *link = to_devlink(dev); INIT_WORK(&link->rm_work, device_link_release_fn); /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or * supplier devices get deleted when it runs, so put it into the * dedicated workqueue. */ queue_work(device_link_wq, &link->rm_work); } /** * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate */ void device_link_wait_removal(void) { /* * devlink removal jobs are queued in the dedicated work queue. * To be sure that all removal jobs are terminated, ensure that any * scheduled work has run to completion. */ flush_workqueue(device_link_wq); } EXPORT_SYMBOL_GPL(device_link_wait_removal); static struct class devlink_class = { .name = "devlink", .dev_groups = devlink_groups, .dev_release = devlink_dev_release, }; static int devlink_add_symlinks(struct device *dev) { char *buf_con __free(kfree) = NULL, *buf_sup __free(kfree) = NULL; int ret; struct device_link *link = to_devlink(dev); struct device *sup = link->supplier; struct device *con = link->consumer; ret = sysfs_create_link(&link->link_dev.kobj, &sup->kobj, "supplier"); if (ret) goto out; ret = sysfs_create_link(&link->link_dev.kobj, &con->kobj, "consumer"); if (ret) goto err_con; buf_con = kasprintf(GFP_KERNEL, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); if (!buf_con) { ret = -ENOMEM; goto err_con_dev; } ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf_con); if (ret) goto err_con_dev; buf_sup = kasprintf(GFP_KERNEL, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); if (!buf_sup) { ret = -ENOMEM; goto err_sup_dev; } ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf_sup); if (ret) goto err_sup_dev; goto out; err_sup_dev: sysfs_remove_link(&sup->kobj, buf_con); err_con_dev: sysfs_remove_link(&link->link_dev.kobj, "consumer"); err_con: sysfs_remove_link(&link->link_dev.kobj, "supplier"); out: return ret; } static void devlink_remove_symlinks(struct device *dev) { char *buf_con __free(kfree) = NULL, *buf_sup __free(kfree) = NULL; struct device_link *link = to_devlink(dev); struct device *sup = link->supplier; struct device *con = link->consumer; sysfs_remove_link(&link->link_dev.kobj, "consumer"); sysfs_remove_link(&link->link_dev.kobj, "supplier"); if (device_is_registered(con)) { buf_sup = kasprintf(GFP_KERNEL, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); if (!buf_sup) goto out; sysfs_remove_link(&con->kobj, buf_sup); } buf_con = kasprintf(GFP_KERNEL, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); if (!buf_con) goto out; sysfs_remove_link(&sup->kobj, buf_con); return; out: WARN(1, "Unable to properly free device link symlinks!\n"); } static struct class_interface devlink_class_intf = { .class = &devlink_class, .add_dev = devlink_add_symlinks, .remove_dev = devlink_remove_symlinks, }; static int __init devlink_class_init(void) { int ret; ret = class_register(&devlink_class); if (ret) return ret; ret = class_interface_register(&devlink_class_intf); if (ret) class_unregister(&devlink_class); return ret; } postcore_initcall(devlink_class_init); #define DL_MANAGED_LINK_FLAGS (DL_FLAG_AUTOREMOVE_CONSUMER | \ DL_FLAG_AUTOREMOVE_SUPPLIER | \ DL_FLAG_AUTOPROBE_CONSUMER | \ DL_FLAG_SYNC_STATE_ONLY | \ DL_FLAG_INFERRED | \ DL_FLAG_CYCLE) #define DL_ADD_VALID_FLAGS (DL_MANAGED_LINK_FLAGS | DL_FLAG_STATELESS | \ DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE) /** * device_link_add - Create a link between two devices. * @consumer: Consumer end of the link. * @supplier: Supplier end of the link. * @flags: Link flags. * * Return: On success, a device_link struct will be returned. * On error or invalid flag settings, NULL will be returned. * * The caller is responsible for the proper synchronization of the link creation * with runtime PM. First, setting the DL_FLAG_PM_RUNTIME flag will cause the * runtime PM framework to take the link into account. Second, if the * DL_FLAG_RPM_ACTIVE flag is set in addition to it, the supplier devices will * be forced into the active meta state and reference-counted upon the creation * of the link. If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be * ignored. * * If DL_FLAG_STATELESS is set in @flags, the caller of this function is * expected to release the link returned by it directly with the help of either * device_link_del() or device_link_remove(). * * If that flag is not set, however, the caller of this function is handing the * management of the link over to the driver core entirely and its return value * can only be used to check whether or not the link is present. In that case, * the DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_AUTOREMOVE_SUPPLIER device link * flags can be used to indicate to the driver core when the link can be safely * deleted. Namely, setting one of them in @flags indicates to the driver core * that the link is not going to be used (by the given caller of this function) * after unbinding the consumer or supplier driver, respectively, from its * device, so the link can be deleted at that point. If none of them is set, * the link will be maintained until one of the devices pointed to by it (either * the consumer or the supplier) is unregistered. * * Also, if DL_FLAG_STATELESS, DL_FLAG_AUTOREMOVE_CONSUMER and * DL_FLAG_AUTOREMOVE_SUPPLIER are not set in @flags (that is, a persistent * managed device link is being added), the DL_FLAG_AUTOPROBE_CONSUMER flag can * be used to request the driver core to automatically probe for a consumer * driver after successfully binding a driver to the supplier device. * * The combination of DL_FLAG_STATELESS and one of DL_FLAG_AUTOREMOVE_CONSUMER, * DL_FLAG_AUTOREMOVE_SUPPLIER, or DL_FLAG_AUTOPROBE_CONSUMER set in @flags at * the same time is invalid and will cause NULL to be returned upfront. * However, if a device link between the given @consumer and @supplier pair * exists already when this function is called for them, the existing link will * be returned regardless of its current type and status (the link's flags may * be modified then). The caller of this function is then expected to treat * the link as though it has just been created, so (in particular) if * DL_FLAG_STATELESS was passed in @flags, the link needs to be released * explicitly when not needed any more (as stated above). * * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending * on it to the ends of these lists (that does not happen to devices that have * not been registered when this function is called). * * The supplier device is required to be registered when this function is called * and NULL will be returned if that is not the case. The consumer device need * not be registered, however. */ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags) { struct device_link *link; if (!consumer || !supplier || consumer == supplier || flags & ~DL_ADD_VALID_FLAGS || (flags & DL_FLAG_STATELESS && flags & DL_MANAGED_LINK_FLAGS) || (flags & DL_FLAG_AUTOPROBE_CONSUMER && flags & (DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER))) return NULL; if (flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) { if (pm_runtime_get_sync(supplier) < 0) { pm_runtime_put_noidle(supplier); return NULL; } } if (!(flags & DL_FLAG_STATELESS)) flags |= DL_FLAG_MANAGED; if (flags & DL_FLAG_SYNC_STATE_ONLY && !device_link_flag_is_sync_state_only(flags)) return NULL; device_links_write_lock(); device_pm_lock(); /* * If the supplier has not been fully registered yet or there is a * reverse (non-SYNC_STATE_ONLY) dependency between the consumer and * the supplier already in the graph, return NULL. If the link is a * SYNC_STATE_ONLY link, we don't check for reverse dependencies * because it only affects sync_state() callbacks. */ if (!device_pm_initialized(supplier) || (!(flags & DL_FLAG_SYNC_STATE_ONLY) && device_is_dependent(consumer, supplier))) { link = NULL; goto out; } /* * SYNC_STATE_ONLY links are useless once a consumer device has probed. * So, only create it if the consumer hasn't probed yet. */ if (flags & DL_FLAG_SYNC_STATE_ONLY && consumer->links.status != DL_DEV_NO_DRIVER && consumer->links.status != DL_DEV_PROBING) { link = NULL; goto out; } /* * DL_FLAG_AUTOREMOVE_SUPPLIER indicates that the link will be needed * longer than for DL_FLAG_AUTOREMOVE_CONSUMER and setting them both * together doesn't make sense, so prefer DL_FLAG_AUTOREMOVE_SUPPLIER. */ if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER; list_for_each_entry(link, &supplier->links.consumers, s_node) { if (link->consumer != consumer) continue; if (link->flags & DL_FLAG_INFERRED && !(flags & DL_FLAG_INFERRED)) link->flags &= ~DL_FLAG_INFERRED; if (flags & DL_FLAG_PM_RUNTIME) { if (!(link->flags & DL_FLAG_PM_RUNTIME)) { pm_runtime_new_link(consumer); link->flags |= DL_FLAG_PM_RUNTIME; } if (flags & DL_FLAG_RPM_ACTIVE) refcount_inc(&link->rpm_active); } if (flags & DL_FLAG_STATELESS) { kref_get(&link->kref); if (link->flags & DL_FLAG_SYNC_STATE_ONLY && !(link->flags & DL_FLAG_STATELESS)) { link->flags |= DL_FLAG_STATELESS; goto reorder; } else { link->flags |= DL_FLAG_STATELESS; goto out; } } /* * If the life time of the link following from the new flags is * longer than indicated by the flags of the existing link, * update the existing link to stay around longer. */ if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) { if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) { link->flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER; link->flags |= DL_FLAG_AUTOREMOVE_SUPPLIER; } } else if (!(flags & DL_FLAG_AUTOREMOVE_CONSUMER)) { link->flags &= ~(DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER); } if (!(link->flags & DL_FLAG_MANAGED)) { kref_get(&link->kref); link->flags |= DL_FLAG_MANAGED; device_link_init_status(link, consumer, supplier); } if (link->flags & DL_FLAG_SYNC_STATE_ONLY && !(flags & DL_FLAG_SYNC_STATE_ONLY)) { link->flags &= ~DL_FLAG_SYNC_STATE_ONLY; goto reorder; } goto out; } link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) goto out; refcount_set(&link->rpm_active, 1); get_device(supplier); link->supplier = supplier; INIT_LIST_HEAD(&link->s_node); get_device(consumer); link->consumer = consumer; INIT_LIST_HEAD(&link->c_node); link->flags = flags; kref_init(&link->kref); link->link_dev.class = &devlink_class; device_set_pm_not_required(&link->link_dev); dev_set_name(&link->link_dev, "%s:%s--%s:%s", dev_bus_name(supplier), dev_name(supplier), dev_bus_name(consumer), dev_name(consumer)); if (device_register(&link->link_dev)) { put_device(&link->link_dev); link = NULL; goto out; } if (flags & DL_FLAG_PM_RUNTIME) { if (flags & DL_FLAG_RPM_ACTIVE) refcount_inc(&link->rpm_active); pm_runtime_new_link(consumer); } /* Determine the initial link state. */ if (flags & DL_FLAG_STATELESS) link->status = DL_STATE_NONE; else device_link_init_status(link, consumer, supplier); /* * Some callers expect the link creation during consumer driver probe to * resume the supplier even without DL_FLAG_RPM_ACTIVE. */ if (link->status == DL_STATE_CONSUMER_PROBE && flags & DL_FLAG_PM_RUNTIME) pm_runtime_resume(supplier); list_add_tail_rcu(&link->s_node, &supplier->links.consumers); list_add_tail_rcu(&link->c_node, &consumer->links.suppliers); if (flags & DL_FLAG_SYNC_STATE_ONLY) { dev_dbg(consumer, "Linked as a sync state only consumer to %s\n", dev_name(supplier)); goto out; } reorder: /* * Move the consumer and all of the devices depending on it to the end * of dpm_list and the devices_kset list. * * It is necessary to hold dpm_list locked throughout all that or else * we may end up suspending with a wrong ordering of it. */ device_reorder_to_tail(consumer, NULL); dev_dbg(consumer, "Linked as a consumer to %s\n", dev_name(supplier)); out: device_pm_unlock(); device_links_write_unlock(); if ((flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) && !link) pm_runtime_put(supplier); return link; } EXPORT_SYMBOL_GPL(device_link_add); static void __device_link_del(struct kref *kref) { struct device_link *link = container_of(kref, struct device_link, kref); dev_dbg(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); pm_runtime_drop_link(link); device_link_remove_from_lists(link); device_unregister(&link->link_dev); } static void device_link_put_kref(struct device_link *link) { if (link->flags & DL_FLAG_STATELESS) kref_put(&link->kref, __device_link_del); else if (!device_is_registered(link->consumer)) __device_link_del(&link->kref); else WARN(1, "Unable to drop a managed device link reference\n"); } /** * device_link_del - Delete a stateless link between two devices. * @link: Device link to delete. * * The caller must ensure proper synchronization of this function with runtime * PM. If the link was added multiple times, it needs to be deleted as often. * Care is required for hotplugged devices: Their links are purged on removal * and calling device_link_del() is then no longer allowed. */ void device_link_del(struct device_link *link) { device_links_write_lock(); device_link_put_kref(link); device_links_write_unlock(); } EXPORT_SYMBOL_GPL(device_link_del); /** * device_link_remove - Delete a stateless link between two devices. * @consumer: Consumer end of the link. * @supplier: Supplier end of the link. * * The caller must ensure proper synchronization of this function with runtime * PM. */ void device_link_remove(void *consumer, struct device *supplier) { struct device_link *link; if (WARN_ON(consumer == supplier)) return; device_links_write_lock(); list_for_each_entry(link, &supplier->links.consumers, s_node) { if (link->consumer == consumer) { device_link_put_kref(link); break; } } device_links_write_unlock(); } EXPORT_SYMBOL_GPL(device_link_remove); static void device_links_missing_supplier(struct device *dev) { struct device_link *link; list_for_each_entry(link, &dev->links.suppliers, c_node) { if (link->status != DL_STATE_CONSUMER_PROBE) continue; if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) { WRITE_ONCE(link->status, DL_STATE_AVAILABLE); } else { WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); WRITE_ONCE(link->status, DL_STATE_DORMANT); } } } static bool dev_is_best_effort(struct device *dev) { return (fw_devlink_best_effort && dev->can_match) || (dev->fwnode && (dev->fwnode->flags & FWNODE_FLAG_BEST_EFFORT)); } static struct fwnode_handle *fwnode_links_check_suppliers( struct fwnode_handle *fwnode) { struct fwnode_link *link; if (!fwnode || fw_devlink_is_permissive()) return NULL; list_for_each_entry(link, &fwnode->suppliers, c_hook) if (!(link->flags & (FWLINK_FLAG_CYCLE | FWLINK_FLAG_IGNORE))) return link->supplier; return NULL; } /** * device_links_check_suppliers - Check presence of supplier drivers. * @dev: Consumer device. * * Check links from this device to any suppliers. Walk the list of the device's * links to suppliers and see if all of them are available. If not, simply * return -EPROBE_DEFER. * * We need to guarantee that the supplier will not go away after the check has * been positive here. It only can go away in __device_release_driver() and * that function checks the device's links to consumers. This means we need to * mark the link as "consumer probe in progress" to make the supplier removal * wait for us to complete (or bad things may happen). * * Links without the DL_FLAG_MANAGED flag set are ignored. */ int device_links_check_suppliers(struct device *dev) { struct device_link *link; int ret = 0, fwnode_ret = 0; struct fwnode_handle *sup_fw; /* * Device waiting for supplier to become available is not allowed to * probe. */ scoped_guard(mutex, &fwnode_link_lock) { sup_fw = fwnode_links_check_suppliers(dev->fwnode); if (sup_fw) { if (dev_is_best_effort(dev)) fwnode_ret = -EAGAIN; else return dev_err_probe(dev, -EPROBE_DEFER, "wait for supplier %pfwf\n", sup_fw); } } device_links_write_lock(); list_for_each_entry(link, &dev->links.suppliers, c_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status != DL_STATE_AVAILABLE && !(link->flags & DL_FLAG_SYNC_STATE_ONLY)) { if (dev_is_best_effort(dev) && link->flags & DL_FLAG_INFERRED && !link->supplier->can_match) { ret = -EAGAIN; continue; } device_links_missing_supplier(dev); ret = dev_err_probe(dev, -EPROBE_DEFER, "supplier %s not ready\n", dev_name(link->supplier)); break; } WRITE_ONCE(link->status, DL_STATE_CONSUMER_PROBE); } dev->links.status = DL_DEV_PROBING; device_links_write_unlock(); return ret ? ret : fwnode_ret; } /** * __device_links_queue_sync_state - Queue a device for sync_state() callback * @dev: Device to call sync_state() on * @list: List head to queue the @dev on * * Queues a device for a sync_state() callback when the device links write lock * isn't held. This allows the sync_state() execution flow to use device links * APIs. The caller must ensure this function is called with * device_links_write_lock() held. * * This function does a get_device() to make sure the device is not freed while * on this list. * * So the caller must also ensure that device_links_flush_sync_list() is called * as soon as the caller releases device_links_write_lock(). This is necessary * to make sure the sync_state() is called in a timely fashion and the * put_device() is called on this device. */ static void __device_links_queue_sync_state(struct device *dev, struct list_head *list) { struct device_link *link; if (!dev_has_sync_state(dev)) return; if (dev->state_synced) return; list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status != DL_STATE_ACTIVE) return; } /* * Set the flag here to avoid adding the same device to a list more * than once. This can happen if new consumers get added to the device * and probed before the list is flushed. */ dev->state_synced = true; if (WARN_ON(!list_empty(&dev->links.defer_sync))) return; get_device(dev); list_add_tail(&dev->links.defer_sync, list); } /** * device_links_flush_sync_list - Call sync_state() on a list of devices * @list: List of devices to call sync_state() on * @dont_lock_dev: Device for which lock is already held by the caller * * Calls sync_state() on all the devices that have been queued for it. This * function is used in conjunction with __device_links_queue_sync_state(). The * @dont_lock_dev parameter is useful when this function is called from a * context where a device lock is already held. */ static void device_links_flush_sync_list(struct list_head *list, struct device *dont_lock_dev) { struct device *dev, *tmp; list_for_each_entry_safe(dev, tmp, list, links.defer_sync) { list_del_init(&dev->links.defer_sync); if (dev != dont_lock_dev) device_lock(dev); dev_sync_state(dev); if (dev != dont_lock_dev) device_unlock(dev); put_device(dev); } } void device_links_supplier_sync_state_pause(void) { device_links_write_lock(); defer_sync_state_count++; device_links_write_unlock(); } void device_links_supplier_sync_state_resume(void) { struct device *dev, *tmp; LIST_HEAD(sync_list); device_links_write_lock(); if (!defer_sync_state_count) { WARN(true, "Unmatched sync_state pause/resume!"); goto out; } defer_sync_state_count--; if (defer_sync_state_count) goto out; list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_sync) { /* * Delete from deferred_sync list before queuing it to * sync_list because defer_sync is used for both lists. */ list_del_init(&dev->links.defer_sync); __device_links_queue_sync_state(dev, &sync_list); } out: device_links_write_unlock(); device_links_flush_sync_list(&sync_list, NULL); } static int sync_state_resume_initcall(void) { device_links_supplier_sync_state_resume(); return 0; } late_initcall(sync_state_resume_initcall); static void __device_links_supplier_defer_sync(struct device *sup) { if (list_empty(&sup->links.defer_sync) && dev_has_sync_state(sup)) list_add_tail(&sup->links.defer_sync, &deferred_sync); } static void device_link_drop_managed(struct device_link *link) { link->flags &= ~DL_FLAG_MANAGED; WRITE_ONCE(link->status, DL_STATE_NONE); kref_put(&link->kref, __device_link_del); } static ssize_t waiting_for_supplier_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); scoped_guard(mutex, &fwnode_link_lock) val = !!fwnode_links_check_suppliers(dev->fwnode); device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static DEVICE_ATTR_RO(waiting_for_supplier); /** * device_links_force_bind - Prepares device to be force bound * @dev: Consumer device. * * device_bind_driver() force binds a device to a driver without calling any * driver probe functions. So the consumer really isn't going to wait for any * supplier before it's bound to the driver. We still want the device link * states to be sensible when this happens. * * In preparation for device_bind_driver(), this function goes through each * supplier device links and checks if the supplier is bound. If it is, then * the device link status is set to CONSUMER_PROBE. Otherwise, the device link * is dropped. Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_force_bind(struct device *dev) { struct device_link *link, *ln; device_links_write_lock(); list_for_each_entry_safe(link, ln, &dev->links.suppliers, c_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status != DL_STATE_AVAILABLE) { device_link_drop_managed(link); continue; } WRITE_ONCE(link->status, DL_STATE_CONSUMER_PROBE); } dev->links.status = DL_DEV_PROBING; device_links_write_unlock(); } /** * device_links_driver_bound - Update device links after probing its driver. * @dev: Device to update the links for. * * The probe has been successful, so update links from this device to any * consumers by changing their status to "available". * * Also change the status of @dev's links to suppliers to "active". * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_driver_bound(struct device *dev) { struct device_link *link, *ln; LIST_HEAD(sync_list); /* * If a device binds successfully, it's expected to have created all * the device links it needs to or make new device links as it needs * them. So, fw_devlink no longer needs to create device links to any * of the device's suppliers. * * Also, if a child firmware node of this bound device is not added as a * device by now, assume it is never going to be added. Make this bound * device the fallback supplier to the dangling consumers of the child * firmware node because this bound device is probably implementing the * child firmware node functionality and we don't want the dangling * consumers to defer probe indefinitely waiting for a device for the * child firmware node. */ if (dev->fwnode && dev->fwnode->dev == dev) { struct fwnode_handle *child; fwnode_links_purge_suppliers(dev->fwnode); guard(mutex)(&fwnode_link_lock); fwnode_for_each_available_child_node(dev->fwnode, child) __fw_devlink_pickup_dangling_consumers(child, dev->fwnode); __fw_devlink_link_to_consumers(dev); } device_remove_file(dev, &dev_attr_waiting_for_supplier); device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; /* * Links created during consumer probe may be in the "consumer * probe" state to start with if the supplier is still probing * when they are created and they may become "active" if the * consumer probe returns first. Skip them here. */ if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) continue; WARN_ON(link->status != DL_STATE_DORMANT); WRITE_ONCE(link->status, DL_STATE_AVAILABLE); if (link->flags & DL_FLAG_AUTOPROBE_CONSUMER) driver_deferred_probe_add(link->consumer); } if (defer_sync_state_count) __device_links_supplier_defer_sync(dev); else __device_links_queue_sync_state(dev, &sync_list); list_for_each_entry_safe(link, ln, &dev->links.suppliers, c_node) { struct device *supplier; if (!(link->flags & DL_FLAG_MANAGED)) continue; supplier = link->supplier; if (link->flags & DL_FLAG_SYNC_STATE_ONLY) { /* * When DL_FLAG_SYNC_STATE_ONLY is set, it means no * other DL_MANAGED_LINK_FLAGS have been set. So, it's * save to drop the managed link completely. */ device_link_drop_managed(link); } else if (dev_is_best_effort(dev) && link->flags & DL_FLAG_INFERRED && link->status != DL_STATE_CONSUMER_PROBE && !link->supplier->can_match) { /* * When dev_is_best_effort() is true, we ignore device * links to suppliers that don't have a driver. If the * consumer device still managed to probe, there's no * point in maintaining a device link in a weird state * (consumer probed before supplier). So delete it. */ device_link_drop_managed(link); } else { WARN_ON(link->status != DL_STATE_CONSUMER_PROBE); WRITE_ONCE(link->status, DL_STATE_ACTIVE); } /* * This needs to be done even for the deleted * DL_FLAG_SYNC_STATE_ONLY device link in case it was the last * device link that was preventing the supplier from getting a * sync_state() call. */ if (defer_sync_state_count) __device_links_supplier_defer_sync(supplier); else __device_links_queue_sync_state(supplier, &sync_list); } dev->links.status = DL_DEV_DRIVER_BOUND; device_links_write_unlock(); device_links_flush_sync_list(&sync_list, dev); } /** * __device_links_no_driver - Update links of a device without a driver. * @dev: Device without a drvier. * * Delete all non-persistent links from this device to any suppliers. * * Persistent links stay around, but their status is changed to "available", * unless they already are in the "supplier unbind in progress" state in which * case they need not be updated. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ static void __device_links_no_driver(struct device *dev) { struct device_link *link, *ln; list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) { device_link_drop_managed(link); continue; } if (link->status != DL_STATE_CONSUMER_PROBE && link->status != DL_STATE_ACTIVE) continue; if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) { WRITE_ONCE(link->status, DL_STATE_AVAILABLE); } else { WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); WRITE_ONCE(link->status, DL_STATE_DORMANT); } } dev->links.status = DL_DEV_NO_DRIVER; } /** * device_links_no_driver - Update links after failing driver probe. * @dev: Device whose driver has just failed to probe. * * Clean up leftover links to consumers for @dev and invoke * %__device_links_no_driver() to update links to suppliers for it as * appropriate. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_no_driver(struct device *dev) { struct device_link *link; device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; /* * The probe has failed, so if the status of the link is * "consumer probe" or "active", it must have been added by * a probing consumer while this device was still probing. * Change its state to "dormant", as it represents a valid * relationship, but it is not functionally meaningful. */ if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) WRITE_ONCE(link->status, DL_STATE_DORMANT); } __device_links_no_driver(dev); device_links_write_unlock(); } /** * device_links_driver_cleanup - Update links after driver removal. * @dev: Device whose driver has just gone away. * * Update links to consumers for @dev by changing their status to "dormant" and * invoke %__device_links_no_driver() to update links to suppliers for it as * appropriate. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_driver_cleanup(struct device *dev) { struct device_link *link, *ln; device_links_write_lock(); list_for_each_entry_safe(link, ln, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER); WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND); /* * autoremove the links between this @dev and its consumer * devices that are not active, i.e. where the link state * has moved to DL_STATE_SUPPLIER_UNBIND. */ if (link->status == DL_STATE_SUPPLIER_UNBIND && link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) device_link_drop_managed(link); WRITE_ONCE(link->status, DL_STATE_DORMANT); } list_del_init(&dev->links.defer_sync); __device_links_no_driver(dev); device_links_write_unlock(); } /** * device_links_busy - Check if there are any busy links to consumers. * @dev: Device to check. * * Check each consumer of the device and return 'true' if its link's status * is one of "consumer probe" or "active" (meaning that the given consumer is * probing right now or its driver is present). Otherwise, change the link * state to "supplier unbind" to prevent the consumer from being probed * successfully going forward. * * Return 'false' if there are no probing or active consumers. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ bool device_links_busy(struct device *dev) { struct device_link *link; bool ret = false; device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) { ret = true; break; } WRITE_ONCE(link->status, DL_STATE_SUPPLIER_UNBIND); } dev->links.status = DL_DEV_UNBINDING; device_links_write_unlock(); return ret; } /** * device_links_unbind_consumers - Force unbind consumers of the given device. * @dev: Device to unbind the consumers of. * * Walk the list of links to consumers for @dev and if any of them is in the * "consumer probe" state, wait for all device probes in progress to complete * and start over. * * If that's not the case, change the status of the link to "supplier unbind" * and check if the link was in the "active" state. If so, force the consumer * driver to unbind and start over (the consumer will not re-probe as we have * changed the state of the link already). * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_unbind_consumers(struct device *dev) { struct device_link *link; start: device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { enum device_link_state status; if (!(link->flags & DL_FLAG_MANAGED) || link->flags & DL_FLAG_SYNC_STATE_ONLY) continue; status = link->status; if (status == DL_STATE_CONSUMER_PROBE) { device_links_write_unlock(); wait_for_device_probe(); goto start; } WRITE_ONCE(link->status, DL_STATE_SUPPLIER_UNBIND); if (status == DL_STATE_ACTIVE) { struct device *consumer = link->consumer; get_device(consumer); device_links_write_unlock(); device_release_driver_internal(consumer, NULL, consumer->parent); put_device(consumer); goto start; } } device_links_write_unlock(); } /** * device_links_purge - Delete existing links to other devices. * @dev: Target device. */ static void device_links_purge(struct device *dev) { struct device_link *link, *ln; if (dev->class == &devlink_class) return; /* * Delete all of the remaining links from this device to any other * devices (either consumers or suppliers). */ device_links_write_lock(); list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) { WARN_ON(link->status == DL_STATE_ACTIVE); __device_link_del(&link->kref); } list_for_each_entry_safe_reverse(link, ln, &dev->links.consumers, s_node) { WARN_ON(link->status != DL_STATE_DORMANT && link->status != DL_STATE_NONE); __device_link_del(&link->kref); } device_links_write_unlock(); } #define FW_DEVLINK_FLAGS_PERMISSIVE (DL_FLAG_INFERRED | \ DL_FLAG_SYNC_STATE_ONLY) #define FW_DEVLINK_FLAGS_ON (DL_FLAG_INFERRED | \ DL_FLAG_AUTOPROBE_CONSUMER) #define FW_DEVLINK_FLAGS_RPM (FW_DEVLINK_FLAGS_ON | \ DL_FLAG_PM_RUNTIME) static u32 fw_devlink_flags = FW_DEVLINK_FLAGS_RPM; static int __init fw_devlink_setup(char *arg) { if (!arg) return -EINVAL; if (strcmp(arg, "off") == 0) { fw_devlink_flags = 0; } else if (strcmp(arg, "permissive") == 0) { fw_devlink_flags = FW_DEVLINK_FLAGS_PERMISSIVE; } else if (strcmp(arg, "on") == 0) { fw_devlink_flags = FW_DEVLINK_FLAGS_ON; } else if (strcmp(arg, "rpm") == 0) { fw_devlink_flags = FW_DEVLINK_FLAGS_RPM; } return 0; } early_param("fw_devlink", fw_devlink_setup); static bool fw_devlink_strict; static int __init fw_devlink_strict_setup(char *arg) { return kstrtobool(arg, &fw_devlink_strict); } early_param("fw_devlink.strict", fw_devlink_strict_setup); #define FW_DEVLINK_SYNC_STATE_STRICT 0 #define FW_DEVLINK_SYNC_STATE_TIMEOUT 1 #ifndef CONFIG_FW_DEVLINK_SYNC_STATE_TIMEOUT static int fw_devlink_sync_state; #else static int fw_devlink_sync_state = FW_DEVLINK_SYNC_STATE_TIMEOUT; #endif static int __init fw_devlink_sync_state_setup(char *arg) { if (!arg) return -EINVAL; if (strcmp(arg, "strict") == 0) { fw_devlink_sync_state = FW_DEVLINK_SYNC_STATE_STRICT; return 0; } else if (strcmp(arg, "timeout") == 0) { fw_devlink_sync_state = FW_DEVLINK_SYNC_STATE_TIMEOUT; return 0; } return -EINVAL; } early_param("fw_devlink.sync_state", fw_devlink_sync_state_setup); static inline u32 fw_devlink_get_flags(u8 fwlink_flags) { if (fwlink_flags & FWLINK_FLAG_CYCLE) return FW_DEVLINK_FLAGS_PERMISSIVE | DL_FLAG_CYCLE; return fw_devlink_flags; } static bool fw_devlink_is_permissive(void) { return fw_devlink_flags == FW_DEVLINK_FLAGS_PERMISSIVE; } bool fw_devlink_is_strict(void) { return fw_devlink_strict && !fw_devlink_is_permissive(); } static void fw_devlink_parse_fwnode(struct fwnode_handle *fwnode) { if (fwnode->flags & FWNODE_FLAG_LINKS_ADDED) return; fwnode_call_int_op(fwnode, add_links); fwnode->flags |= FWNODE_FLAG_LINKS_ADDED; } static void fw_devlink_parse_fwtree(struct fwnode_handle *fwnode) { struct fwnode_handle *child = NULL; fw_devlink_parse_fwnode(fwnode); while ((child = fwnode_get_next_available_child_node(fwnode, child))) fw_devlink_parse_fwtree(child); } static void fw_devlink_relax_link(struct device_link *link) { if (!(link->flags & DL_FLAG_INFERRED)) return; if (device_link_flag_is_sync_state_only(link->flags)) return; pm_runtime_drop_link(link); link->flags = DL_FLAG_MANAGED | FW_DEVLINK_FLAGS_PERMISSIVE; dev_dbg(link->consumer, "Relaxing link with %s\n", dev_name(link->supplier)); } static int fw_devlink_no_driver(struct device *dev, void *data) { struct device_link *link = to_devlink(dev); if (!link->supplier->can_match) fw_devlink_relax_link(link); return 0; } void fw_devlink_drivers_done(void) { fw_devlink_drv_reg_done = true; device_links_write_lock(); class_for_each_device(&devlink_class, NULL, NULL, fw_devlink_no_driver); device_links_write_unlock(); } static int fw_devlink_dev_sync_state(struct device *dev, void *data) { struct device_link *link = to_devlink(dev); struct device *sup = link->supplier; if (!(link->flags & DL_FLAG_MANAGED) || link->status == DL_STATE_ACTIVE || sup->state_synced || !dev_has_sync_state(sup)) return 0; if (fw_devlink_sync_state == FW_DEVLINK_SYNC_STATE_STRICT) { dev_warn(sup, "sync_state() pending due to %s\n", dev_name(link->consumer)); return 0; } if (!list_empty(&sup->links.defer_sync)) return 0; dev_warn(sup, "Timed out. Forcing sync_state()\n"); sup->state_synced = true; get_device(sup); list_add_tail(&sup->links.defer_sync, data); return 0; } void fw_devlink_probing_done(void) { LIST_HEAD(sync_list); device_links_write_lock(); class_for_each_device(&devlink_class, NULL, &sync_list, fw_devlink_dev_sync_state); device_links_write_unlock(); device_links_flush_sync_list(&sync_list, NULL); } /** * wait_for_init_devices_probe - Try to probe any device needed for init * * Some devices might need to be probed and bound successfully before the kernel * boot sequence can finish and move on to init/userspace. For example, a * network interface might need to be bound to be able to mount a NFS rootfs. * * With fw_devlink=on by default, some of these devices might be blocked from * probing because they are waiting on a optional supplier that doesn't have a * driver. While fw_devlink will eventually identify such devices and unblock * the probing automatically, it might be too late by the time it unblocks the * probing of devices. For example, the IP4 autoconfig might timeout before * fw_devlink unblocks probing of the network interface. * * This function is available to temporarily try and probe all devices that have * a driver even if some of their suppliers haven't been added or don't have * drivers. * * The drivers can then decide which of the suppliers are optional vs mandatory * and probe the device if possible. By the time this function returns, all such * "best effort" probes are guaranteed to be completed. If a device successfully * probes in this mode, we delete all fw_devlink discovered dependencies of that * device where the supplier hasn't yet probed successfully because they have to * be optional dependencies. * * Any devices that didn't successfully probe go back to being treated as if * this function was never called. * * This also means that some devices that aren't needed for init and could have * waited for their optional supplier to probe (when the supplier's module is * loaded later on) would end up probing prematurely with limited functionality. * So call this function only when boot would fail without it. */ void __init wait_for_init_devices_probe(void) { if (!fw_devlink_flags || fw_devlink_is_permissive()) return; /* * Wait for all ongoing probes to finish so that the "best effort" is * only applied to devices that can't probe otherwise. */ wait_for_device_probe(); pr_info("Trying to probe devices needed for running init ...\n"); fw_devlink_best_effort = true; driver_deferred_probe_trigger(); /* * Wait for all "best effort" probes to finish before going back to * normal enforcement. */ wait_for_device_probe(); fw_devlink_best_effort = false; } static void fw_devlink_unblock_consumers(struct device *dev) { struct device_link *link; if (!fw_devlink_flags || fw_devlink_is_permissive()) return; device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) fw_devlink_relax_link(link); device_links_write_unlock(); } #define get_dev_from_fwnode(fwnode) get_device((fwnode)->dev) static bool fwnode_init_without_drv(struct fwnode_handle *fwnode) { struct device *dev; bool ret; if (!(fwnode->flags & FWNODE_FLAG_INITIALIZED)) return false; dev = get_dev_from_fwnode(fwnode); ret = !dev || dev->links.status == DL_DEV_NO_DRIVER; put_device(dev); return ret; } static bool fwnode_ancestor_init_without_drv(struct fwnode_handle *fwnode) { struct fwnode_handle *parent; fwnode_for_each_parent_node(fwnode, parent) { if (fwnode_init_without_drv(parent)) { fwnode_handle_put(parent); return true; } } return false; } /** * fwnode_is_ancestor_of - Test if @ancestor is ancestor of @child * @ancestor: Firmware which is tested for being an ancestor * @child: Firmware which is tested for being the child * * A node is considered an ancestor of itself too. * * Return: true if @ancestor is an ancestor of @child. Otherwise, returns false. */ static bool fwnode_is_ancestor_of(const struct fwnode_handle *ancestor, const struct fwnode_handle *child) { struct fwnode_handle *parent; if (IS_ERR_OR_NULL(ancestor)) return false; if (child == ancestor) return true; fwnode_for_each_parent_node(child, parent) { if (parent == ancestor) { fwnode_handle_put(parent); return true; } } return false; } /** * fwnode_get_next_parent_dev - Find device of closest ancestor fwnode * @fwnode: firmware node * * Given a firmware node (@fwnode), this function finds its closest ancestor * firmware node that has a corresponding struct device and returns that struct * device. * * The caller is responsible for calling put_device() on the returned device * pointer. * * Return: a pointer to the device of the @fwnode's closest ancestor. */ static struct device *fwnode_get_next_parent_dev(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; struct device *dev; fwnode_for_each_parent_node(fwnode, parent) { dev = get_dev_from_fwnode(parent); if (dev) { fwnode_handle_put(parent); return dev; } } return NULL; } /** * __fw_devlink_relax_cycles - Relax and mark dependency cycles. * @con: Potential consumer device. * @sup_handle: Potential supplier's fwnode. * * Needs to be called with fwnode_lock and device link lock held. * * Check if @sup_handle or any of its ancestors or suppliers direct/indirectly * depend on @con. This function can detect multiple cyles between @sup_handle * and @con. When such dependency cycles are found, convert all device links * created solely by fw_devlink into SYNC_STATE_ONLY device links. Also, mark * all fwnode links in the cycle with FWLINK_FLAG_CYCLE so that when they are * converted into a device link in the future, they are created as * SYNC_STATE_ONLY device links. This is the equivalent of doing * fw_devlink=permissive just between the devices in the cycle. We need to do * this because, at this point, fw_devlink can't tell which of these * dependencies is not a real dependency. * * Return true if one or more cycles were found. Otherwise, return false. */ static bool __fw_devlink_relax_cycles(struct device *con, struct fwnode_handle *sup_handle) { struct device *sup_dev = NULL, *par_dev = NULL; struct fwnode_link *link; struct device_link *dev_link; bool ret = false; if (!sup_handle) return false; /* * We aren't trying to find all cycles. Just a cycle between con and * sup_handle. */ if (sup_handle->flags & FWNODE_FLAG_VISITED) return false; sup_handle->flags |= FWNODE_FLAG_VISITED; sup_dev = get_dev_from_fwnode(sup_handle); /* Termination condition. */ if (sup_dev == con) { pr_debug("----- cycle: start -----\n"); ret = true; goto out; } /* * If sup_dev is bound to a driver and @con hasn't started binding to a * driver, sup_dev can't be a consumer of @con. So, no need to check * further. */ if (sup_dev && sup_dev->links.status == DL_DEV_DRIVER_BOUND && con->links.status == DL_DEV_NO_DRIVER) { ret = false; goto out; } list_for_each_entry(link, &sup_handle->suppliers, c_hook) { if (link->flags & FWLINK_FLAG_IGNORE) continue; if (__fw_devlink_relax_cycles(con, link->supplier)) { __fwnode_link_cycle(link); ret = true; } } /* * Give priority to device parent over fwnode parent to account for any * quirks in how fwnodes are converted to devices. */ if (sup_dev) par_dev = get_device(sup_dev->parent); else par_dev = fwnode_get_next_parent_dev(sup_handle); if (par_dev && __fw_devlink_relax_cycles(con, par_dev->fwnode)) { pr_debug("%pfwf: cycle: child of %pfwf\n", sup_handle, par_dev->fwnode); ret = true; } if (!sup_dev) goto out; list_for_each_entry(dev_link, &sup_dev->links.suppliers, c_node) { /* * Ignore a SYNC_STATE_ONLY flag only if it wasn't marked as * such due to a cycle. */ if (device_link_flag_is_sync_state_only(dev_link->flags) && !(dev_link->flags & DL_FLAG_CYCLE)) continue; if (__fw_devlink_relax_cycles(con, dev_link->supplier->fwnode)) { pr_debug("%pfwf: cycle: depends on %pfwf\n", sup_handle, dev_link->supplier->fwnode); fw_devlink_relax_link(dev_link); dev_link->flags |= DL_FLAG_CYCLE; ret = true; } } out: sup_handle->flags &= ~FWNODE_FLAG_VISITED; put_device(sup_dev); put_device(par_dev); return ret; } /** * fw_devlink_create_devlink - Create a device link from a consumer to fwnode * @con: consumer device for the device link * @sup_handle: fwnode handle of supplier * @link: fwnode link that's being converted to a device link * * This function will try to create a device link between the consumer device * @con and the supplier device represented by @sup_handle. * * The supplier has to be provided as a fwnode because incorrect cycles in * fwnode links can sometimes cause the supplier device to never be created. * This function detects such cases and returns an error if it cannot create a * device link from the consumer to a missing supplier. * * Returns, * 0 on successfully creating a device link * -EINVAL if the device link cannot be created as expected * -EAGAIN if the device link cannot be created right now, but it may be * possible to do that in the future */ static int fw_devlink_create_devlink(struct device *con, struct fwnode_handle *sup_handle, struct fwnode_link *link) { struct device *sup_dev; int ret = 0; u32 flags; if (link->flags & FWLINK_FLAG_IGNORE) return 0; if (con->fwnode == link->consumer) flags = fw_devlink_get_flags(link->flags); else flags = FW_DEVLINK_FLAGS_PERMISSIVE; /* * In some cases, a device P might also be a supplier to its child node * C. However, this would defer the probe of C until the probe of P * completes successfully. This is perfectly fine in the device driver * model. device_add() doesn't guarantee probe completion of the device * by the time it returns. * * However, there are a few drivers that assume C will finish probing * as soon as it's added and before P finishes probing. So, we provide * a flag to let fw_devlink know not to delay the probe of C until the * probe of P completes successfully. * * When such a flag is set, we can't create device links where P is the * supplier of C as that would delay the probe of C. */ if (sup_handle->flags & FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD && fwnode_is_ancestor_of(sup_handle, con->fwnode)) return -EINVAL; /* * SYNC_STATE_ONLY device links don't block probing and supports cycles. * So, one might expect that cycle detection isn't necessary for them. * However, if the device link was marked as SYNC_STATE_ONLY because * it's part of a cycle, then we still need to do cycle detection. This * is because the consumer and supplier might be part of multiple cycles * and we need to detect all those cycles. */ if (!device_link_flag_is_sync_state_only(flags) || flags & DL_FLAG_CYCLE) { device_links_write_lock(); if (__fw_devlink_relax_cycles(con, sup_handle)) { __fwnode_link_cycle(link); flags = fw_devlink_get_flags(link->flags); pr_debug("----- cycle: end -----\n"); dev_info(con, "Fixed dependency cycle(s) with %pfwf\n", sup_handle); } device_links_write_unlock(); } if (sup_handle->flags & FWNODE_FLAG_NOT_DEVICE) sup_dev = fwnode_get_next_parent_dev(sup_handle); else sup_dev = get_dev_from_fwnode(sup_handle); if (sup_dev) { /* * If it's one of those drivers that don't actually bind to * their device using driver core, then don't wait on this * supplier device indefinitely. */ if (sup_dev->links.status == DL_DEV_NO_DRIVER && sup_handle->flags & FWNODE_FLAG_INITIALIZED) { dev_dbg(con, "Not linking %pfwf - dev might never probe\n", sup_handle); ret = -EINVAL; goto out; } if (con != sup_dev && !device_link_add(con, sup_dev, flags)) { dev_err(con, "Failed to create device link (0x%x) with %s\n", flags, dev_name(sup_dev)); ret = -EINVAL; } goto out; } /* * Supplier or supplier's ancestor already initialized without a struct * device or being probed by a driver. */ if (fwnode_init_without_drv(sup_handle) || fwnode_ancestor_init_without_drv(sup_handle)) { dev_dbg(con, "Not linking %pfwf - might never become dev\n", sup_handle); return -EINVAL; } ret = -EAGAIN; out: put_device(sup_dev); return ret; } /** * __fw_devlink_link_to_consumers - Create device links to consumers of a device * @dev: Device that needs to be linked to its consumers * * This function looks at all the consumer fwnodes of @dev and creates device * links between the consumer device and @dev (supplier). * * If the consumer device has not been added yet, then this function creates a * SYNC_STATE_ONLY link between @dev (supplier) and the closest ancestor device * of the consumer fwnode. This is necessary to make sure @dev doesn't get a * sync_state() callback before the real consumer device gets to be added and * then probed. * * Once device links are created from the real consumer to @dev (supplier), the * fwnode links are deleted. */ static void __fw_devlink_link_to_consumers(struct device *dev) { struct fwnode_handle *fwnode = dev->fwnode; struct fwnode_link *link, *tmp; list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) { struct device *con_dev; bool own_link = true; int ret; con_dev = get_dev_from_fwnode(link->consumer); /* * If consumer device is not available yet, make a "proxy" * SYNC_STATE_ONLY link from the consumer's parent device to * the supplier device. This is necessary to make sure the * supplier doesn't get a sync_state() callback before the real * consumer can create a device link to the supplier. * * This proxy link step is needed to handle the case where the * consumer's parent device is added before the supplier. */ if (!con_dev) { con_dev = fwnode_get_next_parent_dev(link->consumer); /* * However, if the consumer's parent device is also the * parent of the supplier, don't create a * consumer-supplier link from the parent to its child * device. Such a dependency is impossible. */ if (con_dev && fwnode_is_ancestor_of(con_dev->fwnode, fwnode)) { put_device(con_dev); con_dev = NULL; } else { own_link = false; } } if (!con_dev) continue; ret = fw_devlink_create_devlink(con_dev, fwnode, link); put_device(con_dev); if (!own_link || ret == -EAGAIN) continue; __fwnode_link_del(link); } } /** * __fw_devlink_link_to_suppliers - Create device links to suppliers of a device * @dev: The consumer device that needs to be linked to its suppliers * @fwnode: Root of the fwnode tree that is used to create device links * * This function looks at all the supplier fwnodes of fwnode tree rooted at * @fwnode and creates device links between @dev (consumer) and all the * supplier devices of the entire fwnode tree at @fwnode. * * The function creates normal (non-SYNC_STATE_ONLY) device links between @dev * and the real suppliers of @dev. Once these device links are created, the * fwnode links are deleted. * * In addition, it also looks at all the suppliers of the entire fwnode tree * because some of the child devices of @dev that have not been added yet * (because @dev hasn't probed) might already have their suppliers added to * driver core. So, this function creates SYNC_STATE_ONLY device links between * @dev (consumer) and these suppliers to make sure they don't execute their * sync_state() callbacks before these child devices have a chance to create * their device links. The fwnode links that correspond to the child devices * aren't delete because they are needed later to create the device links * between the real consumer and supplier devices. */ static void __fw_devlink_link_to_suppliers(struct device *dev, struct fwnode_handle *fwnode) { bool own_link = (dev->fwnode == fwnode); struct fwnode_link *link, *tmp; struct fwnode_handle *child = NULL; list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) { int ret; struct fwnode_handle *sup = link->supplier; ret = fw_devlink_create_devlink(dev, sup, link); if (!own_link || ret == -EAGAIN) continue; __fwnode_link_del(link); } /* * Make "proxy" SYNC_STATE_ONLY device links to represent the needs of * all the descendants. This proxy link step is needed to handle the * case where the supplier is added before the consumer's parent device * (@dev). */ while ((child = fwnode_get_next_available_child_node(fwnode, child))) __fw_devlink_link_to_suppliers(dev, child); } static void fw_devlink_link_device(struct device *dev) { struct fwnode_handle *fwnode = dev->fwnode; if (!fw_devlink_flags) return; fw_devlink_parse_fwtree(fwnode); guard(mutex)(&fwnode_link_lock); __fw_devlink_link_to_consumers(dev); __fw_devlink_link_to_suppliers(dev, fwnode); } /* Device links support end. */ static struct kobject *dev_kobj; /* /sys/dev/char */ static struct kobject *sysfs_dev_char_kobj; /* /sys/dev/block */ static struct kobject *sysfs_dev_block_kobj; static DEFINE_MUTEX(device_hotplug_lock); void lock_device_hotplug(void) { mutex_lock(&device_hotplug_lock); } void unlock_device_hotplug(void) { mutex_unlock(&device_hotplug_lock); } int lock_device_hotplug_sysfs(void) { if (mutex_trylock(&device_hotplug_lock)) return 0; /* Avoid busy looping (5 ms of sleep should do). */ msleep(5); return restart_syscall(); } #ifdef CONFIG_BLOCK static inline int device_is_not_partition(struct device *dev) { return !(dev->type == &part_type); } #else static inline int device_is_not_partition(struct device *dev) { return 1; } #endif static void device_platform_notify(struct device *dev) { acpi_device_notify(dev); software_node_notify(dev); } static void device_platform_notify_remove(struct device *dev) { software_node_notify_remove(dev); acpi_device_notify_remove(dev); } /** * dev_driver_string - Return a device's driver name, if at all possible * @dev: struct device to get the name of * * Will return the device's driver's name if it is bound to a device. If * the device is not bound to a driver, it will return the name of the bus * it is attached to. If it is not attached to a bus either, an empty * string will be returned. */ const char *dev_driver_string(const struct device *dev) { struct device_driver *drv; /* dev->driver can change to NULL underneath us because of unbinding, * so be careful about accessing it. dev->bus and dev->class should * never change once they are set, so they don't need special care. */ drv = READ_ONCE(dev->driver); return drv ? drv->name : dev_bus_name(dev); } EXPORT_SYMBOL(dev_driver_string); #define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr) static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct device_attribute *dev_attr = to_dev_attr(attr); struct device *dev = kobj_to_dev(kobj); ssize_t ret = -EIO; if (dev_attr->show) ret = dev_attr->show(dev, dev_attr, buf); if (ret >= (ssize_t)PAGE_SIZE) { printk("dev_attr_show: %pS returned bad count\n", dev_attr->show); } return ret; } static ssize_t dev_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct device_attribute *dev_attr = to_dev_attr(attr); struct device *dev = kobj_to_dev(kobj); ssize_t ret = -EIO; if (dev_attr->store) ret = dev_attr->store(dev, dev_attr, buf, count); return ret; } static const struct sysfs_ops dev_sysfs_ops = { .show = dev_attr_show, .store = dev_attr_store, }; #define to_ext_attr(x) container_of(x, struct dev_ext_attribute, attr) ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct dev_ext_attribute *ea = to_ext_attr(attr); int ret; unsigned long new; ret = kstrtoul(buf, 0, &new); if (ret) return ret; *(unsigned long *)(ea->var) = new; /* Always return full write size even if we didn't consume all */ return size; } EXPORT_SYMBOL_GPL(device_store_ulong); ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%lx\n", *(unsigned long *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_ulong); ssize_t device_store_int(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct dev_ext_attribute *ea = to_ext_attr(attr); int ret; long new; ret = kstrtol(buf, 0, &new); if (ret) return ret; if (new > INT_MAX || new < INT_MIN) return -EINVAL; *(int *)(ea->var) = new; /* Always return full write size even if we didn't consume all */ return size; } EXPORT_SYMBOL_GPL(device_store_int); ssize_t device_show_int(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%d\n", *(int *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_int); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct dev_ext_attribute *ea = to_ext_attr(attr); if (kstrtobool(buf, ea->var) < 0) return -EINVAL; return size; } EXPORT_SYMBOL_GPL(device_store_bool); ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%d\n", *(bool *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_bool); ssize_t device_show_string(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%s\n", (char *)ea->var); } EXPORT_SYMBOL_GPL(device_show_string); /** * device_release - free device structure. * @kobj: device's kobject. * * This is called once the reference count for the object * reaches 0. We forward the call to the device's release * method, which should handle actually freeing the structure. */ static void device_release(struct kobject *kobj) { struct device *dev = kobj_to_dev(kobj); struct device_private *p = dev->p; /* * Some platform devices are driven without driver attached * and managed resources may have been acquired. Make sure * all resources are released. * * Drivers still can add resources into device after device * is deleted but alive, so release devres here to avoid * possible memory leak. */ devres_release_all(dev); kfree(dev->dma_range_map); if (dev->release) dev->release(dev); else if (dev->type && dev->type->release) dev->type->release(dev); else if (dev->class && dev->class->dev_release) dev->class->dev_release(dev); else WARN(1, KERN_ERR "Device '%s' does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", dev_name(dev)); kfree(p); } static const void *device_namespace(const struct kobject *kobj) { const struct device *dev = kobj_to_dev(kobj); const void *ns = NULL; if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; } static void device_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct device *dev = kobj_to_dev(kobj); if (dev->class && dev->class->get_ownership) dev->class->get_ownership(dev, uid, gid); } static const struct kobj_type device_ktype = { .release = device_release, .sysfs_ops = &dev_sysfs_ops, .namespace = device_namespace, .get_ownership = device_get_ownership, }; static int dev_uevent_filter(const struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); if (ktype == &device_ktype) { const struct device *dev = kobj_to_dev(kobj); if (dev->bus) return 1; if (dev->class) return 1; } return 0; } static const char *dev_uevent_name(const struct kobject *kobj) { const struct device *dev = kobj_to_dev(kobj); if (dev->bus) return dev->bus->name; if (dev->class) return dev->class->name; return NULL; } static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { const struct device *dev = kobj_to_dev(kobj); struct device_driver *driver; int retval = 0; /* add device node properties if present */ if (MAJOR(dev->devt)) { const char *tmp; const char *name; umode_t mode = 0; kuid_t uid = GLOBAL_ROOT_UID; kgid_t gid = GLOBAL_ROOT_GID; add_uevent_var(env, "MAJOR=%u", MAJOR(dev->devt)); add_uevent_var(env, "MINOR=%u", MINOR(dev->devt)); name = device_get_devnode(dev, &mode, &uid, &gid, &tmp); if (name) { add_uevent_var(env, "DEVNAME=%s", name); if (mode) add_uevent_var(env, "DEVMODE=%#o", mode & 0777); if (!uid_eq(uid, GLOBAL_ROOT_UID)) add_uevent_var(env, "DEVUID=%u", from_kuid(&init_user_ns, uid)); if (!gid_eq(gid, GLOBAL_ROOT_GID)) add_uevent_var(env, "DEVGID=%u", from_kgid(&init_user_ns, gid)); kfree(tmp); } } if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name); /* Synchronize with module_remove_driver() */ rcu_read_lock(); driver = READ_ONCE(dev->driver); if (driver) add_uevent_var(env, "DRIVER=%s", driver->name); rcu_read_unlock(); /* Add common DT information about the device */ of_device_uevent(dev, env); /* have the bus specific function add its stuff */ if (dev->bus && dev->bus->uevent) { retval = dev->bus->uevent(dev, env); if (retval) pr_debug("device: '%s': %s: bus uevent() returned %d\n", dev_name(dev), __func__, retval); } /* have the class specific function add its stuff */ if (dev->class && dev->class->dev_uevent) { retval = dev->class->dev_uevent(dev, env); if (retval) pr_debug("device: '%s': %s: class uevent() " "returned %d\n", dev_name(dev), __func__, retval); } /* have the device type specific function add its stuff */ if (dev->type && dev->type->uevent) { retval = dev->type->uevent(dev, env); if (retval) pr_debug("device: '%s': %s: dev_type uevent() " "returned %d\n", dev_name(dev), __func__, retval); } return retval; } static const struct kset_uevent_ops device_uevent_ops = { .filter = dev_uevent_filter, .name = dev_uevent_name, .uevent = dev_uevent, }; static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, char *buf) { struct kobject *top_kobj; struct kset *kset; struct kobj_uevent_env *env = NULL; int i; int len = 0; int retval; /* search the kset, the device belongs to */ top_kobj = &dev->kobj; while (!top_kobj->kset && top_kobj->parent) top_kobj = top_kobj->parent; if (!top_kobj->kset) goto out; kset = top_kobj->kset; if (!kset->uevent_ops || !kset->uevent_ops->uevent) goto out; /* respect filter */ if (kset->uevent_ops && kset->uevent_ops->filter) if (!kset->uevent_ops->filter(&dev->kobj)) goto out; env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); if (!env) return -ENOMEM; /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(&dev->kobj, env); if (retval) goto out; /* copy keys to file */ for (i = 0; i < env->envp_idx; i++) len += sysfs_emit_at(buf, len, "%s\n", env->envp[i]); out: kfree(env); return len; } static ssize_t uevent_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int rc; rc = kobject_synth_uevent(&dev->kobj, buf, count); if (rc) { dev_err(dev, "uevent: failed to send synthetic uevent: %d\n", rc); return rc; } return count; } static DEVICE_ATTR_RW(uevent); static ssize_t online_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); val = !dev->offline; device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static ssize_t online_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { bool val; int ret; ret = kstrtobool(buf, &val); if (ret < 0) return ret; ret = lock_device_hotplug_sysfs(); if (ret) return ret; ret = val ? device_online(dev) : device_offline(dev); unlock_device_hotplug(); return ret < 0 ? ret : count; } static DEVICE_ATTR_RW(online); static ssize_t removable_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *loc; switch (dev->removable) { case DEVICE_REMOVABLE: loc = "removable"; break; case DEVICE_FIXED: loc = "fixed"; break; default: loc = "unknown"; } return sysfs_emit(buf, "%s\n", loc); } static DEVICE_ATTR_RO(removable); int device_add_groups(struct device *dev, const struct attribute_group **groups) { return sysfs_create_groups(&dev->kobj, groups); } EXPORT_SYMBOL_GPL(device_add_groups); void device_remove_groups(struct device *dev, const struct attribute_group **groups) { sysfs_remove_groups(&dev->kobj, groups); } EXPORT_SYMBOL_GPL(device_remove_groups); union device_attr_group_devres { const struct attribute_group *group; const struct attribute_group **groups; }; static void devm_attr_group_remove(struct device *dev, void *res) { union device_attr_group_devres *devres = res; const struct attribute_group *group = devres->group; dev_dbg(dev, "%s: removing group %p\n", __func__, group); sysfs_remove_group(&dev->kobj, group); } /** * devm_device_add_group - given a device, create a managed attribute group * @dev: The device to create the group for * @grp: The attribute group to create * * This function creates a group for the first time. It will explicitly * warn and error if any of the attribute files being created already exist. * * Returns 0 on success or error code on failure. */ int devm_device_add_group(struct device *dev, const struct attribute_group *grp) { union device_attr_group_devres *devres; int error; devres = devres_alloc(devm_attr_group_remove, sizeof(*devres), GFP_KERNEL); if (!devres) return -ENOMEM; error = sysfs_create_group(&dev->kobj, grp); if (error) { devres_free(devres); return error; } devres->group = grp; devres_add(dev, devres); return 