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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __FS_NOTIFY_FSNOTIFY_H_ #define __FS_NOTIFY_FSNOTIFY_H_ #include <linux/list.h> #include <linux/fsnotify.h> #include <linux/srcu.h> #include <linux/types.h> #include "../mount.h" static inline struct inode *fsnotify_conn_inode( struct fsnotify_mark_connector *conn) { return container_of(conn->obj, struct inode, i_fsnotify_marks); } static inline struct mount *fsnotify_conn_mount( struct fsnotify_mark_connector *conn) { return container_of(conn->obj, struct mount, mnt_fsnotify_marks); } static inline struct super_block *fsnotify_conn_sb( struct fsnotify_mark_connector *conn) { return container_of(conn->obj, struct super_block, s_fsnotify_marks); } /* destroy all events sitting in this groups notification queue */ extern void fsnotify_flush_notify(struct fsnotify_group *group); /* protects reads of inode and vfsmount marks list */ extern struct srcu_struct fsnotify_mark_srcu; /* compare two groups for sorting of marks lists */ extern int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b); /* Destroy all marks attached to an object via connector */ extern void fsnotify_destroy_marks(fsnotify_connp_t *connp); /* run the list of all marks associated with inode and destroy them */ static inline void fsnotify_clear_marks_by_inode(struct inode *inode) { fsnotify_destroy_marks(&inode->i_fsnotify_marks); } /* run the list of all marks associated with vfsmount and destroy them */ static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt) { fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks); } /* run the list of all marks associated with sb and destroy them */ static inline void fsnotify_clear_marks_by_sb(struct super_block *sb) { fsnotify_destroy_marks(&sb->s_fsnotify_marks); } /* * update the dentry->d_flags of all of inode's children to indicate if inode cares * about events that happen to its children. */ extern void __fsnotify_update_child_dentry_flags(struct inode *inode); /* allocate and destroy and event holder to attach events to notification/access queues */ extern struct fsnotify_event_holder *fsnotify_alloc_event_holder(void); extern void fsnotify_destroy_event_holder(struct fsnotify_event_holder *holder); extern struct kmem_cache *fsnotify_mark_connector_cachep; #endif /* __FS_NOTIFY_FSNOTIFY_H_ */
2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 2 2 2 1 1 1 1 2 1 2 1 2 2 2 1 1 2 2 2 1 1 1 1 1 1 1 2 1 1 2 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 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 // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * IPv4 specific functions * * code split from: * linux/ipv4/tcp.c * linux/ipv4/tcp_input.c * linux/ipv4/tcp_output.c * * See tcp.c for author information */ /* * Changes: * David S. Miller : New socket lookup architecture. * This code is dedicated to John Dyson. * David S. Miller : Change semantics of established hash, * half is devoted to TIME_WAIT sockets * and the rest go in the other half. * Andi Kleen : Add support for syncookies and fixed * some bugs: ip options weren't passed to * the TCP layer, missed a check for an * ACK bit. * Andi Kleen : Implemented fast path mtu discovery. * Fixed many serious bugs in the * request_sock handling and moved * most of it into the af independent code. * Added tail drop and some other bugfixes. * Added new listen semantics. * Mike McLagan : Routing by source * Juan Jose Ciarlante: ip_dynaddr bits * Andi Kleen: various fixes. * Vitaly E. Lavrov : Transparent proxy revived after year * coma. * Andi Kleen : Fix new listen. * Andi Kleen : Fix accept error reporting. * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. */ #define pr_fmt(fmt) "TCP: " fmt #include <linux/bottom_half.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> #include <linux/random.h> #include <linux/cache.h> #include <linux/jhash.h> #include <linux/init.h> #include <linux/times.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/icmp.h> #include <net/inet_hashtables.h> #include <net/tcp.h> #include <net/transp_v6.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/busy_poll.h> #include <linux/inet.h> #include <linux/ipv6.h> #include <linux/stddef.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <linux/btf_ids.h> #include <crypto/hash.h> #include <linux/scatterlist.h> #include <trace/events/tcp.h> #ifdef CONFIG_TCP_MD5SIG static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th); #endif struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, tcp_hdr(skb)->dest, tcp_hdr(skb)->source); } static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) { return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) { const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse; if (reuse == 2) { /* Still does not detect *everything* that goes through * lo, since we require a loopback src or dst address * or direct binding to 'lo' interface. */ bool loopback = false; if (tw->tw_bound_dev_if == LOOPBACK_IFINDEX) loopback = true; #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == AF_INET6) { if (ipv6_addr_loopback(&tw->tw_v6_daddr) || ipv6_addr_v4mapped_loopback(&tw->tw_v6_daddr) || ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) || ipv6_addr_v4mapped_loopback(&tw->tw_v6_rcv_saddr)) loopback = true; } else #endif { if (ipv4_is_loopback(tw->tw_daddr) || ipv4_is_loopback(tw->tw_rcv_saddr)) loopback = true; } if (!loopback) reuse = 0; } /* With PAWS, it is safe from the viewpoint of data integrity. Even without PAWS it is safe provided sequence spaces do not overlap i.e. at data rates <= 80Mbit/sec. Actually, the idea is close to VJ's one, only timestamp cache is held not per host, but per port pair and TW bucket is used as state holder. If TW bucket has been already destroyed we fall back to VJ's scheme and use initial timestamp retrieved from peer table. */ if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && time_after32(ktime_get_seconds(), tcptw->tw_ts_recent_stamp)))) { /* In case of repair and re-using TIME-WAIT sockets we still * want to be sure that it is safe as above but honor the * sequence numbers and time stamps set as part of the repair * process. * * Without this check re-using a TIME-WAIT socket with TCP * repair would accumulate a -1 on the repair assigned * sequence number. The first time it is reused the sequence * is -1, the second time -2, etc. This fixes that issue * without appearing to create any others. */ if (likely(!tp->repair)) { u32 seq = tcptw->tw_snd_nxt + 65535 + 2; if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } sock_hold(sktw); return 1; } return 0; } EXPORT_SYMBOL_GPL(tcp_twsk_unique); static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from tcp_v4_connect() and intended to * prevent BPF program called below from accessing bytes that are out * of the bound specified by user in addr_len. */ if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; sock_owned_by_me(sk); return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr); } /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); __be16 orig_sport, orig_dport; __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; struct ip_options_rcu *inet_opt; struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; if (usin->sin_family != AF_INET) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) { if (!daddr) return -EINVAL; nexthop = inet_opt->opt.faddr; } orig_sport = inet->inet_sport; orig_dport = usin->sin_port; fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, orig_sport, orig_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); return err; } if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { ip_rt_put(rt); return -ENETUNREACH; } if (!inet_opt || !inet_opt->opt.srr) daddr = fl4->daddr; if (!inet->inet_saddr) inet->inet_saddr = fl4->saddr; sk_rcv_saddr_set(sk, inet->inet_saddr); if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { /* Reset inherited state */ tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; /* Socket identity is still unknown (sport may be zero). * However we set state to SYN-SENT and not releasing socket * lock select source port, enter ourselves into the hash tables and * complete initialization after this. */ tcp_set_state(sk, TCP_SYN_SENT); err = inet_hash_connect(tcp_death_row, sk); if (err) goto failure; sk_set_txhash(sk); rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto failure; } /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); rt = NULL; if (likely(!tp->repair)) { if (!tp->write_seq) WRITE_ONCE(tp->write_seq, secure_tcp_seq(inet->inet_saddr, inet->inet_daddr, inet->inet_sport, usin->sin_port)); tp->tsoffset = secure_tcp_ts_off(sock_net(sk), inet->inet_saddr, inet->inet_daddr); } inet->inet_id = prandom_u32(); if (tcp_fastopen_defer_connect(sk, &err)) return err; if (err) goto failure; err = tcp_connect(sk); if (err) goto failure; return 0; failure: /* * This unhashes the socket and releases the local port, * if necessary. */ tcp_set_state(sk, TCP_CLOSE); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; return err; } EXPORT_SYMBOL(tcp_v4_connect); /* * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191. * It can be called through tcp_release_cb() if socket was owned by user * at the time tcp_v4_err() was called to handle ICMP message. */ void tcp_v4_mtu_reduced(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct dst_entry *dst; u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; mtu = READ_ONCE(tcp_sk(sk)->mtu_info); dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst)) sk->sk_err_soft = EMSGSIZE; mtu = dst_mtu(dst); if (inet->pmtudisc != IP_PMTUDISC_DONT && ip_sk_accept_pmtu(sk) && inet_csk(sk)->icsk_pmtu_cookie > mtu) { tcp_sync_mss(sk, mtu); /* Resend the TCP packet because it's * clear that the old packet has been * dropped. This is the new "fast" path mtu * discovery. */ tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } EXPORT_SYMBOL(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { struct dst_entry *dst = __sk_dst_check(sk, 0); if (dst) dst->ops->redirect(dst, sk, skb); } /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ void tcp_req_err(struct sock *sk, u32 seq, bool abort) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); /* ICMPs are not backlogged, hence we cannot get * an established socket here. */ if (seq != tcp_rsk(req)->snt_isn) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); } else if (abort) { /* * Still in SYN_RECV, just remove it silently. * There is no good way to pass the error to the newly * created socket, and POSIX does not want network * errors returned from accept(). */ inet_csk_reqsk_queue_drop(req->rsk_listener, req); tcp_listendrop(req->rsk_listener); } reqsk_put(req); } EXPORT_SYMBOL(tcp_req_err); /* TCP-LD (RFC 6069) logic */ void tcp_ld_RTO_revert(struct sock *sk, u32 seq) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; s32 remaining; u32 delta_us; if (sock_owned_by_user(sk)) return; if (seq != tp->snd_una || !icsk->icsk_retransmits || !icsk->icsk_backoff) return; skb = tcp_rtx_queue_head(sk); if (WARN_ON_ONCE(!skb)) return; icsk->icsk_backoff--; icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); tcp_mstamp_refresh(tp); delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); remaining = icsk->icsk_rto - usecs_to_jiffies(delta_us); if (remaining > 0) { inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, TCP_RTO_MAX); } else { /* RTO revert clocked out retransmission. * Will retransmit now. */ tcp_retransmit_timer(sk); } } EXPORT_SYMBOL(tcp_ld_RTO_revert); /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should * be closed and the error returned to the user. If err > 0 * it's just the icmp type << 8 | icmp code. After adjustment * header points to the first 8 bytes of the tcp header. We need * to find the appropriate port. * * The locking strategy used here is very "optimistic". When * someone else accesses the socket the ICMP is just dropped * and for some paths there is no check at all. * A more general error queue to queue errors for later handling * is probably better. * */ int tcp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); struct tcp_sock *tp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; struct request_sock *fastopen; u32 seq, snd_una; int err; struct net *net = dev_net(skb->dev); sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr, th->dest, iph->saddr, ntohs(th->source), inet_iif(skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return 0; } seq = ntohl(th->seq); if (sk->sk_state == TCP_NEW_SYN_RECV) { tcp_req_err(sk, seq, type == ICMP_PARAMETERPROB || type == ICMP_TIME_EXCEEDED || (type == ICMP_DEST_UNREACH && (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH))); return 0; } bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ if (sock_owned_by_user(sk)) { if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); } if (sk->sk_state == TCP_CLOSE) goto out; if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto out; } tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { case ICMP_REDIRECT: if (!sock_owned_by_user(sk)) do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; case ICMP_PARAMETERPROB: err = EPROTO; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). */ if (sk->sk_state == TCP_LISTEN) goto out; WRITE_ONCE(tp->mtu_info, info); if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); } else { if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } goto out; } err = icmp_err_convert[code].errno; /* check if this ICMP message allows revert of backoff. * (see RFC 6069) */ if (!fastopen && (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH)) tcp_ld_RTO_revert(sk, seq); break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; default: goto out; } switch (sk->sk_state) { case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th); if (!sock_owned_by_user(sk)) { sk->sk_err = err; sk->sk_error_report(sk); tcp_done(sk); } else { sk->sk_err_soft = err; } goto out; } /* If we've already connected we will keep trying * until we time out, or the user gives up. * * rfc1122 4.2.3.9 allows to consider as hard errors * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too, * but it is obsoleted by pmtu discovery). * * Note, that in modern internet, where routing is unreliable * and in each dark corner broken firewalls sit, sending random * errors ordered by their masters even this two messages finally lose * their original sense (even Linux sends invalid PORT_UNREACHs) * * Now we are in compliance with RFCs. * --ANK (980905) */ inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else { /* Only an error on timeout */ sk->sk_err_soft = err; } out: bh_unlock_sock(sk); sock_put(sk); return 0; } void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } /* This routine computes an IPv4 TCP checksum. */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) { const struct inet_sock *inet = inet_sk(sk); __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); } EXPORT_SYMBOL(tcp_v4_send_check); /* * This routine will send an RST to the other tcp. * * Someone asks: why I NEVER use socket parameters (TOS, TTL etc.) * for reset. * Answer: if a packet caused RST, it is not for a socket * existing in our system, if it is matched to a socket, * it is just duplicate segment or bug in other side's TCP. * So that we build reply only basing on parameters * arrived with segment. * Exception: precedence violation. We do not implement it in any case. */ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; #ifdef CONFIG_TCP_MD5SIG __be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)]; #endif } rep; struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key = NULL; const __u8 *hash_location = NULL; unsigned char newhash[16]; int genhash; struct sock *sk1 = NULL; #endif u64 transmit_time = 0; struct sock *ctl_sk; struct net *net; /* Never send a reset in response to a reset. */ if (th->rst) return; /* If sk not NULL, it means we did a successful lookup and incoming * route had to be correct. prequeue might have dropped our dst. */ if (!sk && skb_rtable(skb)->rt_type != RTN_LOCAL) return; /* Swap the send and the receive. */ memset(&rep, 0, sizeof(rep)); rep.th.dest = th->source; rep.th.source = th->dest; rep.th.doff = sizeof(struct tcphdr) / 4; rep.th.rst = 1; if (th->ack) { rep.th.seq = th->ack_seq; } else { rep.th.ack = 1; rep.th.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2)); } memset(&arg, 0, sizeof(arg)); arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); if (sk && sk_fullsock(sk)) { const union tcp_md5_addr *addr; int l3index; /* sdif set, means packet ingressed via a device * in an L3 domain and inet_iif is set to it. */ l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } else if (hash_location) { const union tcp_md5_addr *addr; int sdif = tcp_v4_sdif(skb); int dif = inet_iif(skb); int l3index; /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. * we are not loose security here: * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, ntohs(th->source), dif, sdif); /* don't send rst if it can't find key */ if (!sk1) goto out; /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to it. */ l3index = sdif ? dif : 0; addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; key = tcp_md5_do_lookup(sk1, l3index, addr, AF_INET); if (!key) goto out; genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto out; } if (key) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* Update length and the length the header thinks exists */ arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len / 4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1], key, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &rep.th); } #endif arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0; /* When socket is gone, all binding information is lost. * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. */ if (sk) { arg.bound_dev_if = sk->sk_bound_dev_if; if (sk_fullsock(sk)) trace_tcp_send_reset(sk, skb); } BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != offsetof(struct inet_timewait_sock, tw_bound_dev_if)); arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, transmit_time); ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_bh_enable(); #ifdef CONFIG_TCP_MD5SIG out: rcu_read_unlock(); #endif } /* The code following below sending ACKs in SYN-RECV and TIME-WAIT states outside socket context is ugly, certainly. What can I do? */ static void tcp_v4_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; __be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2) #ifdef CONFIG_TCP_MD5SIG + (TCPOLEN_MD5SIG_ALIGNED >> 2) #endif ]; } rep; struct net *net = sock_net(sk); struct ip_reply_arg arg; struct sock *ctl_sk; u64 transmit_time; memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); if (tsecr) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); rep.opt[1] = htonl(tsval); rep.opt[2] = htonl(tsecr); arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; } /* Swap the send and the receive. */ rep.th.dest = th->source; rep.th.source = th->dest; rep.th.doff = arg.iov[0].iov_len / 4; rep.th.seq = htonl(seq); rep.th.ack_seq = htonl(ack); rep.th.ack = 1; rep.th.window = htons(win); #ifdef CONFIG_TCP_MD5SIG if (key) { int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len/4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset], key, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &rep.th); } #endif arg.flags = reply_flags; arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; if (oif) arg.bound_dev_if = oif; arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, transmit_time); ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); } static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, tw->tw_tos ); inet_twsk_put(tw); } static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { const union tcp_md5_addr *addr; int l3index; /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; /* RFC 7323 2.3 * The window field (SEG.WND) of every outgoing segment, with the * exception of <SYN> segments, MUST be right-shifted by * Rcv.Wind.Shift bits: */ addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); } /* * Send a SYN-ACK after having received a SYN. * This still operates on a request_sock only, not on a big * socket. */ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; int err = -1; struct sk_buff *skb; u8 tos; /* First, grab a route. */ if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | (inet_sk(sk)->tos & INET_ECN_MASK) : inet_sk(sk)->tos; if (!INET_ECN_is_capable(tos) && tcp_bpf_ca_needs_ecn((struct sock *)req)) tos |= INET_ECN_ECT_0; rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt), tos); rcu_read_unlock(); err = net_xmit_eval(err); } return err; } /* * IPv4 request_sock destructor. */ static void tcp_v4_reqsk_destructor(struct request_sock *req) { kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } #ifdef CONFIG_TCP_MD5SIG /* * RFC2385 MD5 checksumming requires a mapping of * IP address->MD5 Key. * We need to maintain these in the sk structure. */ DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); EXPORT_SYMBOL(tcp_md5_needed); static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) { if (!old) return true; /* l3index always overrides non-l3index */ if (old->l3index && new->l3index == 0) return false; if (old->l3index == 0 && new->l3index) return true; return old->prefixlen < new->prefixlen; } /* Find the Key structure for an address. */ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; const struct tcp_md5sig_info *md5sig; __be32 mask; struct tcp_md5sig_key *best_match = NULL; bool match; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) return NULL; hlist_for_each_entry_rcu(key, &md5sig->head, node, lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (key->l3index && key->l3index != l3index) continue; if (family == AF_INET) { mask = inet_make_mask(key->prefixlen); match = (key->addr.a4.s_addr & mask) == (addr->a4.s_addr & mask); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { match = ipv6_prefix_equal(&key->addr.a6, &addr->a6, key->prefixlen); #endif } else { match = false; } if (match && better_md5_match(best_match, key)) best_match = key; } return best_match; } EXPORT_SYMBOL(__tcp_md5_do_lookup); static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; unsigned int size = sizeof(struct in_addr); const struct tcp_md5sig_info *md5sig; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) return NULL; #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) size = sizeof(struct in6_addr); #endif hlist_for_each_entry_rcu(key, &md5sig->head, node, lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (key->l3index != l3index) continue; if (!memcmp(&key->addr, addr, size) && key->prefixlen == prefixlen) return key; } return NULL; } struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { const union tcp_md5_addr *addr; int l3index; l3index = l3mdev_master_ifindex_by_index(sock_net(sk), addr_sk->sk_bound_dev_if); addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; return tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } EXPORT_SYMBOL(tcp_v4_md5_lookup); /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); if (key) { /* Pre-existing entry - just update that one. * Note that the key might be used concurrently. * data_race() is telling kcsan that we do not care of * key mismatches, since changing MD5 key on live flows * can lead to packet drops. */ data_race(memcpy(key->key, newkey, newkeylen)); /* Pairs with READ_ONCE() in tcp_md5_hash_key(). * Also note that a reader could catch new key->keylen value * but old key->key[], this is the reason we use __GFP_ZERO * at sock_kmalloc() time below these lines. */ WRITE_ONCE(key->keylen, newkeylen); return 0; } md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) { md5sig = kmalloc(sizeof(*md5sig), gfp); if (!md5sig) return -ENOMEM; sk_nocaps_add(sk, NETIF_F_GSO_MASK); INIT_HLIST_HEAD(&md5sig->head); rcu_assign_pointer(tp->md5sig_info, md5sig); } key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; if (!tcp_alloc_md5sig_pool()) { sock_kfree_s(sk, key, sizeof(*key)); return -ENOMEM; } memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; key->family = family; key->prefixlen = prefixlen; key->l3index = l3index; memcpy(&key->addr, addr, (family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); hlist_add_head_rcu(&key->node, &md5sig->head); return 0; } EXPORT_SYMBOL(tcp_md5_do_add); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index) { struct tcp_md5sig_key *key; key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); if (!key) return -ENOENT; hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); return 0; } EXPORT_SYMBOL(tcp_md5_do_del); static void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; struct hlist_node *n; struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); hlist_for_each_entry_safe(key, n, &md5sig->head, node) { hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); } } static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; const union tcp_md5_addr *addr; u8 prefixlen = 32; int l3index = 0; if (optlen < sizeof(cmd)) return -EINVAL; if (copy_from_sockptr(&cmd, optval, sizeof(cmd))) return -EFAULT; if (sin->sin_family != AF_INET) return -EINVAL; if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; if (prefixlen > 32) return -EINVAL; } if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); if (dev && netif_is_l3_master(dev)) l3index = dev->ifindex; rcu_read_unlock(); /* ok to reference set/not set outside of rcu; * right now device MUST be an L3 master */ if (!dev || !l3index) return -EINVAL; } addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr; if (!cmd.tcpm_keylen) return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, __be32 daddr, __be32 saddr, const struct tcphdr *th, int nbytes) { struct tcp4_pseudohdr *bp; struct scatterlist sg; struct tcphdr *_th; bp = hp->scratch; bp->saddr = saddr; bp->daddr = daddr; bp->pad = 0; bp->protocol = IPPROTO_TCP; bp->len = cpu_to_be16(nbytes); _th = (struct tcphdr *)(bp + 1); memcpy(_th, th, sizeof(*th)); _th->check = 0; sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp) + sizeof(*th)); return crypto_ahash_update(hp->md5_req); } static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th) { struct tcp_md5sig_pool *hp; struct ahash_request *req; hp = tcp_get_md5sig_pool(); if (!hp) goto clear_hash_noput; req = hp->md5_req; if (crypto_ahash_init(req)) goto clear_hash; if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(hp, key)) goto clear_hash; ahash_request_set_crypt(req, NULL, md5_hash, 0); if (crypto_ahash_final(req)) goto clear_hash; tcp_put_md5sig_pool(); return 0; clear_hash: tcp_put_md5sig_pool(); clear_hash_noput: memset(md5_hash, 0, 16); return 1; } int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb) { struct tcp_md5sig_pool *hp; struct ahash_request *req; const struct tcphdr *th = tcp_hdr(skb); __be32 saddr, daddr; if (sk) { /* valid for establish/request sockets */ saddr = sk->sk_rcv_saddr; daddr = sk->sk_daddr; } else { const struct iphdr *iph = ip_hdr(skb); saddr = iph->saddr; daddr = iph->daddr; } hp = tcp_get_md5sig_pool(); if (!hp) goto clear_hash_noput; req = hp->md5_req; if (crypto_ahash_init(req)) goto clear_hash; if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, skb->len)) goto clear_hash; if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(hp, key)) goto clear_hash; ahash_request_set_crypt(req, NULL, md5_hash, 0); if (crypto_ahash_final(req)) goto clear_hash; tcp_put_md5sig_pool(); return 0; clear_hash: tcp_put_md5sig_pool(); clear_hash_noput: memset(md5_hash, 0, 16); return 1; } EXPORT_SYMBOL(tcp_v4_md5_hash_skb); #endif /* Called with rcu_read_lock() */ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, int dif, int sdif) { #ifdef CONFIG_TCP_MD5SIG /* * This gets called for each TCP segment that arrives * so we want to be efficient. * We have 3 drop cases: * o No MD5 hash and one expected. * o MD5 hash and we're not expecting one. * o MD5 hash and its wrong. */ const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; const struct iphdr *iph = ip_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); const union tcp_md5_addr *addr; unsigned char newhash[16]; int genhash, l3index; /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to the l3mdev */ l3index = sdif ? dif : 0; addr = (union tcp_md5_addr *)&iph->saddr; hash_expected = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); hash_location = tcp_parse_md5sig_option(th); /* We've parsed the options - do we have a hash? */ if (!hash_expected && !hash_location) return false; if (hash_expected && !hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); return true; } if (!hash_expected && hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); return true; } /* Okay, so this is hash_expected and hash_location - * so we need to calculate the checksum. */ genhash = tcp_v4_md5_hash_skb(newhash, hash_expected, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n", &iph->saddr, ntohs(th->source), &iph->daddr, ntohs(th->dest), genhash ? " tcp_v4_calc_md5_hash failed" : "", l3index); return true; } return false; #endif return false; } static void tcp_v4_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); struct net *net = sock_net(sk_listener); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct flowi *fl, const struct request_sock *req) { return inet_csk_route_req(sk, &fl->u.ip4, req); } struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .mss_clamp = TCP_MSS_DEFAULT, #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, #endif .init_req = tcp_v4_init_req, #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, .init_seq = tcp_v4_init_seq, .init_ts_off = tcp_v4_init_ts_off, .send_synack = tcp_v4_send_synack, }; int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; return tcp_conn_request(&tcp_request_sock_ops, &tcp_request_sock_ipv4_ops, sk, skb); drop: tcp_listendrop(sk); return 0; } EXPORT_SYMBOL(tcp_v4_conn_request); /* * The three way handshake has completed - we got a valid synack - * now create the new socket. */ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req) { struct inet_request_sock *ireq; bool found_dup_sk = false; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG const union tcp_md5_addr *addr; struct tcp_md5sig_key *key; int l3index; #endif struct ip_options_rcu *inet_opt; if (sk_acceptq_is_full(sk)) goto exit_overflow; newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; inet_sk_rx_dst_set(newsk, skb); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newsk->sk_bound_dev_if = ireq->ir_iif; newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = rcu_dereference(ireq->ireq_opt); RCU_INIT_POINTER(newinet->inet_opt, inet_opt); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = prandom_u32(); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). */ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); if (!dst) goto put_and_exit; } else { /* syncookie case : see end of cookie_v4_check() */ } sk_setup_caps(newsk, dst); tcp_ca_openreq_child(newsk, dst); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst)); tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); /* Copy over the MD5 key from the original socket */ addr = (union tcp_md5_addr *)&newinet->inet_daddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key) { /* * We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key * across. Shucks. */ tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &found_dup_sk); if (likely(*own_req)) { tcp_move_syn(newtp, req); ireq->ireq_opt = NULL; } else { newinet->inet_opt = NULL; if (!req_unhash && found_dup_sk) { /* This code path should only be executed in the * syncookie case only */ bh_unlock_sock(newsk); sock_put(newsk); newsk = NULL; } } return newsk; exit_overflow: NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); exit_nonewsk: dst_release(dst); exit: tcp_listendrop(sk); return NULL; put_and_exit: newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto exit; } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); if (!th->syn) sk = cookie_v4_check(sk, skb); #endif return sk; } u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie) { u16 mss = 0; #ifdef CONFIG_SYN_COOKIES mss = tcp_get_syncookie_mss(&tcp_request_sock_ops, &tcp_request_sock_ipv4_ops, sk, th); if (mss) { *cookie = __cookie_v4_init_sequence(iph, th, &mss); tcp_synq_overflow(sk); } #endif return mss; } /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) { struct sock *rsk; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst = sk->sk_rx_dst; sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || !dst->ops->check(dst, 0)) { dst_release(dst); sk->sk_rx_dst = NULL; } } tcp_rcv_established(sk, skb); return 0; } if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v4_cookie_check(sk, skb); if (!nsk) goto discard; if (nsk != sk) { if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; } return 0; } } else sock_rps_save_rxhash(sk, skb); if (tcp_rcv_state_process(sk, skb)) { rsk = sk; goto reset; } return 0; reset: tcp_v4_send_reset(rsk, skb); discard: kfree_skb(skb); /* Be careful here. If this function gets more complicated and * gcc suffers from register pressure on the x86, sk (in %ebx) * might be destroyed here. This current version compiles correctly, * but you have been warned. */ return 0; csum_err: TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; } EXPORT_SYMBOL(tcp_v4_do_rcv); int tcp_v4_early_demux(struct sk_buff *skb) { const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) return 0; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return 0; iph = ip_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return 0; sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), skb->skb_iif, inet_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); if (dst && inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } return 0; } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) { u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf); u32 tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; struct sk_buff *tail; unsigned int hdrlen; bool fragstolen; u32 gso_segs; u32 gso_size; int delta; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), * we can fix skb->truesize to its real value to avoid future drops. * This is valid because skb is not yet charged to the socket. * It has been noticed pure SACK packets were sometimes dropped * (if cooked by drivers without copybreak feature). */ skb_condense(skb); skb_dst_drop(skb); if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); return true; } /* Attempt coalescing to last skb in backlog, even if we are * above the limits. * This is okay because skb capacity is limited to MAX_SKB_FRAGS. */ th = (const struct tcphdr *)skb->data; hdrlen = th->doff * 4; tail = sk->sk_backlog.tail; if (!tail) goto no_coalesce; thtail = (struct tcphdr *)tail->data; if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq || TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield || ((TCP_SKB_CB(tail)->tcp_flags | TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) || !((TCP_SKB_CB(tail)->tcp_flags & TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || ((TCP_SKB_CB(tail)->tcp_flags ^ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) || #ifdef CONFIG_TLS_DEVICE tail->decrypted != skb->decrypted || #endif thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; __skb_pull(skb, hdrlen); shinfo = skb_shinfo(skb); gso_size = shinfo->gso_size ?: skb->len; gso_segs = shinfo->gso_segs ?: 1; shinfo = skb_shinfo(tail); tail_gso_size = shinfo->gso_size ?: (tail->len - hdrlen); tail_gso_segs = shinfo->gso_segs ?: 1; if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) { TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq; if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) { TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq; thtail->window = th->window; } /* We have to update both TCP_SKB_CB(tail)->tcp_flags and * thtail->fin, so that the fast path in tcp_rcv_established() * is not entered if we append a packet with a FIN. * SYN, RST, URG are not present. * ACK is set on both packets. * PSH : we do not really care in TCP stack, * at least for 'GRO' packets. */ thtail->fin |= th->fin; TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; if (TCP_SKB_CB(skb)->has_rxtstamp) { TCP_SKB_CB(tail)->has_rxtstamp = true; tail->tstamp = skb->tstamp; skb_hwtstamps(tail)->hwtstamp = skb_hwtstamps(skb)->hwtstamp; } /* Not as strict as GRO. We only need to carry mss max value */ shinfo->gso_size = max(gso_size, tail_gso_size); shinfo->gso_segs = min_t(u32, gso_segs + tail_gso_segs, 0xFFFF); sk->sk_backlog.len += delta; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGCOALESCE); kfree_skb_partial(skb, fragstolen); return false; } __skb_push(skb, hdrlen); no_coalesce: /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. * Few sockets backlog are possibly concurrently non empty. */ limit += 64*1024; if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); return true; } return false; } EXPORT_SYMBOL(tcp_add_backlog); int tcp_filter(struct sock *sk, struct sk_buff *skb) { struct tcphdr *th = (struct tcphdr *)skb->data; return sk_filter_trim_cap(sk, skb, th->doff * 4); } EXPORT_SYMBOL(tcp_filter); static void tcp_v4_restore_cb(struct sk_buff *skb) { memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4, sizeof(struct inet_skb_parm)); } static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, const struct tcphdr *th) { /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() * barrier() makes sure compiler wont play fool^Waliasing games. */ memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb), sizeof(struct inet_skb_parm)); barrier(); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff * 4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); TCP_SKB_CB(skb)->tcp_tw_isn = 0; TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; } /* * From tcp_input.c */ int tcp_v4_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct sk_buff *skb_to_free; int sdif = inet_sdif(skb); int dif = inet_iif(skb); const struct iphdr *iph; const struct tcphdr *th; bool refcounted; struct sock *sk; int ret; if (skb->pkt_type != PACKET_HOST) goto discard_it; /* Count it even if it's bad */ __TCP_INC_STATS(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; th = (const struct tcphdr *)skb->data; if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) goto bad_packet; if (!pskb_may_pull(skb, th->doff * 4)) goto discard_it; /* An explanation is required here, I think. * Packet length and doff are validated by header prediction, * provided case of th->doff==0 is eliminated. * So, we defer the checks. */ if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo)) goto csum_error; th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, th->dest, sdif, &refcounted); if (!sk) goto no_tcp_socket; process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { reqsk_put(req); goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } /* We own a reference on the listener, increase it again * as we might lose it too soon. */ sock_hold(sk); refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen); } if (!nsk) { reqsk_put(req); if (req_stolen) { /* Another cpu got exclusive access to req * and created a full blown socket. * Try to feed this packet to this socket * instead of discarding it. */ tcp_v4_restore_cb(skb); sock_put(sk); goto lookup; } goto discard_and_relse; } if (nsk == sk) { reqsk_put(req); tcp_v4_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); goto discard_and_relse; } else { sock_put(sk); return 0; } } if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto discard_and_relse; } if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif)) goto discard_and_relse; nf_reset_ct(skb); if (tcp_filter(sk, skb)) goto discard_and_relse; th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); skb->dev = NULL; if (sk->sk_state == TCP_LISTEN) { ret = tcp_v4_do_rcv(sk, skb); goto put_and_return; } sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { skb_to_free = sk->sk_rx_skb_cache; sk->sk_rx_skb_cache = NULL; ret = tcp_v4_do_rcv(sk, skb); } else { if (tcp_add_backlog(sk, skb)) goto discard_and_relse; skb_to_free = NULL; } bh_unlock_sock(sk); if (skb_to_free) __kfree_skb(skb_to_free); put_and_return: if (refcounted) sock_put(sk); return ret; no_tcp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; tcp_v4_fill_cb(skb, iph, th); if (tcp_checksum_complete(skb)) { csum_error: __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { tcp_v4_send_reset(NULL, skb); } discard_it: /* Discard frame. */ kfree_skb(skb); return 0; discard_and_relse: sk_drops_add(sk, skb); if (refcounted) sock_put(sk); goto discard_it; do_time_wait: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { inet_twsk_put(inet_twsk(sk)); goto discard_it; } tcp_v4_fill_cb(skb, iph, th); if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; } switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, skb, __tcp_hdrlen(th), iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb), sdif); if (sk2) { inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; tcp_v4_restore_cb(skb); refcounted = false; goto process; } } /* to ACK */ fallthrough; case TCP_TW_ACK: tcp_v4_timewait_ack(sk, skb); break; case TCP_TW_RST: tcp_v4_send_reset(sk, skb); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS:; } goto discard_it; } static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, }; void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } } EXPORT_SYMBOL(inet_sk_rx_dst_set); const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .addr2sockaddr = inet_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in), .mtu_reduced = tcp_v4_mtu_reduced, }; EXPORT_SYMBOL(ipv4_specific); #ifdef CONFIG_TCP_MD5SIG