0; } EXPORT_SYMBOL_GPL(devm_device_add_group); static int device_add_attrs(struct device *dev) { const struct class *class = dev->class; const struct device_type *type = dev->type; int error; if (class) { error = device_add_groups(dev, class->dev_groups); if (error) return error; } if (type) { error = device_add_groups(dev, type->groups); if (error) goto err_remove_class_groups; } error = device_add_groups(dev, dev->groups); if (error) goto err_remove_type_groups; if (device_supports_offline(dev) && !dev->offline_disabled) { error = device_create_file(dev, &dev_attr_online); if (error) goto err_remove_dev_groups; } if (fw_devlink_flags && !fw_devlink_is_permissive() && dev->fwnode) { error = device_create_file(dev, &dev_attr_waiting_for_supplier); if (error) goto err_remove_dev_online; } if (dev_removable_is_valid(dev)) { error = device_create_file(dev, &dev_attr_removable); if (error) goto err_remove_dev_waiting_for_supplier; } if (dev_add_physical_location(dev)) { error = device_add_group(dev, &dev_attr_physical_location_group); if (error) goto err_remove_dev_removable; } return 0; err_remove_dev_removable: device_remove_file(dev, &dev_attr_removable); err_remove_dev_waiting_for_supplier: device_remove_file(dev, &dev_attr_waiting_for_supplier); err_remove_dev_online: device_remove_file(dev, &dev_attr_online); err_remove_dev_groups: device_remove_groups(dev, dev->groups); err_remove_type_groups: if (type) device_remove_groups(dev, type->groups); err_remove_class_groups: if (class) device_remove_groups(dev, class->dev_groups); return error; } static void device_remove_attrs(struct device *dev) { const struct class *class = dev->class; const struct device_type *type = dev->type; if (dev->physical_location) { device_remove_group(dev, &dev_attr_physical_location_group); kfree(dev->physical_location); } device_remove_file(dev, &dev_attr_removable); device_remove_file(dev, &dev_attr_waiting_for_supplier); device_remove_file(dev, &dev_attr_online); device_remove_groups(dev, dev->groups); if (type) device_remove_groups(dev, type->groups); if (class) device_remove_groups(dev, class->dev_groups); } static ssize_t dev_show(struct device *dev, struct device_attribute *attr, char *buf) { return print_dev_t(buf, dev->devt); } static DEVICE_ATTR_RO(dev); /* /sys/devices/ */ struct kset *devices_kset; /** * devices_kset_move_before - Move device in the devices_kset's list. * @deva: Device to move. * @devb: Device @deva should come before. */ static void devices_kset_move_before(struct device *deva, struct device *devb) { if (!devices_kset) return; pr_debug("devices_kset: Moving %s before %s\n", dev_name(deva), dev_name(devb)); spin_lock(&devices_kset->list_lock); list_move_tail(&deva->kobj.entry, &devb->kobj.entry); spin_unlock(&devices_kset->list_lock); } /** * devices_kset_move_after - Move device in the devices_kset's list. * @deva: Device to move * @devb: Device @deva should come after. */ static void devices_kset_move_after(struct device *deva, struct device *devb) { if (!devices_kset) return; pr_debug("devices_kset: Moving %s after %s\n", dev_name(deva), dev_name(devb)); spin_lock(&devices_kset->list_lock); list_move(&deva->kobj.entry, &devb->kobj.entry); spin_unlock(&devices_kset->list_lock); } /** * devices_kset_move_last - move the device to the end of devices_kset's list. * @dev: device to move */ void devices_kset_move_last(struct device *dev) { if (!devices_kset) return; pr_debug("devices_kset: Moving %s to end of list\n", dev_name(dev)); spin_lock(&devices_kset->list_lock); list_move_tail(&dev->kobj.entry, &devices_kset->list); spin_unlock(&devices_kset->list_lock); } /** * device_create_file - create sysfs attribute file for device. * @dev: device. * @attr: device attribute descriptor. */ int device_create_file(struct device *dev, const struct device_attribute *attr) { int error = 0; if (dev) { WARN(((attr->attr.mode & S_IWUGO) && !attr->store), "Attribute %s: write permission without 'store'\n", attr->attr.name); WARN(((attr->attr.mode & S_IRUGO) && !attr->show), "Attribute %s: read permission without 'show'\n", attr->attr.name); error = sysfs_create_file(&dev->kobj, &attr->attr); } return error; } EXPORT_SYMBOL_GPL(device_create_file); /** * device_remove_file - remove sysfs attribute file. * @dev: device. * @attr: device attribute descriptor. */ void device_remove_file(struct device *dev, const struct device_attribute *attr) { if (dev) sysfs_remove_file(&dev->kobj, &attr->attr); } EXPORT_SYMBOL_GPL(device_remove_file); /** * device_remove_file_self - remove sysfs attribute file from its own method. * @dev: device. * @attr: device attribute descriptor. * * See kernfs_remove_self() for details. */ bool device_remove_file_self(struct device *dev, const struct device_attribute *attr) { if (dev) return sysfs_remove_file_self(&dev->kobj, &attr->attr); else return false; } EXPORT_SYMBOL_GPL(device_remove_file_self); /** * device_create_bin_file - create sysfs binary attribute file for device. * @dev: device. * @attr: device binary attribute descriptor. */ int device_create_bin_file(struct device *dev, const struct bin_attribute *attr) { int error = -EINVAL; if (dev) error = sysfs_create_bin_file(&dev->kobj, attr); return error; } EXPORT_SYMBOL_GPL(device_create_bin_file); /** * device_remove_bin_file - remove sysfs binary attribute file * @dev: device. * @attr: device binary attribute descriptor. */ void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr) { if (dev) sysfs_remove_bin_file(&dev->kobj, attr); } EXPORT_SYMBOL_GPL(device_remove_bin_file); static void klist_children_get(struct klist_node *n) { struct device_private *p = to_device_private_parent(n); struct device *dev = p->device; get_device(dev); } static void klist_children_put(struct klist_node *n) { struct device_private *p = to_device_private_parent(n); struct device *dev = p->device; put_device(dev); } /** * device_initialize - init device structure. * @dev: device. * * This prepares the device for use by other layers by initializing * its fields. * It is the first half of device_register(), if called by * that function, though it can also be called separately, so one * may use @dev's fields. In particular, get_device()/put_device() * may be used for reference counting of @dev after calling this * function. * * All fields in @dev must be initialized by the caller to 0, except * for those explicitly set to some other value. The simplest * approach is to use kzalloc() to allocate the structure containing * @dev. * * NOTE: Use put_device() to give up your reference instead of freeing * @dev directly once you have called this function. */ void device_initialize(struct device *dev) { dev->kobj.kset = devices_kset; kobject_init(&dev->kobj, &device_ktype); INIT_LIST_HEAD(&dev->dma_pools); mutex_init(&dev->mutex); lockdep_set_novalidate_class(&dev->mutex); spin_lock_init(&dev->devres_lock); INIT_LIST_HEAD(&dev->devres_head); device_pm_init(dev); set_dev_node(dev, NUMA_NO_NODE); INIT_LIST_HEAD(&dev->links.consumers); INIT_LIST_HEAD(&dev->links.suppliers); INIT_LIST_HEAD(&dev->links.defer_sync); dev->links.status = DL_DEV_NO_DRIVER; #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) dev->dma_coherent = dma_default_coherent; #endif swiotlb_dev_init(dev); } EXPORT_SYMBOL_GPL(device_initialize); struct kobject *virtual_device_parent(void) { static struct kobject *virtual_dir = NULL; if (!virtual_dir) virtual_dir = kobject_create_and_add("virtual", &devices_kset->kobj); return virtual_dir; } struct class_dir { struct kobject kobj; const struct class *class; }; #define to_class_dir(obj) container_of(obj, struct class_dir, kobj) static void class_dir_release(struct kobject *kobj) { struct class_dir *dir = to_class_dir(kobj); kfree(dir); } static const struct kobj_ns_type_operations *class_dir_child_ns_type(const struct kobject *kobj) { const struct class_dir *dir = to_class_dir(kobj); return dir->class->ns_type; } static const struct kobj_type class_dir_ktype = { .release = class_dir_release, .sysfs_ops = &kobj_sysfs_ops, .child_ns_type = class_dir_child_ns_type }; static struct kobject *class_dir_create_and_add(struct subsys_private *sp, struct kobject *parent_kobj) { struct class_dir *dir; int retval; dir = kzalloc(sizeof(*dir), GFP_KERNEL); if (!dir) return ERR_PTR(-ENOMEM); dir->class = sp->class; kobject_init(&dir->kobj, &class_dir_ktype); dir->kobj.kset = &sp->glue_dirs; retval = kobject_add(&dir->kobj, parent_kobj, "%s", sp->class->name); if (retval < 0) { kobject_put(&dir->kobj); return ERR_PTR(retval); } return &dir->kobj; } static DEFINE_MUTEX(gdp_mutex); static struct kobject *get_device_parent(struct device *dev, struct device *parent) { struct subsys_private *sp = class_to_subsys(dev->class); struct kobject *kobj = NULL; if (sp) { struct kobject *parent_kobj; struct kobject *k; /* * If we have no parent, we live in "virtual". * Class-devices with a non class-device as parent, live * in a "glue" directory to prevent namespace collisions. */ if (parent == NULL) parent_kobj = virtual_device_parent(); else if (parent->class && !dev->class->ns_type) { subsys_put(sp); return &parent->kobj; } else { parent_kobj = &parent->kobj; } mutex_lock(&gdp_mutex); /* find our class-directory at the parent and reference it */ spin_lock(&sp->glue_dirs.list_lock); list_for_each_entry(k, &sp->glue_dirs.list, entry) if (k->parent == parent_kobj) { kobj = kobject_get(k); break; } spin_unlock(&sp->glue_dirs.list_lock); if (kobj) { mutex_unlock(&gdp_mutex); subsys_put(sp); return kobj; } /* or create a new class-directory at the parent device */ k = class_dir_create_and_add(sp, parent_kobj); /* do not emit an uevent for this simple "glue" directory */ mutex_unlock(&gdp_mutex); subsys_put(sp); return k; } /* subsystems can specify a default root directory for their devices */ if (!parent && dev->bus) { struct device *dev_root = bus_get_dev_root(dev->bus); if (dev_root) { kobj = &dev_root->kobj; put_device(dev_root); return kobj; } } if (parent) return &parent->kobj; return NULL; } static inline bool live_in_glue_dir(struct kobject *kobj, struct device *dev) { struct subsys_private *sp; bool retval; if (!kobj || !dev->class) return false; sp = class_to_subsys(dev->class); if (!sp) return false; if (kobj->kset == &sp->glue_dirs) retval = true; else retval = false; subsys_put(sp); return retval; } static inline struct kobject *get_glue_dir(struct device *dev) { return dev->kobj.parent; } /** * kobject_has_children - Returns whether a kobject has children. * @kobj: the object to test * * This will return whether a kobject has other kobjects as children. * * It does NOT account for the presence of attribute files, only sub * directories. It also assumes there is no concurrent addition or * removal of such children, and thus relies on external locking. */ static inline bool kobject_has_children(struct kobject *kobj) { WARN_ON_ONCE(kref_read(&kobj->kref) == 0); return kobj->sd && kobj->sd->dir.subdirs; } /* * make sure cleaning up dir as the last step, we need to make * sure .release handler of kobject is run with holding the * global lock */ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir) { unsigned int ref; /* see if we live in a "glue" directory */ if (!live_in_glue_dir(glue_dir, dev)) return; mutex_lock(&gdp_mutex); /** * There is a race condition between removing glue directory * and adding a new device under the glue directory. * * CPU1: CPU2: * * device_add() * get_device_parent() * class_dir_create_and_add() * kobject_add_internal() * create_dir() // create glue_dir * * device_add() * get_device_parent() * kobject_get() // get glue_dir * * device_del() * cleanup_glue_dir() * kobject_del(glue_dir) * * kobject_add() * kobject_add_internal() * create_dir() // in glue_dir * sysfs_create_dir_ns() * kernfs_create_dir_ns(sd) * * sysfs_remove_dir() // glue_dir->sd=NULL * sysfs_put() // free glue_dir->sd * * // sd is freed * kernfs_new_node(sd) * kernfs_get(glue_dir) * kernfs_add_one() * kernfs_put() * * Before CPU1 remove last child device under glue dir, if CPU2 add * a new device under glue dir, the glue_dir kobject reference count * will be increase to 2 in kobject_get(k). And CPU2 has been called * kernfs_create_dir_ns(). Meanwhile, CPU1 call sysfs_remove_dir() * and sysfs_put(). This result in glue_dir->sd is freed. * * Then the CPU2 will see a stale "empty" but still potentially used * glue dir around in kernfs_new_node(). * * In order to avoid this happening, we also should make sure that * kernfs_node for glue_dir is released in CPU1 only when refcount * for glue_dir kobj is 1. */ ref = kref_read(&glue_dir->kref); if (!kobject_has_children(glue_dir) && !--ref) kobject_del(glue_dir); kobject_put(glue_dir); mutex_unlock(&gdp_mutex); } static int device_add_class_symlinks(struct device *dev) { struct device_node *of_node = dev_of_node(dev); struct subsys_private *sp; int error; if (of_node) { error = sysfs_create_link(&dev->kobj, of_node_kobj(of_node), "of_node"); if (error) dev_warn(dev, "Error %d creating of_node link\n",error); /* An error here doesn't warrant bringing down the device */ } sp = class_to_subsys(dev->class); if (!sp) return 0; error = sysfs_create_link(&dev->kobj, &sp->subsys.kobj, "subsystem"); if (error) goto out_devnode; if (dev->parent && device_is_not_partition(dev)) { error = sysfs_create_link(&dev->kobj, &dev->parent->kobj, "device"); if (error) goto out_subsys; } /* link in the class directory pointing to the device */ error = sysfs_create_link(&sp->subsys.kobj, &dev->kobj, dev_name(dev)); if (error) goto out_device; goto exit; out_device: sysfs_remove_link(&dev->kobj, "device"); out_subsys: sysfs_remove_link(&dev->kobj, "subsystem"); out_devnode: sysfs_remove_link(&dev->kobj, "of_node"); exit: subsys_put(sp); return error; } static void device_remove_class_symlinks(struct device *dev) { struct subsys_private *sp = class_to_subsys(dev->class); if (dev_of_node(dev)) sysfs_remove_link(&dev->kobj, "of_node"); if (!sp) return; if (dev->parent && device_is_not_partition(dev)) sysfs_remove_link(&dev->kobj, "device"); sysfs_remove_link(&dev->kobj, "subsystem"); sysfs_delete_link(&sp->subsys.kobj, &dev->kobj, dev_name(dev)); subsys_put(sp); } /** * dev_set_name - set a device name * @dev: device * @fmt: format string for the device's name */ int dev_set_name(struct device *dev, const char *fmt, ...) { va_list vargs; int err; va_start(vargs, fmt); err = kobject_set_name_vargs(&dev->kobj, fmt, vargs); va_end(vargs); return err; } EXPORT_SYMBOL_GPL(dev_set_name); /* select a /sys/dev/ directory for the device */ static struct kobject *device_to_dev_kobj(struct device *dev) { if (is_blockdev(dev)) return sysfs_dev_block_kobj; else return sysfs_dev_char_kobj; } static int device_create_sys_dev_entry(struct device *dev) { struct kobject *kobj = device_to_dev_kobj(dev); int error = 0; char devt_str[15]; if (kobj) { format_dev_t(devt_str, dev->devt); error = sysfs_create_link(kobj, &dev->kobj, devt_str); } return error; } static void device_remove_sys_dev_entry(struct device *dev) { struct kobject *kobj = device_to_dev_kobj(dev); char devt_str[15]; if (kobj) { format_dev_t(devt_str, dev->devt); sysfs_remove_link(kobj, devt_str); } } static int device_private_init(struct device *dev) { dev->p = kzalloc(sizeof(*dev->p), GFP_KERNEL); if (!dev->p) return -ENOMEM; dev->p->device = dev; klist_init(&dev->p->klist_children, klist_children_get, klist_children_put); INIT_LIST_HEAD(&dev->p->deferred_probe); return 0; } /** * device_add - add device to device hierarchy. * @dev: device. * * This is part 2 of device_register(), though may be called * separately _iff_ device_initialize() has been called separately. * * This adds @dev to the kobject hierarchy via kobject_add(), adds it * to the global and sibling lists for the device, then * adds it to the other relevant subsystems of the driver model. * * Do not call this routine or device_register() more than once for * any device structure. The driver model core is not designed to work * with devices that get unregistered and then spring back to life. * (Among other things, it's very hard to guarantee that all references * to the previous incarnation of @dev have been dropped.) Allocate * and register a fresh new struct device instead. * * NOTE: _Never_ directly free @dev after calling this function, even * if it returned an error! Always use put_device() to give up your * reference instead. * * Rule of thumb is: if device_add() succeeds, you should call * device_del() when you want to get rid of it. If device_add() has * *not* succeeded, use *only* put_device() to drop the reference * count. */ int device_add(struct device *dev) { struct subsys_private *sp; struct device *parent; struct kobject *kobj; struct class_interface *class_intf; int error = -EINVAL; struct kobject *glue_dir = NULL; dev = get_device(dev); if (!dev) goto done; if (!dev->p) { error = device_private_init(dev); if (error) goto done; } /* * for statically allocated devices, which should all be converted * some day, we need to initialize the name. We prevent reading back * the name, and force the use of dev_name() */ if (dev->init_name) { error = dev_set_name(dev, "%s", dev->init_name); dev->init_name = NULL; } if (dev_name(dev)) error = 0; /* subsystems can specify simple device enumeration */ else if (dev->bus && dev->bus->dev_name) error = dev_set_name(dev, "%s%u", dev->bus->dev_name, dev->id); else error = -EINVAL; if (error) goto name_error; pr_debug("device: '%s': %s\n", dev_name(dev), __func__); parent = get_device(dev->parent); kobj = get_device_parent(dev, parent); if (IS_ERR(kobj)) { error = PTR_ERR(kobj); goto parent_error; } if (kobj) dev->kobj.parent = kobj; /* use parent numa_node */ if (parent && (dev_to_node(dev) == NUMA_NO_NODE)) set_dev_node(dev, dev_to_node(parent)); /* first, register with generic layer. */ /* we require the name to be set before, and pass NULL */ error = kobject_add(&dev->kobj, dev->kobj.parent, NULL); if (error) { glue_dir = kobj; goto Error; } /* notify platform of device entry */ device_platform_notify(dev); error = device_create_file(dev, &dev_attr_uevent); if (error) goto attrError; error = device_add_class_symlinks(dev); if (error) goto SymlinkError; error = device_add_attrs(dev); if (error) goto AttrsError; error = bus_add_device(dev); if (error) goto BusError; error = dpm_sysfs_add(dev); if (error) goto DPMError; device_pm_add(dev); if (MAJOR(dev->devt)) { error = device_create_file(dev, &dev_attr_dev); if (error) goto DevAttrError; error = device_create_sys_dev_entry(dev); if (error) goto SysEntryError; devtmpfs_create_node(dev); } /* Notify clients of device addition. This call must come * after dpm_sysfs_add() and before kobject_uevent(). */ bus_notify(dev, BUS_NOTIFY_ADD_DEVICE); kobject_uevent(&dev->kobj, KOBJ_ADD); /* * Check if any of the other devices (consumers) have been waiting for * this device (supplier) to be added so that they can create a device * link to it. * * This needs to happen after device_pm_add() because device_link_add() * requires the supplier be registered before it's called. * * But this also needs to happen before bus_probe_device() to make sure * waiting consumers can link to it before the driver is bound to the * device and the driver sync_state callback is called for this device. */ if (dev->fwnode && !dev->fwnode->dev) { dev->fwnode->dev = dev; fw_devlink_link_device(dev); } bus_probe_device(dev); /* * If all driver registration is done and a newly added device doesn't * match with any driver, don't block its consumers from probing in * case the consumer device is able to operate without this supplier. */ if (dev->fwnode && fw_devlink_drv_reg_done && !dev->can_match) fw_devlink_unblock_consumers(dev); if (parent) klist_add_tail(&dev->p->knode_parent, &parent->p->klist_children); sp = class_to_subsys(dev->class); if (sp) { mutex_lock(&sp->mutex); /* tie the class to the device */ klist_add_tail(&dev->p->knode_class, &sp->klist_devices); /* notify any interfaces that the device is here */ list_for_each_entry(class_intf, &sp->interfaces, node) if (class_intf->add_dev) class_intf->add_dev(dev); mutex_unlock(&sp->mutex); subsys_put(sp); } done: put_device(dev); return error; SysEntryError: if (MAJOR(dev->devt)) device_remove_file(dev, &dev_attr_dev); DevAttrError: device_pm_remove(dev); dpm_sysfs_remove(dev); DPMError: dev->driver = NULL; bus_remove_device(dev); BusError: device_remove_attrs(dev); AttrsError: device_remove_class_symlinks(dev); SymlinkError: device_remove_file(dev, &dev_attr_uevent); attrError: device_platform_notify_remove(dev); kobject_uevent(&dev->kobj, KOBJ_REMOVE); glue_dir = get_glue_dir(dev); kobject_del(&dev->kobj); Error: cleanup_glue_dir(dev, glue_dir); parent_error: put_device(parent); name_error: kfree(dev->p); dev->p = NULL; goto done; } EXPORT_SYMBOL_GPL(device_add); /** * device_register - register a device with the system. * @dev: pointer to the device structure * * This happens in two clean steps - initialize the device * and add it to the system. The two steps can be called * separately, but this is the easiest and most common. * I.e. you should only call the two helpers separately if * have a clearly defined need to use and refcount the device * before it is added to the hierarchy. * * For more information, see the kerneldoc for device_initialize() * and device_add(). * * NOTE: _Never_ directly free @dev after calling this function, even * if it returned an error! Always use put_device() to give up the * reference initialized in this function instead. */ int device_register(struct device *dev) { device_initialize(dev); return device_add(dev); } EXPORT_SYMBOL_GPL(device_register); /** * get_device - increment reference count for device. * @dev: device. * * This simply forwards the call to kobject_get(), though * we do take care to provide for the case that we get a NULL * pointer passed in. */ struct device *get_device(struct device *dev) { return dev ? kobj_to_dev(kobject_get(&dev->kobj)) : NULL; } EXPORT_SYMBOL_GPL(get_device); /** * put_device - decrement reference count. * @dev: device in question. */ void put_device(struct device *dev) { /* might_sleep(); */ if (dev) kobject_put(&dev->kobj); } EXPORT_SYMBOL_GPL(put_device); bool kill_device(struct device *dev) { /* * Require the device lock and set the "dead" flag to guarantee that * the update behavior is consistent with the other bitfields near * it and that we cannot have an asynchronous probe routine trying * to run while we are tearing out the bus/class/sysfs from * underneath the device. */ device_lock_assert(dev); if (dev->p->dead) return false; dev->p->dead = true; return true; } EXPORT_SYMBOL_GPL(kill_device); /** * device_del - delete device from system. * @dev: device. * * This is the first part of the device unregistration * sequence. This removes the device from the lists we control * from here, has it removed from the other driver model * subsystems it was added to in device_add(), and removes it * from the kobject hierarchy. * * NOTE: this should be called manually _iff_ device_add() was * also called manually. */ void device_del(struct device *dev) { struct subsys_private *sp; struct device *parent = dev->parent; struct kobject *glue_dir = NULL; struct class_interface *class_intf; unsigned int noio_flag; device_lock(dev); kill_device(dev); device_unlock(dev); if (dev->fwnode && dev->fwnode->dev == dev) dev->fwnode->dev = NULL; /* Notify clients of device removal. This call must come * before dpm_sysfs_remove(). */ noio_flag = memalloc_noio_save(); bus_notify(dev, BUS_NOTIFY_DEL_DEVICE); dpm_sysfs_remove(dev); if (parent) klist_del(&dev->p->knode_parent); if (MAJOR(dev->devt)) { devtmpfs_delete_node(dev); device_remove_sys_dev_entry(dev); device_remove_file(dev, &dev_attr_dev); } sp = class_to_subsys(dev->class); if (sp) { device_remove_class_symlinks(dev); mutex_lock(&sp->mutex); /* notify any interfaces that the device is now gone */ list_for_each_entry(class_intf, &sp->interfaces, node) if (class_intf->remove_dev) class_intf->remove_dev(dev); /* remove the device from the class list */ klist_del(&dev->p->knode_class); mutex_unlock(&sp->mutex); subsys_put(sp); } device_remove_file(dev, &dev_attr_uevent); device_remove_attrs(dev); bus_remove_device(dev); device_pm_remove(dev); driver_deferred_probe_del(dev); device_platform_notify_remove(dev); device_links_purge(dev); /* * If a device does not have a driver attached, we need to clean * up any managed resources. We do this in device_release(), but * it's never called (and we leak the device) if a managed * resource holds a reference to the device. So release all * managed resources here, like we do in driver_detach(). We * still need to do so again in device_release() in case someone * adds a new resource after this point, though. */ devres_release_all(dev); bus_notify(dev, BUS_NOTIFY_REMOVED_DEVICE); kobject_uevent(&dev->kobj, KOBJ_REMOVE); glue_dir = get_glue_dir(dev); kobject_del(&dev->kobj); cleanup_glue_dir(dev, glue_dir); memalloc_noio_restore(noio_flag); put_device(parent); } EXPORT_SYMBOL_GPL(device_del); /** * device_unregister - unregister device from system. * @dev: device going away. * * We do this in two parts, like we do device_register(). First, * we remove it from all the subsystems with device_del(), then * we decrement the reference count via put_device(). If that * is the final reference count, the device will be cleaned up * via device_release() above. Otherwise, the structure will * stick around until the final reference to the device is dropped. */ void device_unregister(struct device *dev) { pr_debug("device: '%s': %s\n", dev_name(dev), __func__); device_del(dev); put_device(dev); } EXPORT_SYMBOL_GPL(device_unregister); static struct device *prev_device(struct klist_iter *i) { struct klist_node *n = klist_prev(i); struct device *dev = NULL; struct device_private *p; if (n) { p = to_device_private_parent(n); dev = p->device; } return dev; } static struct device *next_device(struct klist_iter *i) { struct klist_node *n = klist_next(i); struct device *dev = NULL; struct device_private *p; if (n) { p = to_device_private_parent(n); dev = p->device; } return dev; } /** * device_get_devnode - path of device node file * @dev: device * @mode: returned file access mode * @uid: returned file owner * @gid: returned file group * @tmp: possibly allocated string * * Return the relative path of a possible device node. * Non-default names may need to allocate a memory to compose * a name. This memory is returned in tmp and needs to be * freed by the caller. */ const char *device_get_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp) { char *s; *tmp = NULL; /* the device type may provide a specific name */ if (dev->type && dev->type->devnode) *tmp = dev->type->devnode(dev, mode, uid, gid); if (*tmp) return *tmp; /* the class may provide a specific name */ if (dev->class && dev->class->devnode) *tmp = dev->class->devnode(dev, mode); if (*tmp) return *tmp; /* return name without allocation, tmp == NULL */ if (strchr(dev_name(dev), '!') == NULL) return dev_name(dev); /* replace '!' in the name with '/' */ s = kstrdup_and_replace(dev_name(dev), '!', '/', GFP_KERNEL); if (!s) return NULL; return *tmp = s; } /** * device_for_each_child - device child iterator. * @parent: parent struct device. * @fn: function to be called for each device. * @data: data for the callback. * * Iterate over @parent's child devices, and call @fn for each, * passing it @data. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. */ int device_for_each_child(struct device *parent, void *data, int (*fn)(struct device *dev, void *data)) { struct klist_iter i; struct device *child; int error = 0; if (!parent || !parent->p) return 0; klist_iter_init(&parent->p->klist_children, &i); while (!error && (child = next_device(&i))) error = fn(child, data); klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(device_for_each_child); /** * device_for_each_child_reverse - device child iterator in reversed order. * @parent: parent struct device. * @fn: function to be called for each device. * @data: data for the callback. * * Iterate over @parent's child devices, and call @fn for each, * passing it @data. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. */ int device_for_each_child_reverse(struct device *parent, void *data, int (*fn)(struct device *dev, void *data)) { struct klist_iter i; struct device *child; int error = 0; if (!parent || !parent->p) return 0; klist_iter_init(&parent->p->klist_children, &i); while ((child = prev_device(&i)) && !error) error = fn(child, data); klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(device_for_each_child_reverse); /** * device_find_child - device iterator for locating a particular device. * @parent: parent struct device * @match: Callback function to check device * @data: Data to pass to match function * * This is similar to the device_for_each_child() function above, but it * returns a reference to a device that is 'found' for later use, as * determined by the @match callback. * * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero and a reference to the * current device can be obtained, this function will return to the caller * and not iterate over any more devices. * * NOTE: you will need to drop the reference with put_device() after use. */ struct device *device_find_child(struct device *parent, void *data, int (*match)(struct device *dev, void *data)) { struct klist_iter i; struct device *child; if (!parent || !parent->p) return NULL; klist_iter_init(&parent->p->klist_children, &i); while ((child = next_device(&i))) if (match(child, data) && get_device(child)) break; klist_iter_exit(&i); return child; } EXPORT_SYMBOL_GPL(device_find_child); /** * device_find_child_by_name - device iterator for locating a child device. * @parent: parent struct device * @name: name of the child device * * This is similar to the device_find_child() function above, but it * returns a reference to a device that has the name @name. * * NOTE: you will need to drop the reference with put_device() after use. */ struct device *device_find_child_by_name(struct device *parent, const char *name) { struct klist_iter i; struct device *child; if (!parent) return NULL; klist_iter_init(&parent->p->klist_children, &i); while ((child = next_device(&i))) if (sysfs_streq(dev_name(child), name) && get_device(child)) break; klist_iter_exit(&i); return child; } EXPORT_SYMBOL_GPL(device_find_child_by_name); static int match_any(struct device *dev, void *unused) { return 1; } /** * device_find_any_child - device iterator for locating a child device, if any. * @parent: parent struct device * * This is similar to the device_find_child() function above, but it * returns a reference to a child device, if any. * * NOTE: you will need to drop the reference with put_device() after use. */ struct device *device_find_any_child(struct device *parent) { return device_find_child(parent, NULL, match_any); } EXPORT_SYMBOL_GPL(device_find_any_child); int __init devices_init(void) { devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL); if (!devices_kset) return -ENOMEM; dev_kobj = kobject_create_and_add("dev", NULL); if (!dev_kobj) goto dev_kobj_err; sysfs_dev_block_kobj = kobject_create_and_add("block", dev_kobj); if (!sysfs_dev_block_kobj) goto block_kobj_err; sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; device_link_wq = alloc_workqueue("device_link_wq", 0, 0); if (!device_link_wq) goto wq_err; return 0; wq_err: kobject_put(sysfs_dev_char_kobj); char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: kobject_put(dev_kobj); dev_kobj_err: kset_unregister(devices_kset); return -ENOMEM; } static int device_check_offline(struct device *dev, void *not_used) { int ret; ret = device_for_each_child(dev, NULL, device_check_offline); if (ret) return ret; return device_supports_offline(dev) && !dev->offline ? -EBUSY : 0; } /** * device_offline - Prepare the device for hot-removal. * @dev: Device to be put offline. * * Execute the device bus type's .offline() callback, if present, to prepare * the device for a subsequent hot-removal. If that succeeds, the device must * not be used until either it is removed or its bus type's .online() callback * is executed. * * Call under device_hotplug_lock. */ int device_offline(struct device *dev) { int ret; if (dev->offline_disabled) return -EPERM; ret = device_for_each_child(dev, NULL, device_check_offline); if (ret) return ret; device_lock(dev); if (device_supports_offline(dev)) { if (dev->offline) { ret = 1; } else { ret = dev->bus->offline(dev); if (!ret) { kobject_uevent(&dev->kobj, KOBJ_OFFLINE); dev->offline = true; } } } device_unlock(dev); return ret; } /** * device_online - Put the device back online after successful device_offline(). * @dev: Device to be put back online. * * If device_offline() has been successfully executed for @dev, but the device * has not been removed subsequently, execute its bus type's .online() callback * to indicate that the device can be used again. * * Call under device_hotplug_lock. */ int device_online(struct device *dev) { int ret = 0; device_lock(dev); if (device_supports_offline(dev)) { if (dev->offline) { ret = dev->bus->online(dev); if (!ret) { kobject_uevent(&dev->kobj, KOBJ_ONLINE); dev->offline = false; } } else { ret = 1; } } device_unlock(dev); return ret; } struct root_device { struct device dev; struct module *owner; }; static inline struct root_device *to_root_device(struct device *d) { return container_of(d, struct root_device, dev); } static void root_device_release(struct device *dev) { kfree(to_root_device(dev)); } /** * __root_device_register - allocate and register a root device * @name: root device name * @owner: owner module of the root device, usually THIS_MODULE * * This function allocates a root device and registers it * using device_register(). In order to free the returned * device, use root_device_unregister(). * * Root devices are dummy devices which allow other devices * to be grouped under /sys/devices. Use this function to * allocate a root device and then use it as the parent of * any device which should appear under /sys/devices/{name} * * The /sys/devices/{name} directory will also contain a * 'module' symlink which points to the @owner directory * in sysfs. * * Returns &struct device pointer on success, or ERR_PTR() on error. * * Note: You probably want to use root_device_register(). */ struct device *__root_device_register(const char *name, struct module *owner) { struct root_device *root; int err = -ENOMEM; root = kzalloc(sizeof(struct root_device), GFP_KERNEL); if (!root) return ERR_PTR(err); err = dev_set_name(&root->dev, "%s", name); if (err) { kfree(root); return ERR_PTR(err); } root->dev.release = root_device_release; err = device_register(&root->dev); if (err) { put_device(&root->dev); return ERR_PTR(err); } #ifdef CONFIG_MODULES /* gotta find a "cleaner" way to do this */ if (owner) { struct module_kobject *mk = &owner->mkobj; err = sysfs_create_link(&root->dev.kobj, &mk->kobj, "module"); if (err) { device_unregister(&root->dev); return ERR_PTR(err); } root->owner = owner; } #endif return &root->dev; } EXPORT_SYMBOL_GPL(__root_device_register); /** * root_device_unregister - unregister and free a root device * @dev: device going away * * This function unregisters and cleans up a device that was created by * root_device_register(). */ void root_device_unregister(struct device *dev) { struct root_device *root = to_root_device(dev); if (root->owner) sysfs_remove_link(&root->dev.kobj, "module"); device_unregister(dev); } EXPORT_SYMBOL_GPL(root_device_unregister); static void device_create_release(struct device *dev) { pr_debug("device: '%s': %s\n", dev_name(dev), __func__); kfree(dev); } static __printf(6, 0) struct device * device_create_groups_vargs(const struct class *class, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, va_list args) { struct device *dev = NULL; int retval = -ENODEV; if (IS_ERR_OR_NULL(class)) goto error; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) { retval = -ENOMEM; goto error; } device_initialize(dev); dev->devt = devt; dev->class = class; dev->parent = parent; dev->groups = groups; dev->release = device_create_release; dev_set_drvdata(dev, drvdata); retval = kobject_set_name_vargs(&dev->kobj, fmt, args); if (retval) goto error; retval = device_add(dev); if (retval) goto error; return dev; error: put_device(dev); return ERR_PTR(retval); } /** * device_create - creates a device and registers it with sysfs * @class: pointer to the struct class that this device should be registered to * @parent: pointer to the parent struct device of this new device, if any * @devt: the dev_t for the char device to be added * @drvdata: the data to be added to the device for callbacks * @fmt: string for the device's name * * This function can be used by char device classes. A struct device * will be created in sysfs, registered to the specified class. * * A "dev" file will be created, showing the dev_t for the device, if * the dev_t is not 0,0. * If a pointer to a parent struct device is passed in, the newly created * struct device will be a child of that device in sysfs. * The pointer to the struct device will be returned from the call. * Any further sysfs files that might be required can be created using this * pointer. * * Returns &struct device pointer on success, or ERR_PTR() on error. */ struct device *device_create(const struct class *class, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...) { va_list vargs; struct device *dev; va_start(vargs, fmt); dev = device_create_groups_vargs(class, parent, devt, drvdata, NULL, fmt, vargs); va_end(vargs); return dev; } EXPORT_SYMBOL_GPL(device_create); /** * device_create_with_groups - creates a device and registers it with sysfs * @class: pointer to the struct class that this device should be registered to * @parent: pointer to the parent struct device of this new device, if any * @devt: the dev_t for the char device to be added * @drvdata: the data to be added to the device for callbacks * @groups: NULL-terminated list of attribute groups to be created * @fmt: string for the device's name * * This function can be used by char device classes. A struct device * will be created in sysfs, registered to the specified class. * Additional attributes specified in the groups parameter will also * be created automatically. * * A "dev" file will be created, showing the dev_t for the device, if * the dev_t is not 0,0. * If a pointer to a parent struct device is passed in, the newly created * struct device will be a child of that device in sysfs. * The pointer to the struct device will be returned from the call. * Any further sysfs files that might be required can be created using this * pointer. * * Returns &struct device pointer on success, or ERR_PTR() on error. */ struct device *device_create_with_groups(const struct class *class, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...) { va_list vargs; struct device *dev; va_start(vargs, fmt); dev = device_create_groups_vargs(class, parent, devt, drvdata, groups, fmt, vargs); va_end(vargs); return dev; } EXPORT_SYMBOL_GPL(device_create_with_groups); /** * device_destroy - removes a device that was created with device_create() * @class: pointer to the struct class that this device was registered with * @devt: the dev_t of the device that was previously registered * * This call unregisters and cleans up a device that was created with a * call to device_create(). */ void device_destroy(const struct class *class, dev_t devt) { struct device *dev; dev = class_find_device_by_devt(class, devt); if (dev) { put_device(dev); device_unregister(dev); } } EXPORT_SYMBOL_GPL(device_destroy); /** * device_rename - renames a device * @dev: the pointer to the struct device to be renamed * @new_name: the new name of the device * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of device_rename * on the same device to ensure that new_name is valid and * won't conflict with other devices. * * Note: given that some subsystems (networking and infiniband) use this * function, with no immediate plans for this to change, we cannot assume or * require that this function not be called at all. * * However, if you're writing new code, do not call this function. The following * text from Kay Sievers offers some insight: * * Renaming devices is racy at many levels, symlinks and other stuff are not * replaced atomically, and you get a "move" uevent, but it's not easy to * connect the event to the old and new device. Device nodes are not renamed at * all, there isn't even support for that in the kernel now. * * In the meantime, during renaming, your target name might be taken by another * driver, creating conflicts. Or the old name is taken directly after you * renamed it -- then you get events for the same DEVPATH, before you even see * the "move" event. It's just a mess, and nothing new should ever rely on * kernel device renaming. Besides that, it's not even implemented now for * other things than (driver-core wise very simple) network devices. * * Make up a "real" name in the driver before you register anything, or add * some other attributes for userspace to find the device, or use udev to add * symlinks -- but never rename kernel devices later, it's a complete mess. We * don't even want to get into that and try to implement the missing pieces in * the core. We really have other pieces to fix in the driver core mess. :) */ int device_rename(struct device *dev, const char *new_name) { struct subsys_private *sp = NULL; struct kobject *kobj = &dev->kobj; char *old_device_name = NULL; int error; bool is_link_renamed = false; dev = get_device(dev); if (!dev) return -EINVAL; dev_dbg(dev, "renaming to %s\n", new_name); old_device_name = kstrdup(dev_name(dev), GFP_KERNEL); if (!old_device_name) { error = -ENOMEM; goto out; } if (dev->class) { sp = class_to_subsys(dev->class); if (!sp) { error = -EINVAL; goto out; } error = sysfs_rename_link_ns(&sp->subsys.kobj, kobj, old_device_name, new_name, kobject_namespace(kobj)); if (error) goto out; is_link_renamed = true; } error = kobject_rename(kobj, new_name); out: if (error && is_link_renamed) sysfs_rename_link_ns(&sp->subsys.kobj, kobj, new_name, old_device_name, kobject_namespace(kobj)); subsys_put(sp); put_device(dev); kfree(old_device_name); return error; } EXPORT_SYMBOL_GPL(device_rename); static int device_move_class_links(struct device *dev, struct device *old_parent, struct device *new_parent) { int error = 0; if (old_parent) sysfs_remove_link(&dev->kobj, "device"); if (new_parent) error = sysfs_create_link(&dev->kobj, &new_parent->kobj, "device"); return error; } /** * device_move - moves a device to a new parent * @dev: the pointer to the struct device to be moved * @new_parent: the new parent of the device (can be NULL) * @dpm_order: how to reorder the dpm_list */ int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order) { int error; struct device *old_parent; struct kobject *new_parent_kobj; dev = get_device(dev); if (!dev) return -EINVAL; device_pm_lock(); new_parent = get_device(new_parent); new_parent_kobj = get_device_parent(dev, new_parent); if (IS_ERR(new_parent_kobj)) { error = PTR_ERR(new_parent_kobj); put_device(new_parent); goto out; } pr_debug("device: '%s': %s: moving to '%s'\n", dev_name(dev), __func__, new_parent ? dev_name(new_parent) : "<NULL>"); error = kobject_move(&dev->kobj, new_parent_kobj); if (error) { cleanup_glue_dir(dev, new_parent_kobj); put_device(new_parent); goto out; } old_parent = dev->parent; dev->parent = new_parent; if (old_parent) klist_remove(&dev->p->knode_parent); if (new_parent) { klist_add_tail(&dev->p->knode_parent, &new_parent->p->klist_children); set_dev_node(dev, dev_to_node(new_parent)); } if (dev->class) { error = device_move_class_links(dev, old_parent, new_parent); if (error) { /* We ignore errors on cleanup since we're hosed anyway... */ device_move_class_links(dev, new_parent, old_parent); if (!kobject_move(&dev->kobj, &old_parent->kobj)) { if (new_parent) klist_remove(&dev->p->knode_parent); dev->parent = old_parent; if (old_parent) { klist_add_tail(&dev->p->knode_parent, &old_parent->p->klist_children); set_dev_node(dev, dev_to_node(old_parent)); } } cleanup_glue_dir(dev, new_parent_kobj); put_device(new_parent); goto out; } } switch (dpm_order) { case DPM_ORDER_NONE: break; case DPM_ORDER_DEV_AFTER_PARENT: device_pm_move_after(dev, new_parent); devices_kset_move_after(dev, new_parent); break; case DPM_ORDER_PARENT_BEFORE_DEV: device_pm_move_before(new_parent, dev); devices_kset_move_before(new_parent, dev); break; case DPM_ORDER_DEV_LAST: device_pm_move_last(dev); devices_kset_move_last(dev); break; } put_device(old_parent); out: device_pm_unlock(); put_device(dev); return error; } EXPORT_SYMBOL_GPL(device_move); static int device_attrs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { struct kobject *kobj = &dev->kobj; const struct class *class = dev->class; const struct device_type *type = dev->type; int error; if (class) { /* * Change the device groups of the device class for @dev to * @kuid/@kgid. */ error = sysfs_groups_change_owner(kobj, class->dev_groups, kuid, kgid); if (error) return error; } if (type) { /* * Change the device groups of the device type for @dev to * @kuid/@kgid. */ error = sysfs_groups_change_owner(kobj, type->groups, kuid, kgid); if (error) return error; } /* Change the device groups of @dev to @kuid/@kgid. */ error = sysfs_groups_change_owner(kobj, dev->groups, kuid, kgid); if (error) return error; if (device_supports_offline(dev) && !dev->offline_disabled) { /* Change online device attributes of @dev to @kuid/@kgid. */ error = sysfs_file_change_owner(kobj, dev_attr_online.attr.name, kuid, kgid); if (error) return error; } return 0; } /** * device_change_owner - change the owner of an existing device. * @dev: device. * @kuid: new owner's kuid * @kgid: new owner's kgid * * This changes the owner of @dev and its corresponding sysfs entries to * @kuid/@kgid. This function closely mirrors how @dev was added via driver * core. * * Returns 0 on success or error code on failure. */ int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { int error; struct kobject *kobj = &dev->kobj; struct subsys_private *sp; dev = get_device(dev); if (!dev) return -EINVAL; /* * Change the kobject and the default attributes and groups of the * ktype associated with it to @kuid/@kgid. */ error = sysfs_change_owner(kobj, kuid, kgid); if (error) goto out; /* * Change the uevent file for @dev to the new owner. The uevent file * was created in a separate step when @dev got added and we mirror * that step here. */ error = sysfs_file_change_owner(kobj, dev_attr_uevent.attr.name, kuid, kgid); if (error) goto out; /* * Change the device groups, the device groups associated with the * device class, and the groups associated with the device type of @dev * to @kuid/@kgid. */ error = device_attrs_change_owner(dev, kuid, kgid); if (error) goto out; error = dpm_sysfs_change_owner(dev, kuid, kgid); if (error) goto out; /* * Change the owner of the symlink located in the class directory of * the device class associated with @dev which points to the actual * directory entry for @dev to @kuid/@kgid. This ensures that the * symlink shows the same permissions as its target. */ sp = class_to_subsys(dev->class); if (!sp) { error = -EINVAL; goto out; } error = sysfs_link_change_owner(&sp->subsys.kobj, &dev->kobj, dev_name(dev), kuid, kgid); subsys_put(sp); out: put_device(dev); return error; } EXPORT_SYMBOL_GPL(device_change_owner); /** * device_shutdown - call ->shutdown() on each device to shutdown. */ void device_shutdown(void) { struct device *dev, *parent; wait_for_device_probe(); device_block_probing(); cpufreq_suspend(); spin_lock(&devices_kset->list_lock); /* * Walk the devices list backward, shutting down each in turn. * Beware that device unplug events may also start pulling * devices offline, even as the system is shutting down. */ while (!list_empty(&devices_kset->list)) { dev = list_entry(devices_kset->list.prev, struct device, kobj.entry); /* * hold reference count of device's parent to * prevent it from being freed because parent's * lock is to be held */ parent = get_device(dev->parent); get_device(dev); /* * Make sure the device is off the kset list, in the * event that dev->*->shutdown() doesn't remove it. */ list_del_init(&dev->kobj.entry); spin_unlock(&devices_kset->list_lock); /* hold lock to avoid race with probe/release */ if (parent) device_lock(parent); device_lock(dev); /* Don't allow any more runtime suspends */ pm_runtime_get_noresume(dev); pm_runtime_barrier(dev); if (dev->class && dev->class->shutdown_pre) { if (initcall_debug) dev_info(dev, "shutdown_pre\n"); dev->class->shutdown_pre(dev); } if (dev->bus && dev->bus->shutdown) { if (initcall_debug) dev_info(dev, "shutdown\n"); dev->bus->shutdown(dev); } else if (dev->driver && dev->driver->shutdown) { if (initcall_debug) dev_info(dev, "shutdown\n"); dev->driver->shutdown(dev); } device_unlock(dev); if (parent) device_unlock(parent); put_device(dev); put_device(parent); spin_lock(&devices_kset->list_lock); } spin_unlock(&devices_kset->list_lock); } /* * Device logging functions */ #ifdef CONFIG_PRINTK static void set_dev_info(const struct device *dev, struct dev_printk_info *dev_info) { const char *subsys; memset(dev_info, 0, sizeof(*dev_info)); if (dev->class) subsys = dev->class->name; else if (dev->bus) subsys = dev->bus->name; else return; strscpy(dev_info->subsystem, subsys); /* * Add device identifier DEVICE=: * b12:8 block dev_t * c127:3 char dev_t * n8 netdev ifindex * +sound:card0 subsystem:devname */ if (MAJOR(dev->devt)) { char c; if (strcmp(subsys, "block") == 0) c = 'b'; else c = 'c'; snprintf(dev_info->device, sizeof(dev_info->device), "%c%u:%u", c, MAJOR(dev->devt), MINOR(dev->devt)); } else if (strcmp(subsys, "net") == 0) { struct net_device *net = to_net_dev(dev); snprintf(dev_info->device, sizeof(dev_info->device), "n%u", net->ifindex); } else { snprintf(dev_info->device, sizeof(dev_info->device), "+%s:%s", subsys, dev_name(dev)); } } int dev_vprintk_emit(int level, const struct device *dev, const char *fmt, va_list args) { struct dev_printk_info dev_info; set_dev_info(dev, &dev_info); return vprintk_emit(0, level, &dev_info, fmt, args); } EXPORT_SYMBOL(dev_vprintk_emit); int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = dev_vprintk_emit(level, dev, fmt, args); va_end(args); return r; } EXPORT_SYMBOL(dev_printk_emit); static void __dev_printk(const char *level, const struct device *dev, struct va_format *vaf) { if (dev) dev_printk_emit(level[1] - '0', dev, "%s %s: %pV", dev_driver_string(dev), dev_name(dev), vaf); else printk("%s(NULL device *): %pV", level, vaf); } void _dev_printk(const char *level, const struct device *dev, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; __dev_printk(level, dev, &vaf); va_end(args); } EXPORT_SYMBOL(_dev_printk); #define define_dev_printk_level(func, kern_level) \ void func(const struct device *dev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __dev_printk(kern_level, dev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_dev_printk_level(_dev_emerg, KERN_EMERG); define_dev_printk_level(_dev_alert, KERN_ALERT); define_dev_printk_level(_dev_crit, KERN_CRIT); define_dev_printk_level(_dev_err, KERN_ERR); define_dev_printk_level(_dev_warn, KERN_WARNING); define_dev_printk_level(_dev_notice, KERN_NOTICE); define_dev_printk_level(_dev_info, KERN_INFO); #endif /** * dev_err_probe - probe error check and log helper * @dev: the pointer to the struct device * @err: error value to test * @fmt: printf-style format string * @...: arguments as specified in the format string * * This helper implements common pattern present in probe functions for error * checking: print debug or error message depending if the error value is * -EPROBE_DEFER and propagate error upwards. * In case of -EPROBE_DEFER it sets also defer probe reason, which can be * checked later by reading devices_deferred debugfs attribute. * It replaces code sequence:: * * if (err != -EPROBE_DEFER) * dev_err(dev, ...); * else * dev_dbg(dev, ...); * return err; * * with:: * * return dev_err_probe(dev, err, ...); * * Using this helper in your probe function is totally fine even if @err is * known to never be -EPROBE_DEFER. * The benefit compared to a normal dev_err() is the standardized format * of the error code, it being emitted symbolically (i.e. you get "EAGAIN" * instead of "-35") and the fact that the error code is returned which allows * more compact error paths. * * Returns @err. */ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; switch (err) { case -EPROBE_DEFER: device_set_deferred_probe_reason(dev, &vaf); dev_dbg(dev, "error %pe: %pV", ERR_PTR(err), &vaf); break; case -ENOMEM: /* * We don't print anything on -ENOMEM, there is already enough * output. */ break; default: dev_err(dev, "error %pe: %pV", ERR_PTR(err), &vaf); break; } va_end(args); return err; } EXPORT_SYMBOL_GPL(dev_err_probe); static inline bool fwnode_is_primary(struct fwnode_handle *fwnode) { return fwnode && !IS_ERR(fwnode->secondary); } /** * set_primary_fwnode - Change the primary firmware node of a given device. * @dev: Device to handle. * @fwnode: New primary firmware node of the device. * * Set the device's firmware node pointer to @fwnode, but if a secondary * firmware node of the device is present, preserve it. * * Valid fwnode cases are: * - primary --> secondary --> -ENODEV * - primary --> NULL * - secondary --> -ENODEV * - NULL */ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) { struct device *parent = dev->parent; struct fwnode_handle *fn = dev->fwnode; if (fwnode) { if (fwnode_is_primary(fn)) fn = fn->secondary; if (fn) { WARN_ON(fwnode->secondary); fwnode->secondary = fn; } dev->fwnode = fwnode; } else { if (fwnode_is_primary(fn)) { dev->fwnode = fn->secondary; /* Skip nullifying fn->secondary if the primary is shared */ if (parent && fn == parent->fwnode) return; /* Set fn->secondary = NULL, so fn remains the primary fwnode */ fn->secondary = NULL; } else { dev->fwnode = NULL; } } } EXPORT_SYMBOL_GPL(set_primary_fwnode); /** * set_secondary_fwnode - Change the secondary firmware node of a given device. * @dev: Device to handle. * @fwnode: New secondary firmware node of the device. * * If a primary firmware node of the device is present, set its secondary * pointer to @fwnode. Otherwise, set the device's firmware node pointer to * @fwnode. */ void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode) { if (fwnode) fwnode->secondary = ERR_PTR(-ENODEV); if (fwnode_is_primary(dev->fwnode)) dev->fwnode->secondary = fwnode; else dev->fwnode = fwnode; } EXPORT_SYMBOL_GPL(set_secondary_fwnode); /** * device_set_of_node_from_dev - reuse device-tree node of another device * @dev: device whose device-tree node is being set * @dev2: device whose device-tree node is being reused * * Takes another reference to the new device-tree node after first dropping * any reference held to the old node. */ void device_set_of_node_from_dev(struct device *dev, const struct device *dev2) { of_node_put(dev->of_node); dev->of_node = of_node_get(dev2->of_node); dev->of_node_reused = true; } EXPORT_SYMBOL_GPL(device_set_of_node_from_dev); void device_set_node(struct device *dev, struct fwnode_handle *fwnode) { dev->fwnode = fwnode; dev->of_node = to_of_node(fwnode); } EXPORT_SYMBOL_GPL(device_set_node); int device_match_name(struct device *dev, const void *name) { return sysfs_streq(dev_name(dev), name); } EXPORT_SYMBOL_GPL(device_match_name); int device_match_of_node(struct device *dev, const void *np) { return dev->of_node == np; } EXPORT_SYMBOL_GPL(device_match_of_node); int device_match_fwnode(struct device *dev, const void *fwnode) { return dev_fwnode(dev) == fwnode; } EXPORT_SYMBOL_GPL(device_match_fwnode); int device_match_devt(struct device *dev, const void *pdevt) { return dev->devt == *(dev_t *)pdevt; } EXPORT_SYMBOL_GPL(device_match_devt); int device_match_acpi_dev(struct device *dev, const void *adev) { return ACPI_COMPANION(dev) == adev; } EXPORT_SYMBOL(device_match_acpi_dev); int device_match_acpi_handle(struct device *dev, const void *handle) { return ACPI_HANDLE(dev) == handle; } EXPORT_SYMBOL(device_match_acpi_handle); int device_match_any(struct device *dev, const void *unused) { return 1; } EXPORT_SYMBOL_GPL(device_match_any); |
| 923 924 362 362 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bug.h> #include <linux/export.h> #include <linux/types.h> #include <linux/mmdebug.h> #include <linux/mm.h> #include <asm/memory.h> phys_addr_t __virt_to_phys(unsigned long x) { WARN(!__is_lm_address(__tag_reset(x)), "virt_to_phys used for non-linear address: %pK (%pS)\n", (void *)x, (void *)x); return __virt_to_phys_nodebug(x); } EXPORT_SYMBOL(__virt_to_phys); phys_addr_t __phys_addr_symbol(unsigned long x) { /* * This is bounds checking against the kernel image only. * __pa_symbol should only be used on kernel symbol addresses. */ VIRTUAL_BUG_ON(x < (unsigned long) KERNEL_START || x > (unsigned long) KERNEL_END); return __pa_symbol_nodebug(x); } EXPORT_SYMBOL(__phys_addr_symbol); |
| 154 155 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/backing-dev.h * * low-level device information and state which is propagated up through * to high-level code. */ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/device.h> #include <linux/writeback.h> #include <linux/backing-dev-defs.h> #include <linux/slab.h> static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); return bdi; } struct backing_dev_info *bdi_get_by_id(u64 id); void bdi_put(struct backing_dev_info *bdi); __printf(2, 3) int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); __printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); void wb_wait_for_completion(struct wb_completion *done); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { return test_bit(WB_has_dirty_io, &wb->state); } static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) { /* * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are * any dirty wbs. See wb_update_write_bandwidth(). */ return atomic_long_read(&bdi->tot_write_bandwidth); } static inline void wb_stat_mod(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { wb_stat_mod(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { wb_stat_mod(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_read_positive(&wb->stat[item]); } static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ static inline unsigned long wb_stat_error(void) { #ifdef CONFIG_SMP return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif } /* BDI ratio is expressed as part per 1000000 for finer granularity. */ #define BDI_RATIO_SCALE 10000 u64 bdi_get_min_bytes(struct backing_dev_info *bdi); u64 bdi_get_max_bytes(struct backing_dev_info *bdi); int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio); int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes); int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes); int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit); /* * Flags in backing_dev_info::capability * * BDI_CAP_WRITEBACK: Supports dirty page writeback, and dirty pages * should contribute to accounting * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold */ #define BDI_CAP_WRITEBACK (1 << 0) #define BDI_CAP_WRITEBACK_ACCT (1 << 1) #define BDI_CAP_STRICTLIMIT (1 << 2) extern struct backing_dev_info noop_backing_dev_info; int bdi_init(struct backing_dev_info *bdi); /** * writeback_in_progress - determine whether there is writeback in progress * @wb: bdi_writeback of interest * * Determine whether there is writeback waiting to be handled against a * bdi_writeback. */ static inline bool writeback_in_progress(struct bdi_writeback *wb) { return test_bit(WB_writeback_running, &wb->state); } struct backing_dev_info *inode_to_bdi(struct inode *inode); static inline bool mapping_can_writeback(struct address_space *mapping) { return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode * @inode: inode of interest * * Cgroup writeback requires support from the filesystem. Also, both memcg and * iocg have to be on the default hierarchy. Test whether all conditions are * met. * * Note that the test result may change dynamically on the same inode * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && (bdi->capabilities & BDI_CAP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } /** * wb_find_current - find wb for %current on a bdi * @bdi: bdi of interest * * Find the wb of @bdi which matches both the memcg and blkcg of %current. * Must be called under rcu_read_lock() which protects the returend wb. * NULL if not found. */ static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; memcg_css = task_css(current, memory_cgrp_id); if (!memcg_css->parent) return &bdi->wb; wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); /* * %current's blkcg equals the effective blkcg of its memcg. No * need to use the relatively expensive cgroup_get_e_css(). */ if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id))) return wb; return NULL; } /** * wb_get_create_current - get or create wb for %current on a bdi * @bdi: bdi of interest * @gfp: allocation mask * * Equivalent to wb_get_create() on %current's memcg. This function is * called from a relatively hot path and optimizes the common cases using * wb_find_current(). */ static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { struct bdi_writeback *wb; rcu_read_lock(); wb = wb_find_current(bdi); if (wb && unlikely(!wb_tryget(wb))) wb = NULL; rcu_read_unlock(); if (unlikely(!wb)) { struct cgroup_subsys_state *memcg_css; memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, gfp); css_put(memcg_css); } return wb; } /** * inode_to_wb - determine the wb of an inode * @inode: inode of interest * * Returns the wb @inode is currently associated with. The caller must be * holding either @inode->i_lock, the i_pages lock, or the * associated wb's list_lock. */ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&inode->i_lock) && !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); #endif return inode->i_wb; } static inline struct bdi_writeback *inode_to_wb_wbc( struct inode *inode, struct writeback_control *wbc) { /* * If wbc does not have inode attached, it means cgroup writeback was * disabled when wbc started. Just use the default wb in that case. */ return wbc->wb ? wbc->wb : &inode_to_bdi(inode)->wb; } /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This * function determines the wb associated with @inode and ensures that the * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and * can't sleep during the transaction. IRQs may or may not be disabled on * return. */ static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); /* * Paired with store_release in inode_switch_wbs_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; if (unlikely(cookie->locked)) xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages * lock. inode_to_wb() will bark. Deref directly. */ return inode->i_wb; } /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode * @cookie: @cookie from unlocked_inode_to_wb_begin() */ static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { if (unlikely(cookie->locked)) xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool inode_cgwb_enabled(struct inode *inode) { return false; } static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; } static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { return &bdi->wb; } static inline struct bdi_writeback *inode_to_wb(struct inode *inode) { return &inode_to_bdi(inode)->wb; } static inline struct bdi_writeback *inode_to_wb_wbc( struct inode *inode, struct writeback_control *wbc) { return inode_to_wb(inode); } static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { } static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } #endif /* CONFIG_CGROUP_WRITEBACK */ const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ |
| 6 43 43 44 44 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar * Copyright (C) 2005-2006, Thomas Gleixner, Russell King * * This file contains the interrupt descriptor management code. Detailed * information is available in Documentation/core-api/genericirq.rst * */ #include <linux/irq.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/maple_tree.h> #include <linux/irqdomain.h> #include <linux/sysfs.h> #include "internals.h" /* * lockdep: we want to handle all irq_desc locks as a single lock-class: */ static struct lock_class_key irq_desc_lock_class; #if defined(CONFIG_SMP) static int __init irq_affinity_setup(char *str) { alloc_bootmem_cpumask_var(&irq_default_affinity); cpulist_parse(str, irq_default_affinity); /* * Set at least the boot cpu. We don't want to end up with * bugreports caused by random commandline masks */ cpumask_set_cpu(smp_processor_id(), irq_default_affinity); return 1; } __setup("irqaffinity=", irq_affinity_setup); static void __init init_irq_default_affinity(void) { if (!cpumask_available(irq_default_affinity)) zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); if (cpumask_empty(irq_default_affinity)) cpumask_setall(irq_default_affinity); } #else static void __init init_irq_default_affinity(void) { } #endif #ifdef CONFIG_SMP static int alloc_masks(struct irq_desc *desc, int node) { if (!zalloc_cpumask_var_node(&desc->irq_common_data.affinity, GFP_KERNEL, node)) return -ENOMEM; #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK if (!zalloc_cpumask_var_node(&desc->irq_common_data.effective_affinity, GFP_KERNEL, node)) { free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } #endif #ifdef CONFIG_GENERIC_PENDING_IRQ if (!zalloc_cpumask_var_node(&desc->pending_mask, GFP_KERNEL, node)) { #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK free_cpumask_var(desc->irq_common_data.effective_affinity); #endif free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } #endif return 0; } static void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { if (!affinity) affinity = irq_default_affinity; cpumask_copy(desc->irq_common_data.affinity, affinity); #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_clear(desc->pending_mask); #endif #ifdef CONFIG_NUMA desc->irq_common_data.node = node; #endif } static void free_masks(struct irq_desc *desc) { #ifdef CONFIG_GENERIC_PENDING_IRQ free_cpumask_var(desc->pending_mask); #endif free_cpumask_var(desc->irq_common_data.affinity); #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK free_cpumask_var(desc->irq_common_data.effective_affinity); #endif } #else static inline int alloc_masks(struct irq_desc *desc, int node) { return 0; } static inline void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { } static inline void free_masks(struct irq_desc *desc) { } #endif static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, const struct cpumask *affinity, struct module *owner) { int cpu; desc->irq_common_data.handler_data = NULL; desc->irq_common_data.msi_desc = NULL; desc->irq_data.common = &desc->irq_common_data; desc->irq_data.irq = irq; desc->irq_data.chip = &no_irq_chip; desc->irq_data.chip_data = NULL; irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); desc->handle_irq = handle_bad_irq; desc->depth = 1; desc->irq_count = 0; desc->irqs_unhandled = 0; desc->tot_count = 0; desc->name = NULL; desc->owner = owner; for_each_possible_cpu(cpu) *per_cpu_ptr(desc->kstat_irqs, cpu) = (struct irqstat) { }; desc_smp_init(desc, node, affinity); } int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | MT_FLAGS_USE_RCU, sparse_irq_lock); static int irq_find_free_area(unsigned int from, unsigned int cnt) { MA_STATE(mas, &sparse_irqs, 0, 0); if (mas_empty_area(&mas, from, MAX_SPARSE_IRQS, cnt)) return -ENOSPC; return mas.index; } static unsigned int irq_find_at_or_after(unsigned int offset) { unsigned long index = offset; struct irq_desc *desc; guard(rcu)(); desc = mt_find(&sparse_irqs, &index, nr_irqs); return desc ? irq_desc_get_irq(desc) : nr_irqs; } static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) { MA_STATE(mas, &sparse_irqs, irq, irq); WARN_ON(mas_store_gfp(&mas, desc, GFP_KERNEL) != 0); } static void delete_irq_desc(unsigned int irq) { MA_STATE(mas, &sparse_irqs, irq, irq); mas_erase(&mas); } #ifdef CONFIG_SPARSE_IRQ static const struct kobj_type irq_kobj_type; #endif static int init_desc(struct irq_desc *desc, int irq, int node, unsigned int flags, const struct cpumask *affinity, struct module *owner) { desc->kstat_irqs = alloc_percpu(struct irqstat); if (!desc->kstat_irqs) return -ENOMEM; if (alloc_masks(desc, node)) { free_percpu(desc->kstat_irqs); return -ENOMEM; } raw_spin_lock_init(&desc->lock); lockdep_set_class(&desc->lock, &irq_desc_lock_class); mutex_init(&desc->request_mutex); init_waitqueue_head(&desc->wait_for_threads); desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); irq_resend_init(desc); #ifdef CONFIG_SPARSE_IRQ kobject_init(&desc->kobj, &irq_kobj_type); init_rcu_head(&desc->rcu); #endif return 0; } #ifdef CONFIG_SPARSE_IRQ static void irq_kobj_release(struct kobject *kobj); #ifdef CONFIG_SYSFS static struct kobject *irq_kobj_base; #define IRQ_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) static ssize_t per_cpu_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; char *p = ""; int cpu; for_each_possible_cpu(cpu) { unsigned int c = irq_desc_kstat_cpu(desc, cpu); ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c); p = ","; } ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n"); return ret; } IRQ_ATTR_RO(per_cpu_count); static ssize_t chip_name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); if (desc->irq_data.chip && desc->irq_data.chip->name) { ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->irq_data.chip->name); } raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(chip_name); static ssize_t hwirq_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); if (desc->irq_data.domain) ret = sprintf(buf, "%lu\n", desc->irq_data.hwirq); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(hwirq); static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); ret = sprintf(buf, "%s\n", irqd_is_level_type(&desc->irq_data) ? "level" : "edge"); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(type); static ssize_t wakeup_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); ret = sprintf(buf, "%s\n", irqd_is_wakeup_set(&desc->irq_data) ? "enabled" : "disabled"); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(wakeup); static ssize_t name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); if (desc->name) ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->name); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(name); static ssize_t actions_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); struct irqaction *action; ssize_t ret = 0; char *p = ""; raw_spin_lock_irq(&desc->lock); for_each_action_of_desc(desc, action) { ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s", p, action->name); p = ","; } raw_spin_unlock_irq(&desc->lock); if (ret) ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n"); return ret; } IRQ_ATTR_RO(actions); static struct attribute *irq_attrs[] = { &per_cpu_count_attr.attr, &chip_name_attr.attr, &hwirq_attr.attr, &type_attr.attr, &wakeup_attr.attr, &name_attr.attr, &actions_attr.attr, NULL }; ATTRIBUTE_GROUPS(irq); static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = irq_groups, }; static void irq_sysfs_add(int irq, struct irq_desc *desc) { if (irq_kobj_base) { /* * Continue even in case of failure as this is nothing * crucial and failures in the late irq_sysfs_init() * cannot be rolled back. */ if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq)) pr_warn("Failed to add kobject for irq %d\n", irq); else desc->istate |= IRQS_SYSFS; } } static void irq_sysfs_del(struct irq_desc *desc) { /* * Only invoke kobject_del() when kobject_add() was successfully * invoked for the descriptor. This covers both early boot, where * sysfs is not initialized yet, and the case of a failed * kobject_add() invocation. */ if (desc->istate & IRQS_SYSFS) kobject_del(&desc->kobj); } static int __init irq_sysfs_init(void) { struct irq_desc *desc; int irq; /* Prevent concurrent irq alloc/free */ irq_lock_sparse(); irq_kobj_base = kobject_create_and_add("irq", kernel_kobj); if (!irq_kobj_base) { irq_unlock_sparse(); return -ENOMEM; } /* Add the already allocated interrupts */ for_each_irq_desc(irq, desc) irq_sysfs_add(irq, desc); irq_unlock_sparse(); return 0; } postcore_initcall(irq_sysfs_init); #else /* !CONFIG_SYSFS */ static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, }; static void irq_sysfs_add(int irq, struct irq_desc *desc) {} static void irq_sysfs_del(struct irq_desc *desc) {} #endif /* CONFIG_SYSFS */ struct irq_desc *irq_to_desc(unsigned int irq) { return mtree_load(&sparse_irqs, irq); } #ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE EXPORT_SYMBOL_GPL(irq_to_desc); #endif void irq_lock_sparse(void) { mutex_lock(&sparse_irq_lock); } void irq_unlock_sparse(void) { mutex_unlock(&sparse_irq_lock); } static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, const struct cpumask *affinity, struct module *owner) { struct irq_desc *desc; int ret; desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node); if (!desc) return NULL; ret = init_desc(desc, irq, node, flags, affinity, owner); if (unlikely(ret)) { kfree(desc); return NULL; } return desc; } static void irq_kobj_release(struct kobject *kobj) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); free_masks(desc); free_percpu(desc->kstat_irqs); kfree(desc); } static void delayed_free_desc(struct rcu_head *rhp) { struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu); kobject_put(&desc->kobj); } static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); irq_remove_debugfs_entry(desc); unregister_irq_proc(irq, desc); /* * sparse_irq_lock protects also show_interrupts() and * kstat_irq_usr(). Once we deleted the descriptor from the * sparse tree we can free it. Access in proc will fail to * lookup the descriptor. * * The sysfs entry must be serialized against a concurrent * irq_sysfs_init() as well. */ irq_sysfs_del(desc); delete_irq_desc(irq); /* * We free the descriptor, masks and stat fields via RCU. That * allows demultiplex interrupts to do rcu based management of * the child interrupts. * This also allows us to use rcu in kstat_irqs_usr(). */ call_rcu(&desc->rcu, delayed_free_desc); } static int alloc_descs(unsigned int start, unsigned int cnt, int node, const struct irq_affinity_desc *affinity, struct module *owner) { struct irq_desc *desc; int i; /* Validate affinity mask(s) */ if (affinity) { for (i = 0; i < cnt; i++) { if (cpumask_empty(&affinity[i].mask)) return -EINVAL; } } for (i = 0; i < cnt; i++) { const struct cpumask *mask = NULL; unsigned int flags = 0; if (affinity) { if (affinity->is_managed) { flags = IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN; } flags |= IRQD_AFFINITY_SET; mask = &affinity->mask; node = cpu_to_node(cpumask_first(mask)); affinity++; } desc = alloc_desc(start + i, node, flags, mask, owner); if (!desc) goto err; irq_insert_desc(start + i, desc); irq_sysfs_add(start + i, desc); irq_add_debugfs_entry(start + i, desc); } return start; err: for (i--; i >= 0; i--) free_desc(start + i); return -ENOMEM; } static int irq_expand_nr_irqs(unsigned int nr) { if (nr > MAX_SPARSE_IRQS) return -ENOMEM; nr_irqs = nr; return 0; } int __init early_irq_init(void) { int i, initcnt, node = first_online_node; struct irq_desc *desc; init_irq_default_affinity(); /* Let arch update nr_irqs and return the nr of preallocated irqs */ initcnt = arch_probe_nr_irqs(); printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n", NR_IRQS, nr_irqs, initcnt); if (WARN_ON(nr_irqs > MAX_SPARSE_IRQS)) nr_irqs = MAX_SPARSE_IRQS; if (WARN_ON(initcnt > MAX_SPARSE_IRQS)) initcnt = MAX_SPARSE_IRQS; if (initcnt > nr_irqs) nr_irqs = initcnt; for (i = 0; i < initcnt; i++) { desc = alloc_desc(i, node, 0, NULL, NULL); irq_insert_desc(i, desc); } return arch_early_irq_init(); } #else /* !CONFIG_SPARSE_IRQ */ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { [0 ... NR_IRQS-1] = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock), } }; int __init early_irq_init(void) { int count, i, node = first_online_node; int ret; init_irq_default_affinity(); printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS); count = ARRAY_SIZE(irq_desc); for (i = 0; i < count; i++) { ret = init_desc(irq_desc + i, i, node, 0, NULL, NULL); if (unlikely(ret)) goto __free_desc_res; } return arch_early_irq_init(); __free_desc_res: while (--i >= 0) { free_masks(irq_desc + i); free_percpu(irq_desc[i].kstat_irqs); } return ret; } struct irq_desc *irq_to_desc(unsigned int irq) { return (irq < NR_IRQS) ? irq_desc + irq : NULL; } EXPORT_SYMBOL(irq_to_desc); static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL); raw_spin_unlock_irqrestore(&desc->lock, flags); delete_irq_desc(irq); } static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, const struct irq_affinity_desc *affinity, struct module *owner) { u32 i; for (i = 0; i < cnt; i++) { struct irq_desc *desc = irq_to_desc(start + i); desc->owner = owner; irq_insert_desc(start + i, desc); } return start; } static int irq_expand_nr_irqs(unsigned int nr) { return -ENOMEM; } void irq_mark_irq(unsigned int irq) { mutex_lock(&sparse_irq_lock); irq_insert_desc(irq, irq_desc + irq); mutex_unlock(&sparse_irq_lock); } #ifdef CONFIG_GENERIC_IRQ_LEGACY void irq_init_desc(unsigned int irq) { free_desc(irq); } #endif #endif /* !CONFIG_SPARSE_IRQ */ int handle_irq_desc(struct irq_desc *desc) { struct irq_data *data; if (!desc) return -EINVAL; data = irq_desc_get_irq_data(desc); if (WARN_ON_ONCE(!in_hardirq() && handle_enforce_irqctx(data))) return -EPERM; generic_handle_irq_desc(desc); return 0; } /** * generic_handle_irq - Invoke the handler for a particular irq * @irq: The irq number to handle * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an IRQ context with irq regs * initialized. */ int generic_handle_irq(unsigned int irq) { return handle_irq_desc(irq_to_desc(irq)); } EXPORT_SYMBOL_GPL(generic_handle_irq); /** * generic_handle_irq_safe - Invoke the handler for a particular irq from any * context. * @irq: The irq number to handle * * Returns: 0 on success, a negative value on error. * * This function can be called from any context (IRQ or process context). It * will report an error if not invoked from IRQ context and the irq has been * marked to enforce IRQ-context only. */ int generic_handle_irq_safe(unsigned int irq) { unsigned long flags; int ret; local_irq_save(flags); ret = handle_irq_desc(irq_to_desc(irq)); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(generic_handle_irq_safe); #ifdef CONFIG_IRQ_DOMAIN /** * generic_handle_domain_irq - Invoke the handler for a HW irq belonging * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an IRQ context with irq regs * initialized. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); /** * generic_handle_irq_safe - Invoke the handler for a HW irq belonging * to a domain from any context. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, a negative value on error. * * This function can be called from any context (IRQ or process * context). If the interrupt is marked as 'enforce IRQ-context only' then * the function must be invoked from hard interrupt context. */ int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq) { unsigned long flags; int ret; local_irq_save(flags); ret = handle_irq_desc(irq_resolve_mapping(domain, hwirq)); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(generic_handle_domain_irq_safe); /** * generic_handle_domain_nmi - Invoke the handler for a HW nmi belonging * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an NMI context with irq regs * initialized. **/ int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq) { WARN_ON_ONCE(!in_nmi()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } #endif /* Dynamic interrupt handling */ /** * irq_free_descs - free irq descriptors * @from: Start of descriptor range * @cnt: Number of consecutive irqs to free */ void irq_free_descs(unsigned int from, unsigned int cnt) { int i; if (from >= nr_irqs || (from + cnt) > nr_irqs) return; mutex_lock(&sparse_irq_lock); for (i = 0; i < cnt; i++) free_desc(from + i); mutex_unlock(&sparse_irq_lock); } EXPORT_SYMBOL_GPL(irq_free_descs); /** * __irq_alloc_descs - allocate and initialize a range of irq descriptors * @irq: Allocate for specific irq number if irq >= 0 * @from: Start the search from this irq number * @cnt: Number of consecutive irqs to allocate. * @node: Preferred node on which the irq descriptor should be allocated * @owner: Owning module (can be NULL) * @affinity: Optional pointer to an affinity mask array of size @cnt which * hints where the irq descriptors should be allocated and which * default affinities to use * * Returns the first irq number or error code */ int __ref __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, struct module *owner, const struct irq_affinity_desc *affinity) { int start, ret; if (!cnt) return -EINVAL; if (irq >= 0) { if (from > irq) return -EINVAL; from = irq; } else { /* * For interrupts which are freely allocated the * architecture can force a lower bound to the @from * argument. x86 uses this to exclude the GSI space. */ from = arch_dynirq_lower_bound(from); } mutex_lock(&sparse_irq_lock); start = irq_find_free_area(from, cnt); ret = -EEXIST; if (irq >=0 && start != irq) goto unlock; if (start + cnt > nr_irqs) { ret = irq_expand_nr_irqs(start + cnt); if (ret) goto unlock; } ret = alloc_descs(start, cnt, node, affinity, owner); unlock: mutex_unlock(&sparse_irq_lock); return ret; } EXPORT_SYMBOL_GPL(__irq_alloc_descs); /** * irq_get_next_irq - get next allocated irq number * @offset: where to start the search * * Returns next irq number after offset or nr_irqs if none is found. */ unsigned int irq_get_next_irq(unsigned int offset) { return irq_find_at_or_after(offset); } struct irq_desc * __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, unsigned int check) { struct irq_desc *desc = irq_to_desc(irq); if (desc) { if (check & _IRQ_DESC_CHECK) { if ((check & _IRQ_DESC_PERCPU) && !irq_settings_is_per_cpu_devid(desc)) return NULL; if (!(check & _IRQ_DESC_PERCPU) && irq_settings_is_per_cpu_devid(desc)) return NULL; } if (bus) chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, *flags); } return desc; } void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus) __releases(&desc->lock) { raw_spin_unlock_irqrestore(&desc->lock, flags); if (bus) chip_bus_sync_unlock(desc); } int irq_set_percpu_devid_partition(unsigned int irq, const struct cpumask *affinity) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || desc->percpu_enabled) return -EINVAL; desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL); if (!desc->percpu_enabled) return -ENOMEM; desc->percpu_affinity = affinity ? : cpu_possible_mask; irq_set_percpu_devid_flags(irq); return 0; } int irq_set_percpu_devid(unsigned int irq) { return irq_set_percpu_devid_partition(irq, NULL); } int irq_get_percpu_devid_partition(unsigned int irq, struct cpumask *affinity) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->percpu_enabled) return -EINVAL; if (affinity) cpumask_copy(affinity, desc->percpu_affinity); return 0; } EXPORT_SYMBOL_GPL(irq_get_percpu_devid_partition); void kstat_incr_irq_this_cpu(unsigned int irq) { kstat_incr_irqs_this_cpu(irq_to_desc(irq)); } /** * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu * @irq: The interrupt number * @cpu: The cpu number * * Returns the sum of interrupt counts on @cpu since boot for * @irq. The caller must ensure that the interrupt is not removed * concurrently. */ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask) { unsigned int sum = 0; int cpu; if (!irq_settings_is_per_cpu_devid(desc) && !irq_settings_is_per_cpu(desc) && !irq_is_nmi(desc)) return data_race(desc->tot_count); for_each_cpu(cpu, cpumask) sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu)); return sum; } static unsigned int kstat_irqs(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->kstat_irqs) return 0; return kstat_irqs_desc(desc, cpu_possible_mask); } #ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT void kstat_snapshot_irqs(void) { struct irq_desc *desc; unsigned int irq; for_each_irq_desc(irq, desc) { if (!desc->kstat_irqs) continue; this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt)); } } unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->kstat_irqs) return 0; return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref); } #endif /** * kstat_irqs_usr - Get the statistics for an interrupt from thread context * @irq: The interrupt number * * Returns the sum of interrupt counts on all cpus since boot for @irq. * * It uses rcu to protect the access since a concurrent removal of an * interrupt descriptor is observing an rcu grace period before * delayed_free_desc()/irq_kobj_release(). */ unsigned int kstat_irqs_usr(unsigned int irq) { unsigned int sum; rcu_read_lock(); sum = kstat_irqs(irq); rcu_read_unlock(); return sum; } #ifdef CONFIG_LOCKDEP void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class, struct lock_class_key *request_class) { struct irq_desc *desc = irq_to_desc(irq); if (desc) { lockdep_set_class(&desc->lock, lock_class); lockdep_set_class(&desc->request_mutex, request_class); } } EXPORT_SYMBOL_GPL(__irq_set_lockdep_class); #endif |
| 198 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013 Huawei Ltd. * Author: Jiang Liu <liuj97@gmail.com> * * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com> */ #include <linux/bitops.h> #include <linux/bug.h> #include <linux/printk.h> #include <linux/sizes.h> #include <linux/types.h> #include <asm/debug-monitors.h> #include <asm/errno.h> #include <asm/insn.h> #include <asm/kprobes.h> #define AARCH64_INSN_SF_BIT BIT(31) #define AARCH64_INSN_N_BIT BIT(22) #define AARCH64_INSN_LSL_12 BIT(22) static int __kprobes aarch64_get_imm_shift_mask(enum aarch64_insn_imm_type type, u32 *maskp, int *shiftp) { u32 mask; int shift; switch (type) { case AARCH64_INSN_IMM_26: mask = BIT(26) - 1; shift = 0; break; case AARCH64_INSN_IMM_19: mask = BIT(19) - 1; shift = 5; break; case AARCH64_INSN_IMM_16: mask = BIT(16) - 1; shift = 5; break; case AARCH64_INSN_IMM_14: mask = BIT(14) - 1; shift = 5; break; case AARCH64_INSN_IMM_12: mask = BIT(12) - 1; shift = 10; break; case AARCH64_INSN_IMM_9: mask = BIT(9) - 1; shift = 12; break; case AARCH64_INSN_IMM_7: mask = BIT(7) - 1; shift = 15; break; case AARCH64_INSN_IMM_6: case AARCH64_INSN_IMM_S: mask = BIT(6) - 1; shift = 10; break; case AARCH64_INSN_IMM_R: mask = BIT(6) - 1; shift = 16; break; case AARCH64_INSN_IMM_N: mask = 1; shift = 22; break; default: return -EINVAL; } *maskp = mask; *shiftp = shift; return 0; } #define ADR_IMM_HILOSPLIT 2 #define ADR_IMM_SIZE SZ_2M #define ADR_IMM_LOMASK ((1 << ADR_IMM_HILOSPLIT) - 1) #define ADR_IMM_HIMASK ((ADR_IMM_SIZE >> ADR_IMM_HILOSPLIT) - 1) #define ADR_IMM_LOSHIFT 29 #define ADR_IMM_HISHIFT 5 u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn) { u32 immlo, immhi, mask; int shift; switch (type) { case AARCH64_INSN_IMM_ADR: shift = 0; immlo = (insn >> ADR_IMM_LOSHIFT) & ADR_IMM_LOMASK; immhi = (insn >> ADR_IMM_HISHIFT) & ADR_IMM_HIMASK; insn = (immhi << ADR_IMM_HILOSPLIT) | immlo; mask = ADR_IMM_SIZE - 1; break; default: if (aarch64_get_imm_shift_mask(type, &mask, &shift) < 0) { pr_err("%s: unknown immediate encoding %d\n", __func__, type); return 0; } } return (insn >> shift) & mask; } u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type, u32 insn, u64 imm) { u32 immlo, immhi, mask; int shift; if (insn == AARCH64_BREAK_FAULT) return AARCH64_BREAK_FAULT; switch (type) { case AARCH64_INSN_IMM_ADR: shift = 0; immlo = (imm & ADR_IMM_LOMASK) << ADR_IMM_LOSHIFT; imm >>= ADR_IMM_HILOSPLIT; immhi = (imm & ADR_IMM_HIMASK) << ADR_IMM_HISHIFT; imm = immlo | immhi; mask = ((ADR_IMM_LOMASK << ADR_IMM_LOSHIFT) | (ADR_IMM_HIMASK << ADR_IMM_HISHIFT)); break; default: if (aarch64_get_imm_shift_mask(type, &mask, &shift) < 0) { pr_err("%s: unknown immediate encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } } /* Update the immediate field. */ insn &= ~(mask << shift); insn |= (imm & mask) << shift; return insn; } u32 aarch64_insn_decode_register(enum aarch64_insn_register_type type, u32 insn) { int shift; switch (type) { case AARCH64_INSN_REGTYPE_RT: case AARCH64_INSN_REGTYPE_RD: shift = 0; break; case AARCH64_INSN_REGTYPE_RN: shift = 5; break; case AARCH64_INSN_REGTYPE_RT2: case AARCH64_INSN_REGTYPE_RA: shift = 10; break; case AARCH64_INSN_REGTYPE_RM: shift = 16; break; default: pr_err("%s: unknown register type encoding %d\n", __func__, type); return 0; } return (insn >> shift) & GENMASK(4, 0); } static u32 aarch64_insn_encode_register(enum aarch64_insn_register_type type, u32 insn, enum aarch64_insn_register reg) { int shift; if (insn == AARCH64_BREAK_FAULT) return AARCH64_BREAK_FAULT; if (reg < AARCH64_INSN_REG_0 || reg > AARCH64_INSN_REG_SP) { pr_err("%s: unknown register encoding %d\n", __func__, reg); return AARCH64_BREAK_FAULT; } switch (type) { case AARCH64_INSN_REGTYPE_RT: case AARCH64_INSN_REGTYPE_RD: shift = 0; break; case AARCH64_INSN_REGTYPE_RN: shift = 5; break; case AARCH64_INSN_REGTYPE_RT2: case AARCH64_INSN_REGTYPE_RA: shift = 10; break; case AARCH64_INSN_REGTYPE_RM: case AARCH64_INSN_REGTYPE_RS: shift = 16; break; default: pr_err("%s: unknown register type encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } insn &= ~(GENMASK(4, 0) << shift); insn |= reg << shift; return insn; } static const u32 aarch64_insn_ldst_size[] = { [AARCH64_INSN_SIZE_8] = 0, [AARCH64_INSN_SIZE_16] = 1, [AARCH64_INSN_SIZE_32] = 2, [AARCH64_INSN_SIZE_64] = 3, }; static u32 aarch64_insn_encode_ldst_size(enum aarch64_insn_size_type type, u32 insn) { u32 size; if (type < AARCH64_INSN_SIZE_8 || type > AARCH64_INSN_SIZE_64) { pr_err("%s: unknown size encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } size = aarch64_insn_ldst_size[type]; insn &= ~GENMASK(31, 30); insn |= size << 30; return insn; } static inline long label_imm_common(unsigned long pc, unsigned long addr, long range) { long offset; if ((pc & 0x3) || (addr & 0x3)) { pr_err("%s: A64 instructions must be word aligned\n", __func__); return range; } offset = ((long)addr - (long)pc); if (offset < -range || offset >= range) { pr_err("%s: offset out of range\n", __func__); return range; } return offset; } u32 __kprobes aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr, enum aarch64_insn_branch_type type) { u32 insn; long offset; /* * B/BL support [-128M, 128M) offset * ARM64 virtual address arrangement guarantees all kernel and module * texts are within +/-128M. */ offset = label_imm_common(pc, addr, SZ_128M); if (offset >= SZ_128M) return AARCH64_BREAK_FAULT; switch (type) { case AARCH64_INSN_BRANCH_LINK: insn = aarch64_insn_get_bl_value(); break; case AARCH64_INSN_BRANCH_NOLINK: insn = aarch64_insn_get_b_value(); break; default: pr_err("%s: unknown branch encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn, offset >> 2); } u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr, enum aarch64_insn_register reg, enum aarch64_insn_variant variant, enum aarch64_insn_branch_type type) { u32 insn; long offset; offset = label_imm_common(pc, addr, SZ_1M); if (offset >= SZ_1M) return AARCH64_BREAK_FAULT; switch (type) { case AARCH64_INSN_BRANCH_COMP_ZERO: insn = aarch64_insn_get_cbz_value(); break; case AARCH64_INSN_BRANCH_COMP_NONZERO: insn = aarch64_insn_get_cbnz_value(); break; default: pr_err("%s: unknown branch encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT; break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn, offset >> 2); } u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr, enum aarch64_insn_condition cond) { u32 insn; long offset; offset = label_imm_common(pc, addr, SZ_1M); insn = aarch64_insn_get_bcond_value(); if (cond < AARCH64_INSN_COND_EQ || cond > AARCH64_INSN_COND_AL) { pr_err("%s: unknown condition encoding %d\n", __func__, cond); return AARCH64_BREAK_FAULT; } insn |= cond; return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn, offset >> 2); } u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg, enum aarch64_insn_branch_type type) { u32 insn; switch (type) { case AARCH64_INSN_BRANCH_NOLINK: insn = aarch64_insn_get_br_value(); break; case AARCH64_INSN_BRANCH_LINK: insn = aarch64_insn_get_blr_value(); break; case AARCH64_INSN_BRANCH_RETURN: insn = aarch64_insn_get_ret_value(); break; default: pr_err("%s: unknown branch encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, reg); } u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg, enum aarch64_insn_register base, enum aarch64_insn_register offset, enum aarch64_insn_size_type size, enum aarch64_insn_ldst_type type) { u32 insn; switch (type) { case AARCH64_INSN_LDST_LOAD_REG_OFFSET: insn = aarch64_insn_get_ldr_reg_value(); break; case AARCH64_INSN_LDST_SIGNED_LOAD_REG_OFFSET: insn = aarch64_insn_get_signed_ldr_reg_value(); break; case AARCH64_INSN_LDST_STORE_REG_OFFSET: insn = aarch64_insn_get_str_reg_value(); break; default: pr_err("%s: unknown load/store encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_ldst_size(size, insn); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, base); return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, offset); } u32 aarch64_insn_gen_load_store_imm(enum aarch64_insn_register reg, enum aarch64_insn_register base, unsigned int imm, enum aarch64_insn_size_type size, enum aarch64_insn_ldst_type type) { u32 insn; u32 shift; if (size < AARCH64_INSN_SIZE_8 || size > AARCH64_INSN_SIZE_64) { pr_err("%s: unknown size encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } shift = aarch64_insn_ldst_size[size]; if (imm & ~(BIT(12 + shift) - BIT(shift))) { pr_err("%s: invalid imm: %d\n", __func__, imm); return AARCH64_BREAK_FAULT; } imm >>= shift; switch (type) { case AARCH64_INSN_LDST_LOAD_IMM_OFFSET: insn = aarch64_insn_get_ldr_imm_value(); break; case AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET: insn = aarch64_insn_get_signed_load_imm_value(); break; case AARCH64_INSN_LDST_STORE_IMM_OFFSET: insn = aarch64_insn_get_str_imm_value(); break; default: pr_err("%s: unknown load/store encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_ldst_size(size, insn); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, base); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, imm); } u32 aarch64_insn_gen_load_literal(unsigned long pc, unsigned long addr, enum aarch64_insn_register reg, bool is64bit) { u32 insn; long offset; offset = label_imm_common(pc, addr, SZ_1M); if (offset >= SZ_1M) return AARCH64_BREAK_FAULT; insn = aarch64_insn_get_ldr_lit_value(); if (is64bit) insn |= BIT(30); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn, offset >> 2); } u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1, enum aarch64_insn_register reg2, enum aarch64_insn_register base, int offset, enum aarch64_insn_variant variant, enum aarch64_insn_ldst_type type) { u32 insn; int shift; switch (type) { case AARCH64_INSN_LDST_LOAD_PAIR_PRE_INDEX: insn = aarch64_insn_get_ldp_pre_value(); break; case AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX: insn = aarch64_insn_get_stp_pre_value(); break; case AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX: insn = aarch64_insn_get_ldp_post_value(); break; case AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX: insn = aarch64_insn_get_stp_post_value(); break; default: pr_err("%s: unknown load/store encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: if ((offset & 0x3) || (offset < -256) || (offset > 252)) { pr_err("%s: offset must be multiples of 4 in the range of [-256, 252] %d\n", __func__, offset); return AARCH64_BREAK_FAULT; } shift = 2; break; case AARCH64_INSN_VARIANT_64BIT: if ((offset & 0x7) || (offset < -512) || (offset > 504)) { pr_err("%s: offset must be multiples of 8 in the range of [-512, 504] %d\n", __func__, offset); return AARCH64_BREAK_FAULT; } shift = 3; insn |= AARCH64_INSN_SF_BIT; break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg1); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT2, insn, reg2); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, base); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_7, insn, offset >> shift); } u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, enum aarch64_insn_register base, enum aarch64_insn_register state, enum aarch64_insn_size_type size, enum aarch64_insn_ldst_type type) { u32 insn; switch (type) { case AARCH64_INSN_LDST_LOAD_EX: case AARCH64_INSN_LDST_LOAD_ACQ_EX: insn = aarch64_insn_get_load_ex_value(); if (type == AARCH64_INSN_LDST_LOAD_ACQ_EX) insn |= BIT(15); break; case AARCH64_INSN_LDST_STORE_EX: case AARCH64_INSN_LDST_STORE_REL_EX: insn = aarch64_insn_get_store_ex_value(); if (type == AARCH64_INSN_LDST_STORE_REL_EX) insn |= BIT(15); break; default: pr_err("%s: unknown load/store exclusive encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_ldst_size(size, insn); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, base); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT2, insn, AARCH64_INSN_REG_ZR); return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn, state); } #ifdef CONFIG_ARM64_LSE_ATOMICS static u32 aarch64_insn_encode_ldst_order(enum aarch64_insn_mem_order_type type, u32 insn) { u32 order; switch (type) { case AARCH64_INSN_MEM_ORDER_NONE: order = 0; break; case AARCH64_INSN_MEM_ORDER_ACQ: order = 2; break; case AARCH64_INSN_MEM_ORDER_REL: order = 1; break; case AARCH64_INSN_MEM_ORDER_ACQREL: order = 3; break; default: pr_err("%s: unknown mem order %d\n", __func__, type); return AARCH64_BREAK_FAULT; } insn &= ~GENMASK(23, 22); insn |= order << 22; return insn; } u32 aarch64_insn_gen_atomic_ld_op(enum aarch64_insn_register result, enum aarch64_insn_register address, enum aarch64_insn_register value, enum aarch64_insn_size_type size, enum aarch64_insn_mem_atomic_op op, enum aarch64_insn_mem_order_type order) { u32 insn; switch (op) { case AARCH64_INSN_MEM_ATOMIC_ADD: insn = aarch64_insn_get_ldadd_value(); break; case AARCH64_INSN_MEM_ATOMIC_CLR: insn = aarch64_insn_get_ldclr_value(); break; case AARCH64_INSN_MEM_ATOMIC_EOR: insn = aarch64_insn_get_ldeor_value(); break; case AARCH64_INSN_MEM_ATOMIC_SET: insn = aarch64_insn_get_ldset_value(); break; case AARCH64_INSN_MEM_ATOMIC_SWP: insn = aarch64_insn_get_swp_value(); break; default: pr_err("%s: unimplemented mem atomic op %d\n", __func__, op); return AARCH64_BREAK_FAULT; } switch (size) { case AARCH64_INSN_SIZE_32: case AARCH64_INSN_SIZE_64: break; default: pr_err("%s: unimplemented size encoding %d\n", __func__, size); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_ldst_size(size, insn); insn = aarch64_insn_encode_ldst_order(order, insn); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, result); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, address); return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn, value); } static u32 aarch64_insn_encode_cas_order(enum aarch64_insn_mem_order_type type, u32 insn) { u32 order; switch (type) { case AARCH64_INSN_MEM_ORDER_NONE: order = 0; break; case AARCH64_INSN_MEM_ORDER_ACQ: order = BIT(22); break; case AARCH64_INSN_MEM_ORDER_REL: order = BIT(15); break; case AARCH64_INSN_MEM_ORDER_ACQREL: order = BIT(15) | BIT(22); break; default: pr_err("%s: unknown mem order %d\n", __func__, type); return AARCH64_BREAK_FAULT; } insn &= ~(BIT(15) | BIT(22)); insn |= order; return insn; } u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, enum aarch64_insn_register address, enum aarch64_insn_register value, enum aarch64_insn_size_type size, enum aarch64_insn_mem_order_type order) { u32 insn; switch (size) { case AARCH64_INSN_SIZE_32: case AARCH64_INSN_SIZE_64: break; default: pr_err("%s: unimplemented size encoding %d\n", __func__, size); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_get_cas_value(); insn = aarch64_insn_encode_ldst_size(size, insn); insn = aarch64_insn_encode_cas_order(order, insn); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, result); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, address); return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn, value); } #endif u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst, enum aarch64_insn_register src, int imm, enum aarch64_insn_variant variant, enum aarch64_insn_adsb_type type) { u32 insn; switch (type) { case AARCH64_INSN_ADSB_ADD: insn = aarch64_insn_get_add_imm_value(); break; case AARCH64_INSN_ADSB_SUB: insn = aarch64_insn_get_sub_imm_value(); break; case AARCH64_INSN_ADSB_ADD_SETFLAGS: insn = aarch64_insn_get_adds_imm_value(); break; case AARCH64_INSN_ADSB_SUB_SETFLAGS: insn = aarch64_insn_get_subs_imm_value(); break; default: pr_err("%s: unknown add/sub encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT; break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } /* We can't encode more than a 24bit value (12bit + 12bit shift) */ if (imm & ~(BIT(24) - 1)) goto out; /* If we have something in the top 12 bits... */ if (imm & ~(SZ_4K - 1)) { /* ... and in the low 12 bits -> error */ if (imm & (SZ_4K - 1)) goto out; imm >>= 12; insn |= AARCH64_INSN_LSL_12; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, imm); out: pr_err("%s: invalid immediate encoding %d\n", __func__, imm); return AARCH64_BREAK_FAULT; } u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst, enum aarch64_insn_register src, int immr, int imms, enum aarch64_insn_variant variant, enum aarch64_insn_bitfield_type type) { u32 insn; u32 mask; switch (type) { case AARCH64_INSN_BITFIELD_MOVE: insn = aarch64_insn_get_bfm_value(); break; case AARCH64_INSN_BITFIELD_MOVE_UNSIGNED: insn = aarch64_insn_get_ubfm_value(); break; case AARCH64_INSN_BITFIELD_MOVE_SIGNED: insn = aarch64_insn_get_sbfm_value(); break; default: pr_err("%s: unknown bitfield encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: mask = GENMASK(4, 0); break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT | AARCH64_INSN_N_BIT; mask = GENMASK(5, 0); break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } if (immr & ~mask) { pr_err("%s: invalid immr encoding %d\n", __func__, immr); return AARCH64_BREAK_FAULT; } if (imms & ~mask) { pr_err("%s: invalid imms encoding %d\n", __func__, imms); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src); insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_R, insn, immr); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, imms); } u32 aarch64_insn_gen_movewide(enum aarch64_insn_register dst, int imm, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_movewide_type type) { u32 insn; switch (type) { case AARCH64_INSN_MOVEWIDE_ZERO: insn = aarch64_insn_get_movz_value(); break; case AARCH64_INSN_MOVEWIDE_KEEP: insn = aarch64_insn_get_movk_value(); break; case AARCH64_INSN_MOVEWIDE_INVERSE: insn = aarch64_insn_get_movn_value(); break; default: pr_err("%s: unknown movewide encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } if (imm & ~(SZ_64K - 1)) { pr_err("%s: invalid immediate encoding %d\n", __func__, imm); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: if (shift != 0 && shift != 16) { pr_err("%s: invalid shift encoding %d\n", __func__, shift); return AARCH64_BREAK_FAULT; } break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT; if (shift != 0 && shift != 16 && shift != 32 && shift != 48) { pr_err("%s: invalid shift encoding %d\n", __func__, shift); return AARCH64_BREAK_FAULT; } break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn |= (shift >> 4) << 21; insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm); } u32 aarch64_insn_gen_add_sub_shifted_reg(enum aarch64_insn_register dst, enum aarch64_insn_register src, enum aarch64_insn_register reg, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_adsb_type type) { u32 insn; switch (type) { case AARCH64_INSN_ADSB_ADD: insn = aarch64_insn_get_add_value(); break; case AARCH64_INSN_ADSB_SUB: insn = aarch64_insn_get_sub_value(); break; case AARCH64_INSN_ADSB_ADD_SETFLAGS: insn = aarch64_insn_get_adds_value(); break; case AARCH64_INSN_ADSB_SUB_SETFLAGS: insn = aarch64_insn_get_subs_value(); break; default: pr_err("%s: unknown add/sub encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: if (shift & ~(SZ_32 - 1)) { pr_err("%s: invalid shift encoding %d\n", __func__, shift); return AARCH64_BREAK_FAULT; } break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT; if (shift & ~(SZ_64 - 1)) { pr_err("%s: invalid shift encoding %d\n", __func__, shift); return AARCH64_BREAK_FAULT; } break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift); } u32 aarch64_insn_gen_data1(enum aarch64_insn_register dst, enum aarch64_insn_register src, enum aarch64_insn_variant variant, enum aarch64_insn_data1_type type) { u32 insn; switch (type) { case AARCH64_INSN_DATA1_REVERSE_16: insn = aarch64_insn_get_rev16_value(); break; case AARCH64_INSN_DATA1_REVERSE_32: insn = aarch64_insn_get_rev32_value(); break; case AARCH64_INSN_DATA1_REVERSE_64: if (variant != AARCH64_INSN_VARIANT_64BIT) { pr_err("%s: invalid variant for reverse64 %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_get_rev64_value(); break; default: pr_err("%s: unknown data1 encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT; break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst); return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src); } u32 aarch64_insn_gen_data2(enum aarch64_insn_register dst, enum aarch64_insn_register src, enum aarch64_insn_register reg, enum aarch64_insn_variant variant, enum aarch64_insn_data2_type type) { u32 insn; switch (type) { case AARCH64_INSN_DATA2_UDIV: insn = aarch64_insn_get_udiv_value(); break; case AARCH64_INSN_DATA2_SDIV: insn = aarch64_insn_get_sdiv_value(); break; case AARCH64_INSN_DATA2_LSLV: insn = aarch64_insn_get_lslv_value(); break; case AARCH64_INSN_DATA2_LSRV: insn = aarch64_insn_get_lsrv_value(); break; case AARCH64_INSN_DATA2_ASRV: insn = aarch64_insn_get_asrv_value(); break; case AARCH64_INSN_DATA2_RORV: insn = aarch64_insn_get_rorv_value(); break; default: pr_err("%s: unknown data2 encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT; break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src); return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg); } u32 aarch64_insn_gen_data3(enum aarch64_insn_register dst, enum aarch64_insn_register src, enum aarch64_insn_register reg1, enum aarch64_insn_register reg2, enum aarch64_insn_variant variant, enum aarch64_insn_data3_type type) { u32 insn; switch (type) { case AARCH64_INSN_DATA3_MADD: insn = aarch64_insn_get_madd_value(); break; case AARCH64_INSN_DATA3_MSUB: insn = aarch64_insn_get_msub_value(); break; default: pr_err("%s: unknown data3 encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT; break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RA, insn, src); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, reg1); return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg2); } u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, enum aarch64_insn_register src, enum aarch64_insn_register reg, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_logic_type type) { u32 insn; switch (type) { case AARCH64_INSN_LOGIC_AND: insn = aarch64_insn_get_and_value(); break; case AARCH64_INSN_LOGIC_BIC: insn = aarch64_insn_get_bic_value(); break; case AARCH64_INSN_LOGIC_ORR: insn = aarch64_insn_get_orr_value(); break; case AARCH64_INSN_LOGIC_ORN: insn = aarch64_insn_get_orn_value(); break; case AARCH64_INSN_LOGIC_EOR: insn = aarch64_insn_get_eor_value(); break; case AARCH64_INSN_LOGIC_EON: insn = aarch64_insn_get_eon_value(); break; case AARCH64_INSN_LOGIC_AND_SETFLAGS: insn = aarch64_insn_get_ands_value(); break; case AARCH64_INSN_LOGIC_BIC_SETFLAGS: insn = aarch64_insn_get_bics_value(); break; default: pr_err("%s: unknown logical encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } switch (variant) { case AARCH64_INSN_VARIANT_32BIT: if (shift & ~(SZ_32 - 1)) { pr_err("%s: invalid shift encoding %d\n", __func__, shift); return AARCH64_BREAK_FAULT; } break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT; if (shift & ~(SZ_64 - 1)) { pr_err("%s: invalid shift encoding %d\n", __func__, shift); return AARCH64_BREAK_FAULT; } break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift); } /* * MOV (register) is architecturally an alias of ORR (shifted register) where * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m> */ u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, enum aarch64_insn_register src, enum aarch64_insn_variant variant) { return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR, src, 0, variant, AARCH64_INSN_LOGIC_ORR); } u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr, enum aarch64_insn_register reg, enum aarch64_insn_adr_type type) { u32 insn; s32 offset; switch (type) { case AARCH64_INSN_ADR_TYPE_ADR: insn = aarch64_insn_get_adr_value(); offset = addr - pc; break; case AARCH64_INSN_ADR_TYPE_ADRP: insn = aarch64_insn_get_adrp_value(); offset = (addr - ALIGN_DOWN(pc, SZ_4K)) >> 12; break; default: pr_err("%s: unknown adr encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } if (offset < -SZ_1M || offset >= SZ_1M) return AARCH64_BREAK_FAULT; insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, reg); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn, offset); } /* * Decode the imm field of a branch, and return the byte offset as a * signed value (so it can be used when computing a new branch * target). */ s32 aarch64_get_branch_offset(u32 insn) { s32 imm; if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) { imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn); return (imm << 6) >> 4; } if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) || aarch64_insn_is_bcond(insn)) { imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_19, insn); return (imm << 13) >> 11; } if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn)) { imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_14, insn); return (imm << 18) >> 16; } /* Unhandled instruction */ BUG(); } /* * Encode the displacement of a branch in the imm field and return the * updated instruction. */ u32 aarch64_set_branch_offset(u32 insn, s32 offset) { if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn, offset >> 2); if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) || aarch64_insn_is_bcond(insn)) return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn, offset >> 2); if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn)) return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_14, insn, offset >> 2); /* Unhandled instruction */ BUG(); } s32 aarch64_insn_adrp_get_offset(u32 insn) { BUG_ON(!aarch64_insn_is_adrp(insn)); return aarch64_insn_decode_immediate(AARCH64_INSN_IMM_ADR, insn) << 12; } u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset) { BUG_ON(!aarch64_insn_is_adrp(insn)); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn, offset >> 12); } /* * Extract the Op/CR data from a msr/mrs instruction. */ u32 aarch64_insn_extract_system_reg(u32 insn) { return (insn & 0x1FFFE0) >> 5; } bool aarch32_insn_is_wide(u32 insn) { return insn >= 0xe800; } /* * Macros/defines for extracting register numbers from instruction. */ u32 aarch32_insn_extract_reg_num(u32 insn, int offset) { return (insn & (0xf << offset)) >> offset; } #define OPC2_MASK 0x7 #define OPC2_OFFSET 5 u32 aarch32_insn_mcr_extract_opc2(u32 insn) { return (insn & (OPC2_MASK << OPC2_OFFSET)) >> OPC2_OFFSET; } #define CRM_MASK 0xf u32 aarch32_insn_mcr_extract_crm(u32 insn) { return insn & CRM_MASK; } static bool range_of_ones(u64 val) { /* Doesn't handle full ones or full zeroes */ u64 sval = val >> __ffs64(val); /* One of Sean Eron Anderson's bithack tricks */ return ((sval + 1) & (sval)) == 0; } static u32 aarch64_encode_immediate(u64 imm, enum aarch64_insn_variant variant, u32 insn) { unsigned int immr, imms, n, ones, ror, esz, tmp; u64 mask; switch (variant) { case AARCH64_INSN_VARIANT_32BIT: esz = 32; break; case AARCH64_INSN_VARIANT_64BIT: insn |= AARCH64_INSN_SF_BIT; esz = 64; break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } mask = GENMASK(esz - 1, 0); /* Can't encode full zeroes, full ones, or value wider than the mask */ if (!imm || imm == mask || imm & ~mask) return AARCH64_BREAK_FAULT; /* * Inverse of Replicate(). Try to spot a repeating pattern * with a pow2 stride. */ for (tmp = esz / 2; tmp >= 2; tmp /= 2) { u64 emask = BIT(tmp) - 1; if ((imm & emask) != ((imm >> tmp) & emask)) break; esz = tmp; mask = emask; } /* N is only set if we're encoding a 64bit value */ n = esz == 64; /* Trim imm to the element size */ imm &= mask; /* That's how many ones we need to encode */ ones = hweight64(imm); /* * imms is set to (ones - 1), prefixed with a string of ones * and a zero if they fit. Cap it to 6 bits. */ imms = ones - 1; imms |= 0xf << ffs(esz); imms &= BIT(6) - 1; /* Compute the rotation */ if (range_of_ones(imm)) { /* * Pattern: 0..01..10..0 * * Compute how many rotate we need to align it right */ ror = __ffs64(imm); } else { /* * Pattern: 0..01..10..01..1 * * Fill the unused top bits with ones, and check if * the result is a valid immediate (all ones with a * contiguous ranges of zeroes). */ imm |= ~mask; if (!range_of_ones(~imm)) return AARCH64_BREAK_FAULT; /* * Compute the rotation to get a continuous set of * ones, with the first bit set at position 0 */ ror = fls64(~imm); } /* * immr is the number of bits we need to rotate back to the * original set of ones. Note that this is relative to the * element size... */ immr = (esz - ror) % esz; insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_N, insn, n); insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_R, insn, immr); return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, imms); } u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type, enum aarch64_insn_variant variant, enum aarch64_insn_register Rn, enum aarch64_insn_register Rd, u64 imm) { u32 insn; switch (type) { case AARCH64_INSN_LOGIC_AND: insn = aarch64_insn_get_and_imm_value(); break; case AARCH64_INSN_LOGIC_ORR: insn = aarch64_insn_get_orr_imm_value(); break; case AARCH64_INSN_LOGIC_EOR: insn = aarch64_insn_get_eor_imm_value(); break; case AARCH64_INSN_LOGIC_AND_SETFLAGS: insn = aarch64_insn_get_ands_imm_value(); break; default: pr_err("%s: unknown logical encoding %d\n", __func__, type); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, Rd); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, Rn); return aarch64_encode_immediate(imm, variant, insn); } u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant, enum aarch64_insn_register Rm, enum aarch64_insn_register Rn, enum aarch64_insn_register Rd, u8 lsb) { u32 insn; insn = aarch64_insn_get_extr_value(); switch (variant) { case AARCH64_INSN_VARIANT_32BIT: if (lsb > 31) return AARCH64_BREAK_FAULT; break; case AARCH64_INSN_VARIANT_64BIT: if (lsb > 63) return AARCH64_BREAK_FAULT; insn |= AARCH64_INSN_SF_BIT; insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_N, insn, 1); break; default: pr_err("%s: unknown variant encoding %d\n", __func__, variant); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, lsb); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, Rd); insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, Rn); return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm); } u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) { u32 opt; u32 insn; switch (type) { case AARCH64_INSN_MB_SY: opt = 0xf; break; case AARCH64_INSN_MB_ST: opt = 0xe; break; case AARCH64_INSN_MB_LD: opt = 0xd; break; case AARCH64_INSN_MB_ISH: opt = 0xb; break; case AARCH64_INSN_MB_ISHST: opt = 0xa; break; case AARCH64_INSN_MB_ISHLD: opt = 0x9; break; case AARCH64_INSN_MB_NSH: opt = 0x7; break; case AARCH64_INSN_MB_NSHST: opt = 0x6; break; case AARCH64_INSN_MB_NSHLD: opt = 0x5; break; default: pr_err("%s: unknown dmb type %d\n", __func__, type); return AARCH64_BREAK_FAULT; } insn = aarch64_insn_get_dmb_value(); insn &= ~GENMASK(11, 8); insn |= (opt << 8); return insn; } u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result, enum aarch64_insn_system_register sysreg) { u32 insn = aarch64_insn_get_mrs_value(); insn &= ~GENMASK(19, 0); insn |= sysreg << 5; return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, result); } |
| 14 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 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 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains the procedures for the handling of select and poll * * Created for Linux based loosely upon Mathius Lattner's minix * patches by Peter MacDonald. Heavily edited by Linus. * * 4 February 1994 * COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS * flag set in its personality we do *not* modify the given timeout * parameter to reflect time remaining. * * 24 January 2000 * Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation * of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian). */ #include <linux/compat.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/rt.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/personality.h> /* for STICKY_TIMEOUTS */ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/rcupdate.h> #include <linux/hrtimer.h> #include <linux/freezer.h> #include <net/busy_poll.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> /* * Estimate expected accuracy in ns from a timeval. * * After quite a bit of churning around, we've settled on * a simple thing of taking 0.1% of the timeout as the * slack, with a cap of 100 msec. * "nice" tasks get a 0.5% slack instead. * * Consider this comment an open invitation to come up with even * better solutions.. */ #define MAX_SLACK (100 * NSEC_PER_MSEC) static long __estimate_accuracy(struct timespec64 *tv) { long slack; int divfactor = 1000; if (tv->tv_sec < 0) return 0; if (task_nice(current) > 0) divfactor = divfactor / 5; if (tv->tv_sec > MAX_SLACK / (NSEC_PER_SEC/divfactor)) return MAX_SLACK; slack = tv->tv_nsec / divfactor; slack += tv->tv_sec * (NSEC_PER_SEC/divfactor); if (slack > MAX_SLACK) return MAX_SLACK; return slack; } u64 select_estimate_accuracy(struct timespec64 *tv) { u64 ret; struct timespec64 now; u64 slack = current->timer_slack_ns; if (slack == 0) return 0; ktime_get_ts64(&now); now = timespec64_sub(*tv, now); ret = __estimate_accuracy(&now); if (ret < slack) return slack; return ret; } struct poll_table_page { struct poll_table_page * next; struct poll_table_entry * entry; struct poll_table_entry entries[]; }; #define POLL_TABLE_FULL(table) \ ((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table)) /* * Ok, Peter made a complicated, but straightforward multiple_wait() function. * I have rewritten this, taking some shortcuts: This code may not be easy to * follow, but it should be free of race-conditions, and it's practical. If you * understand what I'm doing here, then you understand how the linux * sleep/wakeup mechanism works. * * Two very simple procedures, poll_wait() and poll_freewait() make all the * work. poll_wait() is an inline-function defined in <linux/poll.h>, * as all select/poll functions have to call it to add an entry to the * poll table. */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p); void poll_initwait(struct poll_wqueues *pwq) { init_poll_funcptr(&pwq->pt, __pollwait); pwq->polling_task = current; pwq->triggered = 0; pwq->error = 0; pwq->table = NULL; pwq->inline_index = 0; } EXPORT_SYMBOL(poll_initwait); static void free_poll_entry(struct poll_table_entry *entry) { remove_wait_queue(entry->wait_address, &entry->wait); fput(entry->filp); } void poll_freewait(struct poll_wqueues *pwq) { struct poll_table_page * p = pwq->table; int i; for (i = 0; i < pwq->inline_index; i++) free_poll_entry(pwq->inline_entries + i); while (p) { struct poll_table_entry * entry; struct poll_table_page *old; entry = p->entry; do { entry--; free_poll_entry(entry); } while (entry > p->entries); old = p; p = p->next; free_page((unsigned long) old); } } EXPORT_SYMBOL(poll_freewait); static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) { struct poll_table_page *table = p->table; if (p->inline_index < N_INLINE_POLL_ENTRIES) return p->inline_entries + p->inline_index++; if (!table || POLL_TABLE_FULL(table)) { struct poll_table_page *new_table; new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL); if (!new_table) { p->error = -ENOMEM; return NULL; } new_table->entry = new_table->entries; new_table->next = table; p->table = new_table; table = new_table; } return table->entry++; } static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_wqueues *pwq = wait->private; DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); /* * Although this function is called under waitqueue lock, LOCK * doesn't imply write barrier and the users expect write * barrier semantics on wakeup functions. The following * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() * and is paired with smp_store_mb() in poll_schedule_timeout. */ smp_wmb(); pwq->triggered = 1; /* * Perform the default wake up operation using a dummy * waitqueue. * * TODO: This is hacky but there currently is no interface to * pass in @sync. @sync is scheduled to be removed and once * that happens, wake_up_process() can be used directly. */ return default_wake_function(&dummy_wait, mode, sync, key); } static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_table_entry *entry; entry = container_of(wait, struct poll_table_entry, wait); if (key && !(key_to_poll(key) & entry->key)) return 0; return __pollwake(wait, mode, sync, key); } /* Add a new entry */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt); struct poll_table_entry *entry = poll_get_entry(pwq); if (!entry) return; entry->filp = get_file(filp); entry->wait_address = wait_address; entry->key = p->_key; init_waitqueue_func_entry(&entry->wait, pollwake); entry->wait.private = pwq; add_wait_queue(wait_address, &entry->wait); } static int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack) { int rc = -EINTR; set_current_state(state); if (!pwq->triggered) rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * Prepare for the next iteration. * * The following smp_store_mb() serves two purposes. First, it's * the counterpart rmb of the wmb in pollwake() such that data * written before wake up is always visible after wake up. * Second, the full barrier guarantees that triggered clearing * doesn't pass event check of the next iteration. Note that * this problem doesn't exist for the first iteration as * add_wait_queue() has full barrier semantics. */ smp_store_mb(pwq->triggered, 0); return rc; } /** * poll_select_set_timeout - helper function to setup the timeout value * @to: pointer to timespec64 variable for the final timeout * @sec: seconds (from user space) * @nsec: nanoseconds (from user space) * * Note, we do not use a timespec for the user space value here, That * way we can use the function for timeval and compat interfaces as well. * * Returns -EINVAL if sec/nsec are not normalized. Otherwise 0. */ int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec) { struct timespec64 ts = {.tv_sec = sec, .tv_nsec = nsec}; if (!timespec64_valid(&ts)) return -EINVAL; /* Optimize for the zero timeout value here */ if (!sec && !nsec) { to->tv_sec = to->tv_nsec = 0; } else { ktime_get_ts64(to); *to = timespec64_add_safe(*to, ts); } return 0; } enum poll_time_type { PT_TIMEVAL = 0, PT_OLD_TIMEVAL = 1, PT_TIMESPEC = 2, PT_OLD_TIMESPEC = 3, }; static int poll_select_finish(struct timespec64 *end_time, void __user *p, enum poll_time_type pt_type, int ret) { struct timespec64 rts; restore_saved_sigmask_unless(ret == -ERESTARTNOHAND); if (!p) return ret; if (current->personality & STICKY_TIMEOUTS) goto sticky; /* No update for zero timeout */ if (!end_time->tv_sec && !end_time->tv_nsec) return ret; ktime_get_ts64(&rts); rts = timespec64_sub(*end_time, rts); if (rts.tv_sec < 0) rts.tv_sec = rts.tv_nsec = 0; switch (pt_type) { case PT_TIMEVAL: { struct __kernel_old_timeval rtv; if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec)) memset(&rtv, 0, sizeof(rtv)); rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_OLD_TIMEVAL: { struct old_timeval32 rtv; rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_TIMESPEC: if (!put_timespec64(&rts, p)) return ret; break; case PT_OLD_TIMESPEC: if (!put_old_timespec32(&rts, p)) return ret; break; default: BUG(); } /* * If an application puts its timeval in read-only memory, we * don't want the Linux-specific update to the timeval to * cause a fault after the select has completed * successfully. However, because we're not updating the * timeval, we can't restart the system call. */ sticky: if (ret == -ERESTARTNOHAND) ret = -EINTR; return ret; } /* * Scalable version of the fd_set. */ typedef struct { unsigned long *in, *out, *ex; unsigned long *res_in, *res_out, *res_ex; } fd_set_bits; /* * How many longwords for "nr" bits? */ #define FDS_BITPERLONG (8*sizeof(long)) #define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG) #define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long)) /* * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned. */ static inline int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { nr = FDS_BYTES(nr); if (ufdset) return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0; memset(fdset, 0, nr); return 0; } static inline unsigned long __must_check set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { if (ufdset) return __copy_to_user(ufdset, fdset, FDS_BYTES(nr)); return 0; } static inline void zero_fd_set(unsigned long nr, unsigned long *fdset) { memset(fdset, 0, FDS_BYTES(nr)); } #define FDS_IN(fds, n) (fds->in + n) #define FDS_OUT(fds, n) (fds->out + n) #define FDS_EX(fds, n) (fds->ex + n) #define BITS(fds, n) (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n)) static int max_select_fd(unsigned long n, fd_set_bits *fds) { unsigned long *open_fds; unsigned long set; int max; struct fdtable *fdt; /* handle last in-complete long-word first */ set = ~(~0UL << (n & (BITS_PER_LONG-1))); n /= BITS_PER_LONG; fdt = files_fdtable(current->files); open_fds = fdt->open_fds + n; max = 0; if (set) { set &= BITS(fds, n); if (set) { if (!(set & ~*open_fds)) goto get_max; return -EBADF; } } while (n) { open_fds--; n--; set = BITS(fds, n); if (!set) continue; if (set & ~*open_fds) return -EBADF; if (max) continue; get_max: do { max++; set >>= 1; } while (set); max += n * BITS_PER_LONG; } return max; } #define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR |\ EPOLLNVAL) #define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR |\ EPOLLNVAL) #define POLLEX_SET (EPOLLPRI | EPOLLNVAL) static inline void wait_key_set(poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, __poll_t ll_flag) { wait->_key = POLLEX_SET | ll_flag; if (in & bit) wait->_key |= POLLIN_SET; if (out & bit) wait->_key |= POLLOUT_SET; } static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; poll_table *wait; int retval, i, timed_out = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; rcu_read_lock(); retval = max_select_fd(n, fds); rcu_read_unlock(); if (retval < 0) return retval; n = retval; poll_initwait(&table); wait = &table.pt; if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { wait->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; bool can_busy_loop = false; inp = fds->in; outp = fds->out; exp = fds->ex; rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex; for (i = 0; i < n; ++rinp, ++routp, ++rexp) { unsigned long in, out, ex, all_bits, bit = 1, j; unsigned long res_in = 0, res_out = 0, res_ex = 0; __poll_t mask; in = *inp++; out = *outp++; ex = *exp++; all_bits = in | out | ex; if (all_bits == 0) { i += BITS_PER_LONG; continue; } for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) { struct fd f; if (i >= n) break; if (!(bit & all_bits)) continue; mask = EPOLLNVAL; f = fdget(i); if (fd_file(f)) { wait_key_set(wait, in, out, bit, busy_flag); mask = vfs_poll(fd_file(f), wait); fdput(f); } if ((mask & POLLIN_SET) && (in & bit)) { res_in |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLOUT_SET) && (out & bit)) { res_out |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLEX_SET) && (ex & bit)) { res_ex |= bit; retval++; wait->_qproc = NULL; } /* got something, stop busy polling */ if (retval) { can_busy_loop = false; busy_flag = 0; /* * only remember a returned * POLL_BUSY_LOOP if we asked for it */ } else if (busy_flag & mask) can_busy_loop = true; } if (res_in) *rinp = res_in; if (res_out) *routp = res_out; if (res_ex) *rexp = res_ex; cond_resched(); } wait->_qproc = NULL; if (retval || timed_out || signal_pending(current)) break; if (table.error) { retval = table.error; break; } /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } poll_freewait(&table); return retval; } /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int ret, max_fds; size_t size, alloc_size; struct fdtable *fdt; /* Allocate small arguments on the stack to save memory and be faster */ long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; ret = -EINVAL; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { /* Not enough space in on-stack array; must use kmalloc */ ret = -ENOMEM; if (size > (SIZE_MAX / 6)) goto out_nofds; alloc_size = 6 * size; bits = kvmalloc(alloc_size, GFP_KERNEL); if (!bits) goto out_nofds; } fds.in = bits; fds.out = bits + size; fds.ex = bits + 2*size; fds.res_in = bits + 3*size; fds.res_out = bits + 4*size; fds.res_ex = bits + 5*size; if ((ret = get_fd_set(n, inp, fds.in)) || (ret = get_fd_set(n, outp, fds.out)) || (ret = get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (set_fd_set(n, inp, fds.res_in) || set_fd_set(n, outp, fds.res_out) || set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kvfree(bits); out_nofds: return ret; } static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { struct timespec64 end_time, *to = NULL; struct __kernel_old_timeval tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_TIMEVAL, ret); } SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_old_timeval __user *, tvp) { return kern_select(n, inp, outp, exp, tvp); } static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, void __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } /* * Most architectures can't handle 7-argument syscalls. So we provide a * 6-argument version where the sixth argument is a pointer to a structure * which has a pointer to the sigset_t itself followed by a size_t containing * the sigset size. */ struct sigset_argpack { sigset_t __user *p; size_t size; }; static inline int get_sigset_argpack(struct sigset_argpack *to, struct sigset_argpack __user *from) { // the path is hot enough for overhead of copy_from_user() to matter if (from) { if (can_do_masked_user_access()) from = masked_user_access_begin(from); else if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE6(pselect6_time32, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_OLD_TIMESPEC); } #endif #ifdef __ARCH_WANT_SYS_OLD_SELECT struct sel_arg_struct { unsigned long n; fd_set __user *inp, *outp, *exp; struct __kernel_old_timeval __user *tvp; }; SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) { struct sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return kern_select(a.n, a.inp, a.outp, a.exp, a.tvp); } #endif struct poll_list { struct poll_list *next; unsigned int len; struct pollfd entries[] __counted_by(len); }; #define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd)) /* * Fish for pollable events on the pollfd->fd file descriptor. We're only * interested in events matching the pollfd->events mask, and the result * matching that mask is both recorded in pollfd->revents and returned. The * pwait poll_table will be used by the fd-provided poll handler for waiting, * if pwait->_qproc is non-NULL. */ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait, bool *can_busy_poll, __poll_t busy_flag) { int fd = pollfd->fd; __poll_t mask = 0, filter; struct fd f; if (fd < 0) goto out; mask = EPOLLNVAL; f = fdget(fd); if (!fd_file(f)) goto out; /* userland u16 ->events contains POLL... bitmap */ filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP; pwait->_key = filter | busy_flag; mask = vfs_poll(fd_file(f), pwait); if (mask & busy_flag) *can_busy_poll = true; mask &= filter; /* Mask out unneeded events. */ fdput(f); out: /* ... and so does ->revents */ pollfd->revents = mangle_poll(mask); return mask; } static int do_poll(struct poll_list *list, struct poll_wqueues *wait, struct timespec64 *end_time) { poll_table* pt = &wait->pt; ktime_t expire, *to = NULL; int timed_out = 0, count = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; /* Optimise the no-wait case */ if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { pt->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); for (;;) { struct poll_list *walk; bool can_busy_loop = false; for (walk = list; walk != NULL; walk = walk->next) { struct pollfd * pfd, * pfd_end; pfd = walk->entries; pfd_end = pfd + walk->len; for (; pfd != pfd_end; pfd++) { /* * Fish for events. If we found one, record it * and kill poll_table->_qproc, so we don't * needlessly register any other waiters after * this. They'll get immediately deregistered * when we break out and return. */ if (do_pollfd(pfd, pt, &can_busy_loop, busy_flag)) { count++; pt->_qproc = NULL; /* found something, stop busy polling */ busy_flag = 0; can_busy_loop = false; } } } /* * All waiters have already been registered, so don't provide * a poll_table->_qproc to them on the next loop iteration. */ pt->_qproc = NULL; if (!count) { count = wait->error; if (signal_pending(current)) count = -ERESTARTNOHAND; } if (count || timed_out) break; /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } return count; } #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \ sizeof(struct pollfd)) static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, struct timespec64 *end_time) { struct poll_wqueues table; int err = -EFAULT, fdcount; /* Allocate small arguments on the stack to save memory and be faster - use long to make sure the buffer is aligned properly on 64 bit archs to avoid unaligned access */ long stack_pps[POLL_STACK_ALLOC/sizeof(long)]; struct poll_list *const head = (struct poll_list *)stack_pps; struct poll_list *walk = head; unsigned int todo = nfds; unsigned int len; if (nfds > rlimit(RLIMIT_NOFILE)) return -EINVAL; len = min_t(unsigned int, nfds, N_STACK_PPS); for (;;) { walk->next = NULL; walk->len = len; if (!len) break; if (copy_from_user(walk->entries, ufds + nfds-todo, sizeof(struct pollfd) * walk->len)) goto out_fds; if (walk->len >= todo) break; todo -= walk->len; len = min(todo, POLLFD_PER_PAGE); walk = walk->next = kmalloc(struct_size(walk, entries, len), GFP_KERNEL); if (!walk) { err = -ENOMEM; goto out_fds; } } poll_initwait(&table); fdcount = do_poll(head, &table, end_time); poll_freewait(&table); if (!user_write_access_begin(ufds, nfds * sizeof(*ufds))) goto out_fds; for (walk = head; walk; walk = walk->next) { struct pollfd *fds = walk->entries; unsigned int j; for (j = walk->len; j; fds++, ufds++, j--) unsafe_put_user(fds->revents, &ufds->revents, Efault); } user_write_access_end(); err = fdcount; out_fds: walk = head->next; while (walk) { struct poll_list *pos = walk; walk = walk->next; kfree(pos); } return err; Efault: user_write_access_end(); err = -EFAULT; goto out_fds; } static long do_restart_poll(struct restart_block *restart_block) { struct pollfd __user *ufds = restart_block->poll.ufds; int nfds = restart_block->poll.nfds; struct timespec64 *to = NULL, end_time; int ret; if (restart_block->poll.has_timeout) { end_time.tv_sec = restart_block->poll.tv_sec; end_time.tv_nsec = restart_block->poll.tv_nsec; to = &end_time; } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) ret = set_restart_fn(restart_block, do_restart_poll); return ret; } SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout_msecs) { struct timespec64 end_time, *to = NULL; int ret; if (timeout_msecs >= 0) { to = &end_time; poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC, NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC)); } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) { struct restart_block *restart_block; restart_block = ¤t->restart_block; restart_block->poll.ufds = ufds; restart_block->poll.nfds = nfds; if (timeout_msecs >= 0) { restart_block->poll.tv_sec = end_time.tv_sec; restart_block->poll.tv_nsec = end_time.tv_nsec; restart_block->poll.has_timeout = 1; } else restart_block->poll.has_timeout = 0; ret = set_restart_fn(restart_block, do_restart_poll); } return ret; } SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif #ifdef CONFIG_COMPAT #define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to * 64-bit unsigned longs. */ static int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (ufdset) { return compat_get_bitmap(fdset, ufdset, nr); } else { zero_fd_set(nr, fdset); return 0; } } static int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (!ufdset) return 0; return compat_put_bitmap(ufdset, fdset, nr); } /* * This is a virtual copy of sys_select from fs/select.c and probably * should be compared to it from time to time */ /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ static int compat_core_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int size, max_fds, ret = -EINVAL; struct fdtable *fdt; long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { bits = kmalloc_array(6, size, GFP_KERNEL); ret = -ENOMEM; if (!bits) goto out_nofds; } fds.in = (unsigned long *) bits; fds.out = (unsigned long *) (bits + size); fds.ex = (unsigned long *) (bits + 2*size); fds.res_in = (unsigned long *) (bits + 3*size); fds.res_out = (unsigned long *) (bits + 4*size); fds.res_ex = (unsigned long *) (bits + 5*size); if ((ret = compat_get_fd_set(n, inp, fds.in)) || (ret = compat_get_fd_set(n, outp, fds.out)) || (ret = compat_get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (compat_set_fd_set(n, inp, fds.res_in) || compat_set_fd_set(n, outp, fds.res_out) || compat_set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kfree(bits); out_nofds: return ret; } static int do_compat_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp) { struct timespec64 end_time, *to = NULL; struct old_timeval32 tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_OLD_TIMEVAL, ret); } COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timeval32 __user *, tvp) { return do_compat_select(n, inp, outp, exp, tvp); } struct compat_sel_arg_struct { compat_ulong_t n; compat_uptr_t inp; compat_uptr_t outp; compat_uptr_t exp; compat_uptr_t tvp; }; COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) { struct compat_sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return do_compat_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), compat_ptr(a.exp), compat_ptr(a.tvp)); } static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, void __user *tsp, compat_sigset_t __user *sigmask, compat_size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } struct compat_sigset_argpack { compat_uptr_t p; compat_size_t size; }; static inline int get_compat_sigset_argpack(struct compat_sigset_argpack *to, struct compat_sigset_argpack __user *from) { if (from) { if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_OLD_TIMESPEC); } #endif #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif /* New compat syscall for 64 bit time_t*/ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #endif |
| 2 2 1 1 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2019 Arm Ltd. #include <linux/arm-smccc.h> #include <linux/kvm_host.h> #include <linux/sched/stat.h> #include <asm/kvm_mmu.h> #include <asm/pvclock-abi.h> #include <kvm/arm_hypercalls.h> void kvm_update_stolen_time(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; u64 base = vcpu->arch.steal.base; u64 last_steal = vcpu->arch.steal.last_steal; u64 offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time); u64 steal = 0; int idx; if (base == INVALID_GPA) return; idx = srcu_read_lock(&kvm->srcu); if (!kvm_get_guest(kvm, base + offset, steal)) { steal = le64_to_cpu(steal); vcpu->arch.steal.last_steal = READ_ONCE(current->sched_info.run_delay); steal += vcpu->arch.steal.last_steal - last_steal; kvm_put_guest(kvm, base + offset, cpu_to_le64(steal)); } srcu_read_unlock(&kvm->srcu, idx); } long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) { u32 feature = smccc_get_arg1(vcpu); long val = SMCCC_RET_NOT_SUPPORTED; switch (feature) { case ARM_SMCCC_HV_PV_TIME_FEATURES: case ARM_SMCCC_HV_PV_TIME_ST: if (vcpu->arch.steal.base != INVALID_GPA) val = SMCCC_RET_SUCCESS; break; } return val; } gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) { struct pvclock_vcpu_stolen_time init_values = {}; struct kvm *kvm = vcpu->kvm; u64 base = vcpu->arch.steal.base; if (base == INVALID_GPA) return base; /* * Start counting stolen time from the time the guest requests * the feature enabled. */ vcpu->arch.steal.last_steal = current->sched_info.run_delay; kvm_write_guest_lock(kvm, base, &init_values, sizeof(init_values)); return base; } bool kvm_arm_pvtime_supported(void) { return !!sched_info_on(); } int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { u64 __user *user = (u64 __user *)attr->addr; struct kvm *kvm = vcpu->kvm; u64 ipa; int ret = 0; int idx; if (!kvm_arm_pvtime_supported() || attr->attr != KVM_ARM_VCPU_PVTIME_IPA) return -ENXIO; if (get_user(ipa, user)) return -EFAULT; if (!IS_ALIGNED(ipa, 64)) return -EINVAL; if (vcpu->arch.steal.base != INVALID_GPA) return -EEXIST; /* Check the address is in a valid memslot */ idx = srcu_read_lock(&kvm->srcu); if (kvm_is_error_hva(gfn_to_hva(kvm, ipa >> PAGE_SHIFT))) ret = -EINVAL; srcu_read_unlock(&kvm->srcu, idx); if (!ret) vcpu->arch.steal.base = ipa; return ret; } int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { u64 __user *user = (u64 __user *)attr->addr; u64 ipa; if (!kvm_arm_pvtime_supported() || attr->attr != KVM_ARM_VCPU_PVTIME_IPA) return -ENXIO; ipa = vcpu->arch.steal.base; if (put_user(ipa, user)) return -EFAULT; return 0; } int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VCPU_PVTIME_IPA: if (kvm_arm_pvtime_supported()) return 0; } return -ENXIO; } |
| 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Fast Userspace Mutexes (which I call "Futexes!"). * (C) Rusty Russell, IBM 2002 * * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar * (C) Copyright 2003 Red Hat Inc, All Rights Reserved * * Removed page pinning, fix privately mapped COW pages and other cleanups * (C) Copyright 2003, 2004 Jamie Lokier * * Robust futex support started by Ingo Molnar * (C) Copyright 2006 Red Hat Inc, All Rights Reserved * Thanks to Thomas Gleixner for suggestions, analysis and fixes. * * PI-futex support started by Ingo Molnar and Thomas Gleixner * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * PRIVATE futexes by Eric Dumazet * Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com> * * Requeue-PI support by Darren Hart <dvhltc@us.ibm.com> * Copyright (C) IBM Corporation, 2009 * Thanks to Thomas Gleixner for conceptual design and careful reviews. * * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly * enough at me, Linus for the original (flawed) idea, Matthew * Kirkwood for proof-of-concept implementation. * * "The futexes are also cursed." * "But they come in a choice of three flavours!" */ #include <linux/compat.h> #include <linux/jhash.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/plist.h> #include <linux/memblock.h> #include <linux/fault-inject.h> #include <linux/slab.h> #include "futex.h" #include "../locking/rtmutex_common.h" /* * The base of the bucket array and its size are always used together * (after initialization only in futex_hash()), so ensure that they * reside in the same cacheline. */ static struct { struct futex_hash_bucket *queues; unsigned long hashsize; } __futex_data __read_mostly __aligned(2*sizeof(long)); #define futex_queues (__futex_data.queues) #define futex_hashsize (__futex_data.hashsize) /* * Fault injections for futexes. */ #ifdef CONFIG_FAIL_FUTEX static struct { struct fault_attr attr; bool ignore_private; } fail_futex = { .attr = FAULT_ATTR_INITIALIZER, .ignore_private = false, }; static int __init setup_fail_futex(char *str) { return setup_fault_attr(&fail_futex.attr, str); } __setup("fail_futex=", setup_fail_futex); bool should_fail_futex(bool fshared) { if (fail_futex.ignore_private && !fshared) return false; return should_fail(&fail_futex.attr, 1); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_futex_debugfs(void) { umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; dir = fault_create_debugfs_attr("fail_futex", NULL, &fail_futex.attr); if (IS_ERR(dir)) return PTR_ERR(dir); debugfs_create_bool("ignore-private", mode, dir, &fail_futex.ignore_private); return 0; } late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ #endif /* CONFIG_FAIL_FUTEX */ /** * futex_hash - Return the hash bucket in the global hash * @key: Pointer to the futex key for which the hash is calculated * * We hash on the keys returned from get_futex_key (see below) and return the * corresponding hash bucket in the global hash. */ struct futex_hash_bucket *futex_hash(union futex_key *key) { u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, key->both.offset); return &futex_queues[hash & (futex_hashsize - 1)]; } /** * futex_setup_timer - set up the sleeping hrtimer. * @time: ptr to the given timeout value * @timeout: the hrtimer_sleeper structure to be set up * @flags: futex flags * @range_ns: optional range in ns * * Return: Initialized hrtimer_sleeper structure or NULL if no timeout * value given */ struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns) { if (!time) return NULL; hrtimer_init_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). */ hrtimer_set_expires_range_ns(&timeout->timer, *time, range_ns); return timeout; } /* * Generate a machine wide unique identifier for this inode. * * This relies on u64 not wrapping in the life-time of the machine; which with * 1ns resolution means almost 585 years. * * This further relies on the fact that a well formed program will not unmap * the file while it has a (shared) futex waiting on it. This mapping will have * a file reference which pins the mount and inode. * * If for some reason an inode gets evicted and read back in again, it will get * a new sequence number and will _NOT_ match, even though it is the exact same * file. * * It is important that futex_match() will never have a false-positive, esp. * for PI futexes that can mess up the state. The above argues that false-negatives * are only possible for malformed programs. */ static u64 get_inode_sequence_number(struct inode *inode) { static atomic64_t i_seq; u64 old; /* Does the inode already have a sequence number? */ old = atomic64_read(&inode->i_sequence); if (likely(old)) return old; for (;;) { u64 new = atomic64_add_return(1, &i_seq); if (WARN_ON_ONCE(!new)) continue; old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new); if (old) return old; return new; } } /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex * @flags: FLAGS_* * @key: address where result is stored. * @rw: mapping needs to be read/write (values: FUTEX_READ, * FUTEX_WRITE) * * Return: a negative error code or 0 * * The key words are stored in @key on success. * * For shared mappings (when @fshared), the key is: * * ( inode->i_sequence, page->index, offset_within_page ) * * [ also see get_inode_sequence_number() ] * * For private mappings (or when !@fshared), the key is: * * ( current->mm, address, 0 ) * * This allows (cross process, where applicable) identification of the futex * without keeping the page pinned for the duration of the FUTEX_WAIT. * * lock_page() might sleep, the caller should not hold a spinlock. */ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; struct page *page; struct folio *folio; struct address_space *mapping; int err, ro = 0; bool fshared; fshared = flags & FLAGS_SHARED; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; if (unlikely((address % sizeof(u32)) != 0)) return -EINVAL; address -= key->both.offset; if (unlikely(!access_ok(uaddr, sizeof(u32)))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) return -EFAULT; /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs * virtual address, we dont even have to find the underlying vma. * Note : We do have to check 'uaddr' is a valid user address, * but access_ok() should be faster than find_vma() */ if (!fshared) { /* * On no-MMU, shared futexes are treated as private, therefore * we must not include the current process in the key. Since * there is only one address space, the address is a unique key * on its own. */ if (IS_ENABLED(CONFIG_MMU)) key->private.mm = mm; else key->private.mm = NULL; key->private.address = address; return 0; } again: /* Ignore any VERIFY_READ mapping (futex common case) */ if (unlikely(should_fail_futex(true))) return -EFAULT; err = get_user_pages_fast(address, 1, FOLL_WRITE, &page); /* * If write access is not required (eg. FUTEX_WAIT), try * and get read-only access. */ if (err == -EFAULT && rw == FUTEX_READ) { err = get_user_pages_fast(address, 1, 0, &page); ro = 1; } if (err < 0) return err; else err = 0; /* * The treatment of mapping from this point on is critical. The folio * lock protects many things but in this context the folio lock * stabilizes mapping, prevents inode freeing in the shared * file-backed region case and guards against movement to swap cache. * * Strictly speaking the folio lock is not needed in all cases being * considered here and folio lock forces unnecessarily serialization. * From this point on, mapping will be re-verified if necessary and * folio lock will be acquired only if it is unavoidable * * Mapping checks require the folio so it is looked up now. For * anonymous pages, it does not matter if the folio is split * in the future as the key is based on the address. For * filesystem-backed pages, the precise page is required as the * index of the page determines the key. */ folio = page_folio(page); mapping = READ_ONCE(folio->mapping); /* * If folio->mapping is NULL, then it cannot be an anonymous * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast * found it, but truncated or holepunched or subjected to * invalidate_complete_page2 before we got the folio lock (also * cases which we are happy to fail). And we hold a reference, * so refcount care in invalidate_inode_page's remove_mapping * prevents drop_caches from setting mapping to NULL beneath us. * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for folio->mapping. */ if (unlikely(!mapping)) { int shmem_swizzled; /* * Folio lock is required to identify which special case above * applies. If this is really a shmem page then the folio lock * will prevent unexpected transitions. */ folio_lock(folio); shmem_swizzled = folio_test_swapcache(folio) || folio->mapping; folio_unlock(folio); folio_put(folio); if (shmem_swizzled) goto again; return -EFAULT; } /* * Private mappings are handled in a simple way. * * If the futex key is stored in anonymous memory, then the associated * object is the mm which is implicitly pinned by the calling process. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ if (folio_test_anon(folio)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. */ if (unlikely(should_fail_futex(true)) || ro) { err = -EFAULT; goto out; } key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; } else { struct inode *inode; /* * The associated futex object in this case is the inode and * the folio->mapping must be traversed. Ordinarily this should * be stabilised under folio lock but it's not strictly * necessary in this case as we just want to pin the inode, not * update i_pages or anything like that. * * The RCU read lock is taken as the inode is finally freed * under RCU. If the mapping still matches expectations then the * mapping->host can be safely accessed as being a valid inode. */ rcu_read_lock(); if (READ_ONCE(folio->mapping) != mapping) { rcu_read_unlock(); folio_put(folio); goto again; } inode = READ_ONCE(mapping->host); if (!inode) { rcu_read_unlock(); folio_put(folio); goto again; } key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); key->shared.pgoff = folio->index + folio_page_idx(folio, page); rcu_read_unlock(); } out: folio_put(folio); return err; } /** * fault_in_user_writeable() - Fault in user address and verify RW access * @uaddr: pointer to faulting user space address * * Slow path to fixup the fault we just took in the atomic write * access to @uaddr. * * We have no generic implementation of a non-destructive write to the * user address. We know that we faulted in the atomic pagefault * disabled section so we can as well avoid the #PF overhead by * calling get_user_pages() right away. */ int fault_in_user_writeable(u32 __user *uaddr) { struct mm_struct *mm = current->mm; int ret; mmap_read_lock(mm); ret = fixup_user_fault(mm, (unsigned long)uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(mm); return ret < 0 ? ret : 0; } /** * futex_top_waiter() - Return the highest priority waiter on a futex * @hb: the hash bucket the futex_q's reside in * @key: the futex key (to distinguish it from other futex futex_q's) * * Must be called with the hb lock held. */ struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key) { struct futex_q *this; plist_for_each_entry(this, &hb->chain, list) { if (futex_match(&this->key, key)) return this; } return NULL; } int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval) { int ret; pagefault_disable(); ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); pagefault_enable(); return ret; } int futex_get_value_locked(u32 *dest, u32 __user *from) { int ret; pagefault_disable(); ret = __get_user(*dest, from); pagefault_enable(); return ret ? -EFAULT : 0; } /** * wait_for_owner_exiting - Block until the owner has exited * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. */ void wait_for_owner_exiting(int ret, struct task_struct *exiting) { if (ret != -EBUSY) { WARN_ON_ONCE(exiting); return; } if (WARN_ON_ONCE(ret == -EBUSY && !exiting)) return; mutex_lock(&exiting->futex_exit_mutex); /* * No point in doing state checking here. If the waiter got here * while the task was in exec()->exec_futex_release() then it can * have any FUTEX_STATE_* value when the waiter has acquired the * mutex. OK, if running, EXITING or DEAD if it reached exit() * already. Highly unlikely and not a problem. Just one more round * through the futex maze. */ mutex_unlock(&exiting->futex_exit_mutex); put_task_struct(exiting); } /** * __futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be NULL and must be held by the caller. */ void __futex_unqueue(struct futex_q *q) { struct futex_hash_bucket *hb; if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list))) return; lockdep_assert_held(q->lock_ptr); hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); futex_hb_waiters_dec(hb); } /* The key must be already stored in q->key. */ struct futex_hash_bucket *futex_q_lock(struct futex_q *q) __acquires(&hb->lock) { struct futex_hash_bucket *hb; hb = futex_hash(&q->key); /* * Increment the counter before taking the lock so that * a potential waker won't miss a to-be-slept task that is * waiting for the spinlock. This is safe as all futex_q_lock() * users end up calling futex_queue(). Similarly, for housekeeping, * decrement the counter at futex_q_unlock() when some error has * occurred and we don't end up adding the task to the list. */ futex_hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; spin_lock(&hb->lock); return hb; } void futex_q_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock) { spin_unlock(&hb->lock); futex_hb_waiters_dec(hb); } void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) { int prio; /* * The priority used to register this element is * - either the real thread-priority for the real-time threads * (i.e. threads with a priority lower than MAX_RT_PRIO) * - or MAX_RT_PRIO for non-RT threads. * Thus, all RT-threads are woken first in priority order, and * the others are woken last, in FIFO order. */ prio = min(current->normal_prio, MAX_RT_PRIO); plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); q->task = current; } /** * futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be held by the caller. A call to futex_unqueue() must * be paired with exactly one earlier call to futex_queue(). * * Return: * - 1 - if the futex_q was still queued (and we removed unqueued it); * - 0 - if the futex_q was already removed by the waking thread */ int futex_unqueue(struct futex_q *q) { spinlock_t *lock_ptr; int ret = 0; /* In the common case we don't take the spinlock, which is nice. */ retry: /* * q->lock_ptr can change between this read and the following spin_lock. * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and * optimizing lock_ptr out of the logic below. */ lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and * spin_lock(), causing us to take the wrong lock. This * corrects the race condition. * * Reasoning goes like this: if we have the wrong lock, * q->lock_ptr must have changed (maybe several times) * between reading it and the spin_lock(). It can * change again after the spin_lock() but only if it was * already changed before the spin_lock(). It cannot, * however, change back to the original value. Therefore * we can detect whether we acquired the correct lock. */ if (unlikely(lock_ptr != q->lock_ptr)) { spin_unlock(lock_ptr); goto retry; } __futex_unqueue(q); BUG_ON(q->pi_state); spin_unlock(lock_ptr); ret = 1; } return ret; } /* * PI futexes can not be requeued and must remove themselves from the hash * bucket. The hash bucket lock (i.e. lock_ptr) is held. */ void futex_unqueue_pi(struct futex_q *q) { /* * If the lock was not acquired (due to timeout or signal) then the * rt_waiter is removed before futex_q is. If this is observed by * an unlocker after dropping the rtmutex wait lock and before * acquiring the hash bucket lock, then the unlocker dequeues the * futex_q from the hash bucket list to guarantee consistent state * vs. userspace. Therefore the dequeue here must be conditional. */ if (!plist_node_empty(&q->list)) __futex_unqueue(q); BUG_ON(!q->pi_state); put_pi_state(q->pi_state); q->pi_state = NULL; } /* Constants for the pending_op argument of handle_futex_death */ #define HANDLE_DEATH_PENDING true #define HANDLE_DEATH_LIST false /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { u32 uval, nval, mval; pid_t owner; int err; /* Futex address must be 32bit aligned */ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) return -1; retry: if (get_user(uval, uaddr)) return -1; /* * Special case for regular (non PI) futexes. The unlock path in * user space has two race scenarios: * * 1. The unlock path releases the user space futex value and * before it can execute the futex() syscall to wake up * waiters it is killed. * * 2. A woken up waiter is killed before it can acquire the * futex in user space. * * In the second case, the wake up notification could be generated * by the unlock path in user space after setting the futex value * to zero or by the kernel after setting the OWNER_DIED bit below. * * In both cases the TID validation below prevents a wakeup of * potential waiters which can cause these waiters to block * forever. * * In both cases the following conditions are met: * * 1) task->robust_list->list_op_pending != NULL * @pending_op == true * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false * * If these conditions are met, it is safe to attempt waking up a * potential waiter without touching the user space futex value and * trying to set the OWNER_DIED bit. If the futex value is zero, * the rest of the user space mutex state is consistent, so a woken * waiter will just take over the uncontended futex. Setting the * OWNER_DIED bit would create inconsistent state and malfunction * of the user space owner died handling. Otherwise, the OWNER_DIED * bit is already set, and the woken waiter is expected to deal with * this. */ owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); return 0; } if (owner != task_pid_vnr(curr)) return 0; /* * Ok, this dying thread is truly holding a futex * of interest. Set the OWNER_DIED bit atomically * via cmpxchg, and if the value had FUTEX_WAITERS * set, wake up a waiter (if any). (We have to do a * futex_wake() even if OWNER_DIED is already set - * to handle the rare but possible case of recursive * thread-death.) The rest of the cleanup is done in * userspace. */ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; /* * We are not holding a lock here, but we want to have * the pagefault_disable/enable() protection because * we want to handle the fault gracefully. If the * access fails we try to fault in the futex with R/W * verification via get_user_pages. get_user() above * does not guarantee R/W access. If that fails we * give up and leave the futex locked. */ if ((err = futex_cmpxchg_value_locked(&nval, uaddr, uval, mval))) { switch (err) { case -EFAULT: if (fault_in_user_writeable(uaddr)) return -1; goto retry; case -EAGAIN: cond_resched(); goto retry; default: WARN_ON_ONCE(1); return err; } } if (nval != uval) goto retry; /* * Wake robust non-PI futexes here. The wakeup of * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, unsigned int *pi) { unsigned long uentry; if (get_user(uentry, (unsigned long __user *)head)) return -EFAULT; *entry = (void __user *)(uentry & ~1UL); *pi = uentry & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; unsigned long futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (fetch_robust_entry(&entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); /* * A pending lock might already be on the list, so * don't process it twice: */ if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { handle_futex_death((void __user *)pending + futex_offset, curr, pip, HANDLE_DEATH_PENDING); } } #ifdef CONFIG_COMPAT static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) { compat_uptr_t base = ptr_to_compat(entry); void __user *uaddr = compat_ptr(base + futex_offset); return uaddr; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, compat_uptr_t __user *head, unsigned int *pi) { if (get_user(*uentry, head)) return -EFAULT; *entry = compat_ptr((*uentry) & ~1); *pi = (unsigned int)(*uentry) & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void compat_exit_robust_list(struct task_struct *curr) { struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (compat_fetch_robust_entry(&upending, &pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != (struct robust_list __user *) &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = compat_fetch_robust_entry(&next_uentry, &next_entry, (compat_uptr_t __user *)&entry->next, &next_pi); /* * A pending lock might already be on the list, so * dont process it twice: */ if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); if (handle_futex_death(uaddr, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; uentry = next_uentry; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } #endif #ifdef CONFIG_FUTEX_PI /* * This task is holding PI mutexes at exit time => bad. * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; struct futex_hash_bucket *hb; union futex_key key = FUTEX_KEY_INIT; /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; hb = futex_hash(&key); /* * We can race against put_pi_state() removing itself from the * list (a waiter going away). put_pi_state() will first * decrement the reference count and then modify the list, so * its possible to see the list entry but fail this reference * acquire. * * In that case; drop the locks to let put_pi_state() make * progress and retry the loop. */ if (!refcount_inc_not_zero(&pi_state->refcount)) { raw_spin_unlock_irq(&curr->pi_lock); cpu_relax(); raw_spin_lock_irq(&curr->pi_lock); continue; } raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); put_pi_state(pi_state); continue; } WARN_ON(pi_state->owner != curr); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; raw_spin_unlock(&curr->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); put_pi_state(pi_state); raw_spin_lock_irq(&curr->pi_lock); } raw_spin_unlock_irq(&curr->pi_lock); } #else static inline void exit_pi_state_list(struct task_struct *curr) { } #endif static void futex_cleanup(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); tsk->robust_list = NULL; } #ifdef CONFIG_COMPAT if (unlikely(tsk->compat_robust_list)) { compat_exit_robust_list(tsk); tsk->compat_robust_list = NULL; } #endif if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); } /** * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD * @tsk: task to set the state on * * Set the futex exit state of the task lockless. The futex waiter code * observes that state when a task is exiting and loops until the task has * actually finished the futex cleanup. The worst case for this is that the * waiter runs through the wait loop until the state becomes visible. * * This is called from the recursive fault handling path in make_task_dead(). * * This is best effort. Either the futex exit code has run already or * not. If the OWNER_DIED bit has been set on the futex then the waiter can * take it over. If not, the problem is pushed back to user space. If the * futex exit code did not run yet, then an already queued waiter might * block forever, but there is nothing which can be done about that. */ void futex_exit_recursive(struct task_struct *tsk) { /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ if (tsk->futex_state == FUTEX_STATE_EXITING) mutex_unlock(&tsk->futex_exit_mutex); tsk->futex_state = FUTEX_STATE_DEAD; } static void futex_cleanup_begin(struct task_struct *tsk) { /* * Prevent various race issues against a concurrent incoming waiter * including live locks by forcing the waiter to block on * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in * attach_to_pi_owner(). */ mutex_lock(&tsk->futex_exit_mutex); /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. * * This ensures that all subsequent checks of tsk->futex_state in * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with * tsk->pi_lock held. * * It guarantees also that a pi_state which was queued right before * the state change under tsk->pi_lock by a concurrent waiter must * be observed in exit_pi_state_list(). */ raw_spin_lock_irq(&tsk->pi_lock); tsk->futex_state = FUTEX_STATE_EXITING; raw_spin_unlock_irq(&tsk->pi_lock); } static void futex_cleanup_end(struct task_struct *tsk, int state) { /* * Lockless store. The only side effect is that an observer might * take another loop until it becomes visible. */ tsk->futex_state = state; /* * Drop the exit protection. This unblocks waiters which observed * FUTEX_STATE_EXITING to reevaluate the state. */ mutex_unlock(&tsk->futex_exit_mutex); } void futex_exec_release(struct task_struct *tsk) { /* * The state handling is done for consistency, but in the case of * exec() there is no way to prevent further damage as the PID stays * the same. But for the unlikely and arguably buggy case that a * futex is held on exec(), this provides at least as much state * consistency protection which is possible. */ futex_cleanup_begin(tsk); futex_cleanup(tsk); /* * Reset the state to FUTEX_STATE_OK. The task is alive and about * exec a new binary. */ futex_cleanup_end(tsk, FUTEX_STATE_OK); } void futex_exit_release(struct task_struct *tsk) { futex_cleanup_begin(tsk); futex_cleanup(tsk); futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } static int __init futex_init(void) { unsigned int futex_shift; unsigned long i; #ifdef CONFIG_BASE_SMALL futex_hashsize = 16; #else futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus()); #endif futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), futex_hashsize, 0, 0, &futex_shift, NULL, futex_hashsize, futex_hashsize); futex_hashsize = 1UL << futex_shift; for (i = 0; i < futex_hashsize; i++) { atomic_set(&futex_queues[i].waiters, 0); plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } return 0; } core_initcall(futex_init); |
| 155 156 1 1 1 1 1 1 156 155 156 155 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Implementation of the extensible bitmap type. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Hewlett-Packard <paul@paul-moore.com> * Added support to import/export the NetLabel category bitmap * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 * * Updated: KaiGai Kohei <kaigai@ak.jp.nec.com> * Applied standard bit operations to improve bitmap scanning. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/jhash.h> #include <net/netlabel.h> #include "ebitmap.h" #include "policydb.h" #define BITS_PER_U64 ((u32)(sizeof(u64) * 8)) static struct kmem_cache *ebitmap_node_cachep __ro_after_init; int ebitmap_cmp(const struct ebitmap *e1, const struct ebitmap *e2) { const struct ebitmap_node *n1, *n2; if (e1->highbit != e2->highbit) return 0; n1 = e1->node; n2 = e2->node; while (n1 && n2 && (n1->startbit == n2->startbit) && !memcmp(n1->maps, n2->maps, EBITMAP_SIZE / 8)) { n1 = n1->next; n2 = n2->next; } if (n1 || n2) return 0; return 1; } int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src) { struct ebitmap_node *new, *prev; const struct ebitmap_node *n; ebitmap_init(dst); n = src->node; prev = NULL; while (n) { new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (!new) { ebitmap_destroy(dst); return -ENOMEM; } new->startbit = n->startbit; memcpy(new->maps, n->maps, EBITMAP_SIZE / 8); new->next = NULL; if (prev) prev->next = new; else dst->node = new; prev = new; n = n->next; } dst->highbit = src->highbit; return 0; } int ebitmap_and(struct ebitmap *dst, const struct ebitmap *e1, const struct ebitmap *e2) { struct ebitmap_node *n; u32 bit; int rc; ebitmap_init(dst); ebitmap_for_each_positive_bit(e1, n, bit) { if (ebitmap_get_bit(e2, bit)) { rc = ebitmap_set_bit(dst, bit, 1); if (rc < 0) return rc; } } return 0; } #ifdef CONFIG_NETLABEL /** * ebitmap_netlbl_export - Export an ebitmap into a NetLabel category bitmap * @ebmap: the ebitmap to export * @catmap: the NetLabel category bitmap * * Description: * Export a SELinux extensibile bitmap into a NetLabel category bitmap. * Returns zero on success, negative values on error. * */ int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap) { struct ebitmap_node *e_iter = ebmap->node; unsigned long e_map; u32 offset; unsigned int iter; int rc; if (e_iter == NULL) { *catmap = NULL; return 0; } if (*catmap != NULL) netlbl_catmap_free(*catmap); *catmap = NULL; while (e_iter) { offset = e_iter->startbit; for (iter = 0; iter < EBITMAP_UNIT_NUMS; iter++) { e_map = e_iter->maps[iter]; if (e_map != 0) { rc = netlbl_catmap_setlong(catmap, offset, e_map, GFP_ATOMIC); if (rc != 0) goto netlbl_export_failure; } offset += EBITMAP_UNIT_SIZE; } e_iter = e_iter->next; } return 0; netlbl_export_failure: netlbl_catmap_free(*catmap); return -ENOMEM; } /** * ebitmap_netlbl_import - Import a NetLabel category bitmap into an ebitmap * @ebmap: the ebitmap to import * @catmap: the NetLabel category bitmap * * Description: * Import a NetLabel category bitmap into a SELinux extensibile bitmap. * Returns zero on success, negative values on error. * */ int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap) { int rc; struct ebitmap_node *e_iter = NULL; struct ebitmap_node *e_prev = NULL; u32 offset = 0, idx; unsigned long bitmap; for (;;) { rc = netlbl_catmap_getlong(catmap, &offset, &bitmap); if (rc < 0) goto netlbl_import_failure; if (offset == (u32)-1) return 0; /* don't waste ebitmap space if the netlabel bitmap is empty */ if (bitmap == 0) { offset += EBITMAP_UNIT_SIZE; continue; } if (e_iter == NULL || offset >= e_iter->startbit + EBITMAP_SIZE) { e_prev = e_iter; e_iter = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (e_iter == NULL) goto netlbl_import_failure; e_iter->startbit = offset - (offset % EBITMAP_SIZE); if (e_prev == NULL) ebmap->node = e_iter; else e_prev->next = e_iter; ebmap->highbit = e_iter->startbit + EBITMAP_SIZE; } /* offset will always be aligned to an unsigned long */ idx = EBITMAP_NODE_INDEX(e_iter, offset); e_iter->maps[idx] = bitmap; /* next */ offset += EBITMAP_UNIT_SIZE; } /* NOTE: we should never reach this return */ return 0; netlbl_import_failure: ebitmap_destroy(ebmap); return -ENOMEM; } #endif /* CONFIG_NETLABEL */ /* * Check to see if all the bits set in e2 are also set in e1. Optionally, * if last_e2bit is non-zero, the highest set bit in e2 cannot exceed * last_e2bit. */ int ebitmap_contains(const struct ebitmap *e1, const struct ebitmap *e2, u32 last_e2bit) { const struct ebitmap_node *n1, *n2; int i; if (e1->highbit < e2->highbit) return 0; n1 = e1->node; n2 = e2->node; while (n1 && n2 && (n1->startbit <= n2->startbit)) { if (n1->startbit < n2->startbit) { n1 = n1->next; continue; } for (i = EBITMAP_UNIT_NUMS - 1; (i >= 0) && !n2->maps[i];) i--; /* Skip trailing NULL map entries */ if (last_e2bit && (i >= 0)) { u32 lastsetbit = n2->startbit + i * EBITMAP_UNIT_SIZE + __fls(n2->maps[i]); if (lastsetbit > last_e2bit) return 0; } while (i >= 0) { if ((n1->maps[i] & n2->maps[i]) != n2->maps[i]) return 0; i--; } n1 = n1->next; n2 = n2->next; } if (n2) return 0; return 1; } int ebitmap_get_bit(const struct ebitmap *e, u32 bit) { const struct ebitmap_node *n; if (e->highbit < bit) return 0; n = e->node; while (n && (n->startbit <= bit)) { if ((n->startbit + EBITMAP_SIZE) > bit) return ebitmap_node_get_bit(n, bit); n = n->next; } return 0; } int ebitmap_set_bit(struct ebitmap *e, u32 bit, int value) { struct ebitmap_node *n, *prev, *new; prev = NULL; n = e->node; while (n && n->startbit <= bit) { if ((n->startbit + EBITMAP_SIZE) > bit) { if (value) { ebitmap_node_set_bit(n, bit); } else { u32 s; ebitmap_node_clr_bit(n, bit); s = find_first_bit(n->maps, EBITMAP_SIZE); if (s < EBITMAP_SIZE) return 0; /* drop this node from the bitmap */ if (!n->next) { /* * this was the highest map * within the bitmap */ if (prev) e->highbit = prev->startbit + EBITMAP_SIZE; else e->highbit = 0; } if (prev) prev->next = n->next; else e->node = n->next; kmem_cache_free(ebitmap_node_cachep, n); } return 0; } prev = n; n = n->next; } if (!value) return 0; new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (!new) return -ENOMEM; new->startbit = bit - (bit % EBITMAP_SIZE); ebitmap_node_set_bit(new, bit); if (!n) /* this node will be the highest map within the bitmap */ e->highbit = new->startbit + EBITMAP_SIZE; if (prev) { new->next = prev->next; prev->next = new; } else { new->next = e->node; e->node = new; } return 0; } void ebitmap_destroy(struct ebitmap *e) { struct ebitmap_node *n, *temp; if (!e) return; n = e->node; while (n) { temp = n; n = n->next; kmem_cache_free(ebitmap_node_cachep, temp); } e->highbit = 0; e->node = NULL; } int ebitmap_read(struct ebitmap *e, void *fp) { struct ebitmap_node *n = NULL; u32 mapunit, count, startbit, index, i; __le32 ebitmap_start; u64 map; __le64 mapbits; __le32 buf[3]; int rc; ebitmap_init(e); rc = next_entry(buf, fp, sizeof buf); if (rc < 0) goto out; mapunit = le32_to_cpu(buf[0]); e->highbit = le32_to_cpu(buf[1]); count = le32_to_cpu(buf[2]); if (mapunit != BITS_PER_U64) { pr_err("SELinux: ebitmap: map size %u does not " "match my size %u (high bit was %u)\n", mapunit, BITS_PER_U64, e->highbit); goto bad; } /* round up e->highbit */ e->highbit += EBITMAP_SIZE - 1; e->highbit -= (e->highbit % EBITMAP_SIZE); if (!e->highbit) { e->node = NULL; goto ok; } if (e->highbit && !count) goto bad; for (i = 0; i < count; i++) { rc = next_entry(&ebitmap_start, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: ebitmap: truncated map\n"); goto bad; } startbit = le32_to_cpu(ebitmap_start); if (startbit & (mapunit - 1)) { pr_err("SELinux: ebitmap start bit (%u) is " "not a multiple of the map unit size (%u)\n", startbit, mapunit); goto bad; } if (startbit > e->highbit - mapunit) { pr_err("SELinux: ebitmap start bit (%u) is " "beyond the end of the bitmap (%u)\n", startbit, (e->highbit - mapunit)); goto bad; } if (!n || startbit >= n->startbit + EBITMAP_SIZE) { struct ebitmap_node *tmp; tmp = kmem_cache_zalloc(ebitmap_node_cachep, GFP_KERNEL); if (!tmp) { pr_err("SELinux: ebitmap: out of memory\n"); rc = -ENOMEM; goto bad; } /* round down */ tmp->startbit = startbit - (startbit % EBITMAP_SIZE); if (n) n->next = tmp; else e->node = tmp; n = tmp; } else if (startbit <= n->startbit) { pr_err("SELinux: ebitmap: start bit %u" " comes after start bit %u\n", startbit, n->startbit); goto bad; } rc = next_entry(&mapbits, fp, sizeof(u64)); if (rc < 0) { pr_err("SELinux: ebitmap: truncated map\n"); goto bad; } map = le64_to_cpu(mapbits); if (!map) { pr_err("SELinux: ebitmap: empty map\n"); goto bad; } index = (startbit - n->startbit) / EBITMAP_UNIT_SIZE; while (map) { n->maps[index++] = map & (-1UL); map = EBITMAP_SHIFT_UNIT_SIZE(map); } } if (n && n->startbit + EBITMAP_SIZE != e->highbit) { pr_err("SELinux: ebitmap: high bit %u is not equal to the expected value %zu\n", e->highbit, n->startbit + EBITMAP_SIZE); goto bad; } ok: rc = 0; out: return rc; bad: if (!rc) rc = -EINVAL; ebitmap_destroy(e); goto out; } int ebitmap_write(const struct ebitmap *e, void *fp) { struct ebitmap_node *n; u32 bit, count, last_bit, last_startbit; __le32 buf[3]; u64 map; int rc; buf[0] = cpu_to_le32(BITS_PER_U64); count = 0; last_bit = 0; last_startbit = U32_MAX; ebitmap_for_each_positive_bit(e, n, bit) { if (last_startbit == U32_MAX || rounddown(bit, BITS_PER_U64) > last_startbit) { count++; last_startbit = rounddown(bit, BITS_PER_U64); } last_bit = roundup(bit + 1, BITS_PER_U64); } buf[1] = cpu_to_le32(last_bit); buf[2] = cpu_to_le32(count); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; map = 0; last_startbit = U32_MAX; ebitmap_for_each_positive_bit(e, n, bit) { if (last_startbit == U32_MAX || rounddown(bit, BITS_PER_U64) > last_startbit) { __le64 buf64[1]; /* this is the very first bit */ if (!map) { last_startbit = rounddown(bit, BITS_PER_U64); map = (u64)1 << (bit - last_startbit); continue; } /* write the last node */ buf[0] = cpu_to_le32(last_startbit); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; buf64[0] = cpu_to_le64(map); rc = put_entry(buf64, sizeof(u64), 1, fp); if (rc) return rc; /* set up for the next node */ map = 0; last_startbit = rounddown(bit, BITS_PER_U64); } map |= (u64)1 << (bit - last_startbit); } /* write the last node */ if (map) { __le64 buf64[1]; /* write the last node */ buf[0] = cpu_to_le32(last_startbit); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; buf64[0] = cpu_to_le64(map); rc = put_entry(buf64, sizeof(u64), 1, fp); if (rc) return rc; } return 0; } u32 ebitmap_hash(const struct ebitmap *e, u32 hash) { struct ebitmap_node *node; /* need to change hash even if ebitmap is empty */ hash = jhash_1word(e->highbit, hash); for (node = e->node; node; node = node->next) { hash = jhash_1word(node->startbit, hash); hash = jhash(node->maps, sizeof(node->maps), hash); } return hash; } void __init ebitmap_cache_init(void) { ebitmap_node_cachep = KMEM_CACHE(ebitmap_node, SLAB_PANIC); } |