static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v4_parse_md5_keys, }; #endif /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int tcp_v4_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_init_sock(sk); icsk->icsk_af_ops = &ipv4_specific; #ifdef CONFIG_TCP_MD5SIG tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; #endif return 0; } void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); trace_tcp_destroy_sock(sk); tcp_clear_xmit_timers(sk); tcp_cleanup_congestion_control(sk); tcp_cleanup_ulp(sk); /* Cleanup up the write buffer. */ tcp_write_queue_purge(sk); /* Check if we want to disable active TFO */ tcp_fastopen_active_disable_ofo_check(sk); /* Cleans up our, hopefully empty, out_of_order_queue. */ skb_rbtree_purge(&tp->out_of_order_queue); #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ if (tp->md5sig_info) { tcp_clear_md5_list(sk); kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu); tp->md5sig_info = NULL; } #endif /* Clean up a referenced TCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); tcp_fastopen_destroy_cipher(sk); tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); #ifdef CONFIG_PROC_FS /* Proc filesystem TCP sock list dumping. */ /* * Get next listener socket follow cur. If cur is NULL, get first socket * starting from bucket given in st->bucket; when st->bucket is zero the * very first socket in the hash table is returned. */ static void *listening_get_next(struct seq_file *seq, void *cur) { struct tcp_seq_afinfo *afinfo; struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; struct hlist_nulls_node *node; struct sock *sk = cur; if (st->bpf_seq_afinfo) afinfo = st->bpf_seq_afinfo; else afinfo = PDE_DATA(file_inode(seq->file)); if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } ilb = &tcp_hashinfo.listening_hash[st->bucket]; ++st->num; ++st->offset; sk = sk_nulls_next(sk); get_sk: sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (afinfo->family == AF_UNSPEC || sk->sk_family == afinfo->family) return sk; } spin_unlock(&ilb->lock); st->offset = 0; if (++st->bucket < INET_LHTABLE_SIZE) goto get_head; return NULL; } static void *listening_get_idx(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc; st->bucket = 0; st->offset = 0; rc = listening_get_next(seq, NULL); while (rc && *pos) { rc = listening_get_next(seq, rc); --*pos; } return rc; } static inline bool empty_bucket(const struct tcp_iter_state *st) { return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain); } /* * Get first established socket starting from bucket given in st->bucket. * If st->bucket is zero, the very first socket in the hash is returned. */ static void *established_get_first(struct seq_file *seq) { struct tcp_seq_afinfo *afinfo; struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); void *rc = NULL; if (st->bpf_seq_afinfo) afinfo = st->bpf_seq_afinfo; else afinfo = PDE_DATA(file_inode(seq->file)); st->offset = 0; for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { struct sock *sk; struct hlist_nulls_node *node; spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket); /* Lockless fast path for the common case of empty buckets */ if (empty_bucket(st)) continue; spin_lock_bh(lock); sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { if ((afinfo->family != AF_UNSPEC && sk->sk_family != afinfo->family) || !net_eq(sock_net(sk), net)) { continue; } rc = sk; goto out; } spin_unlock_bh(lock); } out: return rc; } static void *established_get_next(struct seq_file *seq, void *cur) { struct tcp_seq_afinfo *afinfo; struct sock *sk = cur; struct hlist_nulls_node *node; struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); if (st->bpf_seq_afinfo) afinfo = st->bpf_seq_afinfo; else afinfo = PDE_DATA(file_inode(seq->file)); ++st->num; ++st->offset; sk = sk_nulls_next(sk); sk_nulls_for_each_from(sk, node) { if ((afinfo->family == AF_UNSPEC || sk->sk_family == afinfo->family) && net_eq(sock_net(sk), net)) return sk; } spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); ++st->bucket; return established_get_first(seq); } static void *established_get_idx(struct seq_file *seq, loff_t pos) { struct tcp_iter_state *st = seq->private; void *rc; st->bucket = 0; rc = established_get_first(seq); while (rc && pos) { rc = established_get_next(seq, rc); --pos; } return rc; } static void *tcp_get_idx(struct seq_file *seq, loff_t pos) { void *rc; struct tcp_iter_state *st = seq->private; st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_idx(seq, &pos); if (!rc) { st->state = TCP_SEQ_STATE_ESTABLISHED; rc = established_get_idx(seq, pos); } return rc; } static void *tcp_seek_last_pos(struct seq_file *seq) { struct tcp_iter_state *st = seq->private; int bucket = st->bucket; int offset = st->offset; int orig_num = st->num; void *rc = NULL; switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (st->bucket >= INET_LHTABLE_SIZE) break; st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_next(seq, NULL); while (offset-- && rc && bucket == st->bucket) rc = listening_get_next(seq, rc); if (rc) break; st->bucket = 0; st->state = TCP_SEQ_STATE_ESTABLISHED; fallthrough; case TCP_SEQ_STATE_ESTABLISHED: if (st->bucket > tcp_hashinfo.ehash_mask) break; rc = established_get_first(seq); while (offset-- && rc && bucket == st->bucket) rc = established_get_next(seq, rc); } st->num = orig_num; return rc; } void *tcp_seq_start(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc; if (*pos && *pos == st->last_pos) { rc = tcp_seek_last_pos(seq); if (rc) goto out; } st->state = TCP_SEQ_STATE_LISTENING; st->num = 0; st->bucket = 0; st->offset = 0; rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; out: st->last_pos = *pos; return rc; } EXPORT_SYMBOL(tcp_seq_start); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc = NULL; if (v == SEQ_START_TOKEN) { rc = tcp_get_idx(seq, 0); goto out; } switch (st->state) { case TCP_SEQ_STATE_LISTENING: rc = listening_get_next(seq, v); if (!rc) { st->state = TCP_SEQ_STATE_ESTABLISHED; st->bucket = 0; st->offset = 0; rc = established_get_first(seq); } break; case TCP_SEQ_STATE_ESTABLISHED: rc = established_get_next(seq, v); break; } out: ++*pos; st->last_pos = *pos; return rc; } EXPORT_SYMBOL(tcp_seq_next); void tcp_seq_stop(struct seq_file *seq, void *v) { struct tcp_iter_state *st = seq->private; switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) spin_unlock(&tcp_hashinfo.listening_hash[st->bucket].lock); break; case TCP_SEQ_STATE_ESTABLISHED: if (v) spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); break; } } EXPORT_SYMBOL(tcp_seq_stop); static void get_openreq4(const struct request_sock *req, struct seq_file *f, int i) { const struct inet_request_sock *ireq = inet_rsk(req); long delta = req->rsk_timer.expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK", i, ireq->ir_loc_addr, ireq->ir_num, ireq->ir_rmt_addr, ntohs(ireq->ir_rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_delta_to_clock_t(delta), req->num_timeout, from_kuid_munged(seq_user_ns(f), sock_i_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); } static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) { int timer_active; unsigned long timer_expires; const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); const struct inet_sock *inet = inet_sk(sk); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); int rx_queue; int state; if (icsk->icsk_pending == ICSK_TIME_RETRANS || icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = icsk->icsk_timeout; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; timer_expires = icsk->icsk_timeout; } else if (timer_pending(&sk->sk_timer)) { timer_active = 2; timer_expires = sk->sk_timer.expires; } else { timer_active = 0; timer_expires = jiffies; } state = inet_sk_state_load(sk); if (state == TCP_LISTEN) rx_queue = READ_ONCE(sk->sk_ack_backlog); else /* Because we don't lock the socket, * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)), icsk->icsk_probes_out, sock_i_ino(sk), refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sk), tp->snd_cwnd, state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)); } static void get_timewait4_sock(const struct inet_timewait_sock *tw, struct seq_file *f, int i) { long delta = tw->tw_timer.expires - jiffies; __be32 dest, src; __u16 destp, srcp; dest = tw->tw_daddr; src = tw->tw_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } #define TMPSZ 150 static int tcp4_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; struct sock *sk = v; seq_setwidth(seq, TMPSZ - 1); if (v == SEQ_START_TOKEN) { seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode"); goto out; } st = seq->private; if (sk->sk_state == TCP_TIME_WAIT) get_timewait4_sock(v, seq, st->num); else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq4(v, seq, st->num); else get_tcp4_sock(v, seq, st->num); out: seq_pad(seq, '\n'); return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__tcp { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct sock_common *, sk_common); uid_t uid __aligned(8); }; static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, struct sock_common *sk_common, uid_t uid) { struct bpf_iter__tcp ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.sk_common = sk_common; ctx.uid = uid; return bpf_iter_run_prog(prog, &ctx); } static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; uid_t uid; if (v == SEQ_START_TOKEN) return 0; if (sk->sk_state == TCP_TIME_WAIT) { uid = 0; } else if (sk->sk_state == TCP_NEW_SYN_RECV) { const struct request_sock *req = v; uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(req->rsk_listener)); } else { uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); } meta.seq = seq; prog = bpf_iter_get_info(&meta, false); return tcp_prog_seq_show(prog, &meta, v, uid); } static void bpf_iter_tcp_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)tcp_prog_seq_show(prog, &meta, v, 0); } tcp_seq_stop(seq, v); } static const struct seq_operations bpf_iter_tcp_seq_ops = { .show = bpf_iter_tcp_seq_show, .start = tcp_seq_start, .next = tcp_seq_next, .stop = bpf_iter_tcp_seq_stop, }; #endif static const struct seq_operations tcp4_seq_ops = { .show = tcp4_seq_show, .start = tcp_seq_start, .next = tcp_seq_next, .stop = tcp_seq_stop, }; static struct tcp_seq_afinfo tcp4_seq_afinfo = { .family = AF_INET, }; static int __net_init tcp4_proc_init_net(struct net *net) { if (!proc_create_net_data("tcp", 0444, net->proc_net, &tcp4_seq_ops, sizeof(struct tcp_iter_state), &tcp4_seq_afinfo)) return -ENOMEM; return 0; } static void __net_exit tcp4_proc_exit_net(struct net *net) { remove_proc_entry("tcp", net->proc_net); } static struct pernet_operations tcp4_net_ops = { .init = tcp4_proc_init_net, .exit = tcp4_proc_exit_net, }; int __init tcp4_proc_init(void) { return register_pernet_subsys(&tcp4_net_ops); } void tcp4_proc_exit(void) { unregister_pernet_subsys(&tcp4_net_ops); } #endif /* CONFIG_PROC_FS */ struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, .close = tcp_close, .pre_connect = tcp_v4_pre_connect, .connect = tcp_v4_connect, .disconnect = tcp_disconnect, .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v4_init_sock, .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp_timewait_sock_ops, .rsk_prot = &tcp_request_sock_ops, .h.hashinfo = &tcp_hashinfo, .no_autobind = true, .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { int cpu; if (net->ipv4.tcp_congestion_control) bpf_module_put(net->ipv4.tcp_congestion_control, net->ipv4.tcp_congestion_control->owner); for_each_possible_cpu(cpu) inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); free_percpu(net->ipv4.tcp_sk); } static int __net_init tcp_sk_init(struct net *net) { int res, cpu, cnt; net->ipv4.tcp_sk = alloc_percpu(struct sock *); if (!net->ipv4.tcp_sk) return -ENOMEM; for_each_possible_cpu(cpu) { struct sock *sk; res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, IPPROTO_TCP, net); if (res) goto fail; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); /* Please enforce IP_DF and IPID==0 for RST and * ACK sent in SYN-RECV and TIME-WAIT state. */ inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; } net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_ecn_fallback = 1; net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS; net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES; net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; net->ipv4.sysctl_tcp_syncookies = 1; net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; net->ipv4.sysctl_tcp_retries1 = TCP_RETR1; net->ipv4.sysctl_tcp_retries2 = TCP_RETR2; net->ipv4.sysctl_tcp_orphan_retries = 0; net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_tcp_tw_reuse = 2; net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; cnt = tcp_hashinfo.ehash_mask + 1; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; net->ipv4.sysctl_tcp_early_retrans = 3; net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION; net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior. */ net->ipv4.sysctl_tcp_retrans_collapse = 1; net->ipv4.sysctl_tcp_max_reordering = 300; net->ipv4.sysctl_tcp_dsack = 1; net->ipv4.sysctl_tcp_app_win = 31; net->ipv4.sysctl_tcp_adv_win_scale = 1; net->ipv4.sysctl_tcp_frto = 2; net->ipv4.sysctl_tcp_moderate_rcvbuf = 1; /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. */ net->ipv4.sysctl_tcp_tso_win_divisor = 3; /* Default TSQ limit of 16 TSO segments */ net->ipv4.sysctl_tcp_limit_output_bytes = 16 * 65536; /* rfc5961 challenge ack rate limiting */ net->ipv4.sysctl_tcp_challenge_ack_limit = 1000; net->ipv4.sysctl_tcp_min_tso_segs = 2; net->ipv4.sysctl_tcp_min_rtt_wlen = 300; net->ipv4.sysctl_tcp_autocorking = 1; net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2; net->ipv4.sysctl_tcp_pacing_ss_ratio = 200; net->ipv4.sysctl_tcp_pacing_ca_ratio = 120; if (net != &init_net) { memcpy(net->ipv4.sysctl_tcp_rmem, init_net.ipv4.sysctl_tcp_rmem, sizeof(init_net.ipv4.sysctl_tcp_rmem)); memcpy(net->ipv4.sysctl_tcp_wmem, init_net.ipv4.sysctl_tcp_wmem, sizeof(init_net.ipv4.sysctl_tcp_wmem)); } net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC; net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC; net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); /* Reno is always built in */ if (!net_eq(net, &init_net) && bpf_try_module_get(init_net.ipv4.tcp_congestion_control, init_net.ipv4.tcp_congestion_control->owner)) net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control; else net->ipv4.tcp_congestion_control = &tcp_reno; return 0; fail: tcp_sk_exit(net); return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; inet_twsk_purge(&tcp_hashinfo, AF_INET); list_for_each_entry(net, net_exit_list, exit_list) tcp_fastopen_ctx_destroy(net); } static struct pernet_operations __net_initdata tcp_sk_ops = { .init = tcp_sk_init, .exit = tcp_sk_exit, .exit_batch = tcp_sk_exit_batch, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(tcp, struct bpf_iter_meta *meta, struct sock_common *sk_common, uid_t uid) static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux) { struct tcp_iter_state *st = priv_data; struct tcp_seq_afinfo *afinfo; int ret; afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN); if (!afinfo) return -ENOMEM; afinfo->family = AF_UNSPEC; st->bpf_seq_afinfo = afinfo; ret = bpf_iter_init_seq_net(priv_data, aux); if (ret) kfree(afinfo); return ret; } static void bpf_iter_fini_tcp(void *priv_data) { struct tcp_iter_state *st = priv_data; kfree(st->bpf_seq_afinfo); bpf_iter_fini_seq_net(priv_data); } static const struct bpf_iter_seq_info tcp_seq_info = { .seq_ops = &bpf_iter_tcp_seq_ops, .init_seq_private = bpf_iter_init_tcp, .fini_seq_private = bpf_iter_fini_tcp, .seq_priv_size = sizeof(struct tcp_iter_state), }; static struct bpf_iter_reg tcp_reg_info = { .target = "tcp", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__tcp, sk_common), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &tcp_seq_info, }; static void __init bpf_iter_register(void) { tcp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON]; if (bpf_iter_reg_target(&tcp_reg_info)) pr_warn("Warning: could not register bpf iterator tcp\n"); } #endif void __init tcp_v4_init(void) { if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_register(); #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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SMP_H #define _ASM_X86_SMP_H #ifndef __ASSEMBLY__ #include <linux/cpumask.h> #include <asm/percpu.h> #include <asm/thread_info.h> #include <asm/cpumask.h> extern int smp_num_siblings; extern unsigned int num_processors; DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); /* cpus sharing the last level cache: */ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); static inline struct cpumask *cpu_llc_shared_mask(int cpu) { return per_cpu(cpu_llc_shared_map, cpu); } DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid); #endif struct task_struct; struct smp_ops { void (*smp_prepare_boot_cpu)(void); void (*smp_prepare_cpus)(unsigned max_cpus); void (*smp_cpus_done)(unsigned max_cpus); void (*stop_other_cpus)(int wait); void (*crash_stop_other_cpus)(void); void (*smp_send_reschedule)(int cpu); int (*cpu_up)(unsigned cpu, struct task_struct *tidle); int (*cpu_disable)(void); void (*cpu_die)(unsigned int cpu); void (*play_dead)(void); void (*send_call_func_ipi)(const struct cpumask *mask); void (*send_call_func_single_ipi)(int cpu); }; /* Globals due to paravirt */ extern void set_cpu_sibling_map(int cpu); #ifdef CONFIG_SMP extern struct smp_ops smp_ops; static inline void smp_send_stop(void) { smp_ops.stop_other_cpus(0); } static inline void stop_other_cpus(void) { smp_ops.stop_other_cpus(1); } static inline void smp_prepare_boot_cpu(void) { smp_ops.smp_prepare_boot_cpu(); } static inline void smp_prepare_cpus(unsigned int max_cpus) { smp_ops.smp_prepare_cpus(max_cpus); } static inline void smp_cpus_done(unsigned int max_cpus) { smp_ops.smp_cpus_done(max_cpus); } static inline int __cpu_up(unsigned int cpu, struct task_struct *tidle) { return smp_ops.cpu_up(cpu, tidle); } static inline int __cpu_disable(void) { return smp_ops.cpu_disable(); } static inline void __cpu_die(unsigned int cpu) { smp_ops.cpu_die(cpu); } static inline void play_dead(void) { smp_ops.play_dead(); } static inline void smp_send_reschedule(int cpu) { smp_ops.smp_send_reschedule(cpu); } static inline void arch_send_call_function_single_ipi(int cpu) { smp_ops.send_call_func_single_ipi(cpu); } static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) { smp_ops.send_call_func_ipi(mask); } void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); int common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_disable(void); int common_cpu_die(unsigned int cpu); void native_cpu_die(unsigned int cpu); void hlt_play_dead(void); void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); void cond_wakeup_cpu0(void); void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); void smp_store_boot_cpu_info(void); void smp_store_cpu_info(int id); asmlinkage __visible void smp_reboot_interrupt(void); __visible void smp_reschedule_interrupt(struct pt_regs *regs); __visible void smp_call_function_interrupt(struct pt_regs *regs); __visible void smp_call_function_single_interrupt(struct pt_regs *r); #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) #define cpu_acpi_id(cpu) per_cpu(x86_cpu_to_acpiid, cpu) /* * This function is needed by all SMP systems. It must _always_ be valid * from the initial startup. We map APIC_BASE very early in page_setup(), * so this is correct in the x86 case. */ #define raw_smp_processor_id() this_cpu_read(cpu_number) #define __smp_processor_id() __this_cpu_read(cpu_number) #ifdef CONFIG_X86_32 extern int safe_smp_processor_id(void); #else # define safe_smp_processor_id() smp_processor_id() #endif #else /* !CONFIG_SMP */ #define wbinvd_on_cpu(cpu) wbinvd() static inline int wbinvd_on_all_cpus(void) { wbinvd(); return 0; } #endif /* CONFIG_SMP */ extern unsigned disabled_cpus; #ifdef CONFIG_X86_LOCAL_APIC extern int hard_smp_processor_id(void); #else /* CONFIG_X86_LOCAL_APIC */ #define hard_smp_processor_id() 0 #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_DEBUG_NMI_SELFTEST extern void nmi_selftest(void); #else #define nmi_selftest() do { } while (0) #endif #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMP_H */