| 5 5 5 5 156 156 155 156 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the multi-level security (MLS) policy. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * Support for enhanced MLS infrastructure. * Copyright (C) 2004-2006 Trusted Computer Solutions, Inc. * * Updated: Hewlett-Packard <paul@paul-moore.com> * Added support to import/export the MLS label from NetLabel * Copyright (C) Hewlett-Packard Development Company, L.P., 2006 */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/errno.h> #include <net/netlabel.h> #include "sidtab.h" #include "mls.h" #include "policydb.h" #include "services.h" /* * Return the length in bytes for the MLS fields of the * security context string representation of `context'. */ int mls_compute_context_len(struct policydb *p, struct context *context) { int i, l, len, head, prev; char *nm; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return 0; len = 1; /* for the beginning ":" */ for (l = 0; l < 2; l++) { u32 index_sens = context->range.level[l].sens; len += strlen(sym_name(p, SYM_LEVELS, index_sens - 1)); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (head != prev) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } nm = sym_name(p, SYM_CATS, i); len += strlen(nm) + 1; head = i; } prev = i; } if (prev != head) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else len++; } } return len; } /* * Write the security context string representation of * the MLS fields of `context' into the string `*scontext'. * Update `*scontext' to point to the end of the MLS fields. */ void mls_sid_to_context(struct policydb *p, struct context *context, char **scontext) { char *scontextp, *nm; int i, l, head, prev; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return; scontextp = *scontext; *scontextp = ':'; scontextp++; for (l = 0; l < 2; l++) { strcpy(scontextp, sym_name(p, SYM_LEVELS, context->range.level[l].sens - 1)); scontextp += strlen(scontextp); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (prev < 0) *scontextp++ = ':'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, i); strcpy(scontextp, nm); scontextp += strlen(nm); head = i; } prev = i; } if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else *scontextp++ = '-'; } } *scontext = scontextp; } int mls_level_isvalid(struct policydb *p, struct mls_level *l) { struct level_datum *levdatum; if (!l->sens || l->sens > p->p_levels.nprim) return 0; levdatum = symtab_search(&p->p_levels, sym_name(p, SYM_LEVELS, l->sens - 1)); if (!levdatum) return 0; /* * Return 1 iff all the bits set in l->cat are also be set in * levdatum->level->cat and no bit in l->cat is larger than * p->p_cats.nprim. */ return ebitmap_contains(&levdatum->level->cat, &l->cat, p->p_cats.nprim); } int mls_range_isvalid(struct policydb *p, struct mls_range *r) { return (mls_level_isvalid(p, &r->level[0]) && mls_level_isvalid(p, &r->level[1]) && mls_level_dom(&r->level[1], &r->level[0])); } /* * Return 1 if the MLS fields in the security context * structure `c' are valid. Return 0 otherwise. */ int mls_context_isvalid(struct policydb *p, struct context *c) { struct user_datum *usrdatum; if (!p->mls_enabled) return 1; if (!mls_range_isvalid(p, &c->range)) return 0; if (c->role == OBJECT_R_VAL) return 1; /* * User must be authorized for the MLS range. */ if (!c->user || c->user > p->p_users.nprim) return 0; usrdatum = p->user_val_to_struct[c->user - 1]; if (!mls_range_contains(usrdatum->range, c->range)) return 0; /* user may not be associated with range */ return 1; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `scontext'. * * This function modifies the string in place, inserting * NULL characters to terminate the MLS fields. * * If a def_sid is provided and no MLS field is present, * copy the MLS field of the associated default context. * Used for upgraded to MLS systems where objects may lack * MLS fields. * * Policy read-lock must be held for sidtab lookup. * */ int mls_context_to_sid(struct policydb *pol, char oldc, char *scontext, struct context *context, struct sidtab *s, u32 def_sid) { char *sensitivity, *cur_cat, *next_cat, *rngptr; struct level_datum *levdatum; struct cat_datum *catdatum, *rngdatum; u32 i; int l, rc; char *rangep[2]; if (!pol->mls_enabled) { /* * With no MLS, only return -EINVAL if there is a MLS field * and it did not come from an xattr. */ if (oldc && def_sid == SECSID_NULL) return -EINVAL; return 0; } /* * No MLS component to the security context, try and map to * default if provided. */ if (!oldc) { struct context *defcon; if (def_sid == SECSID_NULL) return -EINVAL; defcon = sidtab_search(s, def_sid); if (!defcon) return -EINVAL; return mls_context_cpy(context, defcon); } /* * If we're dealing with a range, figure out where the two parts * of the range begin. */ rangep[0] = scontext; rangep[1] = strchr(scontext, '-'); if (rangep[1]) { rangep[1][0] = '\0'; rangep[1]++; } /* For each part of the range: */ for (l = 0; l < 2; l++) { /* Split sensitivity and category set. */ sensitivity = rangep[l]; if (sensitivity == NULL) break; next_cat = strchr(sensitivity, ':'); if (next_cat) *(next_cat++) = '\0'; /* Parse sensitivity. */ levdatum = symtab_search(&pol->p_levels, sensitivity); if (!levdatum) return -EINVAL; context->range.level[l].sens = levdatum->level->sens; /* Extract category set. */ while (next_cat != NULL) { cur_cat = next_cat; next_cat = strchr(next_cat, ','); if (next_cat != NULL) *(next_cat++) = '\0'; /* Separate into range if exists */ rngptr = strchr(cur_cat, '.'); if (rngptr != NULL) { /* Remove '.' */ *rngptr++ = '\0'; } catdatum = symtab_search(&pol->p_cats, cur_cat); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&context->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; /* If range, set all categories in range */ if (rngptr == NULL) continue; rngdatum = symtab_search(&pol->p_cats, rngptr); if (!rngdatum) return -EINVAL; if (catdatum->value >= rngdatum->value) return -EINVAL; for (i = catdatum->value; i < rngdatum->value; i++) { rc = ebitmap_set_bit( &context->range.level[l].cat, i, 1); if (rc) return rc; } } } /* If we didn't see a '-', the range start is also the range end. */ if (rangep[1] == NULL) { context->range.level[1].sens = context->range.level[0].sens; rc = ebitmap_cpy(&context->range.level[1].cat, &context->range.level[0].cat); if (rc) return rc; } return 0; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `str'. This function will allocate temporary memory with the * given constraints of gfp_mask. */ int mls_from_string(struct policydb *p, char *str, struct context *context, gfp_t gfp_mask) { char *tmpstr; int rc; if (!p->mls_enabled) return -EINVAL; tmpstr = kstrdup(str, gfp_mask); if (!tmpstr) { rc = -ENOMEM; } else { rc = mls_context_to_sid(p, ':', tmpstr, context, NULL, SECSID_NULL); kfree(tmpstr); } return rc; } /* * Copies the MLS range `range' into `context'. */ int mls_range_set(struct context *context, struct mls_range *range) { int l, rc = 0; /* Copy the MLS range into the context */ for (l = 0; l < 2; l++) { context->range.level[l].sens = range->level[l].sens; rc = ebitmap_cpy(&context->range.level[l].cat, &range->level[l].cat); if (rc) break; } return rc; } int mls_setup_user_range(struct policydb *p, struct context *fromcon, struct user_datum *user, struct context *usercon) { if (p->mls_enabled) { struct mls_level *fromcon_sen = &(fromcon->range.level[0]); struct mls_level *fromcon_clr = &(fromcon->range.level[1]); struct mls_level *user_low = &(user->range.level[0]); struct mls_level *user_clr = &(user->range.level[1]); struct mls_level *user_def = &(user->dfltlevel); struct mls_level *usercon_sen = &(usercon->range.level[0]); struct mls_level *usercon_clr = &(usercon->range.level[1]); /* Honor the user's default level if we can */ if (mls_level_between(user_def, fromcon_sen, fromcon_clr)) *usercon_sen = *user_def; else if (mls_level_between(fromcon_sen, user_def, user_clr)) *usercon_sen = *fromcon_sen; else if (mls_level_between(fromcon_clr, user_low, user_def)) *usercon_sen = *user_low; else return -EINVAL; /* Lower the clearance of available contexts if the clearance of "fromcon" is lower than that of the user's default clearance (but only if the "fromcon" clearance dominates the user's computed sensitivity level) */ if (mls_level_dom(user_clr, fromcon_clr)) *usercon_clr = *fromcon_clr; else if (mls_level_dom(fromcon_clr, user_clr)) *usercon_clr = *user_clr; else return -EINVAL; } return 0; } /* * Convert the MLS fields in the security context * structure `oldc' from the values specified in the * policy `oldp' to the values specified in the policy `newp', * storing the resulting context in `newc'. */ int mls_convert_context(struct policydb *oldp, struct policydb *newp, struct context *oldc, struct context *newc) { struct level_datum *levdatum; struct cat_datum *catdatum; struct ebitmap_node *node; u32 i; int l; if (!oldp->mls_enabled || !newp->mls_enabled) return 0; for (l = 0; l < 2; l++) { char *name = sym_name(oldp, SYM_LEVELS, oldc->range.level[l].sens - 1); levdatum = symtab_search(&newp->p_levels, name); if (!levdatum) return -EINVAL; newc->range.level[l].sens = levdatum->level->sens; ebitmap_for_each_positive_bit(&oldc->range.level[l].cat, node, i) { int rc; catdatum = symtab_search(&newp->p_cats, sym_name(oldp, SYM_CATS, i)); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&newc->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; } } return 0; } int mls_compute_sid(struct policydb *p, struct context *scontext, struct context *tcontext, u16 tclass, u32 specified, struct context *newcontext, bool sock) { struct range_trans rtr; struct mls_range *r; struct class_datum *cladatum; char default_range = 0; if (!p->mls_enabled) return 0; switch (specified) { case AVTAB_TRANSITION: /* Look for a range transition rule. */ rtr.source_type = scontext->type; rtr.target_type = tcontext->type; rtr.target_class = tclass; r = policydb_rangetr_search(p, &rtr); if (r) return mls_range_set(newcontext, r); if (tclass && tclass <= p->p_classes.nprim) { cladatum = p->class_val_to_struct[tclass - 1]; if (cladatum) default_range = cladatum->default_range; } switch (default_range) { case DEFAULT_SOURCE_LOW: return mls_context_cpy_low(newcontext, scontext); case DEFAULT_SOURCE_HIGH: return mls_context_cpy_high(newcontext, scontext); case DEFAULT_SOURCE_LOW_HIGH: return mls_context_cpy(newcontext, scontext); case DEFAULT_TARGET_LOW: return mls_context_cpy_low(newcontext, tcontext); case DEFAULT_TARGET_HIGH: return mls_context_cpy_high(newcontext, tcontext); case DEFAULT_TARGET_LOW_HIGH: return mls_context_cpy(newcontext, tcontext); case DEFAULT_GLBLUB: return mls_context_glblub(newcontext, scontext, tcontext); } fallthrough; case AVTAB_CHANGE: if ((tclass == p->process_class) || sock) /* Use the process MLS attributes. */ return mls_context_cpy(newcontext, scontext); else /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); case AVTAB_MEMBER: /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); } return -EINVAL; } #ifdef CONFIG_NETLABEL /** * mls_export_netlbl_lvl - Export the MLS sensitivity levels to NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS sensitivity level into the * NetLabel MLS sensitivity level field. * */ void mls_export_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; secattr->attr.mls.lvl = context->range.level[0].sens - 1; secattr->flags |= NETLBL_SECATTR_MLS_LVL; } /** * mls_import_netlbl_lvl - Import the NetLabel MLS sensitivity levels * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context and the NetLabel security attributes, copy the * NetLabel MLS sensitivity level into the context. * */ void mls_import_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; context->range.level[0].sens = secattr->attr.mls.lvl + 1; context->range.level[1].sens = context->range.level[0].sens; } /** * mls_export_netlbl_cat - Export the MLS categories to NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS categories into the NetLabel * MLS category field. Returns zero on success, negative values on failure. * */ int mls_export_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_export(&context->range.level[0].cat, &secattr->attr.mls.cat); if (rc == 0 && secattr->attr.mls.cat != NULL) secattr->flags |= NETLBL_SECATTR_MLS_CAT; return rc; } /** * mls_import_netlbl_cat - Import the MLS categories from NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Copy the NetLabel security attributes into the SELinux context; since the * NetLabel security attribute only contains a single MLS category use it for * both the low and high categories of the context. Returns zero on success, * negative values on failure. * */ int mls_import_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_import(&context->range.level[0].cat, secattr->attr.mls.cat); if (rc) goto import_netlbl_cat_failure; memcpy(&context->range.level[1].cat, &context->range.level[0].cat, sizeof(context->range.level[0].cat)); return 0; import_netlbl_cat_failure: ebitmap_destroy(&context->range.level[0].cat); return rc; } #endif /* CONFIG_NETLABEL */ |
| 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2015 Linaro Ltd. * Author: Shannon Zhao <shannon.zhao@linaro.org> */ #ifndef __ASM_ARM_KVM_PMU_H #define __ASM_ARM_KVM_PMU_H #include <linux/perf_event.h> #include <linux/perf/arm_pmuv3.h> #define KVM_ARMV8_PMU_MAX_COUNTERS 32 #if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM) struct kvm_pmc { u8 idx; /* index into the pmu->pmc array */ struct perf_event *perf_event; }; struct kvm_pmu_events { u64 events_host; u64 events_guest; }; struct kvm_pmu { struct irq_work overflow_work; struct kvm_pmu_events events; struct kvm_pmc pmc[KVM_ARMV8_PMU_MAX_COUNTERS]; int irq_num; bool created; bool irq_level; }; struct arm_pmu_entry { struct list_head entry; struct arm_pmu *arm_pmu; }; DECLARE_STATIC_KEY_FALSE(kvm_arm_pmu_available); static __always_inline bool kvm_arm_support_pmu_v3(void) { return static_branch_likely(&kvm_arm_pmu_available); } #define kvm_arm_pmu_irq_initialized(v) ((v)->arch.pmu.irq_num >= VGIC_NR_SGIS) u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx); void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val); u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu); u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1); void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu); void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu); void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu); bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu); void kvm_pmu_update_run(struct kvm_vcpu *vcpu); void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx); void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu); int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu); struct kvm_pmu_events *kvm_get_pmu_events(void); void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu); void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); void kvm_vcpu_pmu_resync_el0(void); #define kvm_vcpu_has_pmu(vcpu) \ (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PMU_V3)) /* * Updates the vcpu's view of the pmu events for this cpu. * Must be called before every vcpu run after disabling interrupts, to ensure * that an interrupt cannot fire and update the structure. */ #define kvm_pmu_update_vcpu_events(vcpu) \ do { \ if (!has_vhe() && kvm_arm_support_pmu_v3()) \ vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ } while (0) u8 kvm_arm_pmu_get_pmuver_limit(void); u64 kvm_pmu_evtyper_mask(struct kvm *kvm); int kvm_arm_set_default_pmu(struct kvm *kvm); u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm); u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu); #else struct kvm_pmu { }; static inline bool kvm_arm_support_pmu_v3(void) { return false; } #define kvm_arm_pmu_irq_initialized(v) (false) static inline u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) { return 0; } static inline void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) {} static inline u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu) { return 0; } static inline void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {} static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu) { return false; } static inline void kvm_pmu_update_run(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx) {} static inline int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { return -ENXIO; } static inline int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { return -ENXIO; } static inline int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { return -ENXIO; } static inline int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) { return 0; } static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { return 0; } #define kvm_vcpu_has_pmu(vcpu) ({ false; }) static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) {} static inline u8 kvm_arm_pmu_get_pmuver_limit(void) { return 0; } static inline u64 kvm_pmu_evtyper_mask(struct kvm *kvm) { return 0; } static inline void kvm_vcpu_pmu_resync_el0(void) {} static inline int kvm_arm_set_default_pmu(struct kvm *kvm) { return -ENODEV; } static inline u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) { return 0; } static inline u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu) { return 0; } #endif #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | /* SPDX-License-Identifier: GPL-2.0 */ #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_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return cpuset_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 rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(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); } #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 rebuild_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; } #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ |
| 442 442 377 376 376 374 378 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/local_lock.h> #include <linux/zswap.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_PAGE_ORDER 10 #else #define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER) #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) #define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) # define is_migrate_cma_folio(folio, pfn) (MIGRATE_CMA == \ get_pfnblock_flags_mask(&folio->page, pfn, MIGRATETYPE_MASK)) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false # define is_migrate_cma_folio(folio, pfn) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } /* * Check whether a migratetype can be merged with another migratetype. * * It is only mergeable when it can fall back to other migratetypes for * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. */ static inline bool migratetype_is_mergeable(int mt) { return mt < MIGRATE_PCPTYPES; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < NR_PAGE_ORDERS; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) #define folio_migratetype(folio) \ get_pfnblock_flags_mask(&folio->page, folio_pfn(folio), \ MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; struct pglist_data; #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_EVENT_ITEMS }; #else #define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, #ifdef CONFIG_UNACCEPTED_MEMORY NR_UNACCEPTED, #endif NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ #ifdef CONFIG_IOMMU_SUPPORT NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ #endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ PGPROMOTE_CANDIDATE, /* candidate pages to promote */ #endif /* PGDEMOTE_*: pages demoted */ PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the item should be printed in THPs (/proc/vmstat * currently prints number of anon, file and shmem THPs. But the item * is charged in pages). */ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return false; return item == NR_ANON_THPS || item == NR_FILE_THPS || item == NR_SHMEM_THPS || item == NR_SHMEM_PMDMAPPED || item == NR_FILE_PMDMAPPED; } /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define WORKINGSET_ANON 0 #define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { /* * An lruvec has many dirty pages backed by a congested BDI: * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim. * It can be cleared by cgroup reclaim or kswapd. * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim. * It can only be cleared by kswapd. * * Essentially, kswapd can unthrottle an lruvec throttled by cgroup * reclaim, but not vice versa. This only applies to the root cgroup. * The goal is to prevent cgroup reclaim on the root cgroup (e.g. * memory.reclaim) to unthrottle an unbalanced node (that was throttled * by kswapd). */ LRUVEC_CGROUP_CONGESTED, LRUVEC_NODE_CONGESTED, }; #endif /* !__GENERATING_BOUNDS_H */ /* * Evictable pages are divided into multiple generations. The youngest and the * oldest generation numbers, max_seq and min_seq, are monotonically increasing. * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while * a page is on one of lrugen->folios[]. Otherwise it stores 0. * * A page is added to the youngest generation on faulting. The aging needs to * check the accessed bit at least twice before handing this page over to the * eviction. The first check takes care of the accessed bit set on the initial * fault; the second check makes sure this page hasn't been used since then. * This process, AKA second chance, requires a minimum of two generations, * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive * LRU, e.g., /proc/vmstat, these two generations are considered active; the * rest of generations, if they exist, are considered inactive. See * lru_gen_is_active(). * * PG_active is always cleared while a page is on one of lrugen->folios[] so * that the aging needs not to worry about it. And it's set again when a page * considered active is isolated for non-reclaiming purposes, e.g., migration. * See lru_gen_add_folio() and lru_gen_del_folio(). * * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits * in folio->flags. */ #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U /* * Each generation is divided into multiple tiers. A page accessed N times * through file descriptors is in tier order_base_2(N). A page in the first tier * (N=0,1) is marked by PG_referenced unless it was faulted in through page * tables or read ahead. A page in any other tier (N>1) is marked by * PG_referenced and PG_workingset. This implies a minimum of two tiers is * supported without using additional bits in folio->flags. * * In contrast to moving across generations which requires the LRU lock, moving * across tiers only involves atomic operations on folio->flags and therefore * has a negligible cost in the buffered access path. In the eviction path, * comparisons of refaulted/(evicted+protected) from the first tier and the * rest infer whether pages accessed multiple times through file descriptors * are statistically hot and thus worth protecting. * * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in * folio->flags. */ #define MAX_NR_TIERS 4U #ifndef __GENERATING_BOUNDS_H struct lruvec; struct page_vma_mapped_walk; #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) #ifdef CONFIG_LRU_GEN enum { LRU_GEN_ANON, LRU_GEN_FILE, }; enum { LRU_GEN_CORE, LRU_GEN_MM_WALK, LRU_GEN_NONLEAF_YOUNG, NR_LRU_GEN_CAPS }; #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) /* whether to keep historical stats from evicted generations */ #ifdef CONFIG_LRU_GEN_STATS #define NR_HIST_GENS MAX_NR_GENS #else #define NR_HIST_GENS 1U #endif /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are * stored in min_seq[] separately for anon and file types as clean file pages * can be evicted regardless of swap constraints. * * Normally anon and file min_seq are in sync. But if swapping is constrained, * e.g., out of swap space, file min_seq is allowed to advance and leave anon * min_seq behind. * * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ unsigned long min_seq[ANON_AND_FILE]; /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; /* the exponential moving average of evicted+protected */ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; /* the first tier doesn't need protection, hence the minus one */ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; /* the memcg generation this lru_gen_folio belongs to */ u8 gen; /* the list segment this lru_gen_folio belongs to */ u8 seg; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_node list; }; enum { MM_LEAF_TOTAL, /* total leaf entries */ MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS }; /* double-buffering Bloom filters */ #define NR_BLOOM_FILTERS 2 struct lru_gen_mm_state { /* synced with max_seq after each iteration */ unsigned long seq; /* where the current iteration continues after */ struct list_head *head; /* where the last iteration ended before */ struct list_head *tail; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; }; struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; /* max_seq from lru_gen_folio: can be out of date */ unsigned long seq; /* the next address within an mm to scan */ unsigned long next_addr; /* to batch promoted pages */ int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* to batch the mm stats */ int mm_stats[NR_MM_STATS]; /* total batched items */ int batched; bool can_swap; bool force_scan; }; /* * For each node, memcgs are divided into two generations: the old and the * young. For each generation, memcgs are randomly sharded into multiple bins * to improve scalability. For each bin, the hlist_nulls is virtually divided * into three segments: the head, the tail and the default. * * An onlining memcg is added to the tail of a random bin in the old generation. * The eviction starts at the head of a random bin in the old generation. The * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes * the old generation, is incremented when all its bins become empty. * * There are four operations: * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; * 3. The first attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_TAIL; * 4. The second attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_YOUNG; * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * * Notes: * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing * of their max_seq counters ensures the eventual fairness to all eligible * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). * 2. There are only two valid generations: old (seq) and young (seq+1). * MEMCG_NR_GENS is set to three so that when reading the generation counter * locklessly, a stale value (seq-1) does not wraparound to young. */ #define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { /* the per-node memcg generation counter */ unsigned long seq; /* each memcg has one lru_gen_folio per node */ unsigned long nr_memcgs[MEMCG_NR_GENS]; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; /* protects the above */ spinlock_t lock; }; void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); void lru_gen_online_memcg(struct mem_cgroup *memcg); void lru_gen_offline_memcg(struct mem_cgroup *memcg); void lru_gen_release_memcg(struct mem_cgroup *memcg); void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid); #else /* !CONFIG_LRU_GEN */ static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) { } static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { } #endif /* CONFIG_LRU_GEN */ struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ spinlock_t lru_lock; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ struct lru_gen_folio lrugen; #ifdef CONFIG_LRU_GEN_WALKS_MMU /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif struct zswap_lruvec_state zswap_lruvec_state; }; /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, WMARK_PROMO, NR_WMARK }; /* * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) /* * Flags used in pcp->flags field. * * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the * previous page freeing. To avoid to drain PCP for an accident * high-order page freeing. * * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before * draining PCP for consecutive high-order pages freeing without * allocation if data cache slice of CPU is large enough. To reduce * zone lock contention and keep cache-hot pages reusing. */ #define PCPF_PREV_FREE_HIGH_ORDER BIT(0) #define PCPF_FREE_HIGH_BATCH BIT(1) struct per_cpu_pages { spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int high_min; /* min high watermark */ int high_max; /* max high watermark */ int batch; /* chunk size for buddy add/remove */ u8 flags; /* protected by pcp->lock */ u8 alloc_factor; /* batch scaling factor during allocate */ #ifdef CONFIG_NUMA u8 expire; /* When 0, remote pagesets are drained */ #endif short free_count; /* consecutive free count */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; } ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; s8 stat_threshold; #endif #ifdef CONFIG_NUMA /* * Low priority inaccurate counters that are only folded * on demand. Use a large type to avoid the overhead of * folding during refresh_cpu_vm_stats. */ unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Therefore, we do not allow * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and * faulted, they come from the right zone right away. However, it is * still possible that address space already has pages in * ZONE_MOVABLE at the time when pages are pinned (i.e. user has * touches that memory before pinning). In such case we migrate them * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create * situations where ZERO_PAGE(0) which is allocated differently * on different platforms may end up in a movable zone. ZERO_PAGE(0) * cannot be migrated. * 7. Memory-hotplug: when using memmap_on_memory and onlining the * memory to the MOVABLE zone, the vmemmap pages are also placed in * such zone. Such pages cannot be really moved around as they are * self-stored in the range, but they are treated as movable when * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pages __percpu *per_cpu_pageset; struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access */ int pageset_high_min; int pageset_high_max; int pageset_batch; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * present_early_pages is present pages existing within the zone * located on memory available since early boot, excluding hotplugged * memory. * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * cma pages is present pages that are assigned for CMA use * (MIGRATE_CMA). * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/done(). Any reader who can't tolerant drift of * present_pages should use get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; #if defined(CONFIG_MEMORY_HOTPLUG) unsigned long present_early_pages; #endif #ifdef CONFIG_CMA unsigned long cma_pages; #endif const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[NR_PAGE_ORDERS]; #ifdef CONFIG_UNACCEPTED_MEMORY /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ struct list_head unaccepted_pages; #endif /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; static inline unsigned long wmark_pages(const struct zone *z, enum zone_watermarks w) { return z->_watermark[w] + z->watermark_boost; } static inline unsigned long min_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_MIN); } static inline unsigned long low_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_LOW); } static inline unsigned long high_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_HIGH); } static inline unsigned long promo_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_PROMO); } static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_cma_pages(struct zone *zone) { #ifdef CONFIG_CMA return zone->cma_pages; #else return 0; #endif } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) { return zone->spanned_pages == 0; } #ifndef BUILD_VDSO32_64 /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) #define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) #define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } static inline enum zone_type folio_zonenum(const struct folio *folio) { return page_zonenum(&folio->page); } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } /* * Consecutive zone device pages should not be merged into the same sgl * or bvec segment with other types of pages or if they belong to different * pgmaps. Otherwise getting the pgmap of a given segment is not possible * without scanning the entire segment. This helper returns true either if * both pages are not zone device pages or both pages are zone device pages * with the same pgmap. */ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { if (is_zone_device_page(a) != is_zone_device_page(b)) return false; if (!is_zone_device_page(a)) return true; return a->pgmap == b->pgmap; } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { return true; } #endif static inline bool folio_is_zone_device(const struct folio *folio) { return is_zone_device_page(&folio->page); } static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } static inline bool folio_is_zone_movable(const struct folio *folio) { return folio_zonenum(folio) == ZONE_MOVABLE; } #endif /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; /* * The array of struct pages for flatmem. * It must be declared for SPARSEMEM as well because there are configurations * that rely on that. */ extern struct page *mem_map; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif #ifdef CONFIG_MEMORY_FAILURE /* * Per NUMA node memory failure handling statistics. */ struct memory_failure_stats { /* * Number of raw pages poisoned. * Cases not accounted: memory outside kernel control, offline page, * arch-specific memory_failure (SGX), hwpoison_filter() filtered * error events, and unpoison actions from hwpoison_unpoison. */ unsigned long total; /* * Recovery results of poisoned raw pages handled by memory_failure, * in sync with mf_result. * total = ignored + failed + delayed + recovered. * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted. */ unsigned long ignored; unsigned long failed; unsigned long delayed; unsigned long recovered; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; /* workqueues for throttling reclaim for different reasons. */ wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ #ifdef CONFIG_MEMORY_HOTPLUG struct mutex kswapd_lock; #endif struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_NUMA_BALANCING /* start time in ms of current promote rate limit period */ unsigned int nbp_rl_start; /* number of promote candidate pages at start time of current rate limit period */ unsigned long nbp_rl_nr_cand; /* promote threshold in ms */ unsigned int nbp_threshold; /* start time in ms of current promote threshold adjustment period */ unsigned int nbp_th_start; /* * number of promote candidate pages at start time of current promote * threshold adjustment period */ unsigned long nbp_th_nr_cand; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA struct memory_tier __rcu *memtier; #endif #ifdef CONFIG_MEMORY_FAILURE struct memory_failure_stats mf_stats; #endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) #ifdef CONFIG_ZONE_DEVICE static inline bool zone_is_zone_device(struct zone *zone) { return zone_idx(zone) == ZONE_DEVICE; } #else static inline bool zone_is_zone_device(struct zone *zone) { return false; } #endif /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NUMA static inline int zone_to_nid(struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif } /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone: pointer to struct zone variable * Return: 1 for a highmem zone, 0 otherwise */ static inline int is_highmem(struct zone *zone) { return is_highmem_idx(zone_idx(zone)); } #ifdef CONFIG_ZONE_DMA bool has_managed_dma(void); #else static inline bool has_managed_dma(void) { return false; } #endif #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } #else /* CONFIG_NUMA */ #include <asm/mmzone.h> #endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat: pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone: pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z: The cursor used as a starting point for the search * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. * * Return: the next zone at or below highest_zoneidx within the allowed * nodemask using a cursor within a zonelist as a starting point */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist: The zonelist to search for a suitable zone * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. * * Return: Zoneref pointer for the first suitable zone found */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone: The current zone in the iterator * @z: The current pointer within zonelist->_zonerefs being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * @nodemask: Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone: The current zone in the iterator * @z: The current pointer within zonelist->zones being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) /* Whether the 'nodes' are all movable nodes */ static inline bool movable_only_nodes(nodemask_t *nodes) { struct zonelist *zonelist; struct zoneref *z; int nid; if (nodes_empty(*nodes)) return false; /* * We can chose arbitrary node from the nodemask to get a * zonelist as they are interlinked. We just need to find * at least one zone that can satisfy kernel allocations. */ nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); return (!zonelist_zone(z)) ? true : false; } #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; void subsection_map_init(unsigned long pfn, unsigned long nr_pages); struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse.c::sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store * a little bit of information. The pointer is calculated * as mem_map - section_nr_to_pfn(pnum). The result is * aligned to the minimum alignment of the two values: * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT * lowest bits. PFN_SECTION_SHIFT is arch-specific * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available on all architectures. * However, we can exceed 6 bits on some other architectures except * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available * with the worst case of 64K pages on arm64) if we make sure the * exceeded bit is not applicable to powerpc. */ enum { SECTION_MARKED_PRESENT_BIT, SECTION_HAS_MEM_MAP_BIT, SECTION_IS_ONLINE_BIT, SECTION_IS_EARLY_BIT, #ifdef CONFIG_ZONE_DEVICE SECTION_TAINT_ZONE_DEVICE_BIT, #endif SECTION_MAP_LAST_BIT, }; #define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) #define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) #define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) #define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) #ifdef CONFIG_ZONE_DEVICE #define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) #endif #define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) #define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } #ifdef CONFIG_ZONE_DEVICE static inline int online_device_section(struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } #else static inline int online_device_section(struct mem_section *section) { return 0; } #endif static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); struct mem_section_usage *usage = READ_ONCE(ms->usage); return usage ? test_bit(idx, usage->subsection_map) : 0; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID /** * pfn_valid - check if there is a valid memory map entry for a PFN * @pfn: the page frame number to check * * Check if there is a valid memory map entry aka struct page for the @pfn. * Note, that availability of the memory map entry does not imply that * there is actual usable memory at that @pfn. The struct page may * represent a hole or an unusable page frame. * * Return: 1 for PFNs that have memory map entries and 0 otherwise */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; /* * Ensure the upper PAGE_SHIFT bits are clear in the * pfn. Else it might lead to false positives when * some of the upper bits are set, but the lower bits * match a valid pfn. */ if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) return 0; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock_sched(); if (!valid_section(ms)) { rcu_read_unlock_sched(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock_sched(); return ret; } #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 319 195 292 284 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #define NO_INTERLEAVE_INDEX (-1UL) /* use task il_prev for interleaving */ #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/perfer */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. */ struct shared_policy { struct rb_root root; rwlock_t lock; }; struct sp_node { struct rb_node nd; pgoff_t start, end; struct mempolicy *policy; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *mpol); void mpol_free_shared_policy(struct shared_policy *sp); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); } extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); #else struct mempolicy {}; static inline struct mempolicy *get_task_policy(struct task_struct *p) { return NULL; } static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *pol) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *sp) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { return NULL; } static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { *ilx = 0; return NULL; } static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; } #endif /* CONFIG_NUMA */ #endif |
| 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * linux/drivers/net/netconsole.c * * Copyright (C) 2001 Ingo Molnar <mingo@redhat.com> * * This file contains the implementation of an IRQ-safe, crash-safe * kernel console implementation that outputs kernel messages to the * network. * * Modification history: * * 2001-09-17 started by Ingo Molnar. * 2003-08-11 2.6 port by Matt Mackall * simplified options * generic card hooks * works non-modular * 2003-09-07 rewritten with netpoll api */ /**************************************************************** * ****************************************************************/ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/console.h> #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/netpoll.h> #include <linux/inet.h> #include <linux/configfs.h> #include <linux/etherdevice.h> #include <linux/utsname.h> #include <linux/rtnetlink.h> MODULE_AUTHOR("Matt Mackall <mpm@selenic.com>"); MODULE_DESCRIPTION("Console driver for network interfaces"); MODULE_LICENSE("GPL"); #define MAX_PARAM_LENGTH 256 #define MAX_USERDATA_ENTRY_LENGTH 256 #define MAX_USERDATA_VALUE_LENGTH 200 /* The number 3 comes from userdata entry format characters (' ', '=', '\n') */ #define MAX_USERDATA_NAME_LENGTH (MAX_USERDATA_ENTRY_LENGTH - \ MAX_USERDATA_VALUE_LENGTH - 3) #define MAX_USERDATA_ITEMS 16 #define MAX_PRINT_CHUNK 1000 static char config[MAX_PARAM_LENGTH]; module_param_string(netconsole, config, MAX_PARAM_LENGTH, 0); MODULE_PARM_DESC(netconsole, " netconsole=[src-port]@[src-ip]/[dev],[tgt-port]@<tgt-ip>/[tgt-macaddr]"); static bool oops_only; module_param(oops_only, bool, 0600); MODULE_PARM_DESC(oops_only, "Only log oops messages"); #define NETCONSOLE_PARAM_TARGET_PREFIX "cmdline" #ifndef MODULE static int __init option_setup(char *opt) { strscpy(config, opt, MAX_PARAM_LENGTH); return 1; } __setup("netconsole=", option_setup); #endif /* MODULE */ /* Linked list of all configured targets */ static LIST_HEAD(target_list); /* target_cleanup_list is used to track targets that need to be cleaned outside * of target_list_lock. It should be cleaned in the same function it is * populated. */ static LIST_HEAD(target_cleanup_list); /* This needs to be a spinlock because write_msg() cannot sleep */ static DEFINE_SPINLOCK(target_list_lock); /* This needs to be a mutex because netpoll_cleanup might sleep */ static DEFINE_MUTEX(target_cleanup_list_lock); /* * Console driver for extended netconsoles. Registered on the first use to * avoid unnecessarily enabling ext message formatting. */ static struct console netconsole_ext; /** * struct netconsole_target - Represents a configured netconsole target. * @list: Links this target into the target_list. * @group: Links us into the configfs subsystem hierarchy. * @userdata_group: Links to the userdata configfs hierarchy * @userdata_complete: Cached, formatted string of append * @userdata_length: String length of userdata_complete * @enabled: On / off knob to enable / disable target. * Visible from userspace (read-write). * We maintain a strict 1:1 correspondence between this and * whether the corresponding netpoll is active or inactive. * Also, other parameters of a target may be modified at * runtime only when it is disabled (enabled == 0). * @extended: Denotes whether console is extended or not. * @release: Denotes whether kernel release version should be prepended * to the message. Depends on extended console. * @np: The netpoll structure for this target. * Contains the other userspace visible parameters: * dev_name (read-write) * local_port (read-write) * remote_port (read-write) * local_ip (read-write) * remote_ip (read-write) * local_mac (read-only) * remote_mac (read-write) */ struct netconsole_target { struct list_head list; #ifdef CONFIG_NETCONSOLE_DYNAMIC struct config_group group; struct config_group userdata_group; char userdata_complete[MAX_USERDATA_ENTRY_LENGTH * MAX_USERDATA_ITEMS]; size_t userdata_length; #endif bool enabled; bool extended; bool release; struct netpoll np; }; #ifdef CONFIG_NETCONSOLE_DYNAMIC static struct configfs_subsystem netconsole_subsys; static DEFINE_MUTEX(dynamic_netconsole_mutex); static int __init dynamic_netconsole_init(void) { config_group_init(&netconsole_subsys.su_group); mutex_init(&netconsole_subsys.su_mutex); return configfs_register_subsystem(&netconsole_subsys); } static void __exit dynamic_netconsole_exit(void) { configfs_unregister_subsystem(&netconsole_subsys); } /* * Targets that were created by parsing the boot/module option string * do not exist in the configfs hierarchy (and have NULL names) and will * never go away, so make these a no-op for them. */ static void netconsole_target_get(struct netconsole_target *nt) { if (config_item_name(&nt->group.cg_item)) config_group_get(&nt->group); } static void netconsole_target_put(struct netconsole_target *nt) { if (config_item_name(&nt->group.cg_item)) config_group_put(&nt->group); } #else /* !CONFIG_NETCONSOLE_DYNAMIC */ static int __init dynamic_netconsole_init(void) { return 0; } static void __exit dynamic_netconsole_exit(void) { } /* * No danger of targets going away from under us when dynamic * reconfigurability is off. */ static void netconsole_target_get(struct netconsole_target *nt) { } static void netconsole_target_put(struct netconsole_target *nt) { } static void populate_configfs_item(struct netconsole_target *nt, int cmdline_count) { } #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Allocate and initialize with defaults. * Note that these targets get their config_item fields zeroed-out. */ static struct netconsole_target *alloc_and_init(void) { struct netconsole_target *nt; nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) return nt; if (IS_ENABLED(CONFIG_NETCONSOLE_EXTENDED_LOG)) nt->extended = true; if (IS_ENABLED(CONFIG_NETCONSOLE_PREPEND_RELEASE)) nt->release = true; nt->np.name = "netconsole"; strscpy(nt->np.dev_name, "eth0", IFNAMSIZ); nt->np.local_port = 6665; nt->np.remote_port = 6666; eth_broadcast_addr(nt->np.remote_mac); return nt; } /* Clean up every target in the cleanup_list and move the clean targets back to * the main target_list. */ static void netconsole_process_cleanups_core(void) { struct netconsole_target *nt, *tmp; unsigned long flags; /* The cleanup needs RTNL locked */ ASSERT_RTNL(); mutex_lock(&target_cleanup_list_lock); list_for_each_entry_safe(nt, tmp, &target_cleanup_list, list) { /* all entries in the cleanup_list needs to be disabled */ WARN_ON_ONCE(nt->enabled); do_netpoll_cleanup(&nt->np); /* moved the cleaned target to target_list. Need to hold both * locks */ spin_lock_irqsave(&target_list_lock, flags); list_move(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); } WARN_ON_ONCE(!list_empty(&target_cleanup_list)); mutex_unlock(&target_cleanup_list_lock); } #ifdef CONFIG_NETCONSOLE_DYNAMIC /* * Our subsystem hierarchy is: * * /sys/kernel/config/netconsole/ * | * <target>/ * | enabled * | release * | dev_name * | local_port * | remote_port * | local_ip * | remote_ip * | local_mac * | remote_mac * | userdata/ * | <key>/ * | value * | ... * | * <target>/... */ static struct netconsole_target *to_target(struct config_item *item) { struct config_group *cfg_group; cfg_group = to_config_group(item); if (!cfg_group) return NULL; return container_of(to_config_group(item), struct netconsole_target, group); } /* Do the list cleanup with the rtnl lock hold. rtnl lock is necessary because * netdev might be cleaned-up by calling __netpoll_cleanup(), */ static void netconsole_process_cleanups(void) { /* rtnl lock is called here, because it has precedence over * target_cleanup_list_lock mutex and target_cleanup_list */ rtnl_lock(); netconsole_process_cleanups_core(); rtnl_unlock(); } /* Get rid of possible trailing newline, returning the new length */ static void trim_newline(char *s, size_t maxlen) { size_t len; len = strnlen(s, maxlen); if (s[len - 1] == '\n') s[len - 1] = '\0'; } /* * Attribute operations for netconsole_target. */ static ssize_t enabled_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->enabled); } static ssize_t extended_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->extended); } static ssize_t release_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->release); } static ssize_t dev_name_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%s\n", to_target(item)->np.dev_name); } static ssize_t local_port_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->np.local_port); } static ssize_t remote_port_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->np.remote_port); } static ssize_t local_ip_show(struct config_item *item, char *buf) { struct netconsole_target *nt = to_target(item); if (nt->np.ipv6) return sysfs_emit(buf, "%pI6c\n", &nt->np.local_ip.in6); else return sysfs_emit(buf, "%pI4\n", &nt->np.local_ip); } static ssize_t remote_ip_show(struct config_item *item, char *buf) { struct netconsole_target *nt = to_target(item); if (nt->np.ipv6) return sysfs_emit(buf, "%pI6c\n", &nt->np.remote_ip.in6); else return sysfs_emit(buf, "%pI4\n", &nt->np.remote_ip); } static ssize_t local_mac_show(struct config_item *item, char *buf) { struct net_device *dev = to_target(item)->np.dev; static const u8 bcast[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; return sysfs_emit(buf, "%pM\n", dev ? dev->dev_addr : bcast); } static ssize_t remote_mac_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%pM\n", to_target(item)->np.remote_mac); } /* * This one is special -- targets created through the configfs interface * are not enabled (and the corresponding netpoll activated) by default. * The user is expected to set the desired parameters first (which * would enable him to dynamically add new netpoll targets for new * network interfaces as and when they come up). */ static ssize_t enabled_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); unsigned long flags; bool enabled; ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); ret = kstrtobool(buf, &enabled); if (ret) goto out_unlock; ret = -EINVAL; if (enabled == nt->enabled) { pr_info("network logging has already %s\n", nt->enabled ? "started" : "stopped"); goto out_unlock; } if (enabled) { /* true */ if (nt->release && !nt->extended) { pr_err("Not enabling netconsole. Release feature requires extended log message"); goto out_unlock; } if (nt->extended && !console_is_registered(&netconsole_ext)) register_console(&netconsole_ext); /* * Skip netpoll_parse_options() -- all the attributes are * already configured via configfs. Just print them out. */ netpoll_print_options(&nt->np); ret = netpoll_setup(&nt->np); if (ret) goto out_unlock; nt->enabled = true; pr_info("network logging started\n"); } else { /* false */ /* We need to disable the netconsole before cleaning it up * otherwise we might end up in write_msg() with * nt->np.dev == NULL and nt->enabled == true */ mutex_lock(&target_cleanup_list_lock); spin_lock_irqsave(&target_list_lock, flags); nt->enabled = false; /* Remove the target from the list, while holding * target_list_lock */ list_move(&nt->list, &target_cleanup_list); spin_unlock_irqrestore(&target_list_lock, flags); mutex_unlock(&target_cleanup_list_lock); } ret = strnlen(buf, count); /* Deferred cleanup */ netconsole_process_cleanups(); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t release_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); bool release; ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); ret = -EINVAL; goto out_unlock; } ret = kstrtobool(buf, &release); if (ret) goto out_unlock; nt->release = release; ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t extended_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); bool extended; ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); ret = -EINVAL; goto out_unlock; } ret = kstrtobool(buf, &extended); if (ret) goto out_unlock; nt->extended = extended; ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t dev_name_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } strscpy(nt->np.dev_name, buf, IFNAMSIZ); trim_newline(nt->np.dev_name, IFNAMSIZ); mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); } static ssize_t local_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } ret = kstrtou16(buf, 10, &nt->np.local_port); if (ret < 0) goto out_unlock; ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t remote_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } ret = kstrtou16(buf, 10, &nt->np.remote_port); if (ret < 0) goto out_unlock; ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t local_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } if (strnchr(buf, count, ':')) { const char *end; if (in6_pton(buf, count, nt->np.local_ip.in6.s6_addr, -1, &end) > 0) { if (*end && *end != '\n') { pr_err("invalid IPv6 address at: <%c>\n", *end); goto out_unlock; } nt->np.ipv6 = true; } else goto out_unlock; } else { if (!nt->np.ipv6) nt->np.local_ip.ip = in_aton(buf); else goto out_unlock; } ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t remote_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } if (strnchr(buf, count, ':')) { const char *end; if (in6_pton(buf, count, nt->np.remote_ip.in6.s6_addr, -1, &end) > 0) { if (*end && *end != '\n') { pr_err("invalid IPv6 address at: <%c>\n", *end); goto out_unlock; } nt->np.ipv6 = true; } else goto out_unlock; } else { if (!nt->np.ipv6) nt->np.remote_ip.ip = in_aton(buf); else goto out_unlock; } ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } static ssize_t remote_mac_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); u8 remote_mac[ETH_ALEN]; ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } if (!mac_pton(buf, remote_mac)) goto out_unlock; if (buf[3 * ETH_ALEN - 1] && buf[3 * ETH_ALEN - 1] != '\n') goto out_unlock; memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN); ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } struct userdatum { struct config_item item; char value[MAX_USERDATA_VALUE_LENGTH]; }; static struct userdatum *to_userdatum(struct config_item *item) { return container_of(item, struct userdatum, item); } struct userdata { struct config_group group; }; static struct userdata *to_userdata(struct config_item *item) { return container_of(to_config_group(item), struct userdata, group); } static struct netconsole_target *userdata_to_target(struct userdata *ud) { struct config_group *netconsole_group; netconsole_group = to_config_group(ud->group.cg_item.ci_parent); return to_target(&netconsole_group->cg_item); } static ssize_t userdatum_value_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%s\n", &(to_userdatum(item)->value[0])); } static void update_userdata(struct netconsole_target *nt) { int complete_idx = 0, child_count = 0; struct list_head *entry; /* Clear the current string in case the last userdatum was deleted */ nt->userdata_length = 0; nt->userdata_complete[0] = 0; list_for_each(entry, &nt->userdata_group.cg_children) { struct userdatum *udm_item; struct config_item *item; if (child_count >= MAX_USERDATA_ITEMS) break; child_count++; item = container_of(entry, struct config_item, ci_entry); udm_item = to_userdatum(item); /* Skip userdata with no value set */ if (strnlen(udm_item->value, MAX_USERDATA_VALUE_LENGTH) == 0) continue; /* This doesn't overflow userdata_complete since it will write * one entry length (1/MAX_USERDATA_ITEMS long), entry count is * checked to not exceed MAX items with child_count above */ complete_idx += scnprintf(&nt->userdata_complete[complete_idx], MAX_USERDATA_ENTRY_LENGTH, " %s=%s\n", item->ci_name, udm_item->value); } nt->userdata_length = strnlen(nt->userdata_complete, sizeof(nt->userdata_complete)); } static ssize_t userdatum_value_store(struct config_item *item, const char *buf, size_t count) { struct userdatum *udm = to_userdatum(item); struct netconsole_target *nt; struct userdata *ud; ssize_t ret; if (count > MAX_USERDATA_VALUE_LENGTH) return -EMSGSIZE; mutex_lock(&dynamic_netconsole_mutex); ret = strscpy(udm->value, buf, sizeof(udm->value)); if (ret < 0) goto out_unlock; trim_newline(udm->value, sizeof(udm->value)); ud = to_userdata(item->ci_parent); nt = userdata_to_target(ud); update_userdata(nt); ret = count; out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } CONFIGFS_ATTR(userdatum_, value); static struct configfs_attribute *userdatum_attrs[] = { &userdatum_attr_value, NULL, }; static void userdatum_release(struct config_item *item) { kfree(to_userdatum(item)); } static struct configfs_item_operations userdatum_ops = { .release = userdatum_release, }; static const struct config_item_type userdatum_type = { .ct_item_ops = &userdatum_ops, .ct_attrs = userdatum_attrs, .ct_owner = THIS_MODULE, }; static struct config_item *userdatum_make_item(struct config_group *group, const char *name) { struct netconsole_target *nt; struct userdatum *udm; struct userdata *ud; size_t child_count; if (strlen(name) > MAX_USERDATA_NAME_LENGTH) return ERR_PTR(-ENAMETOOLONG); ud = to_userdata(&group->cg_item); nt = userdata_to_target(ud); child_count = list_count_nodes(&nt->userdata_group.cg_children); if (child_count >= MAX_USERDATA_ITEMS) return ERR_PTR(-ENOSPC); udm = kzalloc(sizeof(*udm), GFP_KERNEL); if (!udm) return ERR_PTR(-ENOMEM); config_item_init_type_name(&udm->item, name, &userdatum_type); return &udm->item; } static void userdatum_drop(struct config_group *group, struct config_item *item) { struct netconsole_target *nt; struct userdata *ud; ud = to_userdata(&group->cg_item); nt = userdata_to_target(ud); mutex_lock(&dynamic_netconsole_mutex); update_userdata(nt); config_item_put(item); mutex_unlock(&dynamic_netconsole_mutex); } static struct configfs_attribute *userdata_attrs[] = { NULL, }; static struct configfs_group_operations userdata_ops = { .make_item = userdatum_make_item, .drop_item = userdatum_drop, }; static const struct config_item_type userdata_type = { .ct_item_ops = &userdatum_ops, .ct_group_ops = &userdata_ops, .ct_attrs = userdata_attrs, .ct_owner = THIS_MODULE, }; CONFIGFS_ATTR(, enabled); CONFIGFS_ATTR(, extended); CONFIGFS_ATTR(, dev_name); CONFIGFS_ATTR(, local_port); CONFIGFS_ATTR(, remote_port); CONFIGFS_ATTR(, local_ip); CONFIGFS_ATTR(, remote_ip); CONFIGFS_ATTR_RO(, local_mac); CONFIGFS_ATTR(, remote_mac); CONFIGFS_ATTR(, release); static struct configfs_attribute *netconsole_target_attrs[] = { &attr_enabled, &attr_extended, &attr_release, &attr_dev_name, &attr_local_port, &attr_remote_port, &attr_local_ip, &attr_remote_ip, &attr_local_mac, &attr_remote_mac, NULL, }; /* * Item operations and type for netconsole_target. */ static void netconsole_target_release(struct config_item *item) { kfree(to_target(item)); } static struct configfs_item_operations netconsole_target_item_ops = { .release = netconsole_target_release, }; static const struct config_item_type netconsole_target_type = { .ct_attrs = netconsole_target_attrs, .ct_item_ops = &netconsole_target_item_ops, .ct_owner = THIS_MODULE, }; static void init_target_config_group(struct netconsole_target *nt, const char *name) { config_group_init_type_name(&nt->group, name, &netconsole_target_type); config_group_init_type_name(&nt->userdata_group, "userdata", &userdata_type); configfs_add_default_group(&nt->userdata_group, &nt->group); } static struct netconsole_target *find_cmdline_target(const char *name) { struct netconsole_target *nt, *ret = NULL; unsigned long flags; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) { if (!strcmp(nt->group.cg_item.ci_name, name)) { ret = nt; break; } } spin_unlock_irqrestore(&target_list_lock, flags); return ret; } /* * Group operations and type for netconsole_subsys. */ static struct config_group *make_netconsole_target(struct config_group *group, const char *name) { struct netconsole_target *nt; unsigned long flags; /* Checking if a target by this name was created at boot time. If so, * attach a configfs entry to that target. This enables dynamic * control. */ if (!strncmp(name, NETCONSOLE_PARAM_TARGET_PREFIX, strlen(NETCONSOLE_PARAM_TARGET_PREFIX))) { nt = find_cmdline_target(name); if (nt) { init_target_config_group(nt, name); return &nt->group; } } nt = alloc_and_init(); if (!nt) return ERR_PTR(-ENOMEM); /* Initialize the config_group member */ init_target_config_group(nt, name); /* Adding, but it is disabled */ spin_lock_irqsave(&target_list_lock, flags); list_add(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); return &nt->group; } static void drop_netconsole_target(struct config_group *group, struct config_item *item) { unsigned long flags; struct netconsole_target *nt = to_target(item); spin_lock_irqsave(&target_list_lock, flags); list_del(&nt->list); spin_unlock_irqrestore(&target_list_lock, flags); /* * The target may have never been enabled, or was manually disabled * before being removed so netpoll may have already been cleaned up. */ if (nt->enabled) netpoll_cleanup(&nt->np); config_item_put(&nt->group.cg_item); } static struct configfs_group_operations netconsole_subsys_group_ops = { .make_group = make_netconsole_target, .drop_item = drop_netconsole_target, }; static const struct config_item_type netconsole_subsys_type = { .ct_group_ops = &netconsole_subsys_group_ops, .ct_owner = THIS_MODULE, }; /* The netconsole configfs subsystem */ static struct configfs_subsystem netconsole_subsys = { .su_group = { .cg_item = { .ci_namebuf = "netconsole", .ci_type = &netconsole_subsys_type, }, }, }; static void populate_configfs_item(struct netconsole_target *nt, int cmdline_count) { char target_name[16]; snprintf(target_name, sizeof(target_name), "%s%d", NETCONSOLE_PARAM_TARGET_PREFIX, cmdline_count); init_target_config_group(nt, target_name); } #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Handle network interface device notifications */ static int netconsole_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { unsigned long flags; struct netconsole_target *nt, *tmp; struct net_device *dev = netdev_notifier_info_to_dev(ptr); bool stopped = false; if (!(event == NETDEV_CHANGENAME || event == NETDEV_UNREGISTER || event == NETDEV_RELEASE || event == NETDEV_JOIN)) goto done; mutex_lock(&target_cleanup_list_lock); spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry_safe(nt, tmp, &target_list, list) { netconsole_target_get(nt); if (nt->np.dev == dev) { switch (event) { case NETDEV_CHANGENAME: strscpy(nt->np.dev_name, dev->name, IFNAMSIZ); break; case NETDEV_RELEASE: case NETDEV_JOIN: case NETDEV_UNREGISTER: nt->enabled = false; list_move(&nt->list, &target_cleanup_list); stopped = true; } } netconsole_target_put(nt); } spin_unlock_irqrestore(&target_list_lock, flags); mutex_unlock(&target_cleanup_list_lock); if (stopped) { const char *msg = "had an event"; switch (event) { case NETDEV_UNREGISTER: msg = "unregistered"; break; case NETDEV_RELEASE: msg = "released slaves"; break; case NETDEV_JOIN: msg = "is joining a master device"; break; } pr_info("network logging stopped on interface %s as it %s\n", dev->name, msg); } /* Process target_cleanup_list entries. By the end, target_cleanup_list * should be empty */ netconsole_process_cleanups_core(); done: return NOTIFY_DONE; } static struct notifier_block netconsole_netdev_notifier = { .notifier_call = netconsole_netdev_event, }; /** * send_ext_msg_udp - send extended log message to target * @nt: target to send message to * @msg: extended log message to send * @msg_len: length of message * * Transfer extended log @msg to @nt. If @msg is longer than * MAX_PRINT_CHUNK, it'll be split and transmitted in multiple chunks with * ncfrag header field added to identify them. */ static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg, int msg_len) { static char buf[MAX_PRINT_CHUNK]; /* protected by target_list_lock */ const char *header, *body; int offset = 0; int header_len, body_len; const char *msg_ready = msg; const char *release; int release_len = 0; int userdata_len = 0; char *userdata = NULL; #ifdef CONFIG_NETCONSOLE_DYNAMIC userdata = nt->userdata_complete; userdata_len = nt->userdata_length; #endif if (nt->release) { release = init_utsname()->release; release_len = strlen(release) + 1; } if (msg_len + release_len + userdata_len <= MAX_PRINT_CHUNK) { /* No fragmentation needed */ if (nt->release) { scnprintf(buf, MAX_PRINT_CHUNK, "%s,%s", release, msg); msg_len += release_len; } else { memcpy(buf, msg, msg_len); } if (userdata) msg_len += scnprintf(&buf[msg_len], MAX_PRINT_CHUNK - msg_len, "%s", userdata); msg_ready = buf; netpoll_send_udp(&nt->np, msg_ready, msg_len); return; } /* need to insert extra header fields, detect header and body */ header = msg; body = memchr(msg, ';', msg_len); if (WARN_ON_ONCE(!body)) return; header_len = body - header; body_len = msg_len - header_len - 1; body++; /* * Transfer multiple chunks with the following extra header. * "ncfrag=<byte-offset>/<total-bytes>" */ if (nt->release) scnprintf(buf, MAX_PRINT_CHUNK, "%s,", release); memcpy(buf + release_len, header, header_len); header_len += release_len; while (offset < body_len + userdata_len) { int this_header = header_len; int this_offset = 0; int this_chunk = 0; this_header += scnprintf(buf + this_header, sizeof(buf) - this_header, ",ncfrag=%d/%d;", offset, body_len + userdata_len); /* Not all body data has been written yet */ if (offset < body_len) { this_chunk = min(body_len - offset, MAX_PRINT_CHUNK - this_header); if (WARN_ON_ONCE(this_chunk <= 0)) return; memcpy(buf + this_header, body + offset, this_chunk); this_offset += this_chunk; } /* Body is fully written and there is pending userdata to write, * append userdata in this chunk */ if (offset + this_offset >= body_len && offset + this_offset < userdata_len + body_len) { int sent_userdata = (offset + this_offset) - body_len; int preceding_bytes = this_chunk + this_header; if (WARN_ON_ONCE(sent_userdata < 0)) return; this_chunk = min(userdata_len - sent_userdata, MAX_PRINT_CHUNK - preceding_bytes); if (WARN_ON_ONCE(this_chunk < 0)) /* this_chunk could be zero if all the previous * message used all the buffer. This is not a * problem, userdata will be sent in the next * iteration */ return; memcpy(buf + this_header + this_offset, userdata + sent_userdata, this_chunk); this_offset += this_chunk; } netpoll_send_udp(&nt->np, buf, this_header + this_offset); offset += this_offset; } } static void write_ext_msg(struct console *con, const char *msg, unsigned int len) { struct netconsole_target *nt; unsigned long flags; if ((oops_only && !oops_in_progress) || list_empty(&target_list)) return; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) if (nt->extended && nt->enabled && netif_running(nt->np.dev)) send_ext_msg_udp(nt, msg, len); spin_unlock_irqrestore(&target_list_lock, flags); } static void write_msg(struct console *con, const char *msg, unsigned int len) { int frag, left; unsigned long flags; struct netconsole_target *nt; const char *tmp; if (oops_only && !oops_in_progress) return; /* Avoid taking lock and disabling interrupts unnecessarily */ if (list_empty(&target_list)) return; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) { if (!nt->extended && nt->enabled && netif_running(nt->np.dev)) { /* * We nest this inside the for-each-target loop above * so that we're able to get as much logging out to * at least one target if we die inside here, instead * of unnecessarily keeping all targets in lock-step. */ tmp = msg; for (left = len; left;) { frag = min(left, MAX_PRINT_CHUNK); netpoll_send_udp(&nt->np, tmp, frag); tmp += frag; left -= frag; } } } spin_unlock_irqrestore(&target_list_lock, flags); } /* Allocate new target (from boot/module param) and setup netpoll for it */ static struct netconsole_target *alloc_param_target(char *target_config, int cmdline_count) { struct netconsole_target *nt; int err; nt = alloc_and_init(); if (!nt) { err = -ENOMEM; goto fail; } if (*target_config == '+') { nt->extended = true; target_config++; } if (*target_config == 'r') { if (!nt->extended) { pr_err("Netconsole configuration error. Release feature requires extended log message"); err = -EINVAL; goto fail; } nt->release = true; target_config++; } /* Parse parameters and setup netpoll */ err = netpoll_parse_options(&nt->np, target_config); if (err) goto fail; err = netpoll_setup(&nt->np); if (err) { pr_err("Not enabling netconsole for %s%d. Netpoll setup failed\n", NETCONSOLE_PARAM_TARGET_PREFIX, cmdline_count); if (!IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) /* only fail if dynamic reconfiguration is set, * otherwise, keep the target in the list, but disabled. */ goto fail; } else { nt->enabled = true; } populate_configfs_item(nt, cmdline_count); return nt; fail: kfree(nt); return ERR_PTR(err); } /* Cleanup netpoll for given target (from boot/module param) and free it */ static void free_param_target(struct netconsole_target *nt) { netpoll_cleanup(&nt->np); kfree(nt); } static struct console netconsole_ext = { .name = "netcon_ext", .flags = CON_ENABLED | CON_EXTENDED, .write = write_ext_msg, }; static struct console netconsole = { .name = "netcon", .flags = CON_ENABLED, .write = write_msg, }; static int __init init_netconsole(void) { int err; struct netconsole_target *nt, *tmp; unsigned int count = 0; bool extended = false; unsigned long flags; char *target_config; char *input = config; if (strnlen(input, MAX_PARAM_LENGTH)) { while ((target_config = strsep(&input, ";"))) { nt = alloc_param_target(target_config, count); if (IS_ERR(nt)) { if (IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) continue; err = PTR_ERR(nt); goto fail; } /* Dump existing printks when we register */ if (nt->extended) { extended = true; netconsole_ext.flags |= CON_PRINTBUFFER; } else { netconsole.flags |= CON_PRINTBUFFER; } spin_lock_irqsave(&target_list_lock, flags); list_add(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); count++; } } err = register_netdevice_notifier(&netconsole_netdev_notifier); if (err) goto fail; err = dynamic_netconsole_init(); if (err) goto undonotifier; if (extended) register_console(&netconsole_ext); register_console(&netconsole); pr_info("network logging started\n"); return err; undonotifier: unregister_netdevice_notifier(&netconsole_netdev_notifier); fail: pr_err("cleaning up\n"); /* * Remove all targets and destroy them (only targets created * from the boot/module option exist here). Skipping the list * lock is safe here, and netpoll_cleanup() will sleep. */ list_for_each_entry_safe(nt, tmp, &target_list, list) { list_del(&nt->list); free_param_target(nt); } return err; } static void __exit cleanup_netconsole(void) { struct netconsole_target *nt, *tmp; if (console_is_registered(&netconsole_ext)) unregister_console(&netconsole_ext); unregister_console(&netconsole); dynamic_netconsole_exit(); unregister_netdevice_notifier(&netconsole_netdev_notifier); /* * Targets created via configfs pin references on our module * and would first be rmdir(2)'ed from userspace. We reach * here only when they are already destroyed, and only those * created from the boot/module option are left, so remove and * destroy them. Skipping the list lock is safe here, and * netpoll_cleanup() will sleep. */ list_for_each_entry_safe(nt, tmp, &target_list, list) { list_del(&nt->list); free_param_target(nt); } } /* * Use late_initcall to ensure netconsole is * initialized after network device driver if built-in. * * late_initcall() and module_init() are identical if built as module. */ late_initcall(init_netconsole); module_exit(cleanup_netconsole); |
| 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 | // SPDX-License-Identifier: GPL-2.0-only /* * ratelimit.c - Do something with rate limit. * * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com> * * 2008-05-01 rewrite the function and use a ratelimit_state data struct as * parameter. Now every user can use their own standalone ratelimit_state. */ #include <linux/ratelimit.h> #include <linux/jiffies.h> #include <linux/export.h> /* * __ratelimit - rate limiting * @rs: ratelimit_state data * @func: name of calling function * * This enforces a rate limit: not more than @rs->burst callbacks * in every @rs->interval * * RETURNS: * 0 means callbacks will be suppressed. * 1 means go ahead and do it. */ int ___ratelimit(struct ratelimit_state *rs, const char *func) { /* Paired with WRITE_ONCE() in .proc_handler(). * Changing two values seperately could be inconsistent * and some message could be lost. (See: net_ratelimit_state). */ int interval = READ_ONCE(rs->interval); int burst = READ_ONCE(rs->burst); unsigned long flags; int ret; if (!interval) return 1; /* * If we contend on this state's lock then almost * by definition we are too busy to print a message, * in addition to the one that will be printed by * the entity that is holding the lock already: */ if (!raw_spin_trylock_irqsave(&rs->lock, flags)) return 0; if (!rs->begin) rs->begin = jiffies; if (time_is_before_jiffies(rs->begin + interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { printk_deferred(KERN_WARNING "%s: %d callbacks suppressed\n", func, rs->missed); rs->missed = 0; } } rs->begin = jiffies; rs->printed = 0; } if (burst && burst > rs->printed) { rs->printed++; ret = 1; } else { rs->missed++; ret = 0; } raw_spin_unlock_irqrestore(&rs->lock, flags); return ret; } EXPORT_SYMBOL(___ratelimit); |
| 85 85 85 491 85 85 179 180 178 179 178 179 179 1 1 19 20 10 11 180 180 179 1 20 31 11 11 144 2 144 144 144 144 2 2 2 2 250 249 202 202 85 388 207 249 471 472 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/capability.h> #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include <linux/mnt_idmapping.h> #include <linux/nospec.h> #include "pnode.h" #include "internal.h" /* Maximum number of mounts in a mount namespace */ static unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __ro_after_init; static unsigned int m_hash_shift __ro_after_init; static unsigned int mp_hash_mask __ro_after_init; static unsigned int mp_hash_shift __ro_after_init; static __initdata unsigned long mhash_entries; static int __init set_mhash_entries(char *str) { if (!str) return 0; mhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mhash_entries=", set_mhash_entries); static __initdata unsigned long mphash_entries; static int __init set_mphash_entries(char *str) { if (!str) return 0; mphash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mphash_entries=", set_mphash_entries); static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); /* Don't allow confusion with old 32bit mount ID */ #define MNT_UNIQUE_ID_OFFSET (1ULL << 31) static atomic64_t mnt_id_ctr = ATOMIC64_INIT(MNT_UNIQUE_ID_OFFSET); static struct hlist_head *mount_hashtable __ro_after_init; static struct hlist_head *mountpoint_hashtable __ro_after_init; static struct kmem_cache *mnt_cache __ro_after_init; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ static DEFINE_RWLOCK(mnt_ns_tree_lock); static struct rb_root mnt_ns_tree = RB_ROOT; /* protected by mnt_ns_tree_lock */ struct mount_kattr { unsigned int attr_set; unsigned int attr_clr; unsigned int propagation; unsigned int lookup_flags; bool recurse; struct user_namespace *mnt_userns; struct mnt_idmap *mnt_idmap; }; /* /sys/fs */ struct kobject *fs_kobj __ro_after_init; EXPORT_SYMBOL_GPL(fs_kobj); /* * vfsmount lock may be taken for read to prevent changes to the * vfsmount hash, ie. during mountpoint lookups or walking back * up the tree. * * It should be taken for write in all cases where the vfsmount * tree or hash is modified or when a vfsmount structure is modified. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); static int mnt_ns_cmp(u64 seq, const struct mnt_namespace *ns) { u64 seq_b = ns->seq; if (seq < seq_b) return -1; if (seq > seq_b) return 1; return 0; } static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node) { if (!node) return NULL; return rb_entry(node, struct mnt_namespace, mnt_ns_tree_node); } static bool mnt_ns_less(struct rb_node *a, const struct rb_node *b) { struct mnt_namespace *ns_a = node_to_mnt_ns(a); struct mnt_namespace *ns_b = node_to_mnt_ns(b); u64 seq_a = ns_a->seq; return mnt_ns_cmp(seq_a, ns_b) < 0; } static void mnt_ns_tree_add(struct mnt_namespace *ns) { guard(write_lock)(&mnt_ns_tree_lock); rb_add(&ns->mnt_ns_tree_node, &mnt_ns_tree, mnt_ns_less); } static void mnt_ns_release(struct mnt_namespace *ns) { lockdep_assert_not_held(&mnt_ns_tree_lock); /* keep alive for {list,stat}mount() */ if (refcount_dec_and_test(&ns->passive)) { put_user_ns(ns->user_ns); kfree(ns); } } DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T)) static void mnt_ns_tree_remove(struct mnt_namespace *ns) { /* remove from global mount namespace list */ if (!is_anon_ns(ns)) { guard(write_lock)(&mnt_ns_tree_lock); rb_erase(&ns->mnt_ns_tree_node, &mnt_ns_tree); } mnt_ns_release(ns); } /* * Returns the mount namespace which either has the specified id, or has the * next smallest id afer the specified one. */ static struct mnt_namespace *mnt_ns_find_id_at(u64 mnt_ns_id) { struct rb_node *node = mnt_ns_tree.rb_node; struct mnt_namespace *ret = NULL; lockdep_assert_held(&mnt_ns_tree_lock); while (node) { struct mnt_namespace *n = node_to_mnt_ns(node); if (mnt_ns_id <= n->seq) { ret = node_to_mnt_ns(node); if (mnt_ns_id == n->seq) break; node = node->rb_left; } else { node = node->rb_right; } } return ret; } /* * Lookup a mount namespace by id and take a passive reference count. Taking a * passive reference means the mount namespace can be emptied if e.g., the last * task holding an active reference exits. To access the mounts of the * namespace the @namespace_sem must first be acquired. If the namespace has * already shut down before acquiring @namespace_sem, {list,stat}mount() will * see that the mount rbtree of the namespace is empty. */ static struct mnt_namespace *lookup_mnt_ns(u64 mnt_ns_id) { struct mnt_namespace *ns; guard(read_lock)(&mnt_ns_tree_lock); ns = mnt_ns_find_id_at(mnt_ns_id); if (!ns || ns->seq != mnt_ns_id) return NULL; refcount_inc(&ns->passive); return ns; } static inline void lock_mount_hash(void) { write_seqlock(&mount_lock); } static inline void unlock_mount_hash(void) { write_sequnlock(&mount_lock); } static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> m_hash_shift); return &mount_hashtable[tmp & m_hash_mask]; } static inline struct hlist_head *mp_hash(struct dentry *dentry) { unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> mp_hash_shift); return &mountpoint_hashtable[tmp & mp_hash_mask]; } static int mnt_alloc_id(struct mount *mnt) { int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); if (res < 0) return res; mnt->mnt_id = res; mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr); return 0; } static void mnt_free_id(struct mount *mnt) { ida_free(&mnt_id_ida, mnt->mnt_id); } /* * Allocate a new peer group ID */ static int mnt_alloc_group_id(struct mount *mnt) { int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL); if (res < 0) return res; mnt->mnt_group_id = res; return 0; } /* * Release a peer group ID */ void mnt_release_group_id(struct mount *mnt) { ida_free(&mnt_group_ida, mnt->mnt_group_id); mnt->mnt_group_id = 0; } /* * vfsmount lock must be held for read */ static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); #else preempt_disable(); mnt->mnt_count += n; preempt_enable(); #endif } /* * vfsmount lock must be held for write */ int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count; } return count; #else return mnt->mnt_count; #endif } static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; err = mnt_alloc_id(mnt); if (err) goto out_free_cache; if (name) { mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL_ACCOUNT); if (!mnt->mnt_devname) goto out_free_id; } #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); if (!mnt->mnt_pcp) goto out_free_devname; this_cpu_add(mnt->mnt_pcp->mnt_count, 1); #else mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); INIT_LIST_HEAD(&mnt->mnt_share); INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); mnt->mnt.mnt_idmap = &nop_mnt_idmap; } return mnt; #ifdef CONFIG_SMP out_free_devname: kfree_const(mnt->mnt_devname); #endif out_free_id: mnt_free_id(mnt); out_free_cache: kmem_cache_free(mnt_cache, mnt); return NULL; } /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). * We must keep track of when those operations start * (for permission checks) and when they end, so that * we can determine when writes are able to occur to * a filesystem. */ /* * __mnt_is_readonly: check whether a mount is read-only * @mnt: the mount to check for its write status * * This shouldn't be used directly ouside of the VFS. * It does not guarantee that the filesystem will stay * r/w, just that it is right *now*. This can not and * should not be used in place of IS_RDONLY(inode). * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ bool __mnt_is_readonly(struct vfsmount *mnt) { return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers++; #endif } static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers--; #endif } static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers; } return count; #else return mnt->mnt_writers; #endif } static int mnt_is_readonly(struct vfsmount *mnt) { if (READ_ONCE(mnt->mnt_sb->s_readonly_remount)) return 1; /* * The barrier pairs with the barrier in sb_start_ro_state_change() * making sure if we don't see s_readonly_remount set yet, we also will * not see any superblock / mount flag changes done by remount. * It also pairs with the barrier in sb_end_ro_state_change() * assuring that if we see s_readonly_remount already cleared, we will * see the values of superblock / mount flags updated by remount. */ smp_rmb(); return __mnt_is_readonly(mnt); } /* * Most r/o & frozen checks on a fs are for operations that take discrete * amounts of time, like a write() or unlink(). We must keep track of when * those operations start (for permission checks) and when they end, so that we * can determine when writes are able to occur to a filesystem. */ /** * mnt_get_write_access - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being * frozen. When the write operation is finished, mnt_put_write_access() must be * called. This is effectively a refcount. */ int mnt_get_write_access(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); mnt_inc_writers(mnt); /* * The store to mnt_inc_writers must be visible before we pass * MNT_WRITE_HOLD loop below, so that the slowpath can see our * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); might_lock(&mount_lock.lock); while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { cpu_relax(); } else { /* * This prevents priority inversion, if the task * setting MNT_WRITE_HOLD got preempted on a remote * CPU, and it prevents life lock if the task setting * MNT_WRITE_HOLD has a lower priority and is bound to * the same CPU as the task that is spinning here. */ preempt_enable(); lock_mount_hash(); unlock_mount_hash(); preempt_disable(); } } /* * The barrier pairs with the barrier sb_start_ro_state_change() making * sure that if we see MNT_WRITE_HOLD cleared, we will also see * s_readonly_remount set (or even SB_RDONLY / MNT_READONLY flags) in * mnt_is_readonly() and bail in case we are racing with remount * read-only. */ smp_rmb(); if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; } preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(mnt_get_write_access); /** * mnt_want_write - get write access to a mount * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mount is read-write, filesystem * is not frozen) before returning success. When the write operation is * finished, mnt_drop_write() must be called. This is effectively a refcount. */ int mnt_want_write(struct vfsmount *m) { int ret; sb_start_write(m->mnt_sb); ret = mnt_get_write_access(m); if (ret) sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); /** * mnt_get_write_access_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_get_write_access, but if @file is already open for write it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the check for emergency r/o remounts. This must be * paired with mnt_put_write_access_file. */ int mnt_get_write_access_file(struct file *file) { if (file->f_mode & FMODE_WRITER) { /* * Superblock may have become readonly while there are still * writable fd's, e.g. due to a fs error with errors=remount-ro */ if (__mnt_is_readonly(file->f_path.mnt)) return -EROFS; return 0; } return mnt_get_write_access(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but if the file is already open for writing it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the freeze protection and the check for emergency r/o * remounts. This must be paired with mnt_drop_write_file. */ int mnt_want_write_file(struct file *file) { int ret; sb_start_write(file_inode(file)->i_sb); ret = mnt_get_write_access_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write_file); /** * mnt_put_write_access - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with * mnt_get_write_access() call above. */ void mnt_put_write_access(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } EXPORT_SYMBOL_GPL(mnt_put_write_access); /** * mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done performing writes to it and * also allows filesystem to be frozen again. Must be matched with * mnt_want_write() call above. */ void mnt_drop_write(struct vfsmount *mnt) { mnt_put_write_access(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); void mnt_put_write_access_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) mnt_put_write_access(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { mnt_put_write_access_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); /** * mnt_hold_writers - prevent write access to the given mount * @mnt: mnt to prevent write access to * * Prevents write access to @mnt if there are no active writers for @mnt. * This function needs to be called and return successfully before changing * properties of @mnt that need to remain stable for callers with write access * to @mnt. * * After this functions has been called successfully callers must pair it with * a call to mnt_unhold_writers() in order to stop preventing write access to * @mnt. * * Context: This function expects lock_mount_hash() to be held serializing * setting MNT_WRITE_HOLD. * Return: On success 0 is returned. * On error, -EBUSY is returned. */ static inline int mnt_hold_writers(struct mount *mnt) { mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store * should be visible before we do. */ smp_mb(); /* * With writers on hold, if this value is zero, then there are * definitely no active writers (although held writers may subsequently * increment the count, they'll have to wait, and decrement it after * seeing MNT_READONLY). * * It is OK to have counter incremented on one CPU and decremented on * another: the sum will add up correctly. The danger would be when we * sum up each counter, if we read a counter before it is incremented, * but then read another CPU's count which it has been subsequently * decremented from -- we would see more decrements than we should. * MNT_WRITE_HOLD protects against this scenario, because * mnt_want_write first increments count, then smp_mb, then spins on * MNT_WRITE_HOLD, so it can't be decremented by another CPU while * we're counting up here. */ if (mnt_get_writers(mnt) > 0) return -EBUSY; return 0; } /** * mnt_unhold_writers - stop preventing write access to the given mount * @mnt: mnt to stop preventing write access to * * Stop preventing write access to @mnt allowing callers to gain write access * to @mnt again. * * This function can only be called after a successful call to * mnt_hold_writers(). * * Context: This function expects lock_mount_hash() to be held. */ static inline void mnt_unhold_writers(struct mount *mnt) { /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } static int mnt_make_readonly(struct mount *mnt) { int ret; ret = mnt_hold_writers(mnt); if (!ret) mnt->mnt.mnt_flags |= MNT_READONLY; mnt_unhold_writers(mnt); return ret; } int sb_prepare_remount_readonly(struct super_block *sb) { struct mount *mnt; int err = 0; /* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */ if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; lock_mount_hash(); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { err = mnt_hold_writers(mnt); if (err) break; } } if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; if (!err) sb_start_ro_state_change(sb); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } unlock_mount_hash(); return err; } static void free_vfsmnt(struct mount *mnt) { mnt_idmap_put(mnt_idmap(&mnt->mnt)); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); #endif kmem_cache_free(mnt_cache, mnt); } static void delayed_free_vfsmnt(struct rcu_head *head) { free_vfsmnt(container_of(head, struct mount, mnt_rcu)); } /* call under rcu_read_lock */ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) { struct mount *mnt; if (read_seqretry(&mount_lock, seq)) return 1; if (bastard == NULL) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); smp_mb(); // see mntput_no_expire() if (likely(!read_seqretry(&mount_lock, seq))) return 0; if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { mnt_add_count(mnt, -1); return 1; } lock_mount_hash(); if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; } unlock_mount_hash(); /* caller will mntput() */ return -1; } /* call under rcu_read_lock */ static bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) { int res = __legitimize_mnt(bastard, seq); if (likely(!res)) return true; if (unlikely(res < 0)) { rcu_read_unlock(); mntput(bastard); rcu_read_lock(); } return false; } /** * __lookup_mnt - find first child mount * @mnt: parent mount * @dentry: mountpoint * * If @mnt has a child mount @c mounted @dentry find and return it. * * Note that the child mount @c need not be unique. There are cases * where shadow mounts are created. For example, during mount * propagation when a source mount @mnt whose root got overmounted by a * mount @o after path lookup but before @namespace_sem could be * acquired gets copied and propagated. So @mnt gets copied including * @o. When @mnt is propagated to a destination mount @d that already * has another mount @n mounted at the same mountpoint then the source * mount @mnt will be tucked beneath @n, i.e., @n will be mounted on * @mnt and @mnt mounted on @d. Now both @n and @o are mounted at @mnt * on @dentry. * * Return: The first child of @mnt mounted @dentry or NULL. */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; } /* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the * following mounts: * * mount /dev/sda1 /mnt * mount /dev/sda2 /mnt * mount /dev/sda3 /mnt * * Then lookup_mnt() on the base /mnt dentry in the root mount will * return successively the root dentry and vfsmount of /dev/sda1, then * /dev/sda2, then /dev/sda3, then NULL. * * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(const struct path *path) { struct mount *child_mnt; struct vfsmount *m; unsigned seq; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry); m = child_mnt ? &child_mnt->mnt : NULL; } while (!legitimize_mnt(m, seq)); rcu_read_unlock(); return m; } /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. * * The common case is dentries are not mountpoints at all and that * test is handled inline. For the slow case when we are actually * dealing with a mountpoint of some kind, walk through all of the * mounts in the current mount namespace and test to see if the dentry * is a mountpoint. * * The mount_hashtable is not usable in the context because we * need to identify all mounts that may be in the current mount * namespace not just a mount that happens to have some specified * parent mount. */ bool __is_local_mountpoint(struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt, *n; bool is_covered = false; down_read(&namespace_sem); rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) { is_covered = (mnt->mnt_mountpoint == dentry); if (is_covered) break; } up_read(&namespace_sem); return is_covered; } static struct mountpoint *lookup_mountpoint(struct dentry *dentry) { struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { mp->m_count++; return mp; } } return NULL; } static struct mountpoint *get_mountpoint(struct dentry *dentry) { struct mountpoint *mp, *new = NULL; int ret; if (d_mountpoint(dentry)) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); read_sequnlock_excl(&mount_lock); if (mp) goto done; } if (!new) new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); /* Someone else set d_mounted? */ if (ret == -EBUSY) goto mountpoint; /* The dentry is not available as a mountpoint? */ mp = ERR_PTR(ret); if (ret) goto done; /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); new->m_dentry = dget(dentry); new->m_count = 1; hlist_add_head(&new->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&new->m_list); read_sequnlock_excl(&mount_lock); mp = new; new = NULL; done: kfree(new); return mp; } /* * vfsmount lock must be held. Additionally, the caller is responsible * for serializing calls for given disposal list. */ static void __put_mountpoint(struct mountpoint *mp, struct list_head *list) { if (!--mp->m_count) { struct dentry *dentry = mp->m_dentry; BUG_ON(!hlist_empty(&mp->m_list)); spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } /* called with namespace_lock and vfsmount lock */ static void put_mountpoint(struct mountpoint *mp) { __put_mountpoint(mp, &ex_mountpoints); } static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } /* * vfsmount lock must be held for write */ static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static struct mountpoint *unhash_mnt(struct mount *mnt) { struct mountpoint *mp; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); mp = mnt->mnt_mp; mnt->mnt_mp = NULL; return mp; } /* * vfsmount lock must be held for write */ static void umount_mnt(struct mount *mnt) { put_mountpoint(unhash_mnt(mnt)); } /* * vfsmount lock must be held for write */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) { mp->m_count++; mnt_add_count(mnt, 1); /* essentially, that's mntget */ child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } /** * mnt_set_mountpoint_beneath - mount a mount beneath another one * * @new_parent: the source mount * @top_mnt: the mount beneath which @new_parent is mounted * @new_mp: the new mountpoint of @top_mnt on @new_parent * * Remove @top_mnt from its current mountpoint @top_mnt->mnt_mp and * parent @top_mnt->mnt_parent and mount it on top of @new_parent at * @new_mp. And mount @new_parent on the old parent and old * mountpoint of @top_mnt. * * Context: This function expects namespace_lock() and lock_mount_hash() * to have been acquired in that order. */ static void mnt_set_mountpoint_beneath(struct mount *new_parent, struct mount *top_mnt, struct mountpoint *new_mp) { struct mount *old_top_parent = top_mnt->mnt_parent; struct mountpoint *old_top_mp = top_mnt->mnt_mp; mnt_set_mountpoint(old_top_parent, old_top_mp, new_parent); mnt_change_mountpoint(new_parent, new_mp, top_mnt); } static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /** * attach_mnt - mount a mount, attach to @mount_hashtable and parent's * list of child mounts * @parent: the parent * @mnt: the new mount * @mp: the new mountpoint * @beneath: whether to mount @mnt beneath or on top of @parent * * If @beneath is false, mount @mnt at @mp on @parent. Then attach @mnt * to @parent's child mount list and to @mount_hashtable. * * If @beneath is true, remove @mnt from its current parent and * mountpoint and mount it on @mp on @parent, and mount @parent on the * old parent and old mountpoint of @mnt. Finally, attach @parent to * @mnt_hashtable and @parent->mnt_parent->mnt_mounts. * * Note, when __attach_mnt() is called @mnt->mnt_parent already points * to the correct parent. * * Context: This function expects namespace_lock() and lock_mount_hash() * to have been acquired in that order. */ static void attach_mnt(struct mount *mnt, struct mount *parent, struct mountpoint *mp, bool beneath) { if (beneath) mnt_set_mountpoint_beneath(mnt, parent, mp); else mnt_set_mountpoint(parent, mp, mnt); /* * Note, @mnt->mnt_parent has to be used. If @mnt was mounted * beneath @parent then @mnt will need to be attached to * @parent's old parent, not @parent. IOW, @mnt->mnt_parent * isn't the same mount as @parent. */ __attach_mnt(mnt, mnt->mnt_parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; struct mount *old_parent = mnt->mnt_parent; list_del_init(&mnt->mnt_child); hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); attach_mnt(mnt, parent, mp, false); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); } static inline struct mount *node_to_mount(struct rb_node *node) { return node ? rb_entry(node, struct mount, mnt_node) : NULL; } static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) { struct rb_node **link = &ns->mounts.rb_node; struct rb_node *parent = NULL; WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB); mnt->mnt_ns = ns; while (*link) { parent = *link; if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) link = &parent->rb_left; else link = &parent->rb_right; } rb_link_node(&mnt->mnt_node, parent, link); rb_insert_color(&mnt->mnt_node, &ns->mounts); mnt->mnt.mnt_flags |= MNT_ONRB; } /* * vfsmount lock must be held for write */ static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; LIST_HEAD(head); struct mnt_namespace *n = parent->mnt_ns; BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); while (!list_empty(&head)) { m = list_first_entry(&head, typeof(*m), mnt_list); list_del(&m->mnt_list); mnt_add_to_ns(n, m); } n->nr_mounts += n->pending_mounts; n->pending_mounts = 0; __attach_mnt(mnt, parent); touch_mnt_namespace(n); } static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct mount, mnt_child); } static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; } /** * vfs_create_mount - Create a mount for a configured superblock * @fc: The configuration context with the superblock attached * * Create a mount to an already configured superblock. If necessary, the * caller should invoke vfs_get_tree() before calling this. * * Note that this does not attach the mount to anything. */ struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; if (!fc->root) return ERR_PTR(-EINVAL); mnt = alloc_vfsmnt(fc->source ?: "none"); if (!mnt) return ERR_PTR(-ENOMEM); if (fc->sb_flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; atomic_inc(&fc->root->d_sb->s_active); mnt->mnt.mnt_sb = fc->root->d_sb; mnt->mnt.mnt_root = dget(fc->root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); return &mnt->mnt; } EXPORT_SYMBOL(vfs_create_mount); struct vfsmount *fc_mount(struct fs_context *fc) { int err = vfs_get_tree(fc); if (!err) { up_write(&fc->root->d_sb->s_umount); return vfs_create_mount(fc); } return ERR_PTR(err); } EXPORT_SYMBOL(fc_mount); struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; struct vfsmount *mnt; int ret = 0; if (!type) return ERR_PTR(-EINVAL); fc = fs_context_for_mount(type, flags); if (IS_ERR(fc)) return ERR_CAST(fc); if (name) ret = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); struct vfsmount * vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data) { /* Until it is worked out how to pass the user namespace * through from the parent mount to the submount don't support * unprivileged mounts with submounts. */ if (mountpoint->d_sb->s_user_ns != &init_user_ns) return ERR_PTR(-EPERM); return vfs_kern_mount(type, SB_SUBMOUNT, name, data); } EXPORT_SYMBOL_GPL(vfs_submount); static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; struct mount *mnt; int err; mnt = alloc_vfsmnt(old->mnt_devname); if (!mnt) return ERR_PTR(-ENOMEM); if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else mnt->mnt_group_id = old->mnt_group_id; if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { err = mnt_alloc_group_id(mnt); if (err) goto out_free; } mnt->mnt.mnt_flags = old->mnt.mnt_flags; mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB); atomic_inc(&sb->s_active); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &sb->s_mounts); unlock_mount_hash(); if ((flag & CL_SLAVE) || ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; CLEAR_MNT_SHARED(mnt); } else if (!(flag & CL_PRIVATE)) { if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) list_add(&mnt->mnt_share, &old->mnt_share); if (IS_MNT_SLAVE(old)) list_add(&mnt->mnt_slave, &old->mnt_slave); mnt->mnt_master = old->mnt_master; } else { CLEAR_MNT_SHARED(mnt); } if (flag & CL_MAKE_SHARED) set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ if (flag & CL_EXPIRE) { if (!list_empty(&old->mnt_expire)) list_add(&mnt->mnt_expire, &old->mnt_expire); } return mnt; out_free: mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); } static void cleanup_mnt(struct mount *mnt) { struct hlist_node *p; struct mount *m; /* * The warning here probably indicates that somebody messed * up a mnt_want/drop_write() pair. If this happens, the * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); mnt_free_id(mnt); call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt); } static void __cleanup_mnt(struct rcu_head *head) { cleanup_mnt(container_of(head, struct mount, mnt_rcu)); } static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); struct mount *m, *t; llist_for_each_entry_safe(m, t, node, mnt_llist) cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); int count; rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* * Since we don't do lock_mount_hash() here, * ->mnt_ns can change under us. However, if it's * non-NULL, then there's a reference that won't * be dropped until after an RCU delay done after * turning ->mnt_ns NULL. So if we observe it * non-NULL under rcu_read_lock(), the reference * we are dropping is not the final one. */ mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab * mount_lock, we'll see their refcount increment here. */ smp_mb(); mnt_add_count(mnt, -1); count = mnt_get_count(mnt); if (count != 0) { WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; } if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) { rcu_read_unlock(); unlock_mount_hash(); return; } mnt->mnt.mnt_flags |= MNT_DOOMED; rcu_read_unlock(); list_del(&mnt->mnt_instance); if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { __put_mountpoint(unhash_mnt(p), &list); hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; if (likely(!(task->flags & PF_KTHREAD))) { init_task_work(&mnt->mnt_rcu, __cleanup_mnt); if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME)) return; } if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1); return; } cleanup_mnt(mnt); } void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); /* avoid cacheline pingpong */ if (unlikely(m->mnt_expiry_mark)) WRITE_ONCE(m->mnt_expiry_mark, 0); mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); /* * Make a mount point inaccessible to new lookups. * Because there may still be current users, the caller MUST WAIT * for an RCU grace period before destroying the mount point. */ void mnt_make_shortterm(struct vfsmount *mnt) { if (mnt) real_mount(mnt)->mnt_ns = NULL; } /** * path_is_mountpoint() - Check if path is a mount in the current namespace. * @path: path to check * * d_mountpoint() can only be used reliably to establish if a dentry is * not mounted in any namespace and that common case is handled inline. * d_mountpoint() isn't aware of the possibility there may be multiple * mounts using a given dentry in a different namespace. This function * checks if the passed in path is a mountpoint rather than the dentry * alone. */ bool path_is_mountpoint(const struct path *path) { unsigned seq; bool res; if (!d_mountpoint(path->dentry)) return false; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); res = __path_is_mountpoint(path); } while (read_seqretry(&mount_lock, seq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL(path_is_mountpoint); struct vfsmount *mnt_clone_internal(const struct path *path) { struct mount *p; p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE); if (IS_ERR(p)) return ERR_CAST(p); p->mnt.mnt_flags |= MNT_INTERNAL; return &p->mnt; } /* * Returns the mount which either has the specified mnt_id, or has the next * smallest id afer the specified one. */ static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id) { struct rb_node *node = ns->mounts.rb_node; struct mount *ret = NULL; while (node) { struct mount *m = node_to_mount(node); if (mnt_id <= m->mnt_id_unique) { ret = node_to_mount(node); if (mnt_id == m->mnt_id_unique) break; node = node->rb_left; } else { node = node->rb_right; } } return ret; } /* * Returns the mount which either has the specified mnt_id, or has the next * greater id before the specified one. */ static struct mount *mnt_find_id_at_reverse(struct mnt_namespace *ns, u64 mnt_id) { struct rb_node *node = ns->mounts.rb_node; struct mount *ret = NULL; while (node) { struct mount *m = node_to_mount(node); if (mnt_id >= m->mnt_id_unique) { ret = node_to_mount(node); if (mnt_id == m->mnt_id_unique) break; node = node->rb_right; } else { node = node->rb_left; } } return ret; } #ifdef CONFIG_PROC_FS /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; down_read(&namespace_sem); return mnt_find_id_at(p->ns, *pos); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct mount *next = NULL, *mnt = v; struct rb_node *node = rb_next(&mnt->mnt_node); ++*pos; if (node) { next = node_to_mount(node); *pos = next->mnt_id_unique; } return next; } static void m_stop(struct seq_file *m, void *v) { up_read(&namespace_sem); } static int m_show(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *r = v; return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show, }; #endif /* CONFIG_PROC_FS */ /** * may_umount_tree - check if a mount tree is busy * @m: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *m) { struct mount *mnt = real_mount(m); int actual_refs = 0; int minimum_refs = 0; struct mount *p; BUG_ON(!m); /* write lock needed for mnt_get_count */ lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += mnt_get_count(p); minimum_refs += 2; } unlock_mount_hash(); if (actual_refs > minimum_refs) return 0; return 1; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); lock_mount_hash(); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; unlock_mount_hash(); up_read(&namespace_sem); return ret; } EXPORT_SYMBOL(may_umount); static void namespace_unlock(void) { struct hlist_head head; struct hlist_node *p; struct mount *m; LIST_HEAD(list); hlist_move_list(&unmounted, &head); list_splice_init(&ex_mountpoints, &list); up_write(&namespace_sem); shrink_dentry_list(&list); if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); hlist_for_each_entry_safe(m, p, &head, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } } static inline void namespace_lock(void) { down_write(&namespace_sem); } enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) { /* Leaving mounts connected is only valid for lazy umounts */ if (how & UMOUNT_SYNC) return true; /* A mount without a parent has nothing to be connected to */ if (!mnt_has_parent(mnt)) return true; /* Because the reference counting rules change when mounts are * unmounted and connected, umounted mounts may not be * connected to mounted mounts. */ if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) return true; /* Has it been requested that the mount remain connected? */ if (how & UMOUNT_CONNECTED) return false; /* Is the mount locked such that it needs to remain connected? */ if (IS_MNT_LOCKED(mnt)) return false; /* By default disconnect the mount */ return true; } /* * mount_lock must be held * namespace_sem must be held for write */ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { LIST_HEAD(tmp_list); struct mount *p; if (how & UMOUNT_PROPAGATE) propagate_mount_unlock(mnt); /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; if (p->mnt.mnt_flags & MNT_ONRB) move_from_ns(p, &tmp_list); else list_move(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } /* Add propagated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { ns->nr_mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { /* Don't forget about p */ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); } } change_mnt_propagation(p, MS_PRIVATE); if (disconnect) hlist_add_head(&p->mnt_umount, &unmounted); } } static void shrink_submounts(struct mount *mnt); static int do_umount_root(struct super_block *sb) { int ret = 0; down_write(&sb->s_umount); if (!sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, SB_RDONLY); if (IS_ERR(fc)) { ret = PTR_ERR(fc); } else { ret = parse_monolithic_mount_data(fc, NULL); if (!ret) ret = reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); return ret; } static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; /* * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ lock_mount_hash(); if (mnt_get_count(mnt) != 2) { unlock_mount_hash(); return -EBUSY; } unlock_mount_hash(); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ if (flags & MNT_FORCE && sb->s_op->umount_begin) { sb->s_op->umount_begin(sb); } /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return do_umount_root(sb); } namespace_lock(); lock_mount_hash(); /* Recheck MNT_LOCKED with the locks held */ retval = -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto out; event++; if (flags & MNT_DETACH) { if (mnt->mnt.mnt_flags & MNT_ONRB || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { if (mnt->mnt.mnt_flags & MNT_ONRB || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } out: unlock_mount_hash(); namespace_unlock(); return retval; } /* * __detach_mounts - lazily unmount all mounts on the specified dentry * * During unlink, rmdir, and d_drop it is possible to loose the path * to an existing mountpoint, and wind up leaking the mount. * detach_mounts allows lazily unmounting those mounts instead of * leaking them. * * The caller may hold dentry->d_inode->i_mutex. */ void __detach_mounts(struct dentry *dentry) { struct mountpoint *mp; struct mount *mnt; namespace_lock(); lock_mount_hash(); mp = lookup_mountpoint(dentry); if (!mp) goto out_unlock; event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { umount_mnt(mnt); hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } put_mountpoint(mp); out_unlock: unlock_mount_hash(); namespace_unlock(); } /* * Is the caller allowed to modify his namespace? */ bool may_mount(void) { return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } static void warn_mandlock(void) { pr_warn_once("=======================================================\n" "WARNING: The mand mount option has been deprecated and\n" " and is ignored by this kernel. Remove the mand\n" " option from the mount to silence this warning.\n" "=======================================================\n"); } static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); if (!may_mount()) return -EPERM; if (!path_mounted(path)) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } // caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); int ret; ret = can_umount(path, flags); if (!ret) ret = do_umount(mnt, flags); /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path->dentry); mntput_no_expire(mnt); return ret; } static int ksys_umount(char __user *name, int flags) { int lookup_flags = LOOKUP_MOUNTPOINT; struct path path; int ret; // basic validity checks done first if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) return -EINVAL; if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (ret) return ret; return path_umount(&path, flags); } SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { return ksys_umount(name, flags); } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ SYSCALL_DEFINE1(oldumount, char __user *, name) { return ksys_umount(name, 0); } #endif static bool is_mnt_ns_file(struct dentry *dentry) { /* Is this a proxy for a mount namespace? */ return dentry->d_op == &ns_dentry_operations && dentry->d_fsdata == &mntns_operations; } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { return &mnt->ns; } struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mntns, bool previous) { guard(read_lock)(&mnt_ns_tree_lock); for (;;) { struct rb_node *node; if (previous) node = rb_prev(&mntns->mnt_ns_tree_node); else node = rb_next(&mntns->mnt_ns_tree_node); if (!node) return ERR_PTR(-ENOENT); mntns = node_to_mnt_ns(node); node = &mntns->mnt_ns_tree_node; if (!ns_capable_noaudit(mntns->user_ns, CAP_SYS_ADMIN)) continue; /* * Holding mnt_ns_tree_lock prevents the mount namespace from * being freed but it may well be on it's deathbed. We want an * active reference, not just a passive one here as we're * persisting the mount namespace. */ if (!refcount_inc_not_zero(&mntns->ns.count)) continue; return mntns; } } static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ struct mnt_namespace *mnt_ns; if (!is_mnt_ns_file(dentry)) return false; mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } struct mount *copy_tree(struct mount *src_root, struct dentry *dentry, int flag) { struct mount *res, *src_parent, *src_root_child, *src_mnt, *dst_parent, *dst_mnt; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(src_root)) return ERR_PTR(-EINVAL); if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = dst_mnt = clone_mnt(src_root, dentry, flag); if (IS_ERR(dst_mnt)) return dst_mnt; src_parent = src_root; dst_mnt->mnt_mountpoint = src_root->mnt_mountpoint; list_for_each_entry(src_root_child, &src_root->mnt_mounts, mnt_child) { if (!is_subdir(src_root_child->mnt_mountpoint, dentry)) continue; for (src_mnt = src_root_child; src_mnt; src_mnt = next_mnt(src_mnt, src_root_child)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(src_mnt)) { if (src_mnt->mnt.mnt_flags & MNT_LOCKED) { /* Both unbindable and locked. */ dst_mnt = ERR_PTR(-EPERM); goto out; } else { src_mnt = skip_mnt_tree(src_mnt); continue; } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(src_mnt->mnt.mnt_root)) { src_mnt = skip_mnt_tree(src_mnt); continue; } while (src_parent != src_mnt->mnt_parent) { src_parent = src_parent->mnt_parent; dst_mnt = dst_mnt->mnt_parent; } src_parent = src_mnt; dst_parent = dst_mnt; dst_mnt = clone_mnt(src_mnt, src_mnt->mnt.mnt_root, flag); if (IS_ERR(dst_mnt)) goto out; lock_mount_hash(); list_add_tail(&dst_mnt->mnt_list, &res->mnt_list); attach_mnt(dst_mnt, dst_parent, src_parent->mnt_mp, false); unlock_mount_hash(); } } return res; out: if (res) { lock_mount_hash(); umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return dst_mnt; } /* Caller should check returned pointer for errors */ struct vfsmount *collect_mounts(const struct path *path) { struct mount *tree; namespace_lock(); if (!check_mnt(real_mount(path->mnt))) tree = ERR_PTR(-EINVAL); else tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) return ERR_CAST(tree); return &tree->mnt; } static void free_mnt_ns(struct mnt_namespace *); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); void dissolve_on_fput(struct vfsmount *mnt) { struct mnt_namespace *ns; namespace_lock(); lock_mount_hash(); ns = real_mount(mnt)->mnt_ns; if (ns) { if (is_anon_ns(ns)) umount_tree(real_mount(mnt), UMOUNT_CONNECTED); else ns = NULL; } unlock_mount_hash(); namespace_unlock(); if (ns) free_mnt_ns(ns); } void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } bool has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, dentry)) continue; if (child->mnt.mnt_flags & MNT_LOCKED) return true; } return false; } /** * clone_private_mount - create a private clone of a path * @path: path to clone * * This creates a new vfsmount, which will be the clone of @path. The new mount * will not be attached anywhere in the namespace and will be private (i.e. * changes to the originating mount won't be propagated into this). * * Release with mntput(). */ struct vfsmount *clone_private_mount(const struct path *path) { struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) goto invalid; if (!check_mnt(old_mnt)) goto invalid; if (has_locked_children(old_mnt, path->dentry)) goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); up_read(&namespace_sem); if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); /* Longterm mount to be removed by kern_unmount*() */ new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; invalid: up_read(&namespace_sem); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { struct mount *mnt; int res = f(root, arg); if (res) return res; list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) { res = f(&mnt->mnt, arg); if (res) return res; } return 0; } static void lock_mnt_tree(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { int flags = p->mnt.mnt_flags; /* Don't allow unprivileged users to change mount flags */ flags |= MNT_LOCK_ATIME; if (flags & MNT_READONLY) flags |= MNT_LOCK_READONLY; if (flags & MNT_NODEV) flags |= MNT_LOCK_NODEV; if (flags & MNT_NOSUID) flags |= MNT_LOCK_NOSUID; if (flags & MNT_NOEXEC) flags |= MNT_LOCK_NOEXEC; /* Don't allow unprivileged users to reveal what is under a mount */ if (list_empty(&p->mnt_expire)) flags |= MNT_LOCKED; p->mnt.mnt_flags = flags; } } static void cleanup_group_ids(struct mount *mnt, struct mount *end) { struct mount *p; for (p = mnt; p != end; p = next_mnt(p, mnt)) { if (p->mnt_group_id && !IS_MNT_SHARED(p)) mnt_release_group_id(p); } } static int invent_group_ids(struct mount *mnt, bool recurse) { struct mount *p; for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) { if (!p->mnt_group_id && !IS_MNT_SHARED(p)) { int err = mnt_alloc_group_id(p); if (err) { cleanup_group_ids(mnt, p); return err; } } } return 0; } int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); unsigned int mounts = 0; struct mount *p; if (ns->nr_mounts >= max) return -ENOSPC; max -= ns->nr_mounts; if (ns->pending_mounts >= max) return -ENOSPC; max -= ns->pending_mounts; for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; if (mounts > max) return -ENOSPC; ns->pending_mounts += mounts; return 0; } enum mnt_tree_flags_t { MNT_TREE_MOVE = BIT(0), MNT_TREE_BENEATH = BIT(1), }; /** * attach_recursive_mnt - attach a source mount tree * @source_mnt: mount tree to be attached * @top_mnt: mount that @source_mnt will be mounted on or mounted beneath * @dest_mp: the mountpoint @source_mnt will be mounted at * @flags: modify how @source_mnt is supposed to be attached * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. * --------------------------------------------------------------------------- * | BIND MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (++) | shared (+) | shared(+++)| invalid | * | | | | | | * |non-shared| shared (+) | private | slave (*) | invalid | * *************************************************************************** * A bind operation clones the source mount and mounts the clone on the * destination mount. * * (++) the cloned mount is propagated to all the mounts in the propagation * tree of the destination mount and the cloned mount is added to * the peer group of the source mount. * (+) the cloned mount is created under the destination mount and is marked * as shared. The cloned mount is added to the peer group of the source * mount. * (+++) the mount is propagated to all the mounts in the propagation tree * of the destination mount and the cloned mount is made slave * of the same master as that of the source mount. The cloned mount * is marked as 'shared and slave'. * (*) the cloned mount is made a slave of the same master as that of the * source mount. * * --------------------------------------------------------------------------- * | MOVE MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (+) | shared (+) | shared(+++) | invalid | * | | | | | | * |non-shared| shared (+*) | private | slave (*) | unbindable | * *************************************************************************** * * (+) the mount is moved to the destination. And is then propagated to * all the mounts in the propagation tree of the destination mount. * (+*) the mount is moved to the destination. * (+++) the mount is moved to the destination and is then propagated to * all the mounts belonging to the destination mount's propagation tree. * the mount is marked as 'shared and slave'. * (*) the mount continues to be a slave at the new location. * * if the source mount is a tree, the operations explained above is * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. * * Context: The function expects namespace_lock() to be held. * Return: If @source_mnt was successfully attached 0 is returned. * Otherwise a negative error code is returned. */ static int attach_recursive_mnt(struct mount *source_mnt, struct mount *top_mnt, struct mountpoint *dest_mp, enum mnt_tree_flags_t flags) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); struct mnt_namespace *ns = top_mnt->mnt_ns; struct mountpoint *smp; struct mount *child, *dest_mnt, *p; struct hlist_node *n; int err = 0; bool moving = flags & MNT_TREE_MOVE, beneath = flags & MNT_TREE_BENEATH; /* * Preallocate a mountpoint in case the new mounts need to be * mounted beneath mounts on the same mountpoint. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) return PTR_ERR(smp); /* Is there space to add these mounts to the mount namespace? */ if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; } if (beneath) dest_mnt = top_mnt->mnt_parent; else dest_mnt = top_mnt; if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); } lock_mount_hash(); if (err) goto out_cleanup_ids; if (IS_MNT_SHARED(dest_mnt)) { for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } if (moving) { if (beneath) dest_mp = smp; unhash_mnt(source_mnt); attach_mnt(source_mnt, top_mnt, dest_mp, beneath); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { LIST_HEAD(head); /* move from anon - the caller will destroy */ for (p = source_mnt; p; p = next_mnt(p, source_mnt)) move_from_ns(p, &head); list_del_init(&head); } if (beneath) mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp); else mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); if (q) mnt_change_mountpoint(child, smp, q); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; commit_tree(child); } put_mountpoint(smp); unlock_mount_hash(); return 0; out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; read_seqlock_excl(&mount_lock); put_mountpoint(smp); read_sequnlock_excl(&mount_lock); return err; } /** * do_lock_mount - lock mount and mountpoint * @path: target path * @beneath: whether the intention is to mount beneath @path * * Follow the mount stack on @path until the top mount @mnt is found. If * the initial @path->{mnt,dentry} is a mountpoint lookup the first * mount stacked on top of it. Then simply follow @{mnt,mnt->mnt_root} * until nothing is stacked on top of it anymore. * * Acquire the inode_lock() on the top mount's ->mnt_root to protect * against concurrent removal of the new mountpoint from another mount * namespace. * * If @beneath is requested, acquire inode_lock() on @mnt's mountpoint * @mp on @mnt->mnt_parent must be acquired. This protects against a * concurrent unlink of @mp->mnt_dentry from another mount namespace * where @mnt doesn't have a child mount mounted @mp. A concurrent * removal of @mnt->mnt_root doesn't matter as nothing will be mounted * on top of it for @beneath. * * In addition, @beneath needs to make sure that @mnt hasn't been * unmounted or moved from its current mountpoint in between dropping * @mount_lock and acquiring @namespace_sem. For the !@beneath case @mnt * being unmounted would be detected later by e.g., calling * check_mnt(mnt) in the function it's called from. For the @beneath * case however, it's useful to detect it directly in do_lock_mount(). * If @mnt hasn't been unmounted then @mnt->mnt_mountpoint still points * to @mnt->mnt_mp->m_dentry. But if @mnt has been unmounted it will * point to @mnt->mnt_root and @mnt->mnt_mp will be NULL. * * Return: Either the target mountpoint on the top mount or the top * mount's mountpoint. */ static struct mountpoint *do_lock_mount(struct path *path, bool beneath) { struct vfsmount *mnt = path->mnt; struct dentry *dentry; struct mountpoint *mp = ERR_PTR(-ENOENT); for (;;) { struct mount *m; if (beneath) { m = real_mount(mnt); read_seqlock_excl(&mount_lock); dentry = dget(m->mnt_mountpoint); read_sequnlock_excl(&mount_lock); } else { dentry = path->dentry; } inode_lock(dentry->d_inode); if (unlikely(cant_mount(dentry))) { inode_unlock(dentry->d_inode); goto out; } namespace_lock(); if (beneath && (!is_mounted(mnt) || m->mnt_mountpoint != dentry)) { namespace_unlock(); inode_unlock(dentry->d_inode); goto out; } mnt = lookup_mnt(path); if (likely(!mnt)) break; namespace_unlock(); inode_unlock(dentry->d_inode); if (beneath) dput(dentry); path_put(path); path->mnt = mnt; path->dentry = dget(mnt->mnt_root); } mp = get_mountpoint(dentry); if (IS_ERR(mp)) { namespace_unlock(); inode_unlock(dentry->d_inode); } out: if (beneath) dput(dentry); return mp; } static inline struct mountpoint *lock_mount(struct path *path) { return do_lock_mount(path, false); } static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; read_seqlock_excl(&mount_lock); put_mountpoint(where); read_sequnlock_excl(&mount_lock); namespace_unlock(); inode_unlock(dentry->d_inode); } static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) { if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->m_dentry) != d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; return attach_recursive_mnt(mnt, p, mp, 0); } /* * Sanity check the flags to change_mnt_propagation. */ static int flags_to_propagation_type(int ms_flags) { int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return 0; /* Only one propagation flag should be set */ if (!is_power_of_2(type)) return 0; return type; } /* * recursively change the type of the mountpoint. */ static int do_change_type(struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); int recurse = ms_flags & MS_REC; int type; int err = 0; if (!path_mounted(path)) return -EINVAL; type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; namespace_lock(); if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) goto out_unlock; } lock_mount_hash(); for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); unlock_mount_hash(); out_unlock: namespace_unlock(); return err; } static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); if (IS_MNT_UNBINDABLE(old)) return mnt; if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) return mnt; if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; if (recurse) mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE); else mnt = clone_mnt(old, old_path->dentry, 0); if (!IS_ERR(mnt)) mnt->mnt.mnt_flags &= ~MNT_LOCKED; return mnt; } /* * do loopback mount. */ static int do_loopback(struct path *path, const char *old_name, int recurse) { struct path old_path; struct mount *mnt = NULL, *parent; struct mountpoint *mp; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) goto out; mp = lock_mount(path); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto out; } parent = real_mount(path->mnt); if (!check_mnt(parent)) goto out2; mnt = __do_loopback(&old_path, recurse); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out2; } err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } out2: unlock_mount(mp); out: path_put(&old_path); return err; } static struct file *open_detached_copy(struct path *path, bool recursive) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true); struct mount *mnt, *p; struct file *file; if (IS_ERR(ns)) return ERR_CAST(ns); namespace_lock(); mnt = __do_loopback(path, recursive); if (IS_ERR(mnt)) { namespace_unlock(); free_mnt_ns(ns); return ERR_CAST(mnt); } lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { mnt_add_to_ns(ns, p); ns->nr_mounts++; } ns->root = mnt; mntget(&mnt->mnt); unlock_mount_hash(); namespace_unlock(); mntput(path->mnt); path->mnt = &mnt->mnt; file = dentry_open(path, O_PATH, current_cred()); if (IS_ERR(file)) dissolve_on_fput(path->mnt); else file->f_mode |= FMODE_NEED_UNMOUNT; return file; } SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { struct file *file; struct path path; int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; bool detached = flags & OPEN_TREE_CLONE; int error; int fd; BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC)) return -EINVAL; if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE) return -EINVAL; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (detached && !may_mount()) return -EPERM; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; error = user_path_at(dfd, filename, lookup_flags, &path); if (unlikely(error)) { file = ERR_PTR(error); } else { if (detached) file = open_detached_copy(&path, flags & AT_RECURSIVE); else file = dentry_open(&path, O_PATH, current_cred()); path_put(&path); } if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } fd_install(fd, file); return fd; } /* * Don't allow locked mount flags to be cleared. * * No locks need to be held here while testing the various MNT_LOCK * flags because those flags can never be cleared once they are set. */ static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { unsigned int fl = mnt->mnt.mnt_flags; if ((fl & MNT_LOCK_READONLY) && !