17 17 17 17 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 // SPDX-License-Identifier: GPL-2.0-or-later /* -*- linux-c -*- --------------------------------------------------------- * * * linux/fs/devpts/inode.c * * Copyright 1998-2004 H. Peter Anvin -- All Rights Reserved * * ------------------------------------------------------------------------- */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/namei.h> #include <linux/slab.h> #include <linux/mount.h> #include <linux/tty.h> #include <linux/mutex.h> #include <linux/magic.h> #include <linux/idr.h> #include <linux/devpts_fs.h> #include <linux/parser.h> #include <linux/fsnotify.h> #include <linux/seq_file.h> #define DEVPTS_DEFAULT_MODE 0600 /* * ptmx is a new node in /dev/pts and will be unused in legacy (single- * instance) mode. To prevent surprises in user space, set permissions of * ptmx to 0. Use 'chmod' or remount with '-o ptmxmode' to set meaningful * permissions. */ #define DEVPTS_DEFAULT_PTMX_MODE 0000 #define PTMX_MINOR 2 /* * sysctl support for setting limits on the number of Unix98 ptys allocated. * Otherwise one can eat up all kernel memory by opening /dev/ptmx repeatedly. */ static int pty_limit = NR_UNIX98_PTY_DEFAULT; static int pty_reserve = NR_UNIX98_PTY_RESERVE; static int pty_limit_min; static int pty_limit_max = INT_MAX; static atomic_t pty_count = ATOMIC_INIT(0); static struct ctl_table pty_table[] = { { .procname = "max", .maxlen = sizeof(int), .mode = 0644, .data = &pty_limit, .proc_handler = proc_dointvec_minmax, .extra1 = &pty_limit_min, .extra2 = &pty_limit_max, }, { .procname = "reserve", .maxlen = sizeof(int), .mode = 0644, .data = &pty_reserve, .proc_handler = proc_dointvec_minmax, .extra1 = &pty_limit_min, .extra2 = &pty_limit_max, }, { .procname = "nr", .maxlen = sizeof(int), .mode = 0444, .data = &pty_count, .proc_handler = proc_dointvec, }, {} }; static struct ctl_table pty_kern_table[] = { { .procname = "pty", .mode = 0555, .child = pty_table, }, {} }; static struct ctl_table pty_root_table[] = { { .procname = "kernel", .mode = 0555, .child = pty_kern_table, }, {} }; struct pts_mount_opts { int setuid; int setgid; kuid_t uid; kgid_t gid; umode_t mode; umode_t ptmxmode; int reserve; int max; }; enum { Opt_uid, Opt_gid, Opt_mode, Opt_ptmxmode, Opt_newinstance, Opt_max, Opt_err }; static const match_table_t tokens = { {Opt_uid, "uid=%u"}, {Opt_gid, "gid=%u"}, {Opt_mode, "mode=%o"}, {Opt_ptmxmode, "ptmxmode=%o"}, {Opt_newinstance, "newinstance"}, {Opt_max, "max=%d"}, {Opt_err, NULL} }; struct pts_fs_info { struct ida allocated_ptys; struct pts_mount_opts mount_opts; struct super_block *sb; struct dentry *ptmx_dentry; }; static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb) { return sb->s_fs_info; } static int devpts_ptmx_path(struct path *path) { struct super_block *sb; int err; /* Is a devpts filesystem at "pts" in the same directory? */ err = path_pts(path); if (err) return err; /* Is the path the root of a devpts filesystem? */ sb = path->mnt->mnt_sb; if ((sb->s_magic != DEVPTS_SUPER_MAGIC) || (path->mnt->mnt_root != sb->s_root)) return -ENODEV; return 0; } /* * Try to find a suitable devpts filesystem. We support the following * scenarios: * - The ptmx device node is located in the same directory as the devpts * mount where the pts device nodes are located. * This is e.g. the case when calling open on the /dev/pts/ptmx device * node when the devpts filesystem is mounted at /dev/pts. * - The ptmx device node is located outside the devpts filesystem mount * where the pts device nodes are located. For example, the ptmx device * is a symlink, separate device node, or bind-mount. * A supported scenario is bind-mounting /dev/pts/ptmx to /dev/ptmx and * then calling open on /dev/ptmx. In this case a suitable pts * subdirectory can be found in the common parent directory /dev of the * devpts mount and the ptmx bind-mount, after resolving the /dev/ptmx * bind-mount. * If no suitable pts subdirectory can be found this function will fail. * This is e.g. the case when bind-mounting /dev/pts/ptmx to /ptmx. */ struct vfsmount *devpts_mntget(struct file *filp, struct pts_fs_info *fsi) { struct path path; int err = 0; path = filp->f_path; path_get(&path); /* Walk upward while the start point is a bind mount of * a single file. */ while (path.mnt->mnt_root == path.dentry) if (follow_up(&path) == 0) break; /* devpts_ptmx_path() finds a devpts fs or returns an error. */ if ((path.mnt->mnt_sb->s_magic != DEVPTS_SUPER_MAGIC) || (DEVPTS_SB(path.mnt->mnt_sb) != fsi)) err = devpts_ptmx_path(&path); dput(path.dentry); if (!err) { if (DEVPTS_SB(path.mnt->mnt_sb) == fsi) return path.mnt; err = -ENODEV; } mntput(path.mnt); return ERR_PTR(err); } struct pts_fs_info *devpts_acquire(struct file *filp) { struct pts_fs_info *result; struct path path; struct super_block *sb; path = filp->f_path; path_get(&path); /* Has the devpts filesystem already been found? */ if (path.mnt->mnt_sb->s_magic != DEVPTS_SUPER_MAGIC) { int err; err = devpts_ptmx_path(&path); if (err) { result = ERR_PTR(err); goto out; } } /* * pty code needs to hold extra references in case of last /dev/tty close */ sb = path.mnt->mnt_sb; atomic_inc(&sb->s_active); result = DEVPTS_SB(sb); out: path_put(&path); return result; } void devpts_release(struct pts_fs_info *fsi) { deactivate_super(fsi->sb); } #define PARSE_MOUNT 0 #define PARSE_REMOUNT 1 /* * parse_mount_options(): * Set @opts to mount options specified in @data. If an option is not * specified in @data, set it to its default value. * * Note: @data may be NULL (in which case all options are set to default). */ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) { char *p; kuid_t uid; kgid_t gid; opts->setuid = 0; opts->setgid = 0; opts->uid = GLOBAL_ROOT_UID; opts->gid = GLOBAL_ROOT_GID; opts->mode = DEVPTS_DEFAULT_MODE; opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE; opts->max = NR_UNIX98_PTY_MAX; /* Only allow instances mounted from the initial mount * namespace to tap the reserve pool of ptys. */ if (op == PARSE_MOUNT) opts->reserve = (current->nsproxy->mnt_ns == init_task.nsproxy->mnt_ns); while ((p = strsep(&data, ",")) != NULL) { substring_t args[MAX_OPT_ARGS]; int token; int option; if (!*p) continue; token = match_token(p, tokens, args); switch (token) { case Opt_uid: if (match_int(&args[0], &option)) return -EINVAL; uid = make_kuid(current_user_ns(), option); if (!uid_valid(uid)) return -EINVAL; opts->uid = uid; opts->setuid = 1; break; case Opt_gid: if (match_int(&args[0], &option)) return -EINVAL; gid = make_kgid(current_user_ns(), option); if (!gid_valid(gid)) return -EINVAL; opts->gid = gid; opts->setgid = 1; break; case Opt_mode: if (match_octal(&args[0], &option)) return -EINVAL; opts->mode = option & S_IALLUGO; break; case Opt_ptmxmode: if (match_octal(&args[0], &option)) return -EINVAL; opts->ptmxmode = option & S_IALLUGO; break; case Opt_newinstance: break; case Opt_max: if (match_int(&args[0], &option) || option < 0 || option > NR_UNIX98_PTY_MAX) return -EINVAL; opts->max = option; break; default: pr_err("called with bogus options\n"); return -EINVAL; } } return 0; } static int mknod_ptmx(struct super_block *sb) { int mode; int rc = -ENOMEM; struct dentry *dentry; struct inode *inode; struct dentry *root = sb->s_root; struct pts_fs_info *fsi = DEVPTS_SB(sb); struct pts_mount_opts *opts = &fsi->mount_opts; kuid_t ptmx_uid = current_fsuid(); kgid_t ptmx_gid = current_fsgid(); inode_lock(d_inode(root)); /* If we have already created ptmx node, return */ if (fsi->ptmx_dentry) { rc = 0; goto out; } dentry = d_alloc_name(root, "ptmx"); if (!dentry) { pr_err("Unable to alloc dentry for ptmx node\n"); goto out; } /* * Create a new 'ptmx' node in this mount of devpts. */ inode = new_inode(sb); if (!inode) { pr_err("Unable to alloc inode for ptmx node\n"); dput(dentry); goto out; } inode->i_ino = 2; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); mode = S_IFCHR|opts->ptmxmode; init_special_inode(inode, mode, MKDEV(TTYAUX_MAJOR, 2)); inode->i_uid = ptmx_uid; inode->i_gid = ptmx_gid; d_add(dentry, inode); fsi->ptmx_dentry = dentry; rc = 0; out: inode_unlock(d_inode(root)); return rc; } static void update_ptmx_mode(struct pts_fs_info *fsi) { struct inode *inode; if (fsi->ptmx_dentry) { inode = d_inode(fsi->ptmx_dentry); inode->i_mode = S_IFCHR|fsi->mount_opts.ptmxmode; } } static int devpts_remount(struct super_block *sb, int *flags, char *data) { int err; struct pts_fs_info *fsi = DEVPTS_SB(sb); struct pts_mount_opts *opts = &fsi->mount_opts; err = parse_mount_options(data, PARSE_REMOUNT, opts); /* * parse_mount_options() restores options to default values * before parsing and may have changed ptmxmode. So, update the * mode in the inode too. Bogus options don't fail the remount, * so do this even on error return. */ update_ptmx_mode(fsi); return err; } static int devpts_show_options(struct seq_file *seq, struct dentry *root) { struct pts_fs_info *fsi = DEVPTS_SB(root->d_sb); struct pts_mount_opts *opts = &fsi->mount_opts; if (opts->setuid) seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, opts->uid)); if (opts->setgid) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, opts->gid)); seq_printf(seq, ",mode=%03o", opts->mode); seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode); if (opts->max < NR_UNIX98_PTY_MAX) seq_printf(seq, ",max=%d", opts->max); return 0; } static const struct super_operations devpts_sops = { .statfs = simple_statfs, .remount_fs = devpts_remount, .show_options = devpts_show_options, }; static void *new_pts_fs_info(struct super_block *sb) { struct pts_fs_info *fsi; fsi = kzalloc(sizeof(struct pts_fs_info), GFP_KERNEL); if (!fsi) return NULL; ida_init(&fsi->allocated_ptys); fsi->mount_opts.mode = DEVPTS_DEFAULT_MODE; fsi->mount_opts.ptmxmode = DEVPTS_DEFAULT_PTMX_MODE; fsi->sb = sb; return fsi; } static int devpts_fill_super(struct super_block *s, void *data, int silent) { struct inode *inode; int error; s->s_iflags &= ~SB_I_NODEV; s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = DEVPTS_SUPER_MAGIC; s->s_op = &devpts_sops; s->s_d_op = &simple_dentry_operations; s->s_time_gran = 1; error = -ENOMEM; s->s_fs_info = new_pts_fs_info(s); if (!s->s_fs_info) goto fail; error = parse_mount_options(data, PARSE_MOUNT, &DEVPTS_SB(s)->mount_opts); if (error) goto fail; error = -ENOMEM; inode = new_inode(s); if (!inode) goto fail; inode->i_ino = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); s->s_root = d_make_root(inode); if (!s->s_root) { pr_err("get root dentry failed\n"); goto fail; } error = mknod_ptmx(s); if (error) goto fail_dput; return 0; fail_dput: dput(s->s_root); s->s_root = NULL; fail: return error; } /* * devpts_mount() * * Mount a new (private) instance of devpts. PTYs created in this * instance are independent of the PTYs in other devpts instances. */ static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { return mount_nodev(fs_type, flags, data, devpts_fill_super); } static void devpts_kill_sb(struct super_block *sb) { struct pts_fs_info *fsi = DEVPTS_SB(sb); if (fsi) ida_destroy(&fsi->allocated_ptys); kfree(fsi); kill_litter_super(sb); } static struct file_system_type devpts_fs_type = { .name = "devpts", .mount = devpts_mount, .kill_sb = devpts_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; /* * The normal naming convention is simply /dev/pts/<number>; this conforms * to the System V naming convention */ int devpts_new_index(struct pts_fs_info *fsi) { int index = -ENOSPC; if (atomic_inc_return(&pty_count) >= (pty_limit - (fsi->mount_opts.reserve ? 0 : pty_reserve))) goto out; index = ida_alloc_max(&fsi->allocated_ptys, fsi->mount_opts.max - 1, GFP_KERNEL); out: if (index < 0) atomic_dec(&pty_count); return index; } void devpts_kill_index(struct pts_fs_info *fsi, int idx) { ida_free(&fsi->allocated_ptys, idx); atomic_dec(&pty_count); } /** * devpts_pty_new -- create a new inode in /dev/pts/ * @ptmx_inode: inode of the master * @device: major+minor of the node to be created * @index: used as a name of the node * @priv: what's given back by devpts_get_priv * * The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill. */ struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv) { struct dentry *dentry; struct super_block *sb = fsi->sb; struct inode *inode; struct dentry *root; struct pts_mount_opts *opts; char s[12]; root = sb->s_root; opts = &fsi->mount_opts; inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); inode->i_ino = index + 3; inode->i_uid = opts->setuid ? opts->uid : current_fsuid(); inode->i_gid = opts->setgid ? opts->gid : current_fsgid(); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); init_special_inode(inode, S_IFCHR|opts->mode, MKDEV(UNIX98_PTY_SLAVE_MAJOR, index)); sprintf(s, "%d", index); dentry = d_alloc_name(root, s); if (dentry) { dentry->d_fsdata = priv; d_add(dentry, inode); fsnotify_create(d_inode(root), dentry); } else { iput(inode); dentry = ERR_PTR(-ENOMEM); } return dentry; } /** * devpts_get_priv -- get private data for a slave * @pts_inode: inode of the slave * * Returns whatever was passed as priv in devpts_pty_new for a given inode. */ void *devpts_get_priv(struct dentry *dentry) { if (dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC) return NULL; return dentry->d_fsdata; } /** * devpts_pty_kill -- remove inode form /dev/pts/ * @inode: inode of the slave to be removed * * This is an inverse operation of devpts_pty_new. */ void devpts_pty_kill(struct dentry *dentry) { WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC); dentry->d_fsdata = NULL; drop_nlink(dentry->d_inode); fsnotify_unlink(d_inode(dentry->d_parent), dentry); d_drop(dentry); dput(dentry); /* d_alloc_name() in devpts_pty_new() */ } static int __init init_devpts_fs(void) { int err = register_filesystem(&devpts_fs_type); if (!err) { register_sysctl_table(pty_root_table); } return err; } module_init(init_devpts_fs)
2 2 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/dd.c - The core device/driver interactions. * * This file contains the (sometimes tricky) code that controls the * interactions between devices and drivers, which primarily includes * driver binding and unbinding. * * All of this code used to exist in drivers/base/bus.c, but was * relocated to here in the name of compartmentalization (since it wasn't * strictly code just for the 'struct bus_type'. * * Copyright (c) 2002-5 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2007-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2007-2009 Novell Inc. */ #include <linux/debugfs.h> #include <linux/device.h> #include <linux/delay.h> #include <linux/dma-map-ops.h> #include <linux/init.h> #include <linux/module.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/async.h> #include <linux/pm_runtime.h> #include <linux/pinctrl/devinfo.h> #include <linux/slab.h> #include "base.h" #include "power/power.h" /* * Deferred Probe infrastructure. * * Sometimes driver probe order matters, but the kernel doesn't always have * dependency information which means some drivers will get probed before a * resource it depends on is available. For example, an SDHCI driver may * first need a GPIO line from an i2c GPIO controller before it can be * initialized. If a required resource is not available yet, a driver can * request probing to be deferred by returning -EPROBE_DEFER from its probe hook * * Deferred probe maintains two lists of devices, a pending list and an active * list. A driver returning -EPROBE_DEFER causes the device to be added to the * pending list. A successful driver probe will trigger moving all devices * from the pending to the active list so that the workqueue will eventually * retry them. * * The deferred_probe_mutex must be held any time the deferred_probe_*_list * of the (struct device*)->p->deferred_probe pointers are manipulated */ static DEFINE_MUTEX(deferred_probe_mutex); static LIST_HEAD(deferred_probe_pending_list); static LIST_HEAD(deferred_probe_active_list); static atomic_t deferred_trigger_count = ATOMIC_INIT(0); static struct dentry *deferred_devices; static bool initcalls_done; /* Save the async probe drivers' name from kernel cmdline */ #define ASYNC_DRV_NAMES_MAX_LEN 256 static char async_probe_drv_names[ASYNC_DRV_NAMES_MAX_LEN]; /* * In some cases, like suspend to RAM or hibernation, It might be reasonable * to prohibit probing of devices as it could be unsafe. * Once defer_all_probes is true all drivers probes will be forcibly deferred. */ static bool defer_all_probes; /* * deferred_probe_work_func() - Retry probing devices in the active list. */ static void deferred_probe_work_func(struct work_struct *work) { struct device *dev; struct device_private *private; /* * This block processes every device in the deferred 'active' list. * Each device is removed from the active list and passed to * bus_probe_device() to re-attempt the probe. The loop continues * until every device in the active list is removed and retried. * * Note: Once the device is removed from the list and the mutex is * released, it is possible for the device get freed by another thread * and cause a illegal pointer dereference. This code uses * get/put_device() to ensure the device structure cannot disappear * from under our feet. */ mutex_lock(&deferred_probe_mutex); while (!list_empty(&deferred_probe_active_list)) { private = list_first_entry(&deferred_probe_active_list, typeof(*dev->p), deferred_probe); dev = private->device; list_del_init(&private->deferred_probe); get_device(dev); kfree(dev->p->deferred_probe_reason); dev->p->deferred_probe_reason = NULL; /* * Drop the mutex while probing each device; the probe path may * manipulate the deferred list */ mutex_unlock(&deferred_probe_mutex); /* * Force the device to the end of the dpm_list since * the PM code assumes that the order we add things to * the list is a good order for suspend but deferred * probe makes that very unsafe. */ device_pm_move_to_tail(dev); dev_dbg(dev, "Retrying from deferred list\n"); bus_probe_device(dev); mutex_lock(&deferred_probe_mutex); put_device(dev); } mutex_unlock(&deferred_probe_mutex); } static DECLARE_WORK(deferred_probe_work, deferred_probe_work_func); void driver_deferred_probe_add(struct device *dev) { mutex_lock(&deferred_probe_mutex); if (list_empty(&dev->p->deferred_probe)) { dev_dbg(dev, "Added to deferred list\n"); list_add_tail(&dev->p->deferred_probe, &deferred_probe_pending_list); } mutex_unlock(&deferred_probe_mutex); } void driver_deferred_probe_del(struct device *dev) { mutex_lock(&deferred_probe_mutex); if (!list_empty(&dev->p->deferred_probe)) { dev_dbg(dev, "Removed from deferred list\n"); list_del_init(&dev->p->deferred_probe); kfree(dev->p->deferred_probe_reason); dev->p->deferred_probe_reason = NULL; } mutex_unlock(&deferred_probe_mutex); } static bool driver_deferred_probe_enable = false; /** * driver_deferred_probe_trigger() - Kick off re-probing deferred devices * * This functions moves all devices from the pending list to the active * list and schedules the deferred probe workqueue to process them. It * should be called anytime a driver is successfully bound to a device. * * Note, there is a race condition in multi-threaded probe. In the case where * more than one device is probing at the same time, it is possible for one * probe to complete successfully while another is about to defer. If the second * depends on the first, then it will get put on the pending list after the * trigger event has already occurred and will be stuck there. * * The atomic 'deferred_trigger_count' is used to determine if a successful * trigger has occurred in the midst of probing a driver. If the trigger count * changes in the midst of a probe, then deferred processing should be triggered * again. */ static void driver_deferred_probe_trigger(void) { if (!driver_deferred_probe_enable) return; /* * A successful probe means that all the devices in the pending list * should be triggered to be reprobed. Move all the deferred devices * into the active list so they can be retried by the workqueue */ mutex_lock(&deferred_probe_mutex); atomic_inc(&deferred_trigger_count); list_splice_tail_init(&deferred_probe_pending_list, &deferred_probe_active_list); mutex_unlock(&deferred_probe_mutex); /* * Kick the re-probe thread. It may already be scheduled, but it is * safe to kick it again. */ schedule_work(&deferred_probe_work); } /** * device_block_probing() - Block/defer device's probes * * It will disable probing of devices and defer their probes instead. */ void device_block_probing(void) { defer_all_probes = true; /* sync with probes to avoid races. */ wait_for_device_probe(); } /** * device_unblock_probing() - Unblock/enable device's probes * * It will restore normal behavior and trigger re-probing of deferred * devices. */ void device_unblock_probing(void) { defer_all_probes = false; driver_deferred_probe_trigger(); } /** * device_set_deferred_probe_reason() - Set defer probe reason message for device * @dev: the pointer to the struct device * @vaf: the pointer to va_format structure with message */ void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf) { const char *drv = dev_driver_string(dev); mutex_lock(&deferred_probe_mutex); kfree(dev->p->deferred_probe_reason); dev->p->deferred_probe_reason = kasprintf(GFP_KERNEL, "%s: %pV", drv, vaf); mutex_unlock(&deferred_probe_mutex); } /* * deferred_devs_show() - Show the devices in the deferred probe pending list. */ static int deferred_devs_show(struct seq_file *s, void *data) { struct device_private *curr; mutex_lock(&deferred_probe_mutex); list_for_each_entry(curr, &deferred_probe_pending_list, deferred_probe) seq_printf(s, "%s\t%s", dev_name(curr->device), curr->device->p->deferred_probe_reason ?: "\n"); mutex_unlock(&deferred_probe_mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(deferred_devs); int driver_deferred_probe_timeout; EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout); static DECLARE_WAIT_QUEUE_HEAD(probe_timeout_waitqueue); static int __init deferred_probe_timeout_setup(char *str) { int timeout; if (!kstrtoint(str, 10, &timeout)) driver_deferred_probe_timeout = timeout; return 1; } __setup("deferred_probe_timeout=", deferred_probe_timeout_setup); /** * driver_deferred_probe_check_state() - Check deferred probe state * @dev: device to check * * Return: * -ENODEV if initcalls have completed and modules are disabled. * -ETIMEDOUT if the deferred probe timeout was set and has expired * and modules are enabled. * -EPROBE_DEFER in other cases. * * Drivers or subsystems can opt-in to calling this function instead of directly * returning -EPROBE_DEFER. */ int driver_deferred_probe_check_state(struct device *dev) { if (!IS_ENABLED(CONFIG_MODULES) && initcalls_done) { dev_warn(dev, "ignoring dependency for device, assuming no driver\n"); return -ENODEV; } if (!driver_deferred_probe_timeout && initcalls_done) { dev_warn(dev, "deferred probe timeout, ignoring dependency\n"); return -ETIMEDOUT; } return -EPROBE_DEFER; } static void deferred_probe_timeout_work_func(struct work_struct *work) { struct device_private *p; driver_deferred_probe_timeout = 0; driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); mutex_lock(&deferred_probe_mutex); list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe) dev_info(p->device, "deferred probe pending\n"); mutex_unlock(&deferred_probe_mutex); wake_up_all(&probe_timeout_waitqueue); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); /** * deferred_probe_initcall() - Enable probing of deferred devices * * We don't want to get in the way when the bulk of drivers are getting probed. * Instead, this initcall makes sure that deferred probing is delayed until * late_initcall time. */ static int deferred_probe_initcall(void) { deferred_devices = debugfs_create_file("devices_deferred", 0444, NULL, NULL, &deferred_devs_fops); driver_deferred_probe_enable = true; driver_deferred_probe_trigger(); /* Sort as many dependencies as possible before exiting initcalls */ flush_work(&deferred_probe_work); initcalls_done = true; /* * Trigger deferred probe again, this time we won't defer anything * that is optional */ driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); if (driver_deferred_probe_timeout > 0) { schedule_delayed_work(&deferred_probe_timeout_work, driver_deferred_probe_timeout * HZ); } return 0; } late_initcall(deferred_probe_initcall); static void __exit deferred_probe_exit(void) { debugfs_remove_recursive(deferred_devices); } __exitcall(deferred_probe_exit); /** * device_is_bound() - Check if device is bound to a driver * @dev: device to check * * Returns true if passed device has already finished probing successfully * against a driver. * * This function must be called with the device lock held. */ bool device_is_bound(struct device *dev) { return dev->p && klist_node_attached(&dev->p->knode_driver); } static void driver_bound(struct device *dev) { if (device_is_bound(dev)) { pr_warn("%s: device %s already bound\n", __func__, kobject_name(&dev->kobj)); return; } pr_debug("driver: '%s': %s: bound to device '%s'\n", dev->driver->name, __func__, dev_name(dev)); klist_add_tail(&dev->p->knode_driver, &dev->driver->p->klist_devices); device_links_driver_bound(dev); device_pm_check_callbacks(dev); /* * Make sure the device is no longer in one of the deferred lists and * kick off retrying all pending devices */ driver_deferred_probe_del(dev); driver_deferred_probe_trigger(); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_BOUND_DRIVER, dev); kobject_uevent(&dev->kobj, KOBJ_BIND); } static ssize_t coredump_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { device_lock(dev); dev->driver->coredump(dev); device_unlock(dev); return count; } static DEVICE_ATTR_WO(coredump); static int driver_sysfs_add(struct device *dev) { int ret; if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_BIND_DRIVER, dev); ret = sysfs_create_link(&dev->driver->p->kobj, &dev->kobj, kobject_name(&dev->kobj)); if (ret) goto fail; ret = sysfs_create_link(&dev->kobj, &dev->driver->p->kobj, "driver"); if (ret) goto rm_dev; if (!IS_ENABLED(CONFIG_DEV_COREDUMP) || !dev->driver->coredump || !device_create_file(dev, &dev_attr_coredump)) return 0; sysfs_remove_link(&dev->kobj, "driver"); rm_dev: sysfs_remove_link(&dev->driver->p->kobj, kobject_name(&dev->kobj)); fail: return ret; } static void driver_sysfs_remove(struct device *dev) { struct device_driver *drv = dev->driver; if (drv) { if (drv->coredump) device_remove_file(dev, &dev_attr_coredump); sysfs_remove_link(&drv->p->kobj, kobject_name(&dev->kobj)); sysfs_remove_link(&dev->kobj, "driver"); } } /** * device_bind_driver - bind a driver to one device. * @dev: device. * * Allow manual attachment of a driver to a device. * Caller must have already set @dev->driver. * * Note that this does not modify the bus reference count. * Please verify that is accounted for before calling this. * (It is ok to call with no other effort from a driver's probe() method.) * * This function must be called with the device lock held. */ int device_bind_driver(struct device *dev) { int ret; ret = driver_sysfs_add(dev); if (!ret) driver_bound(dev); else if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); return ret; } EXPORT_SYMBOL_GPL(device_bind_driver); static atomic_t probe_count = ATOMIC_INIT(0); static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue); static void driver_deferred_probe_add_trigger(struct device *dev, int local_trigger_count) { driver_deferred_probe_add(dev); /* Did a trigger occur while probing? Need to re-trigger if yes */ if (local_trigger_count != atomic_read(&deferred_trigger_count)) driver_deferred_probe_trigger(); } static ssize_t state_synced_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); val = dev->state_synced; device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static DEVICE_ATTR_RO(state_synced); static int really_probe(struct device *dev, struct device_driver *drv) { int ret = -EPROBE_DEFER; int local_trigger_count = atomic_read(&deferred_trigger_count); bool test_remove = IS_ENABLED(CONFIG_DEBUG_TEST_DRIVER_REMOVE) && !drv->suppress_bind_attrs; if (defer_all_probes) { /* * Value of defer_all_probes can be set only by * device_block_probing() which, in turn, will call * wait_for_device_probe() right after that to avoid any races. */ dev_dbg(dev, "Driver %s force probe deferral\n", drv->name); driver_deferred_probe_add(dev); return ret; } ret = device_links_check_suppliers(dev); if (ret == -EPROBE_DEFER) driver_deferred_probe_add_trigger(dev, local_trigger_count); if (ret) return ret; atomic_inc(&probe_count); pr_debug("bus: '%s': %s: probing driver %s with device %s\n", drv->bus->name, __func__, drv->name, dev_name(dev)); if (!list_empty(&dev->devres_head)) { dev_crit(dev, "Resources present before probing\n"); ret = -EBUSY; goto done; } re_probe: dev->driver = drv; /* If using pinctrl, bind pins now before probing */ ret = pinctrl_bind_pins(dev); if (ret) goto pinctrl_bind_failed; if (dev->bus->dma_configure) { ret = dev->bus->dma_configure(dev); if (ret) goto probe_failed; } ret = driver_sysfs_add(dev); if (ret) { pr_err("%s: driver_sysfs_add(%s) failed\n", __func__, dev_name(dev)); goto probe_failed; } if (dev->pm_domain && dev->pm_domain->activate) { ret = dev->pm_domain->activate(dev); if (ret) goto probe_failed; } if (dev->bus->probe) { ret = dev->bus->probe(dev); if (ret) goto probe_failed; } else if (drv->probe) { ret = drv->probe(dev); if (ret) goto probe_failed; } ret = device_add_groups(dev, drv->dev_groups); if (ret) { dev_err(dev, "device_add_groups() failed\n"); goto dev_groups_failed; } if (dev_has_sync_state(dev)) { ret = device_create_file(dev, &dev_attr_state_synced); if (ret) { dev_err(dev, "state_synced sysfs add failed\n"); goto dev_sysfs_state_synced_failed; } } if (test_remove) { test_remove = false; device_remove_file(dev, &dev_attr_state_synced); device_remove_groups(dev, drv->dev_groups); if (dev->bus->remove) dev->bus->remove(dev); else if (drv->remove) drv->remove(dev); devres_release_all(dev); driver_sysfs_remove(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev); pm_runtime_reinit(dev); goto re_probe; } pinctrl_init_done(dev); if (dev->pm_domain && dev->pm_domain->sync) dev->pm_domain->sync(dev); driver_bound(dev); ret = 1; pr_debug("bus: '%s': %s: bound device %s to driver %s\n", drv->bus->name, __func__, dev_name(dev), drv->name); goto done; dev_sysfs_state_synced_failed: device_remove_groups(dev, drv->dev_groups); dev_groups_failed: if (dev->bus->remove) dev->bus->remove(dev); else if (drv->remove) drv->remove(dev); probe_failed: if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); pinctrl_bind_failed: device_links_no_driver(dev); devres_release_all(dev); arch_teardown_dma_ops(dev); kfree(dev->dma_range_map); dev->dma_range_map = NULL; driver_sysfs_remove(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev); pm_runtime_reinit(dev); dev_pm_set_driver_flags(dev, 0); switch (ret) { case -EPROBE_DEFER: /* Driver requested deferred probing */ dev_dbg(dev, "Driver %s requests probe deferral\n", drv->name); driver_deferred_probe_add_trigger(dev, local_trigger_count); break; case -ENODEV: case -ENXIO: pr_debug("%s: probe of %s rejects match %d\n", drv->name, dev_name(dev), ret); break; default: /* driver matched but the probe failed */ pr_warn("%s: probe of %s failed with error %d\n", drv->name, dev_name(dev), ret); } /* * Ignore errors returned by ->probe so that the next driver can try * its luck. */ ret = 0; done: atomic_dec(&probe_count); wake_up_all(&probe_waitqueue); return ret; } /* * For initcall_debug, show the driver probe time. */ static int really_probe_debug(struct device *dev, struct device_driver *drv) { ktime_t calltime, rettime; int ret; calltime = ktime_get(); ret = really_probe(dev, drv); rettime = ktime_get(); pr_debug("probe of %s returned %d after %lld usecs\n", dev_name(dev), ret, ktime_us_delta(rettime, calltime)); return ret; } /** * driver_probe_done * Determine if the probe sequence is finished or not. * * Should somehow figure out how to use a semaphore, not an atomic variable... */ int driver_probe_done(void) { int local_probe_count = atomic_read(&probe_count); pr_debug("%s: probe_count = %d\n", __func__, local_probe_count); if (local_probe_count) return -EBUSY; return 0; } /** * wait_for_device_probe * Wait for device probing to be completed. */ void wait_for_device_probe(void) { /* wait for probe timeout */ wait_event(probe_timeout_waitqueue, !driver_deferred_probe_timeout); /* wait for the deferred probe workqueue to finish */ flush_work(&deferred_probe_work); /* wait for the known devices to complete their probing */ wait_event(probe_waitqueue, atomic_read(&probe_count) == 0); async_synchronize_full(); } EXPORT_SYMBOL_GPL(wait_for_device_probe); /** * driver_probe_device - attempt to bind device & driver together * @drv: driver to bind a device to * @dev: device to try to bind to the driver * * This function returns -ENODEV if the device is not registered, * 1 if the device is bound successfully and 0 otherwise. * * This function must be called with @dev lock held. When called for a * USB interface, @dev->parent lock must be held as well. * * If the device has a parent, runtime-resume the parent before driver probing. */ int driver_probe_device(struct device_driver *drv, struct device *dev) { int ret = 0; if (!device_is_registered(dev)) return -ENODEV; pr_debug("bus: '%s': %s: matched device %s with driver %s\n", drv->bus->name, __func__, dev_name(dev), drv->name); pm_runtime_get_suppliers(dev); if (dev->parent) pm_runtime_get_sync(dev->parent); pm_runtime_barrier(dev); if (initcall_debug) ret = really_probe_debug(dev, drv); else ret = really_probe(dev, drv); pm_request_idle(dev); if (dev->parent) pm_runtime_put(dev->parent); pm_runtime_put_suppliers(dev); return ret; } static inline bool cmdline_requested_async_probing(const char *drv_name) { return parse_option_str(async_probe_drv_names, drv_name); } /* The option format is "driver_async_probe=drv_name1,drv_name2,..." */ static int __init save_async_options(char *buf) { if (strlen(buf) >= ASYNC_DRV_NAMES_MAX_LEN) pr_warn("Too long list of driver names for 'driver_async_probe'!\n"); strlcpy(async_probe_drv_names, buf, ASYNC_DRV_NAMES_MAX_LEN); return 0; } __setup("driver_async_probe=", save_async_options); bool driver_allows_async_probing(struct device_driver *drv) { switch (drv->probe_type) { case PROBE_PREFER_ASYNCHRONOUS: return true; case PROBE_FORCE_SYNCHRONOUS: return false; default: if (cmdline_requested_async_probing(drv->name)) return true; if (module_requested_async_probing(drv->owner)) return true; return false; } } struct device_attach_data { struct device *dev; /* * Indicates whether we are are considering asynchronous probing or * not. Only initial binding after device or driver registration * (including deferral processing) may be done asynchronously, the * rest is always synchronous, as we expect it is being done by * request from userspace. */ bool check_async; /* * Indicates if we are binding synchronous or asynchronous drivers. * When asynchronous probing is enabled we'll execute 2 passes * over drivers: first pass doing synchronous probing and second * doing asynchronous probing (if synchronous did not succeed - * most likely because there was no driver requiring synchronous * probing - and we found asynchronous driver during first pass). * The 2 passes are done because we can't shoot asynchronous * probe for given device and driver from bus_for_each_drv() since * driver pointer is not guaranteed to stay valid once * bus_for_each_drv() iterates to the next driver on the bus. */ bool want_async; /* * We'll set have_async to 'true' if, while scanning for matching * driver, we'll encounter one that requests asynchronous probing. */ bool have_async; }; static int __device_attach_driver(struct device_driver *drv, void *_data) { struct device_attach_data *data = _data; struct device *dev = data->dev; bool async_allowed; int ret; ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ return 0; } else if (ret == -EPROBE_DEFER) { dev_dbg(dev, "Device match requests probe deferral\n"); driver_deferred_probe_add(dev); } else if (ret < 0) { dev_dbg(dev, "Bus failed to match device: %d\n", ret); return ret; } /* ret > 0 means positive match */ async_allowed = driver_allows_async_probing(drv); if (async_allowed) data->have_async = true; if (data->check_async && async_allowed != data->want_async) return 0; return driver_probe_device(drv, dev); } static void __device_attach_async_helper(void *_dev, async_cookie_t cookie) { struct device *dev = _dev; struct device_attach_data data = { .dev = dev, .check_async = true, .want_async = true, }; device_lock(dev); /* * Check if device has already been removed or claimed. This may * happen with driver loading, device discovery/registration, * and deferred probe processing happens all at once with * multiple threads. */ if (dev->p->dead || dev->driver) goto out_unlock; if (dev->parent) pm_runtime_get_sync(dev->parent); bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver); dev_dbg(dev, "async probe completed\n"); pm_request_idle(dev); if (dev->parent) pm_runtime_put(dev->parent); out_unlock: device_unlock(dev); put_device(dev); } static int __device_attach(struct device *dev, bool allow_async) { int ret = 0; device_lock(dev); if (dev->p->dead) { goto out_unlock; } else if (dev->driver) { if (device_is_bound(dev)) { ret = 1; goto out_unlock; } ret = device_bind_driver(dev); if (ret == 0) ret = 1; else { dev->driver = NULL; ret = 0; } } else { struct device_attach_data data = { .dev = dev, .check_async = allow_async, .want_async = false, }; if (dev->parent) pm_runtime_get_sync(dev->parent); ret = bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver); if (!ret && allow_async && data.have_async) { /* * If we could not find appropriate driver * synchronously and we are allowed to do * async probes and there are drivers that * want to probe asynchronously, we'll * try them. */ dev_dbg(dev, "scheduling asynchronous probe\n"); get_device(dev); async_schedule_dev(__device_attach_async_helper, dev); } else { pm_request_idle(dev); } if (dev->parent) pm_runtime_put(dev->parent); } out_unlock: device_unlock(dev); return ret; } /** * device_attach - try to attach device to a driver. * @dev: device. * * Walk the list of drivers that the bus has and call * driver_probe_device() for each pair. If a compatible * pair is found, break out and return. * * Returns 1 if the device was bound to a driver; * 0 if no matching driver was found; * -ENODEV if the device is not registered. * * When called for a USB interface, @dev->parent lock must be held. */ int device_attach(struct device *dev) { return __device_attach(dev, false); } EXPORT_SYMBOL_GPL(device_attach); void device_initial_probe(struct device *dev) { __device_attach(dev, true); } /* * __device_driver_lock - acquire locks needed to manipulate dev->drv * @dev: Device we will update driver info for * @parent: Parent device. Needed if the bus requires parent lock * * This function will take the required locks for manipulating dev->drv. * Normally this will just be the @dev lock, but when called for a USB * interface, @parent lock will be held as well. */ static void __device_driver_lock(struct device *dev, struct device *parent) { if (parent && dev->bus->need_parent_lock) device_lock(parent); device_lock(dev); } /* * __device_driver_unlock - release locks needed to manipulate dev->drv * @dev: Device we will update driver info for * @parent: Parent device. Needed if the bus requires parent lock * * This function will release the required locks for manipulating dev->drv. * Normally this will just be the the @dev lock, but when called for a * USB interface, @parent lock will be released as well. */ static void __device_driver_unlock(struct device *dev, struct device *parent) { device_unlock(dev); if (parent && dev->bus->need_parent_lock) device_unlock(parent); } /** * device_driver_attach - attach a specific driver to a specific device * @drv: Driver to attach * @dev: Device to attach it to * * Manually attach driver to a device. Will acquire both @dev lock and * @dev->parent lock if needed. */ int device_driver_attach(struct device_driver *drv, struct device *dev) { int ret = 0; __device_driver_lock(dev, dev->parent); /* * If device has been removed or someone has already successfully * bound a driver before us just skip the driver probe call. */ if (!dev->p->dead && !dev->driver) ret = driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); return ret; } static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie) { struct device *dev = _dev; struct device_driver *drv; int ret = 0; __device_driver_lock(dev, dev->parent); drv = dev->p->async_driver; /* * If device has been removed or someone has already successfully * bound a driver before us just skip the driver probe call. */ if (!dev->p->dead && !dev->driver) ret = driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); dev_dbg(dev, "driver %s async attach completed: %d\n", drv->name, ret); put_device(dev); } static int __driver_attach(struct device *dev, void *data) { struct device_driver *drv = data; int ret; /* * Lock device and try to bind to it. We drop the error * here and always return 0, because we need to keep trying * to bind to devices and some drivers will return an error * simply if it didn't support the device. * * driver_probe_device() will spit a warning if there * is an error. */ ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ return 0; } else if (ret == -EPROBE_DEFER) { dev_dbg(dev, "Device match requests probe deferral\n"); driver_deferred_probe_add(dev); } else if (ret < 0) { dev_dbg(dev, "Bus failed to match device: %d\n", ret); return ret; } /* ret > 0 means positive match */ if (driver_allows_async_probing(drv)) { /* * Instead of probing the device synchronously we will * probe it asynchronously to allow for more parallelism. * * We only take the device lock here in order to guarantee * that the dev->driver and async_driver fields are protected */ dev_dbg(dev, "probing driver %s asynchronously\n", drv->name); device_lock(dev); if (!dev->driver) { get_device(dev); dev->p->async_driver = drv; async_schedule_dev(__driver_attach_async_helper, dev); } device_unlock(dev); return 0; } device_driver_attach(drv, dev); return 0; } /** * driver_attach - try to bind driver to devices. * @drv: driver. * * Walk the list of devices that the bus has on it and try to * match the driver with each one. If driver_probe_device() * returns 