(mnt_flags & MNT_READONLY)) return false; if ((fl & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) return false; if ((fl & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) return false; if ((fl & MNT_LOCK_NOEXEC) && !(mnt_flags & MNT_NOEXEC)) return false; if ((fl & MNT_LOCK_ATIME) && ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) return false; return true; } static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) { bool readonly_request = (mnt_flags & MNT_READONLY); if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) return mnt_make_readonly(mnt); mnt->mnt.mnt_flags &= ~MNT_READONLY; return 0; } static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); } static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; if (!__mnt_is_readonly(mnt) && (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf, *mntpath; buf = (char *)__get_free_page(GFP_KERNEL); if (buf) mntpath = d_path(mountpoint, buf, PAGE_SIZE); else mntpath = ERR_PTR(-ENOMEM); if (IS_ERR(mntpath)) mntpath = "(unknown)"; pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", mntpath, &sb->s_time_max, (unsigned long long)sb->s_time_max); sb->s_iflags |= SB_I_TS_EXPIRY_WARNED; if (buf) free_page((unsigned long)buf); } } /* * Handle reconfiguration of the mountpoint only without alteration of the * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND * to mount(2). */ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) { struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); int ret; if (!check_mnt(mnt)) return -EINVAL; if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; /* * We're only checking whether the superblock is read-only not * changing it, so only take down_read(&sb->s_umount). */ down_read(&sb->s_umount); lock_mount_hash(); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); up_read(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); return ret; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(struct path *path, int ms_flags, int sb_flags, int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the remount request is coming * from the legacy mount system call. */ fc->oldapi = true; err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); if (!err) { lock_mount_hash(); set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); } } up_write(&sb->s_umount); } mnt_warn_timestamp_expiry(path, &mnt->mnt); put_fs_context(fc); return err; } static inline int tree_contains_unbindable(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { if (IS_MNT_UNBINDABLE(p)) return 1; } return 0; } /* * Check that there aren't references to earlier/same mount namespaces in the * specified subtree. Such references can act as pins for mount namespaces * that aren't checked by the mount-cycle checking code, thereby allowing * cycles to be made. */ static bool check_for_nsfs_mounts(struct mount *subtree) { struct mount *p; bool ret = false; lock_mount_hash(); for (p = subtree; p; p = next_mnt(p, subtree)) if (mnt_ns_loop(p->mnt.mnt_root)) goto out; ret = true; out: unlock_mount_hash(); return ret; } static int do_set_group(struct path *from_path, struct path *to_path) { struct mount *from, *to; int err; from = real_mount(from_path->mnt); to = real_mount(to_path->mnt); namespace_lock(); err = -EINVAL; /* To and From must be mounted */ if (!is_mounted(&from->mnt)) goto out; if (!is_mounted(&to->mnt)) goto out; err = -EPERM; /* We should be allowed to modify mount namespaces of both mounts */ if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN)) goto out; if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN)) goto out; err = -EINVAL; /* To and From paths should be mount roots */ if (!path_mounted(from_path)) goto out; if (!path_mounted(to_path)) goto out; /* Setting sharing groups is only allowed across same superblock */ if (from->mnt.mnt_sb != to->mnt.mnt_sb) goto out; /* From mount root should be wider than To mount root */ if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root)) goto out; /* From mount should not have locked children in place of To's root */ if (has_locked_children(from, to->mnt.mnt_root)) goto out; /* Setting sharing groups is only allowed on private mounts */ if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to)) goto out; /* From should not be private */ if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from)) goto out; if (IS_MNT_SLAVE(from)) { struct mount *m = from->mnt_master; list_add(&to->mnt_slave, &m->mnt_slave_list); to->mnt_master = m; } if (IS_MNT_SHARED(from)) { to->mnt_group_id = from->mnt_group_id; list_add(&to->mnt_share, &from->mnt_share); lock_mount_hash(); set_mnt_shared(to); unlock_mount_hash(); } err = 0; out: namespace_unlock(); return err; } /** * path_overmounted - check if path is overmounted * @path: path to check * * Check if path is overmounted, i.e., if there's a mount on top of * @path->mnt with @path->dentry as mountpoint. * * Context: This function expects namespace_lock() to be held. * Return: If path is overmounted true is returned, false if not. */ static inline bool path_overmounted(const struct path *path) { rcu_read_lock(); if (unlikely(__lookup_mnt(path->mnt, path->dentry))) { rcu_read_unlock(); return true; } rcu_read_unlock(); return false; } /** * can_move_mount_beneath - check that we can mount beneath the top mount * @from: mount to mount beneath * @to: mount under which to mount * @mp: mountpoint of @to * * - Make sure that @to->dentry is actually the root of a mount under * which we can mount another mount. * - Make sure that nothing can be mounted beneath the caller's current * root or the rootfs of the namespace. * - Make sure that the caller can unmount the topmost mount ensuring * that the caller could reveal the underlying mountpoint. * - Ensure that nothing has been mounted on top of @from before we * grabbed @namespace_sem to avoid creating pointless shadow mounts. * - Prevent mounting beneath a mount if the propagation relationship * between the source mount, parent mount, and top mount would lead to * nonsensical mount trees. * * Context: This function expects namespace_lock() to be held. * Return: On success 0, and on error a negative error code is returned. */ static int can_move_mount_beneath(const struct path *from, const struct path *to, const struct mountpoint *mp) { struct mount *mnt_from = real_mount(from->mnt), *mnt_to = real_mount(to->mnt), *parent_mnt_to = mnt_to->mnt_parent; if (!mnt_has_parent(mnt_to)) return -EINVAL; if (!path_mounted(to)) return -EINVAL; if (IS_MNT_LOCKED(mnt_to)) return -EINVAL; /* Avoid creating shadow mounts during mount propagation. */ if (path_overmounted(from)) return -EINVAL; /* * Mounting beneath the rootfs only makes sense when the * semantics of pivot_root(".", ".") are used. */ if (&mnt_to->mnt == current->fs->root.mnt) return -EINVAL; if (parent_mnt_to == current->nsproxy->mnt_ns->root) return -EINVAL; for (struct mount *p = mnt_from; mnt_has_parent(p); p = p->mnt_parent) if (p == mnt_to) return -EINVAL; /* * If the parent mount propagates to the child mount this would * mean mounting @mnt_from on @mnt_to->mnt_parent and then * propagating a copy @c of @mnt_from on top of @mnt_to. This * defeats the whole purpose of mounting beneath another mount. */ if (propagation_would_overmount(parent_mnt_to, mnt_to, mp)) return -EINVAL; /* * If @mnt_to->mnt_parent propagates to @mnt_from this would * mean propagating a copy @c of @mnt_from on top of @mnt_from. * Afterwards @mnt_from would be mounted on top of * @mnt_to->mnt_parent and @mnt_to would be unmounted from * @mnt->mnt_parent and remounted on @mnt_from. But since @c is * already mounted on @mnt_from, @mnt_to would ultimately be * remounted on top of @c. Afterwards, @mnt_from would be * covered by a copy @c of @mnt_from and @c would be covered by * @mnt_from itself. This defeats the whole purpose of mounting * @mnt_from beneath @mnt_to. */ if (propagation_would_overmount(parent_mnt_to, mnt_from, mp)) return -EINVAL; return 0; } static int do_move_mount(struct path *old_path, struct path *new_path, bool beneath) { struct mnt_namespace *ns; struct mount *p; struct mount *old; struct mount *parent; struct mountpoint *mp, *old_mp; int err; bool attached; enum mnt_tree_flags_t flags = 0; mp = do_lock_mount(new_path, beneath); if (IS_ERR(mp)) return PTR_ERR(mp); old = real_mount(old_path->mnt); p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); if (attached) flags |= MNT_TREE_MOVE; old_mp = old->mnt_mp; ns = old->mnt_ns; err = -EINVAL; /* The mountpoint must be in our namespace. */ if (!check_mnt(p)) goto out; /* The thing moved must be mounted... */ if (!is_mounted(&old->mnt)) goto out; /* ... and either ours or the root of anon namespace */ if (!(attached ? check_mnt(old) : is_anon_ns(ns))) goto out; if (old->mnt.mnt_flags & MNT_LOCKED) goto out; if (!path_mounted(old_path)) goto out; if (d_is_dir(new_path->dentry) != d_is_dir(old_path->dentry)) goto out; /* * Don't move a mount residing in a shared parent. */ if (attached && IS_MNT_SHARED(parent)) goto out; if (beneath) { err = can_move_mount_beneath(old_path, new_path, mp); if (err) goto out; err = -EINVAL; p = p->mnt_parent; flags |= MNT_TREE_BENEATH; } /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old)) goto out; err = -ELOOP; if (!check_for_nsfs_mounts(old)) goto out; for (; mnt_has_parent(p); p = p->mnt_parent) if (p == old) goto out; err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, flags); if (err) goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: unlock_mount(mp); if (!err) { if (attached) mntput_no_expire(parent); else free_mnt_ns(ns); } return err; } static int do_move_mount_old(struct path *path, const char *old_name) { struct path old_path; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; err = do_move_mount(&old_path, path, false); path_put(&old_path); return err; } /* * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, const struct path *path, int mnt_flags) { struct mount *parent = real_mount(path->mnt); mnt_flags &= ~MNT_INTERNAL_FLAGS; if (unlikely(!check_mnt(parent))) { /* that's acceptable only for automounts done in private ns */ if (!(mnt_flags & MNT_SHRINKABLE)) return -EINVAL; /* ... and for those we'd better have mountpoint still alive */ if (!parent->mnt_ns) return -EINVAL; } /* Refuse the same filesystem on the same mount point */ if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path_mounted(path)) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) return -EINVAL; newmnt->mnt.mnt_flags = mnt_flags; return graft_tree(newmnt, parent, mp); } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags); /* * Create a new mount using a superblock configuration and request it * be added to the namespace tree. */ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, unsigned int mnt_flags) { struct vfsmount *mnt; struct mountpoint *mp; struct super_block *sb = fc->root->d_sb; int error; error = security_sb_kern_mount(sb); if (!error && mount_too_revealing(sb, &mnt_flags)) error = -EPERM; if (unlikely(error)) { fc_drop_locked(fc); return error; } up_write(&sb->s_umount); mnt = vfs_create_mount(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); mnt_warn_timestamp_expiry(mountpoint, mnt); mp = lock_mount(mountpoint); if (IS_ERR(mp)) { mntput(mnt); return PTR_ERR(mp); } error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags); unlock_mount(mp); if (error < 0) mntput(mnt); return error; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; struct fs_context *fc; const char *subtype = NULL; int err = 0; if (!fstype) return -EINVAL; type = get_fs_type(fstype); if (!type) return -ENODEV; if (type->fs_flags & FS_HAS_SUBTYPE) { subtype = strchr(fstype, '.'); if (subtype) { subtype++; if (!*subtype) { put_filesystem(type); return -EINVAL; } } } fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the mount request is coming * from the legacy mount system call. */ fc->oldapi = true; if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype, strlen(subtype)); if (!err && name) err = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!err) err = parse_monolithic_mount_data(fc, data); if (!err && !mount_capable(fc)) err = -EPERM; if (!err) err = vfs_get_tree(fc); if (!err) err = do_new_mount_fc(fc, path, mnt_flags); put_fs_context(fc); return err; } int finish_automount(struct vfsmount *m, const struct path *path) { struct dentry *dentry = path->dentry; struct mountpoint *mp; struct mount *mnt; int err; if (!m) return 0; if (IS_ERR(m)) return PTR_ERR(m); mnt = real_mount(m); /* The new mount record should have at least 2 refs to prevent it being * expired before we get a chance to add it */ BUG_ON(mnt_get_count(mnt) < 2); if (m->mnt_sb == path->mnt->mnt_sb && m->mnt_root == dentry) { err = -ELOOP; goto discard; } /* * we don't want to use lock_mount() - in this case finding something * that overmounts our mountpoint to be means "quitely drop what we've * got", not "try to mount it on top". */ inode_lock(dentry->d_inode); namespace_lock(); if (unlikely(cant_mount(dentry))) { err = -ENOENT; goto discard_locked; } if (path_overmounted(path)) { err = 0; goto discard_locked; } mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto discard_locked; } err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE); unlock_mount(mp); if (unlikely(err)) goto discard; mntput(m); return 0; discard_locked: namespace_unlock(); inode_unlock(dentry->d_inode); discard: /* remove m from any expiration list it may be on */ if (!list_empty(&mnt->mnt_expire)) { namespace_lock(); list_del_init(&mnt->mnt_expire); namespace_unlock(); } mntput(m); mntput(m); return err; } /** * mnt_set_expiry - Put a mount on an expiration list * @mnt: The mount to list. * @expiry_list: The list to add the mount to. */ void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { namespace_lock(); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); namespace_unlock(); } EXPORT_SYMBOL(mnt_set_expiry); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct mount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; namespace_lock(); lock_mount_hash(); /* extract from the expiration list every vfsmount that matches the * following criteria: * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_expire) { if (!xchg(&mnt->mnt_expiry_mark, 1) || propagate_mount_busy(mnt, 1)) continue; list_move(&mnt->mnt_expire, &graveyard); } while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } unlock_mount_hash(); namespace_unlock(); } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Ripoff of 'select_parent()' * * search the list of submounts for a given mountpoint, and move any * shrinkable submounts to the 'graveyard' list. */ static int select_submounts(struct mount *parent, struct list_head *graveyard) { struct mount *this_parent = parent; struct list_head *next; int found = 0; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct list_head *tmp = next; struct mount *mnt = list_entry(tmp, struct mount, mnt_child); next = tmp->next; if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE)) continue; /* * Descend a level if the d_mounts list is non-empty. */ if (!list_empty(&mnt->mnt_mounts)) { this_parent = mnt; goto repeat; } if (!propagate_mount_busy(mnt, 1)) { list_move_tail(&mnt->mnt_expire, graveyard); found++; } } /* * All done at this level ... ascend and resume the search */ if (this_parent != parent) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } return found; } /* * process a list of expirable mountpoints with the intent of discarding any * submounts of a specific parent mountpoint * * mount_lock must be held for write */ static void shrink_submounts(struct mount *mnt) { LIST_HEAD(graveyard); struct mount *m; /* extract submounts of 'mountpoint' from the expiration list */ while (select_submounts(mnt, &graveyard)) { while (!list_empty(&graveyard)) { m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } static void *copy_mount_options(const void __user * data) { char *copy; unsigned left, offset; if (!data) return NULL; copy = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!copy) return ERR_PTR(-ENOMEM); left = copy_from_user(copy, data, PAGE_SIZE); /* * Not all architectures have an exact copy_from_user(). Resort to * byte at a time. */ offset = PAGE_SIZE - left; while (left) { char c; if (get_user(c, (const char __user *)data + offset)) break; copy[offset] = c; left--; offset++; } if (left == PAGE_SIZE) { kfree(copy); return ERR_PTR(-EFAULT); } return copy; } static char *copy_mount_string(const void __user *data) { return data ? strndup_user(data, PATH_MAX) : NULL; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; int ret; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; if (flags & MS_NOUSER) return -EINVAL; ret = security_sb_mount(dev_name, path, type_page, flags, data_page); if (ret) return ret; if (!may_mount()) return -EPERM; if (flags & SB_MANDLOCK) warn_mandlock(); /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; if (flags & MS_NOATIME) mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; if (flags & MS_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME)) == 0)) { mnt_flags &= ~MNT_ATIME_MASK; mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK; } sb_flags = flags & (SB_RDONLY | SB_SYNCHRONOUS | SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | SB_POSIXACL | SB_LAZYTIME | SB_I_VERSION); if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) return do_reconfigure_mnt(path, mnt_flags); if (flags & MS_REMOUNT) return do_remount(path, flags, sb_flags, mnt_flags, data_page); if (flags & MS_BIND) return do_loopback(path, dev_name, flags & MS_REC); if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return do_change_type(path, flags); if (flags & MS_MOVE) return do_move_mount_old(path, dev_name); return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name, data_page); } long do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; int ret; ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path); if (ret) return ret; ret = path_mount(dev_name, &path, type_page, flags, data_page); path_put(&path); return ret; } static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES); } static void dec_mnt_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES); } static void free_mnt_ns(struct mnt_namespace *ns) { if (!is_anon_ns(ns)) ns_free_inum(&ns->ns); dec_mnt_namespaces(ns->ucounts); mnt_ns_tree_remove(ns); } /* * Assign a sequence number so we can detect when we attempt to bind * mount a reference to an older mount namespace into the current * mount namespace, preventing reference counting loops. A 64bit * number incrementing at 10Ghz will take 12,427 years to wrap which * is effectively never, so we can ignore the possibility. */ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon) { struct mnt_namespace *new_ns; struct ucounts *ucounts; int ret; ucounts = inc_mnt_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL_ACCOUNT); if (!new_ns) { dec_mnt_namespaces(ucounts); return ERR_PTR(-ENOMEM); } if (!anon) { ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } } new_ns->ns.ops = &mntns_operations; if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); refcount_set(&new_ns->ns.count, 1); refcount_set(&new_ns->passive, 1); new_ns->mounts = RB_ROOT; RB_CLEAR_NODE(&new_ns->mnt_ns_tree_node); init_waitqueue_head(&new_ns->poll); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; } __latent_entropy struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct mnt_namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct mount *p, *q; struct mount *old; struct mount *new; int copy_flags; BUG_ON(!ns); if (likely(!(flags & CLONE_NEWNS))) { get_mnt_ns(ns); return ns; } old = ns->root; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return new_ns; namespace_lock(); /* First pass: copy the tree topology */ copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != ns->user_ns) copy_flags |= CL_SHARED_TO_SLAVE; new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { namespace_unlock(); free_mnt_ns(new_ns); return ERR_CAST(new); } if (user_ns != ns->user_ns) { lock_mount_hash(); lock_mnt_tree(new); unlock_mount_hash(); } new_ns->root = new; /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ p = old; q = new; while (p) { mnt_add_to_ns(new_ns, q); new_ns->nr_mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); rootmnt = &p->mnt; } if (&p->mnt == new_fs->pwd.mnt) { new_fs->pwd.mnt = mntget(&q->mnt); pwdmnt = &p->mnt; } } p = next_mnt(p, old); q = next_mnt(q, new); if (!q) break; // an mntns binding we'd skipped? while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(skip_mnt_tree(p), old); } mnt_ns_tree_add(new_ns); namespace_unlock(); if (rootmnt) mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); return new_ns; } struct dentry *mount_subtree(struct vfsmount *m, const char *name) { struct mount *mnt = real_mount(m); struct mnt_namespace *ns; struct super_block *s; struct path path; int err; ns = alloc_mnt_ns(&init_user_ns, true); if (IS_ERR(ns)) { mntput(m); return ERR_CAST(ns); } ns->root = mnt; ns->nr_mounts++; mnt_add_to_ns(ns, mnt); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); put_mnt_ns(ns); if (err) return ERR_PTR(err); /* trade a vfsmount reference for active sb one */ s = path.mnt->mnt_sb; atomic_inc(&s->s_active); mntput(path.mnt); /* lock the sucker */ down_write(&s->s_umount); /* ... and return the root of (sub)tree on it */ return path.dentry; } EXPORT_SYMBOL(mount_subtree); SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; char *kernel_dev; void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); if (IS_ERR(kernel_type)) goto out_type; kernel_dev = copy_mount_string(dev_name); ret = PTR_ERR(kernel_dev); if (IS_ERR(kernel_dev)) goto out_dev; options = copy_mount_options(data); ret = PTR_ERR(options); if (IS_ERR(options)) goto out_data; ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); kfree(options); out_data: kfree(kernel_dev); out_dev: kfree(kernel_type); out_type: return ret; } #define FSMOUNT_VALID_FLAGS \ (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME | \ MOUNT_ATTR_NOSYMFOLLOW) #define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP) #define MOUNT_SETATTR_PROPAGATION_FLAGS \ (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) { unsigned int mnt_flags = 0; if (attr_flags & MOUNT_ATTR_RDONLY) mnt_flags |= MNT_READONLY; if (attr_flags & MOUNT_ATTR_NOSUID) mnt_flags |= MNT_NOSUID; if (attr_flags & MOUNT_ATTR_NODEV) mnt_flags |= MNT_NODEV; if (attr_flags & MOUNT_ATTR_NOEXEC) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (attr_flags & MOUNT_ATTR_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; return mnt_flags; } /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. */ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { struct mnt_namespace *ns; struct fs_context *fc; struct file *file; struct path newmount; struct mount *mnt; struct fd f; unsigned int mnt_flags = 0; long ret; if (!may_mount()) return -EPERM; if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) return -EINVAL; if (attr_flags & ~FSMOUNT_VALID_FLAGS) return -EINVAL; mnt_flags = attr_flags_to_mnt_flags(attr_flags); switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: break; case MOUNT_ATTR_NOATIME: mnt_flags |= MNT_NOATIME; break; case MOUNT_ATTR_RELATIME: mnt_flags |= MNT_RELATIME; break; default: return -EINVAL; } f = fdget(fs_fd); if (!fd_file(f)) return -EBADF; ret = -EINVAL; if (fd_file(f)->f_op != &fscontext_fops) goto err_fsfd; fc = fd_file(f)->private_data; ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret < 0) goto err_fsfd; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) goto err_unlock; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { pr_warn("VFS: Mount too revealing\n"); goto err_unlock; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) goto err_unlock; if (fc->sb_flags & SB_MANDLOCK) warn_mandlock(); newmount.mnt = vfs_create_mount(fc); if (IS_ERR(newmount.mnt)) { ret = PTR_ERR(newmount.mnt); goto err_unlock; } newmount.dentry = dget(fc->root); newmount.mnt->mnt_flags = mnt_flags; /* We've done the mount bit - now move the file context into more or * less the same state as if we'd done an fspick(). We don't want to * do any memory allocation or anything like that at this point as we * don't want to have to handle any errors incurred. */ vfs_clean_context(fc); ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); if (IS_ERR(ns)) { ret = PTR_ERR(ns); goto err_path; } mnt = real_mount(newmount.mnt); ns->root = mnt; ns->nr_mounts = 1; mnt_add_to_ns(ns, mnt); mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount * it, not just simply put it. */ file = dentry_open(&newmount, O_PATH, fc->cred); if (IS_ERR(file)) { dissolve_on_fput(newmount.mnt); ret = PTR_ERR(file); goto err_path; } file->f_mode |= FMODE_NEED_UNMOUNT; ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0); if (ret >= 0) fd_install(ret, file); else fput(file); err_path: path_put(&newmount); err_unlock: mutex_unlock(&fc->uapi_mutex); err_fsfd: fdput(f); return ret; } /* * Move a mount from one place to another. In combination with * fsopen()/fsmount() this is used to install a new mount and in combination * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy * a mount subtree. * * Note the flags value is a combination of MOVE_MOUNT_* flags. */ SYSCALL_DEFINE5(move_mount, int, from_dfd, const char __user *, from_pathname, int, to_dfd, const char __user *, to_pathname, unsigned int, flags) { struct path from_path, to_path; unsigned int lflags; int ret = 0; if (!may_mount()) return -EPERM; if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; if ((flags & (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) == (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) return -EINVAL; /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. */ lflags = 0; if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_F_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(from_dfd, from_pathname, lflags, &from_path); if (ret < 0) return ret; lflags = 0; if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_T_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(to_dfd, to_pathname, lflags, &to_path); if (ret < 0) goto out_from; ret = security_move_mount(&from_path, &to_path); if (ret < 0) goto out_to; if (flags & MOVE_MOUNT_SET_GROUP) ret = do_set_group(&from_path, &to_path); else ret = do_move_mount(&from_path, &to_path, (flags & MOVE_MOUNT_BENEATH)); out_to: path_put(&to_path); out_from: path_put(&from_path); return ret; } /* * Return true if path is reachable from root * * namespace_sem or mount_lock is held */ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, const struct path *root) { while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) { dentry = mnt->mnt_mountpoint; mnt = mnt->mnt_parent; } return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } bool path_is_under(const struct path *path1, const struct path *path2) { bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); return res; } EXPORT_SYMBOL(path_is_under); /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem. * See Documentation/filesystems/ramfs-rootfs-initramfs.rst for alternatives * in this situation. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { struct path new, old, root; struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; struct mountpoint *old_mp, *root_mp; int error; if (!may_mount()) return -EPERM; error = user_path_at(AT_FDCWD, new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new); if (error) goto out0; error = user_path_at(AT_FDCWD, put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old); if (error) goto out1; error = security_sb_pivotroot(&old, &new); if (error) goto out2; get_fs_root(current->fs, &root); old_mp = lock_mount(&old); error = PTR_ERR(old_mp); if (IS_ERR(old_mp)) goto out3; error = -EINVAL; new_mnt = real_mount(new.mnt); root_mnt = real_mount(root.mnt); old_mnt = real_mount(old.mnt); ex_parent = new_mnt->mnt_parent; root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || IS_MNT_SHARED(ex_parent) || IS_MNT_SHARED(root_parent)) goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; if (new_mnt->mnt.mnt_flags & MNT_LOCKED) goto out4; error = -ENOENT; if (d_unlinked(new.dentry)) goto out4; error = -EBUSY; if (new_mnt == root_mnt || old_mnt == root_mnt) goto out4; /* loop, on the same file system */ error = -EINVAL; if (!path_mounted(&root)) goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ if (!path_mounted(&new)) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) goto out4; /* not attached */ /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new.dentry, &root)) goto out4; lock_mount_hash(); umount_mnt(new_mnt); root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */ if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp, false); /* mount new_root on / */ attach_mnt(new_mnt, root_parent, root_mp, false); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); put_mountpoint(root_mp); unlock_mount_hash(); chroot_fs_refs(&root, &new); error = 0; out4: unlock_mount(old_mp); if (!error) mntput_no_expire(ex_parent); out3: path_put(&root); out2: path_put(&old); out1: path_put(&new); out0: return error; } static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) { unsigned int flags = mnt->mnt.mnt_flags; /* flags to clear */ flags &= ~kattr->attr_clr; /* flags to raise */ flags |= kattr->attr_set; return flags; } static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct vfsmount *m = &mnt->mnt; struct user_namespace *fs_userns = m->mnt_sb->s_user_ns; if (!kattr->mnt_idmap) return 0; /* * Creating an idmapped mount with the filesystem wide idmapping * doesn't make sense so block that. We don't allow mushy semantics. */ if (kattr->mnt_userns == m->mnt_sb->s_user_ns) return -EINVAL; /* * Once a mount has been idmapped we don't allow it to change its * mapping. It makes things simpler and callers can just create * another bind-mount they can idmap if they want to. */ if (is_idmapped_mnt(m)) return -EPERM; /* The underlying filesystem doesn't support idmapped mounts yet. */ if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) return -EINVAL; /* The filesystem has turned off idmapped mounts. */ if (m->mnt_sb->s_iflags & SB_I_NOIDMAP) return -EINVAL; /* We're not controlling the superblock. */ if (!ns_capable(fs_userns, CAP_SYS_ADMIN)) return -EPERM; /* Mount has already been visible in the filesystem hierarchy. */ if (!is_anon_ns(mnt->mnt_ns)) return -EINVAL; return 0; } /** * mnt_allow_writers() - check whether the attribute change allows writers * @kattr: the new mount attributes * @mnt: the mount to which @kattr will be applied * * Check whether thew new mount attributes in @kattr allow concurrent writers. * * Return: true if writers need to be held, false if not */ static inline bool mnt_allow_writers(const struct mount_kattr *kattr, const struct mount *mnt) { return (!(kattr->attr_set & MNT_READONLY) || (mnt->mnt.mnt_flags & MNT_READONLY)) && !kattr->mnt_idmap; } static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; int err; for (m = mnt; m; m = next_mnt(m, mnt)) { if (!can_change_locked_flags(m, recalc_flags(kattr, m))) { err = -EPERM; break; } err = can_idmap_mount(kattr, m); if (err) break; if (!mnt_allow_writers(kattr, m)) { err = mnt_hold_writers(m); if (err) break; } if (!kattr->recurse) return 0; } if (err) { struct mount *p; /* * If we had to call mnt_hold_writers() MNT_WRITE_HOLD will * be set in @mnt_flags. The loop unsets MNT_WRITE_HOLD for all * mounts and needs to take care to include the first mount. */ for (p = mnt; p; p = next_mnt(p, mnt)) { /* If we had to hold writers unblock them. */ if (p->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(p); /* * We're done once the first mount we changed got * MNT_WRITE_HOLD unset. */ if (p == m) break; } } return err; } static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { if (!kattr->mnt_idmap) return; /* * Pairs with smp_load_acquire() in mnt_idmap(). * * Since we only allow a mount to change the idmapping once and * verified this in can_idmap_mount() we know that the mount has * @nop_mnt_idmap attached to it. So there's no need to drop any * references. */ smp_store_release(&mnt->mnt.mnt_idmap, mnt_idmap_get(kattr->mnt_idmap)); } static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; for (m = mnt; m; m = next_mnt(m, mnt)) { unsigned int flags; do_idmap_mount(kattr, m); flags = recalc_flags(kattr, m); WRITE_ONCE(m->mnt.mnt_flags, flags); /* If we had to hold writers unblock them. */ if (m->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(m); if (kattr->propagation) change_mnt_propagation(m, kattr->propagation); if (!kattr->recurse) break; } touch_mnt_namespace(mnt->mnt_ns); } static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) { struct mount *mnt = real_mount(path->mnt); int err = 0; if (!path_mounted(path)) return -EINVAL; if (kattr->mnt_userns) { struct mnt_idmap *mnt_idmap; mnt_idmap = alloc_mnt_idmap(kattr->mnt_userns); if (IS_ERR(mnt_idmap)) return PTR_ERR(mnt_idmap); kattr->mnt_idmap = mnt_idmap; } if (kattr->propagation) { /* * Only take namespace_lock() if we're actually changing * propagation. */ namespace_lock(); if (kattr->propagation == MS_SHARED) { err = invent_group_ids(mnt, kattr->recurse); if (err) { namespace_unlock(); return err; } } } err = -EINVAL; lock_mount_hash(); /* Ensure that this isn't anything purely vfs internal. */ if (!is_mounted(&mnt->mnt)) goto out; /* * If this is an attached mount make sure it's located in the callers * mount namespace. If it's not don't let the caller interact with it. * * If this mount doesn't have a parent it's most often simply a * detached mount with an anonymous mount namespace. IOW, something * that's simply not attached yet. But there are apparently also users * that do change mount properties on the rootfs itself. That obviously * neither has a parent nor is it a detached mount so we cannot * unconditionally check for detached mounts. */ if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) goto out; /* * First, we get the mount tree in a shape where we can change mount * properties without failure. If we succeeded to do so we commit all * changes and if we failed we clean up. */ err = mount_setattr_prepare(kattr, mnt); if (!err) mount_setattr_commit(kattr, mnt); out: unlock_mount_hash(); if (kattr->propagation) { if (err) cleanup_group_ids(mnt, NULL); namespace_unlock(); } return err; } static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { int err = 0; struct ns_common *ns; struct user_namespace *mnt_userns; struct fd f; if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP)) return 0; /* * We currently do not support clearing an idmapped mount. If this ever * is a use-case we can revisit this but for now let's keep it simple * and not allow it. */ if (attr->attr_clr & MOUNT_ATTR_IDMAP) return -EINVAL; if (attr->userns_fd > INT_MAX) return -EINVAL; f = fdget(attr->userns_fd); if (!fd_file(f)) return -EBADF; if (!proc_ns_file(fd_file(f))) { err = -EINVAL; goto out_fput; } ns = get_proc_ns(file_inode(fd_file(f))); if (ns->ops->type != CLONE_NEWUSER) { err = -EINVAL; goto out_fput; } /* * The initial idmapping cannot be used to create an idmapped * mount. We use the initial idmapping as an indicator of a mount * that is not idmapped. It can simply be passed into helpers that * are aware of idmapped mounts as a convenient shortcut. A user * can just create a dedicated identity mapping to achieve the same * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); if (mnt_userns == &init_user_ns) { err = -EPERM; goto out_fput; } /* We're not controlling the target namespace. */ if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) { err = -EPERM; goto out_fput; } kattr->mnt_userns = get_user_ns(mnt_userns); out_fput: fdput(f); return err; } static int build_mount_kattr(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; *kattr = (struct mount_kattr) { .lookup_flags = lookup_flags, .recurse = !!(flags & AT_RECURSIVE), }; if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS) return -EINVAL; if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1) return -EINVAL; kattr->propagation = attr->propagation; if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) return -EINVAL; kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); /* * Since the MOUNT_ATTR_<atime> values are an enum, not a bitmap, * users wanting to transition to a different atime setting cannot * simply specify the atime setting in @attr_set, but must also * specify MOUNT_ATTR__ATIME in the @attr_clr field. * So ensure that MOUNT_ATTR__ATIME can't be partially set in * @attr_clr and that @attr_set can't have any atime bits set if * MOUNT_ATTR__ATIME isn't set in @attr_clr. */ if (attr->attr_clr & MOUNT_ATTR__ATIME) { if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME) return -EINVAL; /* * Clear all previous time settings as they are mutually * exclusive. */ kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME; switch (attr->attr_set & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_RELATIME: kattr->attr_set |= MNT_RELATIME; break; case MOUNT_ATTR_NOATIME: kattr->attr_set |= MNT_NOATIME; break; case MOUNT_ATTR_STRICTATIME: break; default: return -EINVAL; } } else { if (attr->attr_set & MOUNT_ATTR__ATIME) return -EINVAL; } return build_mount_idmapped(attr, usize, kattr, flags); } static void finish_mount_kattr(struct mount_kattr *kattr) { put_user_ns(kattr->mnt_userns); kattr->mnt_userns = NULL; if (kattr->mnt_idmap) mnt_idmap_put(kattr->mnt_idmap); } SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, unsigned int, flags, struct mount_attr __user *, uattr, size_t, usize) { int err; struct path target; struct mount_attr attr; struct mount_kattr kattr; BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0); if (flags & ~(AT_EMPTY_PATH | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) return -EINVAL; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < MOUNT_ATTR_SIZE_VER0)) return -EINVAL; if (!may_mount()) return -EPERM; err = copy_struct_from_user(&attr, sizeof(attr), uattr, usize); if (err) return err; /* Don't bother walking through the mounts if this is a nop. */ if (attr.attr_set == 0 && attr.attr_clr == 0 && attr.propagation == 0) return 0; err = build_mount_kattr(&attr, usize, &kattr, flags); if (err) return err; err = user_path_at(dfd, path, kattr.lookup_flags, &target); if (!err) { err = do_mount_setattr(&target, &kattr); path_put(&target); } finish_mount_kattr(&kattr); return err; } int show_path(struct seq_file *m, struct dentry *root) { if (root->d_sb->s_op->show_path) return root->d_sb->s_op->show_path(m, root); seq_dentry(m, root, " \t\n\\"); return 0; } static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns) { struct mount *mnt = mnt_find_id_at(ns, id); if (!mnt || mnt->mnt_id_unique != id) return NULL; return &mnt->mnt; } struct kstatmount { struct statmount __user *buf; size_t bufsize; struct vfsmount *mnt; u64 mask; struct path root; struct statmount sm; struct seq_file seq; }; static u64 mnt_to_attr_flags(struct vfsmount *mnt) { unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags); u64 attr_flags = 0; if (mnt_flags & MNT_READONLY) attr_flags |= MOUNT_ATTR_RDONLY; if (mnt_flags & MNT_NOSUID) attr_flags |= MOUNT_ATTR_NOSUID; if (mnt_flags & MNT_NODEV) attr_flags |= MOUNT_ATTR_NODEV; if (mnt_flags & MNT_NOEXEC) attr_flags |= MOUNT_ATTR_NOEXEC; if (mnt_flags & MNT_NODIRATIME) attr_flags |= MOUNT_ATTR_NODIRATIME; if (mnt_flags & MNT_NOSYMFOLLOW) attr_flags |= MOUNT_ATTR_NOSYMFOLLOW; if (mnt_flags & MNT_NOATIME) attr_flags |= MOUNT_ATTR_NOATIME; else if (mnt_flags & MNT_RELATIME) attr_flags |= MOUNT_ATTR_RELATIME; else attr_flags |= MOUNT_ATTR_STRICTATIME; if (is_idmapped_mnt(mnt)) attr_flags |= MOUNT_ATTR_IDMAP; return attr_flags; } static u64 mnt_to_propagation_flags(struct mount *m) { u64 propagation = 0; if (IS_MNT_SHARED(m)) propagation |= MS_SHARED; if (IS_MNT_SLAVE(m)) propagation |= MS_SLAVE; if (IS_MNT_UNBINDABLE(m)) propagation |= MS_UNBINDABLE; if (!propagation) propagation |= MS_PRIVATE; return propagation; } static void statmount_sb_basic(struct kstatmount *s) { struct super_block *sb = s->mnt->mnt_sb; s->sm.mask |= STATMOUNT_SB_BASIC; s->sm.sb_dev_major = MAJOR(sb->s_dev); s->sm.sb_dev_minor = MINOR(sb->s_dev); s->sm.sb_magic = sb->s_magic; s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME); } static void statmount_mnt_basic(struct kstatmount *s) { struct mount *m = real_mount(s->mnt); s->sm.mask |= STATMOUNT_MNT_BASIC; s->sm.mnt_id = m->mnt_id_unique; s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique; s->sm.mnt_id_old = m->mnt_id; s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id; s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt); s->sm.mnt_propagation = mnt_to_propagation_flags(m); s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0; s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0; } static void statmount_propagate_from(struct kstatmount *s) { struct mount *m = real_mount(s->mnt); s->sm.mask |= STATMOUNT_PROPAGATE_FROM; if (IS_MNT_SLAVE(m)) s->sm.propagate_from = get_dominating_id(m, ¤t->fs->root); } static int statmount_mnt_root(struct kstatmount *s, struct seq_file *seq) { int ret; size_t start = seq->count; ret = show_path(seq, s->mnt->mnt_root); if (ret) return ret; if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; /* * Unescape the result. It would be better if supplied string was not * escaped in the first place, but that's a pretty invasive change. */ seq->buf[seq->count] = '\0'; seq->count = start; seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL)); return 0; } static int statmount_mnt_point(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; int err; err = seq_path_root(seq, &mnt_path, &s->root, ""); return err == SEQ_SKIP ? 0 : err; } static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq) { struct super_block *sb = s->mnt->mnt_sb; seq_puts(seq, sb->s_type->name); return 0; } static void statmount_mnt_ns_id(struct kstatmount *s, struct mnt_namespace *ns) { s->sm.mask |= STATMOUNT_MNT_NS_ID; s->sm.mnt_ns_id = ns->seq; } static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct super_block *sb = mnt->mnt_sb; int err; if (sb->s_op->show_options) { size_t start = seq->count; err = sb->s_op->show_options(seq, mnt->mnt_root); if (err) return err; if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; if (seq->count == start) return 0; /* skip leading comma */ memmove(seq->buf + start, seq->buf + start + 1, seq->count - start - 1); seq->count--; } return 0; } static int statmount_string(struct kstatmount *s, u64 flag) { int ret; size_t kbufsize; struct seq_file *seq = &s->seq; struct statmount *sm = &s->sm; switch (flag) { case STATMOUNT_FS_TYPE: sm->fs_type = seq->count; ret = statmount_fs_type(s, seq); break; case STATMOUNT_MNT_ROOT: sm->mnt_root = seq->count; ret = statmount_mnt_root(s, seq); break; case STATMOUNT_MNT_POINT: sm->mnt_point = seq->count; ret = statmount_mnt_point(s, seq); break; case STATMOUNT_MNT_OPTS: sm->mnt_opts = seq->count; ret = statmount_mnt_opts(s, seq); break; default: WARN_ON_ONCE(true); return -EINVAL; } if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize))) return -EOVERFLOW; if (kbufsize >= s->bufsize) return -EOVERFLOW; /* signal a retry */ if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; if (ret) return ret; seq->buf[seq->count++] = '\0'; sm->mask |= flag; return 0; } static int copy_statmount_to_user(struct kstatmount *s) { struct statmount *sm = &s->sm; struct seq_file *seq = &s->seq; char __user *str = ((char __user *)s->buf) + sizeof(*sm); size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm)); if (seq->count && copy_to_user(str, seq->buf, seq->count)) return -EFAULT; /* Return the number of bytes copied to the buffer */ sm->size = copysize + seq->count; if (copy_to_user(s->buf, sm, copysize)) return -EFAULT; return 0; } static struct mount *listmnt_next(struct mount *curr, bool reverse) { struct rb_node *node; if (reverse) node = rb_prev(&curr->mnt_node); else node = rb_next(&curr->mnt_node); return node_to_mount(node); } static int grab_requested_root(struct mnt_namespace *ns, struct path *root) { struct mount *first, *child; rwsem_assert_held(&namespace_sem); /* We're looking at our own ns, just use get_fs_root. */ if (ns == current->nsproxy->mnt_ns) { get_fs_root(current->fs, root); return 0; } /* * We have to find the first mount in our ns and use that, however it * may not exist, so handle that properly. */ if (RB_EMPTY_ROOT(&ns->mounts)) return -ENOENT; first = child = ns->root; for (;;) { child = listmnt_next(child, false); if (!child) return -ENOENT; if (child->mnt_parent == first) break; } root->mnt = mntget(&child->mnt); root->dentry = dget(root->mnt->mnt_root); return 0; } static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id, struct mnt_namespace *ns) { struct path root __free(path_put) = {}; struct mount *m; int err; /* Has the namespace already been emptied? */ if (mnt_ns_id && RB_EMPTY_ROOT(&ns->mounts)) return -ENOENT; s->mnt = lookup_mnt_in_ns(mnt_id, ns); if (!s->mnt) return -ENOENT; err = grab_requested_root(ns, &root); if (err) return err; /* * Don't trigger audit denials. We just want to determine what * mounts to show users. */ m = real_mount(s->mnt); if (!is_path_reachable(m, m->mnt.mnt_root, &root) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; err = security_sb_statfs(s->mnt->mnt_root); if (err) return err; s->root = root; if (s->mask & STATMOUNT_SB_BASIC) statmount_sb_basic(s); if (s->mask & STATMOUNT_MNT_BASIC) statmount_mnt_basic(s); if (s->mask & STATMOUNT_PROPAGATE_FROM) statmount_propagate_from(s); if (s->mask & STATMOUNT_FS_TYPE) err = statmount_string(s, STATMOUNT_FS_TYPE); if (!err && s->mask & STATMOUNT_MNT_ROOT) err = statmount_string(s, STATMOUNT_MNT_ROOT); if (!err && s->mask & STATMOUNT_MNT_POINT) err = statmount_string(s, STATMOUNT_MNT_POINT); if (!err && s->mask & STATMOUNT_MNT_OPTS) err = statmount_string(s, STATMOUNT_MNT_OPTS); if (!err && s->mask & STATMOUNT_MNT_NS_ID) statmount_mnt_ns_id(s, ns); if (err) return err; return 0; } static inline bool retry_statmount(const long ret, size_t *seq_size) { if (likely(ret != -EAGAIN)) return false; if (unlikely(check_mul_overflow(*seq_size, 2, seq_size))) return false; if (unlikely(*seq_size > MAX_RW_COUNT)) return false; return true; } #define STATMOUNT_STRING_REQ (STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | \ STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS) static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq, struct statmount __user *buf, size_t bufsize, size_t seq_size) { if (!access_ok(buf, bufsize)) return -EFAULT; memset(ks, 0, sizeof(*ks)); ks->mask = kreq->param; ks->buf = buf; ks->bufsize = bufsize; if (ks->mask & STATMOUNT_STRING_REQ) { if (bufsize == sizeof(ks->sm)) return -EOVERFLOW; ks->seq.buf = kvmalloc(seq_size, GFP_KERNEL_ACCOUNT); if (!ks->seq.buf) return -ENOMEM; ks->seq.size = seq_size; } return 0; } static int copy_mnt_id_req(const struct mnt_id_req __user *req, struct mnt_id_req *kreq) { int ret; size_t usize; BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER1); ret = get_user(usize, &req->size); if (ret) return -EFAULT; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < MNT_ID_REQ_SIZE_VER0)) return -EINVAL; memset(kreq, 0, sizeof(*kreq)); ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize); if (ret) return ret; if (kreq->spare != 0) return -EINVAL; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (kreq->mnt_id <= MNT_UNIQUE_ID_OFFSET) return -EINVAL; return 0; } /* * If the user requested a specific mount namespace id, look that up and return * that, or if not simply grab a passive reference on our mount namespace and * return that. */ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq) { struct mnt_namespace *mnt_ns; if (kreq->mnt_ns_id && kreq->spare) return ERR_PTR(-EINVAL); if (kreq->mnt_ns_id) return lookup_mnt_ns(kreq->mnt_ns_id); if (kreq->spare) { struct ns_common *ns; CLASS(fd, f)(kreq->spare); if (fd_empty(f)) return ERR_PTR(-EBADF); if (!proc_ns_file(fd_file(f))) return ERR_PTR(-EINVAL); ns = get_proc_ns(file_inode(fd_file(f))); if (ns->ops->type != CLONE_NEWNS) return ERR_PTR(-EINVAL); mnt_ns = to_mnt_ns(ns); } else { mnt_ns = current->nsproxy->mnt_ns; } refcount_inc(&mnt_ns->passive); return mnt_ns; } SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, struct statmount __user *, buf, size_t, bufsize, unsigned int, flags) { struct mnt_namespace *ns __free(mnt_ns_release) = NULL; struct kstatmount *ks __free(kfree) = NULL; struct mnt_id_req kreq; /* We currently support retrieval of 3 strings. */ size_t seq_size = 3 * PATH_MAX; int ret; if (flags) return -EINVAL; ret = copy_mnt_id_req(req, &kreq); if (ret) return ret; ns = grab_requested_mnt_ns(&kreq); if (!ns) return -ENOENT; if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -ENOENT; ks = kmalloc(sizeof(*ks), GFP_KERNEL_ACCOUNT); if (!ks) return -ENOMEM; retry: ret = prepare_kstatmount(ks, &kreq, buf, bufsize, seq_size); if (ret) return ret; scoped_guard(rwsem_read, &namespace_sem) ret = do_statmount(ks, kreq.mnt_id, kreq.mnt_ns_id, ns); if (!ret) ret = copy_statmount_to_user(ks); kvfree(ks->seq.buf); if (retry_statmount(ret, &seq_size)) goto retry; return ret; } static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id, u64 last_mnt_id, u64 *mnt_ids, size_t nr_mnt_ids, bool reverse) { struct path root __free(path_put) = {}; struct path orig; struct mount *r, *first; ssize_t ret; rwsem_assert_held(&namespace_sem); ret = grab_requested_root(ns, &root); if (ret) return ret; if (mnt_parent_id == LSMT_ROOT) { orig = root; } else { orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns); if (!orig.mnt) return -ENOENT; orig.dentry = orig.mnt->mnt_root; } /* * Don't trigger audit denials. We just want to determine what * mounts to show users. */ if (!is_path_reachable(real_mount(orig.mnt), orig.dentry, &root) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; ret = security_sb_statfs(orig.dentry); if (ret) return ret; if (!last_mnt_id) { if (reverse) first = node_to_mount(rb_last(&ns->mounts)); else first = node_to_mount(rb_first(&ns->mounts)); } else { if (reverse) first = mnt_find_id_at_reverse(ns, last_mnt_id - 1); else first = mnt_find_id_at(ns, last_mnt_id + 1); } for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r, reverse)) { if (r->mnt_id_unique == mnt_parent_id) continue; if (!is_path_reachable(r, r->mnt.mnt_root, &orig)) continue; *mnt_ids = r->mnt_id_unique; mnt_ids++; nr_mnt_ids--; ret++; } return ret; } SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, u64 __user *, mnt_ids, size_t, nr_mnt_ids, unsigned int, flags) { u64 *kmnt_ids __free(kvfree) = NULL; const size_t maxcount = 1000000; struct mnt_namespace *ns __free(mnt_ns_release) = NULL; struct mnt_id_req kreq; u64 last_mnt_id; ssize_t ret; if (flags & ~LISTMOUNT_REVERSE) return -EINVAL; /* * If the mount namespace really has more than 1 million mounts the * caller must iterate over the mount namespace (and reconsider their * system design...). */ if (unlikely(nr_mnt_ids > maxcount)) return -EOVERFLOW; if (!access_ok(mnt_ids, nr_mnt_ids * sizeof(*mnt_ids))) return -EFAULT; ret = copy_mnt_id_req(req, &kreq); if (ret) return ret; last_mnt_id = kreq.param; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET) return -EINVAL; kmnt_ids = kvmalloc_array(nr_mnt_ids, sizeof(*kmnt_ids), GFP_KERNEL_ACCOUNT); if (!kmnt_ids) return -ENOMEM; ns = grab_requested_mnt_ns(&kreq); if (!ns) return -ENOENT; if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -ENOENT; scoped_guard(rwsem_read, &namespace_sem) ret = do_listmount(ns, kreq.mnt_id, last_mnt_id, kmnt_ids, nr_mnt_ids, (flags & LISTMOUNT_REVERSE)); if (ret <= 0) return ret; if (copy_to_user(mnt_ids, kmnt_ids, ret * sizeof(*mnt_ids))) return -EFAULT; return ret; } static void __init init_mount_tree(void) { struct vfsmount *mnt; struct mount *m; struct mnt_namespace *ns; struct path root; mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); ns = alloc_mnt_ns(&init_user_ns, false); if (IS_ERR(ns)) panic("Can't allocate initial namespace"); m = real_mount(mnt); ns->root = m; ns->nr_mounts = 1; mnt_add_to_ns(ns, m); init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); root.mnt = mnt; root.dentry = mnt->mnt_root; mnt->mnt_flags |= MNT_LOCKED; set_fs_pwd(current->fs, &root); set_fs_root(current->fs, &root); mnt_ns_tree_add(ns); } void __init mnt_init(void) { int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); kernfs_init(); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __func__, err); fs_kobj = kobject_create_and_add("fs", NULL); if (!fs_kobj) printk(KERN_WARNING "%s: kobj create error\n", __func__); shmem_init(); init_rootfs(); init_mount_tree(); } void put_mnt_ns(struct mnt_namespace *ns) { if (!refcount_dec_and_test(&ns->ns.count)) return; drop_collected_mounts(&ns->root->mnt); free_mnt_ns(ns); } struct vfsmount *kern_mount(struct file_system_type *type) { struct vfsmount *mnt; mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR(mnt)) { mnt_make_shortterm(mnt); synchronize_rcu(); /* yecchhh... */ mntput(mnt); } } EXPORT_SYMBOL(kern_unmount); void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) { unsigned int i; for (i = 0; i < num; i++) mnt_make_shortterm(mnt[i]); synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); } EXPORT_SYMBOL(kern_unmount_array); bool our_mnt(struct vfsmount *mnt) { return check_mnt(real_mount(mnt)); } bool current_chrooted(void) { /* Does the current process have a non-standard root */ struct path ns_root; struct path fs_root; bool chrooted; /* Find the namespace root */ ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt; ns_root.dentry = ns_root.mnt->mnt_root; path_get(&ns_root); while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) ; get_fs_root(current->fs, &fs_root); chrooted = !path_equal(&fs_root, &ns_root); path_put(&fs_root); path_put(&ns_root); return chrooted; } static bool mnt_already_visible(struct mnt_namespace *ns, const struct super_block *sb, int *new_mnt_flags) { int new_flags = *new_mnt_flags; struct mount *mnt, *n; bool visible = false; down_read(&namespace_sem); rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) { struct mount *child; int mnt_flags; if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; /* This mount is not fully visible if it's root directory * is not the root directory of the filesystem. */ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; /* A local view of the mount flags */ mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; if ((mnt_flags & MNT_LOCK_ATIME) && ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any * locked child mounts that cover anything except for * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanently empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ MNT_LOCK_ATIME); visible = true; goto found; next: ; } found: up_read(&namespace_sem); return visible; } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags) { const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV; struct mnt_namespace *ns = current->nsproxy->mnt_ns; unsigned long s_iflags; if (ns->user_ns == &init_user_ns) return false; /* Can this filesystem be too revealing? */ s_iflags = sb->s_iflags; if (!(s_iflags & SB_I_USERNS_VISIBLE)) return false; if ((s_iflags & required_iflags) != required_iflags) { WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n", required_iflags); return true; } return !mnt_already_visible(ns, sb, new_mnt_flags); } bool mnt_may_suid(struct vfsmount *mnt) { /* * Foreign mounts (accessed via fchdir or through /proc * symlinks) are always treated as if they are nosuid. This * prevents namespaces from trusting potentially unsafe * suid/sgid bits, file caps, or security labels that originate * in other namespaces. */ return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) && current_in_userns(mnt->mnt_sb->s_user_ns); } static struct ns_common *mntns_get(struct task_struct *task) { struct ns_common *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = &nsproxy->mnt_ns->ns; get_mnt_ns(to_mnt_ns(ns)); } task_unlock(task); return ns; } static void mntns_put(struct ns_common *ns) { put_mnt_ns(to_mnt_ns(ns)); } static int mntns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct fs_struct *fs = nsset->fs; struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns; struct user_namespace *user_ns = nsset->cred->user_ns; struct path root; int err; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(user_ns, CAP_SYS_CHROOT) || !ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; if (is_anon_ns(mnt_ns)) return -EINVAL; if (fs->users != 1) return -EINVAL; get_mnt_ns(mnt_ns); old_mnt_ns = nsproxy->mnt_ns; nsproxy->mnt_ns = mnt_ns; /* Find the root */ err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt, "/", LOOKUP_DOWN, &root); if (err) { /* revert to old namespace */ nsproxy->mnt_ns = old_mnt_ns; put_mnt_ns(mnt_ns); return err; } put_mnt_ns(old_mnt_ns); /* Update the pwd and root */ set_fs_pwd(fs, &root); set_fs_root(fs, &root); path_put(&root); return 0; } static struct user_namespace *mntns_owner(struct ns_common *ns) { return to_mnt_ns(ns)->user_ns; } const struct proc_ns_operations mntns_operations = { .name = "mnt", .type = CLONE_NEWNS, .get = mntns_get, .put = mntns_put, .install = mntns_install, .owner = mntns_owner, }; #ifdef CONFIG_SYSCTL static struct ctl_table fs_namespace_sysctls[] = { { .procname = "mount-max", .data = &sysctl_mount_max, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, }; static int __init init_fs_namespace_sysctls(void) { register_sysctl_init("fs", fs_namespace_sysctls); return 0; } fs_initcall(init_fs_namespace_sysctls); #endif /* CONFIG_SYSCTL */ |