0 and the @dev->driver is set, we've found a * compatible pair. */ int driver_attach(struct device_driver *drv) { return bus_for_each_dev(drv->bus, NULL, drv, __driver_attach); } EXPORT_SYMBOL_GPL(driver_attach); /* * __device_release_driver() must be called with @dev lock held. * When called for a USB interface, @dev->parent lock must be held as well. */ static void __device_release_driver(struct device *dev, struct device *parent) { struct device_driver *drv; drv = dev->driver; if (drv) { pm_runtime_get_sync(dev); while (device_links_busy(dev)) { __device_driver_unlock(dev, parent); device_links_unbind_consumers(dev); __device_driver_lock(dev, parent); /* * A concurrent invocation of the same function might * have released the driver successfully while this one * was waiting, so check for that. */ if (dev->driver != drv) { pm_runtime_put(dev); return; } } driver_sysfs_remove(dev); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_UNBIND_DRIVER, dev); pm_runtime_put_sync(dev); device_remove_file(dev, &dev_attr_state_synced); device_remove_groups(dev, drv->dev_groups); if (dev->bus && dev->bus->remove) dev->bus->remove(dev); else if (drv->remove) drv->remove(dev); device_links_driver_cleanup(dev); devres_release_all(dev); arch_teardown_dma_ops(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev); pm_runtime_reinit(dev); dev_pm_set_driver_flags(dev, 0); klist_remove(&dev->p->knode_driver); device_pm_check_callbacks(dev); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_UNBOUND_DRIVER, dev); kobject_uevent(&dev->kobj, KOBJ_UNBIND); } } void device_release_driver_internal(struct device *dev, struct device_driver *drv, struct device *parent) { __device_driver_lock(dev, parent); if (!drv || drv == dev->driver) __device_release_driver(dev, parent); __device_driver_unlock(dev, parent); } /** * device_release_driver - manually detach device from driver. * @dev: device. * * Manually detach device from driver. * When called for a USB interface, @dev->parent lock must be held. * * If this function is to be called with @dev->parent lock held, ensure that * the device's consumers are unbound in advance or that their locks can be * acquired under the @dev->parent lock. */ void device_release_driver(struct device *dev) { /* * If anyone calls device_release_driver() recursively from * within their ->remove callback for the same device, they * will deadlock right here. */ device_release_driver_internal(dev, NULL, NULL); } EXPORT_SYMBOL_GPL(device_release_driver); /** * device_driver_detach - detach driver from a specific device * @dev: device to detach driver from * * Detach driver from device. Will acquire both @dev lock and @dev->parent * lock if needed. */ void device_driver_detach(struct device *dev) { device_release_driver_internal(dev, NULL, dev->parent); } /** * driver_detach - detach driver from all devices it controls. * @drv: driver. */ void driver_detach(struct device_driver *drv) { struct device_private *dev_prv; struct device *dev; if (driver_allows_async_probing(drv)) async_synchronize_full(); for (;;) { spin_lock(&drv->p->klist_devices.k_lock); if (list_empty(&drv->p->klist_devices.k_list)) { spin_unlock(&drv->p->klist_devices.k_lock); break; } dev_prv = list_last_entry(&drv->p->klist_devices.k_list, struct device_private, knode_driver.n_node); dev = dev_prv->device; get_device(dev); spin_unlock(&drv->p->klist_devices.k_lock); device_release_driver_internal(dev, drv, dev->parent); put_device(dev); } }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __VDSO_HELPERS_H #define __VDSO_HELPERS_H #ifndef __ASSEMBLY__ #include <vdso/datapage.h> static __always_inline u32 vdso_read_begin(const struct vdso_data *vd) { u32 seq; while (unlikely((seq = READ_ONCE(vd->seq)) & 1)) cpu_relax(); smp_rmb(); return seq; } static __always_inline u32 vdso_read_retry(const struct vdso_data *vd, u32 start) { u32 seq; smp_rmb(); seq = READ_ONCE(vd->seq); return seq != start; } static __always_inline void vdso_write_begin(struct vdso_data *vd) { /* * WRITE_ONCE it is required otherwise the compiler can validly tear * updates to vd[x].seq and it is possible that the value seen by the * reader it is inconsistent. */ WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1); WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1); smp_wmb(); } static __always_inline void vdso_write_end(struct vdso_data *vd) { smp_wmb(); /* * WRITE_ONCE it is required otherwise the compiler can validly tear * updates to vd[x].seq and it is possible that the value seen by the * reader it is inconsistent. */ WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1); WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1); } #endif /* !__ASSEMBLY__ */ #endif /* __VDSO_HELPERS_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_SECTIONS_H_ #define _ASM_GENERIC_SECTIONS_H_ /* References to section boundaries */ #include <linux/compiler.h> #include <linux/types.h> /* * Usage guidelines: * _text, _data: architecture specific, don't use them in arch-independent code * [_stext, _etext]: contains .text.* sections, may also contain .rodata.* * and/or .init.* sections * [_sdata, _edata]: contains .data.* sections, may also contain .rodata.* * and/or .init.* sections. * [__start_rodata, __end_rodata]: contains .rodata.* sections * [__start_ro_after_init, __end_ro_after_init]: * contains .data..ro_after_init section * [__init_begin, __init_end]: contains .init.* sections, but .init.text.* * may be out of this range on some architectures. * [_sinittext, _einittext]: contains .init.text.* sections * [__bss_start, __bss_stop]: contains BSS sections * * Following global variables are optional and may be unavailable on some * architectures and/or kernel configurations. * _text, _data * __kprobes_text_start, __kprobes_text_end * __entry_text_start, __entry_text_end * __ctors_start, __ctors_end * __irqentry_text_start, __irqentry_text_end * __softirqentry_text_start, __softirqentry_text_end * __start_opd, __end_opd */ extern char _text[], _stext[], _etext[]; extern char _data[], _sdata[], _edata[]; extern char __bss_start[], __bss_stop[]; extern char __init_begin[], __init_end[]; extern char _sinittext[], _einittext[]; extern char __start_ro_after_init[], __end_ro_after_init[]; extern char _end[]; extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[]; extern char __kprobes_text_start[], __kprobes_text_end[]; extern char __entry_text_start[], __entry_text_end[]; extern char __start_rodata[], __end_rodata[]; extern char __irqentry_text_start[], __irqentry_text_end[]; extern char __softirqentry_text_start[], __softirqentry_text_end[]; extern char __start_once[], __end_once[]; /* Start and end of .ctors section - used for constructor calls. */ extern char __ctors_start[], __ctors_end[]; /* Start and end of .opd section - used for function descriptors. */ extern char __start_opd[], __end_opd[]; /* Start and end of instrumentation protected text section */ extern char __noinstr_text_start[], __noinstr_text_end[]; extern __visible const void __nosave_begin, __nosave_end; /* Function descriptor handling (if any). Override in asm/sections.h */ #ifndef dereference_function_descriptor #define dereference_function_descriptor(p) ((void *)(p)) #define dereference_kernel_function_descriptor(p) ((void *)(p)) #endif /* random extra sections (if any). Override * in asm/sections.h */ #ifndef arch_is_kernel_text static inline int arch_is_kernel_text(unsigned long addr) { return 0; } #endif #ifndef arch_is_kernel_data static inline int arch_is_kernel_data(unsigned long addr) { return 0; } #endif /* * Check if an address is part of freed initmem. This is needed on architectures * with virt == phys kernel mapping, for code that wants to check if an address * is part of a static object within [_stext, _end]. After initmem is freed, * memory can be allocated from it, and such allocations would then have * addresses within the range [_stext, _end]. */ #ifndef arch_is_kernel_initmem_freed static inline int arch_is_kernel_initmem_freed(unsigned long addr) { return 0; } #endif /** * memory_contains - checks if an object is contained within a memory region * @begin: virtual address of the beginning of the memory region * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if the object specified by @virt and @size is entirely * contained within the memory region defined by @begin and @end, false * otherwise. */ static inline bool memory_contains(void *begin, void *end, void *virt, size_t size) { return virt >= begin && virt + size <= end; } /** * memory_intersects - checks if the region occupied by an object intersects * with another memory region * @begin: virtual address of the beginning of the memory regien * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if an object's memory region, specified by @virt and @size, * intersects with the region specified by @begin and @end, false otherwise. */ static inline bool memory_intersects(void *begin, void *end, void *virt, size_t size) { void *vend = virt + size; return (virt >= begin && virt < end) || (vend >= begin && vend < end); } /** * init_section_contains - checks if an object is contained within the init * section * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if the object specified by @virt and @size is entirely * contained within the init section, false otherwise. */ static inline bool init_section_contains(void *virt, size_t size) { return memory_contains(__init_begin, __init_end, virt, size); } /** * init_section_intersects - checks if the region occupied by an object * intersects with the init section * @virt: virtual address of the memory object * @size: size of the memory object * * Returns: true if an object's memory region, specified by @virt and @size, * intersects with the init section, false otherwise. */ static inline bool init_section_intersects(void *virt, size_t size) { return memory_intersects(__init_begin, __init_end, virt, size); } /** * is_kernel_rodata - checks if the pointer address is located in the * .rodata section * * @addr: address to check * * Returns: true if the address is located in .rodata, false otherwise. */ static inline bool is_kernel_rodata(unsigned long addr) { return addr >= (unsigned long)__start_rodata && addr < (unsigned long)__end_rodata; } #endif /* _ASM_GENERIC_SECTIONS_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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * pm_wakeup.h - Power management wakeup interface * * Copyright (C) 2008 Alan Stern * Copyright (C) 2010 Rafael J. Wysocki, Novell Inc. */ #ifndef _LINUX_PM_WAKEUP_H #define _LINUX_PM_WAKEUP_H #ifndef _DEVICE_H_ # error "please don't include this file directly" #endif #include <linux/types.h> struct wake_irq; /** * struct wakeup_source - Representation of wakeup sources * * @name: Name of the wakeup source * @id: Wakeup source id * @entry: Wakeup source list entry * @lock: Wakeup source lock * @wakeirq: Optional device specific wakeirq * @timer: Wakeup timer list * @timer_expires: Wakeup timer expiration * @total_time: Total time this wakeup source has been active. * @max_time: Maximum time this wakeup source has been continuously active. * @last_time: Monotonic clock when the wakeup source's was touched last time. * @prevent_sleep_time: Total time this source has been preventing autosleep. * @event_count: Number of signaled wakeup events. * @active_count: Number of times the wakeup source was activated. * @relax_count: Number of times the wakeup source was deactivated. * @expire_count: Number of times the wakeup source's timeout has expired. * @wakeup_count: Number of times the wakeup source might abort suspend. * @dev: Struct device for sysfs statistics about the wakeup source. * @active: Status of the wakeup source. * @autosleep_enabled: Autosleep is active, so update @prevent_sleep_time. */ struct wakeup_source { const char *name; int id; struct list_head entry; spinlock_t lock; struct wake_irq *wakeirq; struct timer_list timer; unsigned long timer_expires; ktime_t total_time; ktime_t max_time; ktime_t last_time; ktime_t start_prevent_time; ktime_t prevent_sleep_time; unsigned long event_count; unsigned long active_count; unsigned long relax_count; unsigned long expire_count; unsigned long wakeup_count; struct device *dev; bool active:1; bool autosleep_enabled:1; }; #define for_each_wakeup_source(ws) \ for ((ws) = wakeup_sources_walk_start(); \ (ws); \ (ws) = wakeup_sources_walk_next((ws))) #ifdef CONFIG_PM_SLEEP /* * Changes to device_may_wakeup take effect on the next pm state change. */ static inline bool device_can_wakeup(struct device *dev) { return dev->power.can_wakeup; } static inline bool device_may_wakeup(struct device *dev) { return dev->power.can_wakeup && !!dev->power.wakeup; } static inline void device_set_wakeup_path(struct device *dev) { dev->power.wakeup_path = true; } /* drivers/base/power/wakeup.c */ extern struct wakeup_source *wakeup_source_create(const char *name); extern void wakeup_source_destroy(struct wakeup_source *ws); extern void wakeup_source_add(struct wakeup_source *ws); extern void wakeup_source_remove(struct wakeup_source *ws); extern struct wakeup_source *wakeup_source_register(struct device *dev, const char *name); extern void wakeup_source_unregister(struct wakeup_source *ws); extern int wakeup_sources_read_lock(void); extern void wakeup_sources_read_unlock(int idx); extern struct wakeup_source *wakeup_sources_walk_start(void); extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws); extern int device_wakeup_enable(struct device *dev); extern int device_wakeup_disable(struct device *dev); extern void device_set_wakeup_capable(struct device *dev, bool capable); extern int device_init_wakeup(struct device *dev, bool val); extern int device_set_wakeup_enable(struct device *dev, bool enable); extern void __pm_stay_awake(struct wakeup_source *ws); extern void pm_stay_awake(struct device *dev); extern void __pm_relax(struct wakeup_source *ws); extern void pm_relax(struct device *dev); extern void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard); extern void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard); #else /* !CONFIG_PM_SLEEP */ static inline void device_set_wakeup_capable(struct device *dev, bool capable) { dev->power.can_wakeup = capable; } static inline bool device_can_wakeup(struct device *dev) { return dev->power.can_wakeup; } static inline struct wakeup_source *wakeup_source_create(const char *name) { return NULL; } static inline void wakeup_source_destroy(struct wakeup_source *ws) {} static inline void wakeup_source_add(struct wakeup_source *ws) {} static inline void wakeup_source_remove(struct wakeup_source *ws) {} static inline struct wakeup_source *wakeup_source_register(struct device *dev, const char *name) { return NULL; } static inline void wakeup_source_unregister(struct wakeup_source *ws) {} static inline int device_wakeup_enable(struct device *dev) { dev->power.should_wakeup = true; return 0; } static inline int device_wakeup_disable(struct device *dev) { dev->power.should_wakeup = false; return 0; } static inline int device_set_wakeup_enable(struct device *dev, bool enable) { dev->power.should_wakeup = enable; return 0; } static inline int device_init_wakeup(struct device *dev, bool val) { device_set_wakeup_capable(dev, val); device_set_wakeup_enable(dev, val); return 0; } static inline bool device_may_wakeup(struct device *dev) { return dev->power.can_wakeup && dev->power.should_wakeup; } static inline void device_set_wakeup_path(struct device *dev) {} static inline void __pm_stay_awake(struct wakeup_source *ws) {} static inline void pm_stay_awake(struct device *dev) {} static inline void __pm_relax(struct wakeup_source *ws) {} static inline void pm_relax(struct device *dev) {} static inline void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard) {} static inline void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard) {} #endif /* !CONFIG_PM_SLEEP */ static inline void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec) { return pm_wakeup_ws_event(ws, msec, false); } static inline void pm_wakeup_event(struct device *dev, unsigned int msec) { return pm_wakeup_dev_event(dev, msec, false); } static inline void pm_wakeup_hard_event(struct device *dev) { return pm_wakeup_dev_event(dev, 0, true); } #endif /* _LINUX_PM_WAKEUP_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_TYPES_H #define _LINUX_MM_TYPES_H #include <linux/mm_types_task.h> #include <linux/auxvec.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/rwsem.h> #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/uprobes.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> #include <linux/seqlock.h> #include <asm/mmu.h> #ifndef AT_VECTOR_SIZE_ARCH #define AT_VECTOR_SIZE_ARCH 0 #endif #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) #define INIT_PASID 0 struct address_space; struct mem_cgroup; /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the * moment. Note that we have no way to track which tasks are using * a page, though if it is a pagecache page, rmap structures can tell us * who is mapping it. * * If you allocate the page using alloc_pages(), you can use some of the * space in struct page for your own purposes. The five words in the main * union are available, except for bit 0 of the first word which must be * kept clear. Many users use this word to store a pointer to an object * which is guaranteed to be aligned. If you use the same storage as * page->mapping, you must restore it to NULL before freeing the page. * * If your page will not be mapped to userspace, you can also use the four * bytes in the mapcount union, but you must call page_mapcount_reset() * before freeing it. * * If you want to use the refcount field, it must be used in such a way * that other CPUs temporarily incrementing and then decrementing the * refcount does not cause problems. On receiving the page from * alloc_pages(), the refcount will be positive. * * If you allocate pages of order > 0, you can use some of the fields * in each subpage, but you may need to restore some of their values * afterwards. * * SLUB uses cmpxchg_double() to atomically update its freelist and * counters. That requires that freelist & counters be adjacent and * double-word aligned. We align all struct pages to double-word * boundaries, and ensure that 'freelist' is aligned within the * struct. */ #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE #define _struct_page_alignment __aligned(2 * sizeof(unsigned long)) #else #define _struct_page_alignment #endif struct page { unsigned long flags; /* Atomic flags, some possibly * updated asynchronously */ /* * Five words (20/40 bytes) are available in this union. * WARNING: bit 0 of the first word is used for PageTail(). That * means the other users of this union MUST NOT use the bit to * avoid collision and false-positive PageTail(). */ union { struct { /* Page cache and anonymous pages */ /** * @lru: Pageout list, eg. active_list protected by * pgdat->lru_lock. Sometimes used as a generic list * by the page owner. */ struct list_head lru; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; pgoff_t index; /* Our offset within mapping. */ /** * @private: Mapping-private opaque data. * Usually used for buffer_heads if PagePrivate. * Used for swp_entry_t if PageSwapCache. * Indicates order in the buddy system if PageBuddy. */ unsigned long private; }; struct { /* page_pool used by netstack */ /** * @dma_addr: might require a 64-bit value on * 32-bit architectures. */ unsigned long dma_addr[2]; }; struct { /* slab, slob and slub */ union { struct list_head slab_list; struct { /* Partial pages */ struct page *next; #ifdef CONFIG_64BIT int pages; /* Nr of pages left */ int pobjects; /* Approximate count */ #else short int pages; short int pobjects; #endif }; }; struct kmem_cache *slab_cache; /* not slob */ /* Double-word boundary */ void *freelist; /* first free object */ union { void *s_mem; /* slab: first object */ unsigned long counters; /* SLUB */ struct { /* SLUB */ unsigned inuse:16; unsigned objects:15; unsigned frozen:1; }; }; }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ /* First tail page only */ unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; unsigned int compound_nr; /* 1 << compound_order */ }; struct { /* Second tail page of compound page */ unsigned long _compound_pad_1; /* compound_head */ atomic_t hpage_pinned_refcount; /* For both global and memcg */ struct list_head deferred_list; }; struct { /* Page table pages */ unsigned long _pt_pad_1; /* compound_head */ pgtable_t pmd_huge_pte; /* protected by page->ptl */ unsigned long _pt_pad_2; /* mapping */ union { struct mm_struct *pt_mm; /* x86 pgds only */ atomic_t pt_frag_refcount; /* powerpc */ }; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else spinlock_t ptl; #endif }; struct { /* ZONE_DEVICE pages */ /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; void *zone_device_data; /* * ZONE_DEVICE private pages are counted as being * mapped so the next 3 words hold the mapping, index, * and private fields from the source anonymous or * page cache page while the page is migrated to device * private memory. * ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also * use the mapping, index, and private fields when * pmem backed DAX files are mapped. */ }; /** @rcu_head: You can use this to free a page by RCU. */ struct rcu_head rcu_head; }; union { /* This union is 4 bytes in size. */ /* * If the page can be mapped to userspace, encodes the number * of times this page is referenced by a page table. */ atomic_t _mapcount; /* * If the page is neither PageSlab nor mappable to userspace, * the value stored here may help determine what this page * is used for. See page-flags.h for a list of page types * which are currently stored here. */ unsigned int page_type; unsigned int active; /* SLAB */ int units; /* SLOB */ }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ atomic_t _refcount; #ifdef CONFIG_MEMCG union { struct mem_cgroup *mem_cgroup; struct obj_cgroup **obj_cgroups; }; #endif /* * On machines where all RAM is mapped into kernel address space, * we can simply calculate the virtual address. On machines with * highmem some memory is mapped into kernel virtual memory * dynamically, so we need a place to store that address. * Note that this field could be 16 bits on x86 ... ;) * * Architectures with slow multiplication can define * WANT_PAGE_VIRTUAL in asm/page.h */ #if defined(WANT_PAGE_VIRTUAL) void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif } _struct_page_alignment; static inline atomic_t *compound_mapcount_ptr(struct page *page) { return &page[1].compound_mapcount; } static inline atomic_t *compound_pincount_ptr(struct page *page) { return &page[2].hpage_pinned_refcount; } /* * Used for sizing the vmemmap region on some architectures */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) #define page_private(page) ((page)->private) static inline void set_page_private(struct page *page, unsigned long private) { page->private = private; } struct page_frag_cache { void * va; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) __u16 offset; __u16 size; #else __u32 offset; #endif /* we maintain a pagecount bias, so that we dont dirty cache line * containing page->_refcount every time we allocate a fragment. */ unsigned int pagecnt_bias; bool pfmemalloc; }; typedef unsigned long vm_flags_t; /* * A region containing a mapping of a non-memory backed file under NOMMU * conditions. These are held in a global tree and are pinned by the VMAs that * map parts of them. */ struct vm_region { struct rb_node vm_rb; /* link in global region tree */ vm_flags_t vm_flags; /* VMA vm_flags */ unsigned long vm_start; /* start address of region */ unsigned long vm_end; /* region initialised to here */ unsigned long vm_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ int vm_usage; /* region usage count (access under nommu_region_sem) */ bool vm_icache_flushed : 1; /* true if the icache has been flushed for * this region */ }; #ifdef CONFIG_USERFAULTFD #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, }) struct vm_userfaultfd_ctx { struct userfaultfd_ctx *ctx; }; #else /* CONFIG_USERFAULTFD */ #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {}) struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory * space that has a special rule for the page-fault handlers (ie a shared * library, the executable area etc). */ struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ unsigned long vm_start; /* Our start address within vm_mm. */ unsigned long vm_end; /* The first byte after our end address within vm_mm. */ /* linked list of VM areas per task, sorted by address */ struct vm_area_struct *vm_next, *vm_prev; struct rb_node vm_rb; /* * Largest free memory gap in bytes to the left of this VMA. * Either between this VMA and vma->vm_prev, or between one of the * VMAs below us in the VMA rbtree and its ->vm_prev. This helps * get_unmapped_area find a free area of the right size. */ unsigned long rb_subtree_gap; /* Second cache line starts here. */ struct mm_struct *vm_mm; /* The address space we belong to. */ /* * Access permissions of this VMA. * See vmf_insert_mixed_prot() for discussion. */ pgprot_t vm_page_prot; unsigned long vm_flags; /* Flags, see mm.h. */ /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. */ struct { struct rb_node rb; unsigned long rb_subtree_last; } shared; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma * list, after a COW of one of the file pages. A MAP_SHARED vma * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ struct list_head anon_vma_chain; /* Serialized by mmap_lock & * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ /* Function pointers to deal with this struct. */ const struct vm_operations_struct *vm_ops; /* Information about our backing store: */ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE units */ struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ #ifdef CONFIG_SWAP atomic_long_t swap_readahead_info; #endif #ifndef CONFIG_MMU struct vm_region *vm_region; /* NOMMU mapping region */ #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; struct core_thread { struct task_struct *task; struct core_thread *next; }; struct core_state { atomic_t nr_threads; struct core_thread dumper; struct completion startup; }; struct kioctx_table; struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES /* Base adresses for compatible mmap() */ unsigned long mmap_compat_base; unsigned long mmap_compat_legacy_base; #endif unsigned long task_size; /* size of task vm space */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; #ifdef CONFIG_MEMBARRIER /** * @membarrier_state: Flags controlling membarrier behavior. * * This field is close to @pgd to hopefully fit in the same * cache-line, which needs to be touched by switch_mm(). */ atomic_t membarrier_state; #endif /** * @mm_users: The number of users including userspace. * * Use mmget()/mmget_not_zero()/mmput() to modify. When this * drops to 0 (i.e. when the task exits and there are no other * temporary reference holders), we also release a reference on * @mm_count (which may then free the &struct mm_struct if * @mm_count also drops to 0). */ atomic_t mm_users; /** * @mm_count: The number of references to &struct mm_struct * (@mm_users count as 1). * * Use mmgrab()/mmdrop() to modify. When this drops to 0, the * &struct mm_struct is freed. */ atomic_t mm_count; /** * @has_pinned: Whether this mm has pinned any pages. This can * be either replaced in the future by @pinned_vm when it * becomes stable, or grow into a counter on its own. We're * aggresive on this bit now - even if the pinned pages were * unpinned later on, we'll still keep this bit set for the * lifecycle of this mm just for simplicity. */ atomic_t has_pinned; #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif int map_count; /* number of VMAs */ spinlock_t page_table_lock; /* Protects page tables and some * counters */ /* * With some kernel config, the current mmap_lock's offset * inside 'mm_struct' is at 0x120, which is very optimal, as * its two hot fields 'count' and 'owner' sit in 2 different * cachelines, and when mmap_lock is highly contended, both * of the 2 fields will be accessed frequently, current layout * will help to reduce cache bouncing. * * So please be careful with adding new fields before * mmap_lock, which can easily push the 2 fields into one * cacheline. */ struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These * are globally strung together off * init_mm.mmlist, and are protected * by mmlist_lock */ unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ atomic64_t pinned_vm; /* Refcount permanently increased */ unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; /** * @write_protect_seq: Locked when any thread is write * protecting pages mapped by this mm to enforce a later COW, * for instance during page table copying for fork(). */ seqcount_t write_protect_seq; spinlock_t arg_lock; /* protect the below fields */ unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ /* * Special counters, in some configurations protected by the * page_table_lock, in other configurations by being atomic. */ struct mm_rss_stat rss_stat; struct linux_binfmt *binfmt; /* Architecture-specific MM context */ mm_context_t context; unsigned long flags; /* Must use atomic bitops to access */ struct core_state *core_state; /* coredumping support */ #ifdef CONFIG_AIO spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; #endif #ifdef CONFIG_MEMCG /* * "owner" points to a task that is regarded as the canonical * user/owner of this mm. All of the following must be true in * order for it to be changed: * * current == mm->owner * current->mm != mm * new_owner->mm == mm * new_owner->alloc_lock is held */ struct task_struct __rcu *owner; #endif struct user_namespace *user_ns; /* store ref to file /proc/<pid>/exe symlink points to */ struct file __rcu *exe_file; #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions; #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING /* * numa_next_scan is the next time that the PTEs will be marked * pte_numa. NUMA hinting faults will gather statistics and * migrate pages to new nodes if necessary. */ unsigned long numa_next_scan; /* Restart point for scanning and setting pte_numa */ unsigned long numa_scan_offset; /* numa_scan_seq prevents two threads setting pte_numa */ int numa_scan_seq; #endif /* * An operation with batched TLB flushing is going on. Anything * that can move process memory needs to flush the TLB when * moving a PROT_NONE or PROT_NUMA mapped page. */ atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ bool tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; #ifdef CONFIG_IOMMU_SUPPORT u32 pasid; #endif } __randomize_layout; /* * The mm_cpumask needs to be at the end of mm_struct, because it * is dynamically sized based on nr_cpu_ids. */ unsigned long cpu_bitmap[]; }; extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { unsigned long cpu_bitmap = (unsigned long)mm; cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { return (struct cpumask *)&mm->cpu_bitmap; } struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); extern void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end); static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } struct vm_fault; /** * typedef vm_fault_t - Return type for page fault handlers. * * Page fault handlers return a bitmask of %VM_FAULT values. */ typedef __bitwise unsigned int vm_fault_t; /** * enum vm_fault_reason - Page fault handlers return a bitmask of * these values to tell the core VM what happened when handling the * fault. Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. * * @VM_FAULT_OOM: Out Of Memory * @VM_FAULT_SIGBUS: Bad access * @VM_FAULT_MAJOR: Page read from storage * @VM_FAULT_WRITE: Special case for get_user_pages * @VM_FAULT_HWPOISON: Hit poisoned small page * @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded * in upper bits * @VM_FAULT_SIGSEGV: segmentation fault * @VM_FAULT_NOPAGE: ->fault installed the pte, not return page * @VM_FAULT_LOCKED: ->fault locked the returned page * @VM_FAULT_RETRY: ->fault blocked, must retry * @VM_FAULT_FALLBACK: huge page fault failed, fall back to small * @VM_FAULT_DONE_COW: ->fault has fully handled COW * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ enum vm_fault_reason { VM_FAULT_OOM = (__force vm_fault_t)0x000001, VM_FAULT_SIGBUS = (__force vm_fault_t)0x000002, VM_FAULT_MAJOR = (__force vm_fault_t)0x000004, VM_FAULT_WRITE = (__force vm_fault_t)0x000008, VM_FAULT_HWPOISON = (__force vm_fault_t)0x000010, VM_FAULT_HWPOISON_LARGE = (__force vm_fault_t)0x000020, VM_FAULT_SIGSEGV = (__force vm_fault_t)0x000040, VM_FAULT_NOPAGE = (__force vm_fault_t)0x000100, VM_FAULT_LOCKED = (__force vm_fault_t)0x000200, VM_FAULT_RETRY = (__force vm_fault_t)0x000400, VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16)) #define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf) #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \ VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \ VM_FAULT_HWPOISON_LARGE | VM_FAULT_FALLBACK) #define VM_FAULT_RESULT_TRACE \ { VM_FAULT_OOM, "OOM" }, \ { VM_FAULT_SIGBUS, "SIGBUS" }, \ { VM_FAULT_MAJOR, "MAJOR" }, \ { VM_FAULT_WRITE, "WRITE" }, \ { VM_FAULT_HWPOISON, "HWPOISON" }, \ { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ { VM_FAULT_NOPAGE, "NOPAGE" }, \ { VM_FAULT_LOCKED, "LOCKED" }, \ { VM_FAULT_RETRY, "RETRY" }, \ { VM_FAULT_FALLBACK, "FALLBACK" }, \ { VM_FAULT_DONE_COW, "DONE_COW" }, \ { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" } struct vm_special_mapping { const char *name; /* The name, e.g. "[vdso]". */ /* * If .fault is not provided, this points to a * NULL-terminated array of pages that back the special mapping. * * This must not be NULL unless .fault is provided. */ struct page **pages; /* * If non-NULL, then this is called to resolve page faults * on the special mapping. If used, .pages is not checked. */ vm_fault_t (*fault)(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf); int (*mremap)(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma); }; enum tlb_flush_reason { TLB_FLUSH_ON_TASK_SWITCH, TLB_REMOTE_SHOOTDOWN, TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, TLB_REMOTE_SEND_IPI, NR_TLB_FLUSH_REASONS, }; /* * A swap entry has to fit into a "unsigned long", as the entry is hidden * in the "index" field of the swapper address space. */ typedef struct { unsigned long val; } swp_entry_t; #endif /* _LINUX_MM_TYPES_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM exceptions #if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGE_FAULT_H #include <linux/tracepoint.h> #include <asm/trace/common.h> extern int trace_pagefault_reg(void); extern void trace_pagefault_unreg(void); DECLARE_EVENT_CLASS(x86_exceptions, TP_PROTO(unsigned long address, struct pt_regs *regs, unsigned long error_code), TP_ARGS(address, regs, error_code), TP_STRUCT__entry( __field( unsigned long, address ) __field( unsigned long, ip ) __field( unsigned long, error_code ) ), TP_fast_assign( __entry->address = address; __entry->ip = regs->ip; __entry->error_code = error_code; ), TP_printk("address=%ps ip=%ps error_code=0x%lx", (void *)__entry->address, (void *)__entry->ip, __entry->error_code) ); #define DEFINE_PAGE_FAULT_EVENT(name) \ DEFINE_EVENT_FN(x86_exceptions, name, \ TP_PROTO(unsigned long address, struct pt_regs *regs, \ unsigned long error_code), \ TP_ARGS(address, regs, error_code), \ trace_pagefault_reg, trace_pagefault_unreg); DEFINE_PAGE_FAULT_EVENT(page_fault_user); DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); #undef TRACE_INCLUDE_PATH #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE exceptions #endif /* _TRACE_PAGE_FAULT_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
4 6 1 6 4 4 13 6 13 13 11 11 13 13 7 7 7 4 4 4 4 4 4 4 4 1 3 3 3 1 2 6 3 2 1 1 1 1 1 1 2 7 7 5 7 4 4 3 4 4 4 7 7 7 3 7 7 7 4 7 7 7 4 4 3 3 3 3 3 3 1 3 3 3 3 3 3 4 4 4 4 4 4 3 4 4 4 3 3 3 3 3 5 5 5 5 5 5 5 3 3 3 3 3 3 3 3 3 3 3 6 6 6 6 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 // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation * Copyright (c) 2017-2018 Microsoft Corporation * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <willy@infradead.org> */ #include <linux/bitmap.h> #include <linux/export.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/xarray.h> /* * Coding conventions in this file: * * @xa is used to refer to the entire xarray. * @xas is the 'xarray operation state'. It may be either a pointer to * an xa_state, or an xa_state stored on the stack. This is an unfortunate * ambiguity. * @index is the index of the entry being operated on * @mark is an xa_mark_t; a small number indicating one of the mark bits. * @node refers to an xa_node; usually the primary one being operated on by * this function. * @offset is the index into the slots array inside an xa_node. * @parent refers to the @xa_node closer to the head than @node. * @entry refers to something stored in a slot in the xarray */ static inline unsigned int xa_lock_type(const struct xarray *xa) { return (__force unsigned int)xa->xa_flags & 3; } static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_lock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_lock_bh(xas); else xas_lock(xas); } static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_unlock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_unlock_bh(xas); else xas_unlock(xas); } static inline bool xa_track_free(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_TRACK_FREE; } static inline bool xa_zero_busy(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_ZERO_BUSY; } static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) xa->xa_flags |= XA_FLAGS_MARK(mark); } static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark) { if (xa->xa_flags & XA_FLAGS_MARK(mark)) xa->xa_flags &= ~(XA_FLAGS_MARK(mark)); } static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark) { return node->marks[(__force unsigned)mark]; } static inline bool node_get_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return test_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_set_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_set_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_clear_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_clear_bit(offset, node_marks(node, mark)); } static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) { return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) { bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE); } #define mark_inc(mark) do { \ mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ } while (0) /* * xas_squash_marks() - Merge all marks to the first entry * @xas: Array operation state. * * Set a mark on the first entry if any entry has it set. Clear marks on * all sibling entries. */ static void xas_squash_marks(const struct xa_state *xas) { unsigned int mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; if (!xas->xa_sibs) return; do { unsigned long *marks = xas->xa_node->marks[mark]; if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) continue; __set_bit(xas->xa_offset, marks); bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); } while (mark++ != (__force unsigned)XA_MARK_MAX); } /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { return (index >> node->shift) & XA_CHUNK_MASK; } static void xas_set_offset(struct xa_state *xas) { xas->xa_offset = get_offset(xas->xa_index, xas->xa_node); } /* move the index either forwards (find) or backwards (sibling slot) */ static void xas_move_index(struct xa_state *xas, unsigned long offset) { unsigned int shift = xas->xa_node->shift; xas->xa_index &= ~XA_CHUNK_MASK << shift; xas->xa_index += offset << shift; } static void xas_advance(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); } static void *set_bounds(struct xa_state *xas) { xas->xa_node = XAS_BOUNDS; return NULL; } /* * Starts a walk. If the @xas is already valid, we assume that it's on * the right path and just return where we've got to. If we're in an * error state, return NULL. If the index is outside the current scope * of the xarray, return NULL without changing @xas->xa_node. Otherwise * set @xas->xa_node to NULL and return the current head of the array. */ static void *xas_start(struct xa_state *xas) { void *entry; if (xas_valid(xas)) return xas_reload(xas); if (xas_error(xas)) return NULL; entry = xa_head(xas->xa); if (!xa_is_node(entry)) { if (xas->xa_index) return set_bounds(xas); } else { if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) return set_bounds(xas); } xas->xa_node = NULL; return entry; } static void *xas_descend(struct xa_state *xas, struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); xas->xa_node = node; if (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); } xas->xa_offset = offset; return entry; } /** * xas_load() - Load an entry from the XArray (advanced). * @xas: XArray operation state. * * Usually walks the @xas to the appropriate state to load the entry * stored at xa_index. However, it will do nothing and return %NULL if * @xas is in an error state. xas_load() will never expand the tree. * * If the xa_state is set up to operate on a multi-index entry, xas_load() * may return %NULL or an internal entry, even if there are entries * present within the range specified by @xas. * * Context: Any context. The caller should hold the xa_lock or the RCU lock. * Return: Usually an entry in the XArray, but see description for exceptions. */ void *xas_load(struct xa_state *xas) { void *entry = xas_start(xas); while (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); if (xas->xa_shift > node->shift) break; entry = xas_descend(xas, node); if (node->shift == 0) break; } return