| 81 81 80 81 81 81 81 80 81 3 3 4 52 52 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/irqflags.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/tlbflush.h> struct tlb_inv_context { struct kvm_s2_mmu *mmu; unsigned long flags; u64 tcr; u64 sctlr; }; static void enter_vmid_context(struct kvm_s2_mmu *mmu, struct tlb_inv_context *cxt) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); u64 val; local_irq_save(cxt->flags); if (vcpu && mmu != vcpu->arch.hw_mmu) cxt->mmu = vcpu->arch.hw_mmu; else cxt->mmu = NULL; if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { /* * For CPUs that are affected by ARM errata 1165522 or 1530923, * we cannot trust stage-1 to be in a correct state at that * point. Since we do not want to force a full load of the * vcpu state, we prevent the EL1 page-table walker to * allocate new TLBs. This is done by setting the EPD bits * in the TCR_EL1 register. We also need to prevent it to * allocate IPA->PA walks, so we enable the S1 MMU... */ val = cxt->tcr = read_sysreg_el1(SYS_TCR); val |= TCR_EPD1_MASK | TCR_EPD0_MASK; write_sysreg_el1(val, SYS_TCR); val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR); val |= SCTLR_ELx_M; write_sysreg_el1(val, SYS_SCTLR); } /* * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and * most TLB operations target EL2/EL0. In order to affect the * guest TLBs (EL1/EL0), we need to change one of these two * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so * let's flip TGE before executing the TLB operation. * * ARM erratum 1165522 requires some special handling (again), * as we need to make sure both stages of translation are in * place before clearing TGE. __load_stage2() already * has an ISB in order to deal with this. */ __load_stage2(mmu, mmu->arch); val = read_sysreg(hcr_el2); val &= ~HCR_TGE; write_sysreg(val, hcr_el2); isb(); } static void exit_vmid_context(struct tlb_inv_context *cxt) { /* * We're done with the TLB operation, let's restore the host's * view of HCR_EL2. */ write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); isb(); /* ... and the stage-2 MMU context that we switched away from */ if (cxt->mmu) __load_stage2(cxt->mmu, cxt->mmu->arch); if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { /* Restore the registers to what they were */ write_sysreg_el1(cxt->tcr, SYS_TCR); write_sysreg_el1(cxt->sctlr, SYS_SCTLR); } local_irq_restore(cxt->flags); } void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa, int level) { struct tlb_inv_context cxt; dsb(ishst); /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); /* * We could do so much better if we had the VA as well. * Instead, we invalidate Stage-2 for this IPA, and the * whole of Stage-1. Weep... */ ipa >>= 12; __tlbi_level(ipas2e1is, ipa, level); /* * We have to ensure completion of the invalidation at Stage-2, * since a table walk on another CPU could refill a TLB with a * complete (S1 + S2) walk based on the old Stage-2 mapping if * the Stage-1 invalidation happened first. */ dsb(ish); __tlbi(vmalle1is); dsb(ish); isb(); exit_vmid_context(&cxt); } void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu, phys_addr_t ipa, int level) { struct tlb_inv_context cxt; dsb(nshst); /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); /* * We could do so much better if we had the VA as well. * Instead, we invalidate Stage-2 for this IPA, and the * whole of Stage-1. Weep... */ ipa >>= 12; __tlbi_level(ipas2e1, ipa, level); /* * We have to ensure completion of the invalidation at Stage-2, * since a table walk on another CPU could refill a TLB with a * complete (S1 + S2) walk based on the old Stage-2 mapping if * the Stage-1 invalidation happened first. */ dsb(nsh); __tlbi(vmalle1); dsb(nsh); isb(); exit_vmid_context(&cxt); } void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, phys_addr_t start, unsigned long pages) { struct tlb_inv_context cxt; unsigned long stride; /* * Since the range of addresses may not be mapped at * the same level, assume the worst case as PAGE_SIZE */ stride = PAGE_SIZE; start = round_down(start, stride); dsb(ishst); /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, TLBI_TTL_UNKNOWN); dsb(ish); __tlbi(vmalle1is); dsb(ish); isb(); exit_vmid_context(&cxt); } void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu) { struct tlb_inv_context cxt; dsb(ishst); /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); __tlbi(vmalls12e1is); dsb(ish); isb(); exit_vmid_context(&cxt); } void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu) { struct tlb_inv_context cxt; /* Switch to requested VMID */ enter_vmid_context(mmu, &cxt); __tlbi(vmalle1); asm volatile("ic iallu"); dsb(nsh); isb(); exit_vmid_context(&cxt); } void __kvm_flush_vm_context(void) { dsb(ishst); __tlbi(alle1is); dsb(ish); } /* * TLB invalidation emulation for NV. For any given instruction, we * perform the following transformtions: * * - a TLBI targeting EL2 S1 is remapped to EL1 S1 * - a non-shareable TLBI is upgraded to being inner-shareable * - an outer-shareable TLBI is also mapped to inner-shareable * - an nXS TLBI is upgraded to XS */ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding) { struct tlb_inv_context cxt; int ret = 0; /* * The guest will have provided its own DSB ISHST before trapping. * If it hasn't, that's its own problem, and we won't paper over it * (plus, there is plenty of extra synchronisation before we even * get here...). */ if (mmu) enter_vmid_context(mmu, &cxt); switch (sys_encoding) { case OP_TLBI_ALLE2: case OP_TLBI_ALLE2IS: case OP_TLBI_ALLE2OS: case OP_TLBI_VMALLE1: case OP_TLBI_VMALLE1IS: case OP_TLBI_VMALLE1OS: case OP_TLBI_ALLE2NXS: case OP_TLBI_ALLE2ISNXS: case OP_TLBI_ALLE2OSNXS: case OP_TLBI_VMALLE1NXS: case OP_TLBI_VMALLE1ISNXS: case OP_TLBI_VMALLE1OSNXS: __tlbi(vmalle1is); break; case OP_TLBI_VAE2: case OP_TLBI_VAE2IS: case OP_TLBI_VAE2OS: case OP_TLBI_VAE1: case OP_TLBI_VAE1IS: case OP_TLBI_VAE1OS: case OP_TLBI_VAE2NXS: case OP_TLBI_VAE2ISNXS: case OP_TLBI_VAE2OSNXS: case OP_TLBI_VAE1NXS: case OP_TLBI_VAE1ISNXS: case OP_TLBI_VAE1OSNXS: __tlbi(vae1is, va); break; case OP_TLBI_VALE2: case OP_TLBI_VALE2IS: case OP_TLBI_VALE2OS: case OP_TLBI_VALE1: case OP_TLBI_VALE1IS: case OP_TLBI_VALE1OS: case OP_TLBI_VALE2NXS: case OP_TLBI_VALE2ISNXS: case OP_TLBI_VALE2OSNXS: case OP_TLBI_VALE1NXS: case OP_TLBI_VALE1ISNXS: case OP_TLBI_VALE1OSNXS: __tlbi(vale1is, va); break; case OP_TLBI_ASIDE1: case OP_TLBI_ASIDE1IS: case OP_TLBI_ASIDE1OS: case OP_TLBI_ASIDE1NXS: case OP_TLBI_ASIDE1ISNXS: case OP_TLBI_ASIDE1OSNXS: __tlbi(aside1is, va); break; case OP_TLBI_VAAE1: case OP_TLBI_VAAE1IS: case OP_TLBI_VAAE1OS: case OP_TLBI_VAAE1NXS: case OP_TLBI_VAAE1ISNXS: case OP_TLBI_VAAE1OSNXS: __tlbi(vaae1is, va); break; case OP_TLBI_VAALE1: case OP_TLBI_VAALE1IS: case OP_TLBI_VAALE1OS: case OP_TLBI_VAALE1NXS: case OP_TLBI_VAALE1ISNXS: case OP_TLBI_VAALE1OSNXS: __tlbi(vaale1is, va); break; case OP_TLBI_RVAE2: case OP_TLBI_RVAE2IS: case OP_TLBI_RVAE2OS: case OP_TLBI_RVAE1: case OP_TLBI_RVAE1IS: case OP_TLBI_RVAE1OS: case OP_TLBI_RVAE2NXS: case OP_TLBI_RVAE2ISNXS: case OP_TLBI_RVAE2OSNXS: case OP_TLBI_RVAE1NXS: case OP_TLBI_RVAE1ISNXS: case OP_TLBI_RVAE1OSNXS: __tlbi(rvae1is, va); break; case OP_TLBI_RVALE2: case OP_TLBI_RVALE2IS: case OP_TLBI_RVALE2OS: case OP_TLBI_RVALE1: case OP_TLBI_RVALE1IS: case OP_TLBI_RVALE1OS: case OP_TLBI_RVALE2NXS: case OP_TLBI_RVALE2ISNXS: case OP_TLBI_RVALE2OSNXS: case OP_TLBI_RVALE1NXS: case OP_TLBI_RVALE1ISNXS: case OP_TLBI_RVALE1OSNXS: __tlbi(rvale1is, va); break; case OP_TLBI_RVAAE1: case OP_TLBI_RVAAE1IS: case OP_TLBI_RVAAE1OS: case OP_TLBI_RVAAE1NXS: case OP_TLBI_RVAAE1ISNXS: case OP_TLBI_RVAAE1OSNXS: __tlbi(rvaae1is, va); break; case OP_TLBI_RVAALE1: case OP_TLBI_RVAALE1IS: case OP_TLBI_RVAALE1OS: case OP_TLBI_RVAALE1NXS: case OP_TLBI_RVAALE1ISNXS: case OP_TLBI_RVAALE1OSNXS: __tlbi(rvaale1is, va); break; default: ret = -EINVAL; } dsb(ish); isb(); if (mmu) exit_vmid_context(&cxt); return ret; } |
| 37 37 37 37 37 37 37 37 37 37 43 44 44 44 44 44 44 25 25 25 25 25 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <hyp/sysreg-sr.h> #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_nested.h> /* * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and * pstate, which are handled as part of the el2 return state) on every * switch (sp_el0 is being dealt with in the assembly code). * tpidr_el0 and tpidrro_el0 only need to be switched when going * to host userspace or a different VCPU. EL1 registers only need to be * switched when potentially going to run a different VCPU. The latter two * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put. */ void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); __sysreg_save_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); __sysreg_restore_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); /** * __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU * * @vcpu: The VCPU pointer * * Load system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_load() function * and loading system register state early avoids having to load them on * every entry to the VM. */ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; host_ctxt = host_data_ptr(host_ctxt); __sysreg_save_user_state(host_ctxt); /* * When running a normal EL1 guest, we only load a new vcpu * after a context switch, which imvolves a DSB, so all * speculative EL1&0 walks will have already completed. * If running NV, the vcpu may transition between vEL1 and * vEL2 without a context switch, so make sure we complete * those walks before loading a new context. */ if (vcpu_has_nv(vcpu)) dsb(nsh); /* * Load guest EL1 and user state * * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). */ __sysreg32_restore_state(vcpu); __sysreg_restore_user_state(guest_ctxt); __sysreg_restore_el1_state(guest_ctxt); vcpu_set_flag(vcpu, SYSREGS_ON_CPU); } /** * __vcpu_put_switch_sysregs - Restore host system registers to the physical CPU * * @vcpu: The VCPU pointer * * Save guest system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_put() function * and deferring saving system register state until we're no longer running the * VCPU avoids having to save them on every exit from the VM. */ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; host_ctxt = host_data_ptr(host_ctxt); __sysreg_save_el1_state(guest_ctxt); __sysreg_save_user_state(guest_ctxt); __sysreg32_save_state(vcpu); /* Restore host user state */ __sysreg_restore_user_state(host_ctxt); vcpu_clear_flag(vcpu, SYSREGS_ON_CPU); } |
| 23 23 23 23 22 23 23 23 23 23 23 23 23 23 22 23 23 23 53 53 99 99 98 99 43 43 43 65 92 40 40 39 40 40 40 40 40 23 23 23 40 64 63 64 65 65 4 4 32 32 4 4 4 32 32 32 4 4 4 4 4 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/syscalls.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include <linux/migrate.h> #include <linux/pipe_fs_i.h> #include <linux/splice.h> #include <linux/rcupdate_wait.h> #include <linux/sched/mm.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> #include "swap.h" /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->block_dirty_folio) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_rwsem * ->invalidate_lock (acquired by fs in truncate path) * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->invalidate_lock (filemap_fault) * ->lock_page (filemap_fault, access_process_vm) * * ->i_rwsem (generic_perform_write) * ->mmap_lock (fault_in_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_merge) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->lruvec->lru_lock (follow_page_mask->mark_page_accessed) * ->lruvec->lru_lock (check_pte_range->folio_isolate_lru) * ->private_lock (folio_remove_rmap_pte->set_page_dirty) * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) * ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) * ->memcg->move_lock (folio_remove_rmap_pte->folio_memcg_lock) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->block_dirty_folio) */ static void mapping_set_update(struct xa_state *xas, struct address_space *mapping) { if (dax_mapping(mapping) || shmem_mapping(mapping)) return; xas_set_update(xas, workingset_update_node); xas_set_lru(xas, &shadow_nodes); } static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { XA_STATE(xas, &mapping->i_pages, folio->index); long nr = 1; mapping_set_update(&xas, mapping); xas_set_order(&xas, folio->index, folio_order(folio)); nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow); xas_init_marks(&xas); folio->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ mapping->nrpages -= nr; } static void filemap_unaccount_folio(struct address_space *mapping, struct folio *folio) { long nr; VM_BUG_ON_FOLIO(folio_mapped(folio), folio); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, folio_pfn(folio)); dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); if (mapping_exiting(mapping) && !folio_test_large(folio)) { int mapcount = folio_mapcount(folio); if (folio_ref_count(folio) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped * and we'd rather not leak it: if we're wrong, * another bad page check should catch it later. */ atomic_set(&folio->_mapcount, -1); folio_ref_sub(folio, mapcount); } } } /* hugetlb folios do not participate in page cache accounting. */ if (folio_test_hugetlb(folio)) return; nr = folio_nr_pages(folio); __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); if (folio_test_swapbacked(folio)) { __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else if (folio_test_pmd_mappable(folio)) { __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } /* * At this point folio must be either written or cleaned by * truncate. Dirty folio here signals a bug and loss of * unwritten data - on ordinary filesystems. * * But it's harmless on in-memory filesystems like tmpfs; and can * occur when a driver which did get_user_pages() sets page dirty * before putting it, while the inode is being finally evicted. * * Below fixes dirty accounting after removing the folio entirely * but leaves the dirty flag set: it has no effect for truncated * folio and anyway will be cleared before returning folio to * buddy allocator. */ if (WARN_ON_ONCE(folio_test_dirty(folio) && mapping_can_writeback(mapping))) folio_account_cleaned(folio, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __filemap_remove_folio(struct folio *folio, void *shadow) { struct address_space *mapping = folio->mapping; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); page_cache_delete(mapping, folio, shadow); } void filemap_free_folio(struct address_space *mapping, struct folio *folio) { void (*free_folio)(struct folio *); int refs = 1; free_folio = mapping->a_ops->free_folio; if (free_folio) free_folio(folio); if (folio_test_large(folio)) refs = folio_nr_pages(folio); folio_put_refs(folio, refs); } /** * filemap_remove_folio - Remove folio from page cache. * @folio: The folio. * * This must be called only on folios that are locked and have been * verified to be in the page cache. It will never put the folio into * the free list because the caller has a reference on the page. */ void filemap_remove_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); } /* * page_cache_delete_batch - delete several folios from page cache * @mapping: the mapping to which folios belong * @fbatch: batch of folios to delete * * The function walks over mapping->i_pages and removes folios passed in * @fbatch from the mapping. The function expects @fbatch to be sorted * by page index and is optimised for it to be dense. * It tolerates holes in @fbatch (mapping entries at those indices are not * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); long total_pages = 0; int i = 0; struct folio *folio; mapping_set_update(&xas, mapping); xas_for_each(&xas, folio, ULONG_MAX) { if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(folio)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (folio != fbatch->folios[i]) { VM_BUG_ON_FOLIO(folio->index > fbatch->folios[i]->index, folio); continue; } WARN_ON_ONCE(!folio_test_locked(folio)); folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies on it */ i++; xas_store(&xas, NULL); total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch) { int i; if (!folio_batch_count(fbatch)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); } page_cache_delete_batch(mapping, fbatch); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); for (i = 0; i < folio_batch_count(fbatch); i++) filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } /** * filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @wbc: the writeback_control controlling the writeout * * Call writepages on the mapping using the provided wbc to control the * writeout. * * Return: %0 on success, negative error code otherwise. */ int filemap_fdatawrite_wbc(struct address_space *mapping, struct writeback_control *wbc) { int ret; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(wbc, mapping->host); ret = do_writepages(mapping, wbc); wbc_detach_inode(wbc); return ret; } EXPORT_SYMBOL(filemap_fdatawrite_wbc); /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. * * Return: %0 on success, negative error code otherwise. */ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; return filemap_fdatawrite_wbc(mapping, &wbc); } static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); } EXPORT_SYMBOL(filemap_flush); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct folio *folio; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { folio = xas_find(&xas, max); if (xas_retry(&xas, folio)) continue; /* Shadow entries don't count */ if (xa_is_value(folio)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct folio_batch fbatch; unsigned nr_folios; folio_batch_init(&fbatch); while (index <= end) { unsigned i; nr_folios = filemap_get_folios_tag(mapping, &index, end, PAGECACHE_TAG_WRITEBACK, &fbatch); if (!nr_folios) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; folio_wait_writeback(folio); } folio_batch_release(&fbatch); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { return mapping->nrpages; } bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; struct folio *folio; if (end_byte < start_byte) return false; rcu_read_lock(); xas_for_each(&xas, folio, max) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_dirty(folio) || folio_test_locked(folio) || folio_test_writeback(folio)) break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL_GPL(filemap_range_has_writeback); /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0, err2; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = filemap_check_errors(mapping); if (!err) err = err2; return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_folio - replace a pagecache folio with a new one * @old: folio to be replaced * @new: folio to replace with * * This function replaces a folio in the pagecache with a new one. On * success it acquires the pagecache reference for the new folio and * drops it for the old folio. Both the old and new folios must be * locked. This function does not add the new folio to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. */ void replace_page_cache_folio(struct folio *old, struct folio *new) { struct address_space *mapping = old->mapping; void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); VM_BUG_ON_FOLIO(!folio_test_locked(old), old); VM_BUG_ON_FOLIO(!folio_test_locked(new), new); VM_BUG_ON_FOLIO(new->mapping, new); folio_get(new); new->mapping = mapping; new->index = offset; mem_cgroup_replace_folio(old, new); xas_lock_irq(&xas); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!folio_test_hugetlb(old)) __lruvec_stat_sub_folio(old, NR_FILE_PAGES); if (!folio_test_hugetlb(new)) __lruvec_stat_add_folio(new, NR_FILE_PAGES); if (folio_test_swapbacked(old)) __lruvec_stat_sub_folio(old, NR_SHMEM); if (folio_test_swapbacked(new)) __lruvec_stat_add_folio(new, NR_SHMEM); xas_unlock_irq(&xas); if (free_folio) free_folio(old); folio_put(old); } EXPORT_SYMBOL_GPL(replace_page_cache_folio); noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, index); void *alloced_shadow = NULL; int alloced_order = 0; bool huge; long nr; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping), folio); mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); xas_set_order(&xas, index, folio_order(folio)); huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; folio_ref_add(folio, nr); folio->mapping = mapping; folio->index = xas.xa_index; for (;;) { int order = -1, split_order = 0; void *entry, *old = NULL; xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } /* * If a larger entry exists, * it will be the first and only entry iterated. */ if (order == -1) order = xas_get_order(&xas); } /* entry may have changed before we re-acquire the lock */ if (alloced_order && (old != alloced_shadow || order != alloced_order)) { xas_destroy(&xas); alloced_order = 0; } if (old) { if (order > 0 && order > folio_order(folio)) { /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); if (!alloced_order) { split_order = order; goto unlock; } xas_split(&xas, old, order); xas_reset(&xas); } if (shadowp) *shadowp = old; } xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; mapping->nrpages += nr; /* hugetlb pages do not participate in page cache accounting */ if (!huge) { __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } unlock: xas_unlock_irq(&xas); /* split needed, alloc here and retry. */ if (split_order) { xas_split_alloc(&xas, old, split_order, gfp); if (xas_error(&xas)) goto error; alloced_shadow = old; alloced_order = split_order; xas_reset(&xas); continue; } if (!xas_nomem(&xas, gfp)) break; } if (xas_error(&xas)) goto error; trace_mm_filemap_add_to_page_cache(folio); return 0; error: folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ folio_put_refs(folio, nr); return xas_error(&xas); } ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; ret = mem_cgroup_charge(folio, NULL, gfp); if (ret) return ret; __folio_set_locked(folio); ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) { mem_cgroup_uncharge(folio); __folio_clear_locked(folio); } else { /* * The folio might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed folio. * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(folio_test_active(folio)); if (!(gfp & __GFP_WRITE) && shadow) workingset_refault(folio, shadow); folio_add_lru(folio); } return ret; } EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { int n; struct folio *folio; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); folio = __folio_alloc_node_noprof(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); return folio; } return folio_alloc_noprof(gfp, order); } EXPORT_SYMBOL(filemap_alloc_folio_noprof); #endif /* * filemap_invalidate_lock_two - lock invalidate_lock for two mappings * * Lock exclusively invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to lock * @mapping2: the second mapping to lock */ void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1 > mapping2) swap(mapping1, mapping2); if (mapping1) down_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) down_write_nested(&mapping2->invalidate_lock, 1); } EXPORT_SYMBOL(filemap_invalidate_lock_two); /* * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings * * Unlock exclusive invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to unlock * @mapping2: the second mapping to unlock */ void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1) up_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) up_write(&mapping2->invalidate_lock); } EXPORT_SYMBOL(filemap_invalidate_unlock_two); /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *folio_waitqueue(struct folio *folio) { return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->folio->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->folio->flags)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void folio_wake_bit(struct folio *folio, int bit_nr) { wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key(q, TASK_NORMAL, &key); /* * It's possible to miss clearing waiters here, when we woke our page * waiters, but the hashed waitqueue has waiters for other pages on it. * That's okay, it's a rare case. The next waker will clear it. * * Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE, * other), the flag may be cleared in the course of freeing the page; * but that is not required for correctness. */ if (!waitqueue_active(q) || !key.page_match) folio_clear_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } /* * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like folio_put_wait_locked() on PG_locked. */ }; /* * Attempt to check (or get) the folio flag, and mark us done * if successful. */ static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &folio->flags)) return false; } else if (test_bit(bit_nr, &folio->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, int state, enum behavior behavior) { wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; if (bit_nr == PG_locked && !folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the folio. */ if (behavior == DROP) folio_put(folio); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } #ifdef CONFIG_MIGRATION /** * migration_entry_wait_on_locked - Wait for a migration entry to be removed * @entry: migration swap entry. * @ptl: already locked ptl. This function will drop the lock. * * Wait for a migration entry referencing the given page to be removed. This is * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except * this can be called without taking a reference on the page. Instead this * should be called while holding the ptl for the migration entry referencing * the page. * * Returns after unlocking the ptl. * * This follows the same logic as folio_wait_bit_common() so see the comments * there. */ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) __releases(ptl) { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; wait_queue_head_t *q; struct folio *folio = pfn_swap_entry_folio(entry); q = folio_waitqueue(folio); if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = PG_locked; wait->flags = 0; spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, PG_locked, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * If a migration entry exists for the page the migration path must hold * a valid reference to the page, and it must take the ptl to remove the * migration entry. So the page is valid until the ptl is dropped. */ spin_unlock(ptl); for (;;) { unsigned int flags; set_current_state(TASK_UNINTERRUPTIBLE); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) break; io_schedule(); continue; } break; } finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } } #endif void folio_wait_bit(struct folio *folio, int bit_nr) { folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit); int folio_wait_bit_killable(struct folio *folio, int bit_nr) { return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit_killable); /** * folio_put_wait_locked - Drop a reference and wait for it to be unlocked * @folio: The folio to wait for. * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not * dereference @folio. * * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ static int folio_put_wait_locked(struct folio *folio, int state) { return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue * @folio: Folio defining the wait queue of interest * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @folio. */ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) { wait_queue_head_t *q = folio_waitqueue(folio); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); folio_set_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(folio_add_wait_queue); /** * folio_unlock - Unlock a locked folio. * @folio: The folio. * * Unlocks the folio and wakes up any thread sleeping on the page lock. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_unlock(struct folio *folio) { /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); BUILD_BUG_ON(PG_locked > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_xor_flags_has_waiters(folio, 1 << PG_locked)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_unlock); /** * folio_end_read - End read on a folio. * @folio: The folio. * @success: True if all reads completed successfully. * * When all reads against a folio have completed, filesystems should * call this function to let the pagecache know that no more reads * are outstanding. This will unlock the folio and wake up any thread * sleeping on the lock. The folio will also be marked uptodate if all * reads succeeded. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_end_read(struct folio *folio, bool success) { unsigned long mask = 1 << PG_locked; /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; if (folio_xor_flags_has_waiters(folio, mask)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_end_read); /** * folio_end_private_2 - Clear PG_private_2 and wake any waiters. * @folio: The folio. * * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for * it. The folio reference held for PG_private_2 being set is released. * * This is, for example, used when a netfs folio is being written to a local * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ void folio_end_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); folio_wake_bit(folio, PG_private_2); folio_put(folio); } EXPORT_SYMBOL(folio_end_private_2); /** * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio. */ void folio_wait_private_2(struct folio *folio) { while (folio_test_private_2(folio)) folio_wait_bit(folio, PG_private_2); } EXPORT_SYMBOL(folio_wait_private_2); /** * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is * received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ int folio_wait_private_2_killable(struct folio *folio) { int ret = 0; while (folio_test_private_2(folio)) { ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } return ret; } EXPORT_SYMBOL(folio_wait_private_2_killable); /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. * * The folio must actually be under writeback. * * Context: May be called from process or interrupt context. */ void folio_end_writeback(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* * folio_test_clear_reclaim() could be used here but it is an * atomic operation and overkill in this particular case. Failing * to shuffle a folio marked for immediate reclaim is too mild * a gain to justify taking an atomic operation penalty at the * end of every folio writeback. */ if (folio_test_reclaim(folio)) { folio_clear_reclaim(folio); folio_rotate_reclaimable(folio); } /* * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the folio is not freed and * reused before the folio_wake_bit(). */ folio_get(folio); if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); /** * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. * @folio: The folio to lock */ void __folio_lock(struct folio *folio) { folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__folio_lock); int __folio_lock_killable(struct folio *folio) { return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__folio_lock_killable); static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { struct wait_queue_head *q = folio_waitqueue(folio); int ret; wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); folio_set_waiters(folio); ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } /* * Return values: * 0 - folio is locked. * non-zero - folio is not locked. * mmap_lock or per-VMA lock has been released (mmap_read_unlock() or * vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 0 * with the folio locked and the mmap_lock/per-VMA lock is left unperturbed. */ vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { unsigned int flags = vmf->flags; if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock/per-VMA lock is not * released even though returning VM_FAULT_RETRY. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return VM_FAULT_RETRY; release_fault_lock(vmf); if (flags & FAULT_FLAG_KILLABLE) folio_wait_locked_killable(folio); else folio_wait_locked(folio); return VM_FAULT_RETRY; } if (flags & FAULT_FLAG_KILLABLE) { bool ret; ret = __folio_lock_killable(folio); if (ret) { release_fault_lock(vmf); return VM_FAULT_RETRY; } } else { __folio_lock(folio); } return 0; } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) return xas.xa_index; if (xas.xa_index == 0) return 0; } return index + max_scan; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /* * Lockless page cache protocol: * On the lookup side: * 1. Load the folio from i_pages * 2. Increment the refcount if it's not zero * 3. If the folio is not found by xas_reload(), put the refcount and retry * * On the removal side: * A. Freeze the page (by zeroing the refcount if nobody else has a reference) * B. Remove the page from i_pages * C. Return the page to the page allocator * * This means that any page may have its reference count temporarily * increased by a speculative page cache (or GUP-fast) lookup as it can * be allocated by another user before the RCU grace period expires. * Because the refcount temporarily acquired here may end up being the * last refcount on the page, any page allocation must be freeable by * folio_put(). */ /* * filemap_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache entry at @mapping & @index. If it is a folio, * it is returned with an increased refcount. If it is a shadow entry * of a previously evicted folio, or a swap entry from shmem/tmpfs, * it is returned without further action. * * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); folio = xas_load(&xas); if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!folio || xa_is_value(folio)) goto out; if (!folio_try_get(folio)) goto repeat; if (unlikely(folio != xas_reload(&xas))) { folio_put(folio); goto repeat; } out: rcu_read_unlock(); return folio; } /** * __filemap_get_folio - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the folio is returned. * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If this function returns a folio, it is returned with an increased refcount. * * Return: The found folio or an ERR_PTR() otherwise. */ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; repeat: folio = filemap_get_entry(mapping, index); if (xa_is_value(folio)) folio = NULL; if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EAGAIN); } } else { folio_lock(folio); } /* Has the page been truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (folio_test_idle(folio)) folio_clear_idle(folio); } if (fgp_flags & FGP_STABLE) folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { unsigned int min_order = mapping_min_folio_order(mapping); unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags)); int err; index = mapping_align_index(mapping, index); if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp &= ~__GFP_FS; if (fgp_flags & FGP_NOWAIT) { gfp &= ~GFP_KERNEL; gfp |= GFP_NOWAIT | __GFP_NOWARN; } if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; if (order > mapping_max_folio_order(mapping)) order = mapping_max_folio_order(mapping); /* If we're not aligned, allocate a smaller folio */ if (index & ((1UL << order) - 1)) order = __ffs(index); do { gfp_t alloc_gfp = gfp; err = -ENOMEM; if (order > min_order) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; folio = filemap_alloc_folio(alloc_gfp, order); if (!folio) continue; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) break; folio_put(folio); folio = NULL; } while (order-- > min_order); if (err == -EEXIST) goto repeat; if (err) return ERR_PTR(err); /* * filemap_add_folio locks the page, and for mmap * we expect an unlocked page. */ if (folio && (fgp_flags & FGP_FOR_MMAP)) folio_unlock(folio); } if (!folio) return ERR_PTR(-ENOENT); return folio; } EXPORT_SYMBOL(__filemap_get_folio); static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) { struct folio *folio; retry: if (mark == XA_PRESENT) folio = xas_find(xas, max); else folio = xas_find_marked(xas, max, mark); if (xas_retry(xas, folio)) goto retry; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (!folio || xa_is_value(folio)) return folio; if (!folio_try_get(folio)) goto reset; if (unlikely(folio != xas_reload(xas))) { folio_put(folio); goto reset; } return folio; reset: xas_reset(xas); goto retry; } /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a batch of entries in * the mapping. The entries are placed in @fbatch. find_get_entries() * takes a reference on any actual folios it returns. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries or large folios. * * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * * Return: The number of entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; } if (folio_batch_count(fbatch)) { unsigned long nr; int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; if (!xa_is_value(folio)) nr = folio_nr_pages(folio); else nr = 1 << xa_get_order(&mapping->i_pages, indices[idx]); *start = round_down(indices[idx] + nr, nr); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * find_lock_entries - Find a batch of pagecache entries. * @mapping: The address_space to search. * @start: The starting page cache index. * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices of the entries in @fbatch. * * find_lock_entries() will return a batch of entries from @mapping. * Swap, shadow and DAX entries are included. Folios are returned * locked and with an incremented refcount. Folios which are locked * by somebody else or under writeback are skipped. Folios which are * partially outside the range are not returned. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries, large folios, folios which could not be * locked or folios under writeback. * * Return: The number of entries which were found. */ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { unsigned long base; unsigned long nr; if (!xa_is_value(folio)) { nr = folio_nr_pages(folio); base = folio->index; /* Omit large folio which begins before the start */ if (base < *start) goto put; /* Omit large folio which extends beyond the end */ if (base + nr - 1 > end) goto put; if (!folio_trylock(folio)) goto put; if (folio->mapping != mapping || folio_test_writeback(folio)) goto unlock; VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), folio); } else { nr = 1 << xas_get_order(&xas); base = xas.xa_index & ~(nr - 1); /* Omit order>0 value which begins before the start */ if (base < *start) continue; /* Omit order>0 value which extends beyond the end */ if (base + nr - 1 > end) break; } /* Update start now so that last update is correct on return */ *start = base + nr; indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; continue; unlock: folio_unlock(folio); put: folio_put(folio); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * filemap_get_folios - Get a batch of folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill. * * Search for and return a batch of folios in the mapping starting at * index @start and up to index @end (inclusive). The folios are returned * in @fbatch with an elevated reference count. * * Return: The number of folios which were found. * We also update @start to index the next folio for the traversal. */ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch); } EXPORT_SYMBOL(filemap_get_folios); /** * filemap_get_folios_contig - Get a batch of contiguous folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill * * filemap_get_folios_contig() works exactly like filemap_get_folios(), * except the returned folios are guaranteed to be contiguous. This may * not return all contiguous folios if the batch gets filled up. * * Return: The number of folios found. * Also update @start to be positioned for traversal of the next folio. */ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); unsigned long nr; struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio && xas.xa_index <= end; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(folio)) goto update_start; /* If we landed in the middle of a THP, continue at its end. */ if (xa_is_sibling(folio)) goto update_start; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) { nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } update_start: nr = folio_batch_count(fbatch); if (nr) { folio = fbatch->folios[nr - 1]; *start = folio_next_index(folio); } out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_contig); /** * filemap_get_folios_tag - Get a batch of folios matching @tag * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @tag: The tag index * @fbatch: The batch to fill * * The first folio may start before @start; if it does, it will contain * @start. The final folio may extend beyond @end; if it does, it will * contain @end. The folios have ascending indices. There may be gaps * between the folios if there are indices which have no folio in the * page cache. If folios are added to or removed from the page cache * while this is running, they may or may not be found by this call. * Only returns folios that are tagged with @tag. * * Return: The number of folios found. * Also update @start to index the next folio for traversal. */ unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, tag)) != NULL) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(folio)) continue; if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broke anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_tag); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /* * filemap_get_read_batch - Get a batch of folios for read * * Get a batch of folios which represent a contiguous range of bytes in * the file. No exceptional entries will be returned. If @index is in * the middle of a folio, the entire folio will be returned. The last * folio in the batch may have the readahead flag set or the uptodate flag * clear so that the caller can take the appropriate action. */ static void filemap_get_read_batch(struct address_space *mapping, pgoff_t index, pgoff_t max, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; if (xas.xa_index > max || xa_is_value(folio)) break; if (xa_is_sibling(folio)) break; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) break; if (!folio_test_uptodate(folio)) break; if (folio_test_readahead(folio)) break; xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } rcu_read_unlock(); } static int filemap_read_folio(struct file *file, filler_t filler, struct folio *folio) { bool workingset = folio_test_workingset(folio); unsigned long pflags; int error; /* Start the actual read. The read will unlock the page. */ if (unlikely(workingset)) psi_memstall_enter(&pflags); error = filler(file, folio); if (unlikely(workingset)) psi_memstall_leave(&pflags); if (error) return error; error = folio_wait_locked_killable(folio); if (error) return error; if (folio_test_uptodate(folio)) return 0; if (file) shrink_readahead_size_eio(&file->f_ra); return -EIO; } static bool filemap_range_uptodate(struct address_space *mapping, loff_t pos, size_t count, struct folio *folio, bool need_uptodate) { if (folio_test_uptodate(folio)) return true; /* pipes can't handle partially uptodate pages */ if (need_uptodate) return false; if (!mapping->a_ops->is_partially_uptodate) return false; if (mapping->host->i_blkbits >= folio_shift(folio)) return false; if (folio_pos(folio) > pos) { count -= folio_pos(folio) - pos; pos = 0; } else { pos -= folio_pos(folio); } return mapping->a_ops->is_partially_uptodate(folio, pos, count); } static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, size_t count, struct folio *folio, bool need_uptodate) { int error; if (iocb->ki_flags & IOCB_NOWAIT) { if (!filemap_invalidate_trylock_shared(mapping)) return -EAGAIN; } else { filemap_invalidate_lock_shared(mapping); } if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); /* * This is where we usually end up waiting for a * previously submitted readahead to finish. */ folio_put_wait_locked(folio, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; if (!folio->mapping) goto unlock; error = 0; if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio, need_uptodate)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); goto unlock_mapping; unlock: folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) folio_put(folio); return error; } static int filemap_create_folio(struct file *file, struct address_space *mapping, loff_t pos, struct folio_batch *fbatch) { struct folio *folio; int error; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t index; folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order); if (!folio) return -ENOMEM; /* * Protect against truncate / hole punch. Grabbing invalidate_lock * here assures we cannot instantiate and bring uptodate new * pagecache folios after evicting page cache during truncate * and before actually freeing blocks. Note that we could * release invalidate_lock after inserting the folio into * the page cache as the locked folio would then be enough to * synchronize with hole punching. But there are code paths * such as filemap_update_page() filling in partially uptodate * pages or ->readahead() that need to hold invalidate_lock * while mapping blocks for IO so let's hold the lock here as * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); index = (pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) error = AOP_TRUNCATED_PAGE; if (error) goto error; error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (error) goto error; filemap_invalidate_unlock_shared(mapping); folio_batch_add(fbatch, folio); return 0; error: filemap_invalidate_unlock_shared(mapping); folio_put(folio); return error; } static int filemap_readahead(struct kiocb *iocb, struct file *file, struct address_space *mapping, struct folio *folio, pgoff_t last_index) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } static int filemap_get_pages(struct kiocb *iocb, size_t count, struct folio_batch *fbatch, bool need_uptodate) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct file_ra_state *ra = &filp->f_ra; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; unsigned int flags; int err = 0; /* "last_index" is the index of the page beyond the end of the read */ last_index = DIV_ROUND_UP(iocb->ki_pos + count, PAGE_SIZE); retry: if (fatal_signal_pending(current)) return -EINTR; filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_NOWAIT) flags = memalloc_noio_save(); page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); if (iocb->ki_flags & IOCB_NOWAIT) memalloc_noio_restore(flags); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } folio = fbatch->folios[folio_batch_count(fbatch) - 1]; if (folio_test_readahead(folio)) { err = filemap_readahead(iocb, filp, mapping, folio, last_index); if (err) goto err; } if (!folio_test_uptodate(folio)) { if ((iocb->ki_flags & IOCB_WAITQ) && folio_batch_count(fbatch) > 1) iocb->ki_flags |= IOCB_NOWAIT; err = filemap_update_page(iocb, mapping, count, folio, need_uptodate); if (err) goto err; } trace_mm_filemap_get_pages(mapping, index, last_index - 1); return 0; err: if (err < 0) folio_put(folio); if (likely(--fbatch->nr)) return 0; if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) { unsigned int shift = folio_shift(folio); return (pos1 >> shift == pos2 >> shift); } /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. * @iter: Destination for the data. * @already_read: Number of bytes already read by the caller. * * Copies data from the page cache. If the data is not currently present, * uses the readahead and read_folio address_space operations to fetch it. * * Return: Total number of bytes copied, including those already read by * the caller. If an error happens before any bytes are copied, returns * a negative error number. */ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t already_read) { struct file *filp = iocb->ki_filp; struct file_ra_state *ra = &filp->f_ra; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct folio_batch fbatch; int i, error = 0; bool writably_mapped; loff_t isize, end_offset; loff_t last_pos = ra->prev_pos; if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes)) return 0; if (unlikely(!iov_iter_count(iter))) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); folio_batch_init(&fbatch); do { cond_resched(); /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; error = filemap_get_pages(iocb, iter->count, &fbatch, false); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); if (unlikely(iocb->ki_pos >= isize)) goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(mapping); /* * When a read accesses the same folio several times, only * mark it as accessed the first time. */ if (!pos_same_folio(iocb->ki_pos, last_pos - 1, fbatch.folios[0])) folio_mark_accessed(fbatch.folios[0]); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t fsize = folio_size(folio); size_t offset = iocb->ki_pos & (fsize - 1); size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); size_t copied; if (end_offset < folio_pos(folio)) break; if (i > 0) folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); copied = copy_folio_to_iter(folio, offset, bytes, iter); already_read += copied; iocb->ki_pos += copied; last_pos = iocb->ki_pos; if (copied < bytes) { error = -EFAULT; break; } } put_folios: for (i = 0; i < folio_batch_count(&fbatch); i++) folio_put(fbatch.folios[i]); folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); file_accessed(filp); ra->prev_pos = last_pos; return already_read ? already_read : error; } EXPORT_SYMBOL_GPL(filemap_read); int kiocb_write_and_wait(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos; loff_t end = pos + count - 1; if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, pos, end)) return -EAGAIN; return 0; } return filemap_write_and_wait_range(mapping, pos, end); } EXPORT_SYMBOL_GPL(kiocb_write_and_wait); int filemap_invalidate_pages(struct address_space *mapping, loff_t pos, loff_t end, bool nowait) { int ret; if (nowait) { /* we could block if there are any pages in the range */ if (filemap_range_has_page(mapping, pos, end)) return -EAGAIN; } else { ret = filemap_write_and_wait_range(mapping, pos, end); if (ret) return ret; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; return filemap_invalidate_pages(mapping, iocb->ki_pos, iocb->ki_pos + count - 1, iocb->ki_flags & IOCB_NOWAIT); } EXPORT_SYMBOL_GPL(kiocb_invalidate_pages); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) return 0; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; retval = kiocb_write_and_wait(iocb, count); if (retval < 0) return retval; file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } if (retval != -EIOCBQUEUED) iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || IS_DAX(inode)) return retval; if (iocb->ki_pos >= i_size_read(inode)) return retval; } return filemap_read(iocb, iter, retval); } EXPORT_SYMBOL(generic_file_read_iter); /* * Splice subpages from a folio into a pipe. */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size) { struct page *page; size_t spliced = 0, offset = offset_in_folio(folio, fpos); page = folio_page(folio, offset / PAGE_SIZE); size = min(size, folio_size(folio) - offset); offset %= PAGE_SIZE; while (spliced < size && !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { struct pipe_buffer *buf = pipe_head_buf(pipe); size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); *buf = (struct pipe_buffer) { .ops = &page_cache_pipe_buf_ops, .page = page, .offset = offset, .len = part, }; folio_get(folio); pipe->head++; page++; spliced += part; offset = 0; } return spliced; } /** * filemap_splice_read - Splice data from a file's pagecache into a pipe * @in: The file to read from * @ppos: Pointer to the file position to read from * @pipe: The pipe to splice into * @len: The amount to splice * @flags: The SPLICE_F_* flags * * This function gets folios from a file's pagecache and splices them into the * pipe. Readahead will be called as necessary to fill more folios. This may * be used for blockdevs also. * * Return: On success, the number of bytes read will be returned and *@ppos * will be updated if appropriate; 0 will be returned if there is no more data * to be read; -EAGAIN will be returned if the pipe had no space, and some * other negative error code will be returned on error. A short read may occur * if the pipe has insufficient space, we reach the end of the data or we hit a * hole. */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct folio_batch fbatch; struct kiocb iocb; size_t total_spliced = 0, used, npages; loff_t isize, end_offset; bool writably_mapped; int i, error = 0; if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes)) return 0; init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; /* Work out how much data we can actually add into the pipe */ used = pipe_occupancy(pipe->head, pipe->tail); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); folio_batch_init(&fbatch); do { cond_resched(); if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos; error = filemap_get_pages(&iocb, len, &fbatch, true); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) break; end_offset = min_t(loff_t, isize, *ppos + len); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(in->f_mapping); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t n; if (folio_pos(folio) >= end_offset) goto out; folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); n = min_t(loff_t, len, isize - *ppos); n = splice_folio_into_pipe(pipe, folio, *ppos, n); if (!n) goto out; len -= n; total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) goto out; } folio_batch_release(&fbatch); } while (len); out: folio_batch_release(&fbatch); file_accessed(in); return total_spliced ? total_spliced : error; } EXPORT_SYMBOL(filemap_splice_read); static inline loff_t folio_seek_hole_data(struct xa_state *xas, struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) { const struct address_space_operations *ops = mapping->a_ops; size_t offset, bsz = i_blocksize(mapping->host); if (xa_is_value(folio) || folio_test_uptodate(folio)) return seek_data ? start : end; if (!ops->is_partially_uptodate) return seek_data ? end : start; xas_pause(xas); rcu_read_unlock(); folio_lock(folio); if (unlikely(folio->mapping != mapping)) goto unlock; offset = offset_in_folio(folio, start) & ~(bsz - 1); do { if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; start = (start + bsz) & ~(bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: folio_unlock(folio); rcu_read_lock(); return start; } static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio) { if (xa_is_value(folio)) return PAGE_SIZE << xas_get_order(xas); return folio_size(folio); } /** * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. * @mapping: Address space to search. * @start: First byte to consider. * @end: Limit of search (exclusive). * @whence: Either SEEK_HOLE or SEEK_DATA. * * If the page cache knows which blocks contain holes and which blocks * contain data, your filesystem can use this function to implement * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are * entirely memory-based such as tmpfs, and filesystems which support * unwritten extents. * * Return: The requested offset on success, or -ENXIO if @whence specifies * SEEK_DATA and there is no data after @start. There is an implicit hole * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start * and @end contain data. */ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, loff_t end, int whence) { XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); pgoff_t max = (end - 1) >> PAGE_SHIFT; bool seek_data = (whence == SEEK_DATA); struct folio *folio; if (end <= start) return -ENXIO; rcu_read_lock(); while ((folio = find_get_entry(&xas, max, XA_PRESENT))) { loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; size_t seek_size; if (start < pos) { if (!seek_data) goto unlock; start = pos; } seek_size = seek_folio_size(&xas, folio); pos = round_up((u64)pos + 1, seek_size); start = folio_seek_hole_data(&xas, mapping, folio, start, pos, seek_data); if (start < pos) goto unlock; if (start >= end) break; if (seek_size > PAGE_SIZE) xas_set(&xas, pos >> PAGE_SHIFT); if (!xa_is_value(folio)) folio_put(folio); } if (seek_data) start = -ENXIO; unlock: rcu_read_unlock(); if (folio && !xa_is_value(folio)) folio_put(folio); if (start > end) return end; return start; } #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @folio - the folio to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_folio_or_retry in that it can drop the * mmap_lock. It differs in that it actually returns the folio locked * if it returns 1 and 0 if it couldn't lock the folio. If we did have * to drop the mmap_lock then fpin will point to the pinned file and * needs to be fput()'ed at a later point. */ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, struct file **fpin) { if (folio_trylock(folio)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the * fault lock, but all fault_handlers only check * for fatal signals if we return VM_FAULT_RETRY, * so we need to drop the fault lock here and * return 0 if we don't have a fpin. */ if (*fpin == NULL) release_fault_lock(vmf); return 0; } } else __folio_lock(folio); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff); struct file *fpin = NULL; unsigned long vm_flags = vmf->vma->vm_flags; unsigned int mmap_miss; #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1); ra->size = HPAGE_PMD_NR; /* * Fetch two PMD folios, so we get the chance to actually * readahead, unless we've been told not to. */ if (!(vm_flags & VM_RAND_READ)) ra->size *= 2; ra->async_size = HPAGE_PMD_NR; page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER); return fpin; } #endif /* If we don't want any read-ahead, don't bother */ if (vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ractl._index = ra->start; page_cache_ra_order(&ractl, ra, 0); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct folio *folio) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_ra(&ractl, folio, ra->ra_pages); } return fpin; } static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; pte_t *ptep; /* * We might have COW'ed a pagecache folio and might now have an mlocked * anon folio mapped. The original pagecache folio is not mlocked and * might have been evicted. During a read+clear/modify/write update of * the PTE, such as done in do_numa_page()/change_pte_range(), we * temporarily clear the PTE under PT lock and might detect it here as * "none" when not holding the PT lock. * * Not rechecking the PTE under PT lock could result in an unexpected * major fault in an mlock'ed region. Recheck only for this special * scenario while holding the PT lock, to not degrade non-mlocked * scenarios. Recheck the PTE without PT lock firstly, thereby reducing * the number of times we hold PT lock. */ if (!(vma->vm_flags & VM_LOCKED)) return 0; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; ptep = pte_offset_map_nolock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; if (unlikely(!pte_none(ptep_get_lockless(ptep)))) { ret = VM_FAULT_NOPAGE; } else { spin_lock(vmf->ptl); if (unlikely(!pte_none(ptep_get(ptep)))) ret = VM_FAULT_NOPAGE; spin_unlock(vmf->ptl); } pte_unmap(ptep); return ret; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_folio_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; pgoff_t max_idx, index = vmf->pgoff; struct folio *folio; vm_fault_t ret = 0; bool mapping_locked = false; max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) return VM_FAULT_SIGBUS; trace_mm_filemap_fault(mapping, index); /* * Do we have something in the page cache already? */ folio = filemap_get_folio(mapping, index); if (likely(!IS_ERR(folio))) { /* * We found the page, so try async readahead before waiting for * the lock. */ if (!(vmf->flags & FAULT_FLAG_TRIED)) fpin = do_async_mmap_readahead(vmf, folio); if (unlikely(!folio_test_uptodate(folio))) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } } else { ret = filemap_fault_recheck_pte_none(vmf); if (unlikely(ret)) return ret; /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: /* * See comment in filemap_create_folio() why we need * invalidate_lock */ if (!mapping_locked) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (IS_ERR(folio)) { if (fpin) goto out_retry; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_OOM; } } if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto retry_find; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* * We have a locked folio in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error, * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we * didn't hold the page lock all the time. Let's drop * everything, get the invalidate lock and try again. */ if (!mapping_locked) { folio_unlock(folio); folio_put(folio); goto retry_find; } /* * OK, the folio is really not uptodate. This can be because the * VMA has the VM_RAND_READ flag set, or because an error * arose. Let's read it in directly. */ goto page_not_uptodate; } /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { folio_unlock(folio); goto out_retry; } if (mapping_locked) filemap_invalidate_unlock_shared(mapping); /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) { folio_unlock(folio); folio_put(folio); return VM_FAULT_SIGBUS; } vmf->page = folio_file_page(folio, index); return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (fpin) goto out_retry; folio_put(folio); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (!IS_ERR(folio)) folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio, pgoff_t start) { struct mm_struct *mm = vmf->vma->vm_mm; /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) { folio_unlock(folio); folio_put(folio); return true; } if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) { struct page *page = folio_file_page(folio, start); vm_fault_t ret = do_set_pmd(vmf, page); if (!ret) { /* The page is mapped successfully, reference consumed. */ folio_unlock(folio); return true; } } if (pmd_none(*vmf->pmd) && vmf->prealloc_pte) pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); return false; } static struct folio *next_uptodate_folio(struct xa_state *xas, struct address_space *mapping, pgoff_t end_pgoff) { struct folio *folio = xas_next_entry(xas, end_pgoff); unsigned long max_idx; do { if (!folio) return NULL; if (xas_retry(xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_locked(folio)) continue; if (!folio_try_get(folio)) continue; /* Has the page moved or been split? */ if (unlikely(folio != xas_reload(xas))) goto skip; if (!folio_test_uptodate(folio) || folio_test_readahead(folio)) goto skip; if (!folio_trylock(folio)) goto skip; if (folio->mapping != mapping) goto unlock; if (!folio_test_uptodate(folio)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas->xa_index >= max_idx) goto unlock; return folio; unlock: folio_unlock(folio); skip: folio_put(folio); } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL); return NULL; } /* * Map page range [start_page, start_page + nr_pages) of folio. * start_page is gotten from start by folio_page(folio, start) */ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = folio_page(folio, start); unsigned int count = 0; pte_t *old_ptep = vmf->pte; do { if (PageHWPoison(page + count)) goto skip; /* * If there are too many folios that are recently evicted * in a file, they will probably continue to be evicted. * In such situation, read-ahead is only a waste of IO. * Don't decrease mmap_miss in this scenario to make sure * we can stop read-ahead. */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip; count++; continue; skip: if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } count++; page += count; vmf->pte += count; addr += count * PAGE_SIZE; count = 0; } while (--nr_pages > 0); if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } vmf->pte = old_ptep; return ret; } static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, struct folio *folio, unsigned long addr, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = &folio->page; if (PageHWPoison(page)) return ret; /* See comment of filemap_map_folio_range() */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit * the fault-around logic. */ if (!pte_none(ptep_get(vmf->pte))) return ret; if (vmf->address == addr) ret = VM_FAULT_NOPAGE; set_pte_range(vmf, folio, page, 1, addr); (*rss)++; folio_ref_inc(folio); return ret; } vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct vm_area_struct *vma = vmf->vma; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t file_end, last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; unsigned long rss = 0; unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; if (filemap_map_pmd(vmf, folio, start_pgoff)) { ret = VM_FAULT_NOPAGE; goto out; } addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) { folio_unlock(folio); folio_put(folio); goto out; } file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; if (end_pgoff > file_end) end_pgoff = file_end; folio_type = mm_counter_file(folio); do { unsigned long end; addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; if (!folio_test_large(folio)) ret |= filemap_map_order0_folio(vmf, folio, addr, &rss, &mmap_miss); else ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, nr_pages, &rss, &mmap_miss); folio_unlock(folio); folio_put(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); add_mm_counter(vma->vm_mm, folio_type, rss); pte_unmap_unlock(vmf->pte, vmf->ptl); trace_mm_filemap_map_pages(mapping, start_pgoff, end_pgoff); out: rcu_read_unlock(); mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss); if (mmap_miss >= mmap_miss_saved) WRITE_ONCE(file->f_ra.mmap_miss, 0); else WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss); return ret; } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_fi |