entry; } EXPORT_SYMBOL_GPL(xas_load); /* Move the radix tree node cache here */ extern struct kmem_cache *radix_tree_node_cachep; extern void radix_tree_node_rcu_free(struct rcu_head *head); #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->array = XA_RCU_FREE; call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * xas_destroy() - Free any resources allocated during the XArray operation. * @xas: XArray operation state. * * This function is now internal-only. */ static void xas_destroy(struct xa_state *xas) { struct xa_node *next, *node = xas->xa_alloc; while (node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); next = rcu_dereference_raw(node->parent); radix_tree_node_rcu_free(&node->rcu_head); xas->xa_alloc = node = next; } } /** * xas_nomem() - Allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * If we need to add new nodes to the XArray, we try to allocate memory * with GFP_NOWAIT while holding the lock, which will usually succeed. * If it fails, @xas is flagged as needing memory to continue. The caller * should drop the lock and call xas_nomem(). If xas_nomem() succeeds, * the caller should retry the operation. * * Forward progress is guaranteed as one node is allocated here and * stored in the xa_state where it will be found by xas_alloc(). More * nodes will likely be found in the slab allocator, but we do not tie * them up here. * * Return: true if memory was needed, and was successfully allocated. */ bool xas_nomem(struct xa_state *xas, gfp_t gfp) { if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } EXPORT_SYMBOL_GPL(xas_nomem); /* * __xas_nomem() - Drop locks and allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * Internal variant of xas_nomem(). * * Return: true if memory was needed, and was successfully allocated. */ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) __must_hold(xas->xa->xa_lock) { unsigned int lock_type = xa_lock_type(xas->xa); if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); xas_lock_type(xas, lock_type); } else { xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); } if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } static void xas_update(struct xa_state *xas, struct xa_node *node) { if (xas->xa_update) xas->xa_update(node); else XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); } static void *xas_alloc(struct xa_state *xas, unsigned int shift) { struct xa_node *parent = xas->xa_node; struct xa_node *node = xas->xa_alloc; if (xas_invalid(xas)) return NULL; if (node) { xas->xa_alloc = NULL; } else { gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN; if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; } } if (parent) { node->offset = xas->xa_offset; parent->count++; XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE); xas_update(xas, parent); } XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->shift = shift; node->count = 0; node->nr_values = 0; RCU_INIT_POINTER(node->parent, xas->xa_node); node->array = xas->xa; return node; } #ifdef CONFIG_XARRAY_MULTI /* Returns the number of indices covered by a given xa_state */ static unsigned long xas_size(const struct xa_state *xas) { return (xas->xa_sibs + 1UL) << xas->xa_shift; } #endif /* * Use this to calculate the maximum index that will need to be created * in order to add the entry described by @xas. Because we cannot store a * multi-index entry at index 0, the calculation is a little more complex * than you might expect. */ static unsigned long xas_max(struct xa_state *xas) { unsigned long max = xas->xa_index; #ifdef CONFIG_XARRAY_MULTI if (xas->xa_shift || xas->xa_sibs) { unsigned long mask = xas_size(xas) - 1; max |= mask; if (mask == max) max++; } #endif return max; } /* The maximum index that can be contained in the array without expanding it */ static unsigned long max_index(void *entry) { if (!xa_is_node(entry)) return 0; return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; struct xa_node *node = xas->xa_node; for (;;) { void *entry; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count != 1) break; entry = xa_entry_locked(xa, node, 0); if (!entry) break; if (!xa_is_node(entry) && node->shift) break; if (xa_is_zero(entry) && xa_zero_busy(xa)) entry = NULL; xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) xa_mark_clear(xa, XA_FREE_MARK); node->count = 0; node->nr_values = 0; if (!xa_is_node(entry)) RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); xas_update(xas, node); xa_node_free(node); if (!xa_is_node(entry)) break; node = xa_to_node(entry); node->parent = NULL; } } /* * xas_delete_node() - Attempt to delete an xa_node * @xas: Array operation state. * * Attempts to delete the @xas->xa_node. This will fail if xa->node has * a non-zero reference count. */ static void xas_delete_node(struct xa_state *xas) { struct xa_node *node = xas->xa_node; for (;;) { struct xa_node *parent; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count) break; parent = xa_parent_locked(xas->xa, node); xas->xa_node = parent; xas->xa_offset = node->offset; xa_node_free(node); if (!parent) { xas->xa->xa_head = NULL; xas->xa_node = XAS_BOUNDS; return; } parent->slots[xas->xa_offset] = NULL; parent->count--; XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE); node = parent; xas_update(xas, node); } if (!node->parent) xas_shrink(xas); } /** * xas_free_nodes() - Free this node and all nodes that it references * @xas: Array operation state. * @top: Node to free * * This node has been removed from the tree. We must now free it and all * of its subnodes. There may be RCU walkers with references into the tree, * so we must replace all entries with retry markers. */ static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) { unsigned int offset = 0; struct xa_node *node = top; for (;;) { void *entry = xa_entry_locked(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) { node = xa_to_node(entry); offset = 0; continue; } if (entry) RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY); offset++; while (offset == XA_CHUNK_SIZE) { struct xa_node *parent; parent = xa_parent_locked(xas->xa, node); offset = node->offset + 1; node->count = 0; node->nr_values = 0; xas_update(xas, node); xa_node_free(node); if (node == top) return; node = parent; } } } /* * xas_expand adds nodes to the head of the tree until it has reached * sufficient height to be able to contain @xas->xa_index */ static int xas_expand(struct xa_state *xas, void *head) { struct xarray *xa = xas->xa; struct xa_node *node = NULL; unsigned int shift = 0; unsigned long max = xas_max(xas); if (!head) { if (max == 0) return 0; while ((max >> shift) >= XA_CHUNK_SIZE) shift += XA_CHUNK_SHIFT; return shift + XA_CHUNK_SHIFT; } else if (xa_is_node(head)) { node = xa_to_node(head); shift = node->shift + XA_CHUNK_SHIFT; } xas->xa_node = NULL; while (max > max_index(head)) { xa_mark_t mark = 0; XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); node = xas_alloc(xas, shift); if (!node) return -ENOMEM; node->count = 1; if (xa_is_value(head)) node->nr_values = 1; RCU_INIT_POINTER(node->slots[0], head); /* Propagate the aggregated mark info to the new child */ for (;;) { if (xa_track_free(xa) && mark == XA_FREE_MARK) { node_mark_all(node, XA_FREE_MARK); if (!xa_marked(xa, XA_FREE_MARK)) { node_clear_mark(node, 0, XA_FREE_MARK); xa_mark_set(xa, XA_FREE_MARK); } } else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } /* * Now that the new node is fully initialised, we can add * it to the tree */ if (xa_is_node(head)) { xa_to_node(head)->offset = 0; rcu_assign_pointer(xa_to_node(head)->parent, node); } head = xa_mk_node(node); rcu_assign_pointer(xa->xa_head, head); xas_update(xas, node); shift += XA_CHUNK_SHIFT; } xas->xa_node = node; return shift; } /* * xas_create() - Create a slot to store an entry in. * @xas: XArray operation state. * @allow_root: %true if we can store the entry in the root directly * * Most users will not need to call this function directly, as it is called * by xas_store(). It is useful for doing conditional store operations * (see the xa_cmpxchg() implementation for an example). * * Return: If the slot already existed, returns the contents of this slot. * If the slot was newly created, returns %NULL. If it failed to create the * slot, returns %NULL and indicates the error in @xas. */ static void *xas_create(struct xa_state *xas, bool allow_root) { struct xarray *xa = xas->xa; void *entry; void __rcu **slot; struct xa_node *node = xas->xa_node; int shift; unsigned int order = xas->xa_shift; if (xas_top(node)) { entry = xa_head_locked(xa); xas->xa_node = NULL; if (!entry && xa_zero_busy(xa)) entry = XA_ZERO_ENTRY; shift = xas_expand(xas, entry); if (shift < 0) return NULL; if (!shift && !allow_root) shift = XA_CHUNK_SHIFT; entry = xa_head_locked(xa); slot = &xa->xa_head; } else if (xas_error(xas)) { return NULL; } else if (node) { unsigned int offset = xas->xa_offset; shift = node->shift; entry = xa_entry_locked(xa, node, offset); slot = &node->slots[offset]; } else { shift = 0; entry = xa_head_locked(xa); slot = &xa->xa_head; } while (shift > order) { shift -= XA_CHUNK_SHIFT; if (!entry) { node = xas_alloc(xas, shift); if (!node) break; if (xa_track_free(xa)) node_mark_all(node, XA_FREE_MARK); rcu_assign_pointer(*slot, xa_mk_node(node)); } else if (xa_is_node(entry)) { node = xa_to_node(entry); } else { break; } entry = xas_descend(xas, node); slot = &node->slots[xas->xa_offset]; } return entry; } /** * xas_create_range() - Ensure that stores to this range will succeed * @xas: XArray operation state. * * Creates all of the slots in the range covered by @xas. Sets @xas to * create single-index entries and positions it at the beginning of the * range. This is for the benefit of users which have not yet been * converted to use multi-index entries. */ void xas_create_range(struct xa_state *xas) { unsigned long index = xas->xa_index; unsigned char shift = xas->xa_shift; unsigned char sibs = xas->xa_sibs; xas->xa_index |= ((sibs + 1UL) << shift) - 1; if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift) xas->xa_offset |= sibs; xas->xa_shift = 0; xas->xa_sibs = 0; for (;;) { xas_create(xas, true); if (xas_error(xas)) goto restore; if (xas->xa_index <= (index | XA_CHUNK_MASK)) goto success; xas->xa_index -= XA_CHUNK_SIZE; for (;;) { struct xa_node *node = xas->xa_node; xas->xa_node = xa_parent_locked(xas->xa, node); xas->xa_offset = node->offset - 1; if (node->offset != 0) break; } } restore: xas->xa_shift = shift; xas->xa_sibs = sibs; xas->xa_index = index; return; success: xas->xa_index = index; if (xas->xa_node) xas_set_offset(xas); } EXPORT_SYMBOL_GPL(xas_create_range); static void update_node(struct xa_state *xas, struct xa_node *node, int count, int values) { if (!node || (!count && !values)) return; node->count += count; node->nr_values += values; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE); xas_update(xas, node); if (count < 0) xas_delete_node(xas); } /** * xas_store() - Store this entry in the XArray. * @xas: XArray operation state. * @entry: New entry. * * If @xas is operating on a multi-index entry, the entry returned by this * function is essentially meaningless (it may be an internal entry or it * may be %NULL, even if there are non-NULL entries at some of the indices * covered by the range). This is not a problem for any current users, * and can be changed if needed. * * Return: The old entry at this index. */ void *xas_store(struct xa_state *xas, void *entry) { struct xa_node *node; void __rcu **slot = &xas->xa->xa_head; unsigned int offset, max; int count = 0; int values = 0; void *first, *next; bool value = xa_is_value(entry); if (entry) { bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry); first = xas_create(xas, allow_root); } else { first = xas_load(xas); } if (xas_invalid(xas)) return first; node = xas->xa_node; if (node && (xas->xa_shift < node->shift)) xas->xa_sibs = 0; if ((first == entry) && !xas->xa_sibs) return first; next = first; offset = xas->xa_offset; max = xas->xa_offset + xas->xa_sibs; if (node) { slot = &node->slots[offset]; if (xas->xa_sibs) xas_squash_marks(xas); } if (!entry) xas_init_marks(xas); for (;;) { /* * Must clear the marks before setting the entry to NULL, * otherwise xas_for_each_marked may find a NULL entry and * stop early. rcu_assign_pointer contains a release barrier * so the mark clearing will appear to happen before the * entry is set to NULL. */ rcu_assign_pointer(*slot, entry); if (xa_is_node(next) && (!node || node->shift)) xas_free_nodes(xas, xa_to_node(next)); if (!node) break; count += !next - !entry; values += !xa_is_value(first) - !value; if (entry) { if (offset == max) break; if (!xa_is_sibling(entry)) entry = xa_mk_sibling(xas->xa_offset); } else { if (offset == XA_CHUNK_MASK) break; } next = xa_entry_locked(xas->xa, node, ++offset); if (!xa_is_sibling(next)) { if (!entry && (offset > max)) break; first = next; } slot++; } update_node(xas, node, count, values); return first; } EXPORT_SYMBOL_GPL(xas_store); /** * xas_get_mark() - Returns the state of this mark. * @xas: XArray operation state. * @mark: Mark number. * * Return: true if the mark is set, false if the mark is clear or @xas * is in an error state. */ bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark) { if (xas_invalid(xas)) return false; if (!xas->xa_node) return xa_marked(xas->xa, mark); return node_get_mark(xas->xa_node, xas->xa_offset, mark); } EXPORT_SYMBOL_GPL(xas_get_mark); /** * xas_set_mark() - Sets the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Sets the specified mark on this entry, and walks up the tree setting it * on all the ancestor entries. Does nothing if @xas has not been walked to * an entry, or is in an error state. */ void xas_set_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (node_set_mark(node, offset, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (!xa_marked(xas->xa, mark)) xa_mark_set(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_set_mark); /** * xas_clear_mark() - Clears the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Clears the specified mark on this entry, and walks back to the head * attempting to clear it on all the ancestor entries. Does nothing if * @xas has not been walked to an entry, or is in an error state. */ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (!node_clear_mark(node, offset, mark)) return; if (node_any_mark(node, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (xa_marked(xas->xa, mark)) xa_mark_clear(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_clear_mark); /** * xas_init_marks() - Initialise all marks for the entry * @xas: Array operations state. * * Initialise all marks for the entry specified by @xas. If we're tracking * free entries with a mark, we need to set it on all entries. All other * marks are cleared. * * This implementation is not as efficient as it could be; we may walk * up the tree multiple times. */ void xas_init_marks(const struct xa_state *xas) { xa_mark_t mark = 0; for (;;) { if (xa_track_free(xas->xa) && mark == XA_FREE_MARK) xas_set_mark(xas, mark); else xas_clear_mark(xas, mark); if (mark == XA_MARK_MAX) break; mark_inc(mark); } } EXPORT_SYMBOL_GPL(xas_init_marks); #ifdef CONFIG_XARRAY_MULTI static unsigned int node_get_marks(struct xa_node *node, unsigned int offset) { unsigned int marks = 0; xa_mark_t mark = XA_MARK_0; for (;;) { if (node_get_mark(node, offset, mark)) marks |= 1 << (__force unsigned int)mark; if (mark == XA_MARK_MAX) break; mark_inc(mark); } return marks; } static void node_set_marks(struct xa_node *node, unsigned int offset, struct xa_node *child, unsigned int marks) { xa_mark_t mark = XA_MARK_0; for (;;) { if (marks & (1 << (__force unsigned int)mark)) { node_set_mark(node, offset, mark); if (child) node_mark_all(child, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } } /** * xas_split_alloc() - Allocate memory for splitting an entry. * @xas: XArray operation state. * @entry: New entry which will be stored in the array. * @order: New entry order. * @gfp: Memory allocation flags. * * This function should be called before calling xas_split(). * If necessary, it will allocate new nodes (and fill them with @entry) * to prepare for the upcoming split of an entry of @order size into * entries of the order stored in the @xas. * * Context: May sleep if @gfp flags permit. */ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int mask = xas->xa_sibs; /* XXX: no support for splitting really large entries yet */ if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; do { unsigned int i; void *sibling = NULL; struct xa_node *node; node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) goto nomem; node->array = xas->xa; for (i = 0; i < XA_CHUNK_SIZE; i++) { if ((i & mask) == 0) { RCU_INIT_POINTER(node->slots[i], entry); sibling = xa_mk_sibling(i); } else { RCU_INIT_POINTER(node->slots[i], sibling); } } RCU_INIT_POINTER(node->parent, xas->xa_alloc); xas->xa_alloc = node; } while (sibs-- > 0); return; nomem: xas_destroy(xas); xas_set_err(xas, -ENOMEM); } EXPORT_SYMBOL_GPL(xas_split_alloc); /** * xas_split() - Split a multi-index entry into smaller entries. * @xas: XArray operation state. * @entry: New entry to store in the array. * @order: New entry order. * * The value in the entry is copied to all the replacement entries. * * Context: Any context. The caller should hold the xa_lock. */ void xas_split(struct xa_state *xas, void *entry, unsigned int order) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int offset, marks; struct xa_node *node; void *curr = xas_load(xas); int values = 0; node = xas->xa_node; if (xas_top(node)) return; marks = node_get_marks(node, xas->xa_offset); offset = xas->xa_offset + sibs; do { if (xas->xa_shift < node->shift) { struct xa_node *child = xas->xa_alloc; xas->xa_alloc = rcu_dereference_raw(child->parent); child->shift = node->shift - XA_CHUNK_SHIFT; child->offset = offset; child->count = XA_CHUNK_SIZE; child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); node_set_marks(node, offset, child, marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) values--; } else { unsigned int canon = offset - xas->xa_sibs; node_set_marks(node, canon, NULL, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], xa_mk_sibling(canon)); values += (xa_is_value(entry) - xa_is_value(curr)) * (xas->xa_sibs + 1); } } while (offset-- > xas->xa_offset); node->nr_values += values; } EXPORT_SYMBOL_GPL(xas_split); #endif /** * xas_pause() - Pause a walk to drop a lock. * @xas: XArray operation state. * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @xas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call xas_pause(), the xa_for_each() * iterator may be more appropriate. * * Note that xas_pause() only works for forward iteration. If a user needs * to pause a reverse iteration, we will need a xas_pause_rev(). */ void xas_pause(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (xas_invalid(xas)) return; xas->xa_node = XAS_RESTART; if (node) { unsigned long offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } } EXPORT_SYMBOL_GPL(xas_pause); /* * __xas_prev() - Find the previous entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_prev() which handles all the complex cases * out of line. */ void *__xas_prev(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index--; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset--; while (xas->xa_offset == 255) { xas->xa_offset = xas->xa_node->offset - 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_prev); /* * __xas_next() - Find the next entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_next() which handles all the complex cases * out of line. */ void *__xas_next(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index++; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset++; while (xas->xa_offset == XA_CHUNK_SIZE) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_next); /** * xas_find() - Find the next present entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * * If the @xas has not yet been walked to an entry, return the entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we move to the * next entry. * * If no entry is found and the array is smaller than @max, the iterator * is set to the smallest index not yet in the array. This allows @xas * to be immediately passed to xas_store(). * * Return: The entry, if found, otherwise %NULL. */ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; if (xas->xa_index > max) return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; } else if (!xas->xa_node->shift && xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) { xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } xas_advance(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_node(entry)) { xas->xa_node = xa_to_node(entry); xas->xa_offset = 0; continue; } if (entry && !xa_is_sibling(entry)) return entry; xas_advance(xas); } if (!xas->xa_node) xas->xa_node = XAS_BOUNDS; return NULL; } EXPORT_SYMBOL_GPL(xas_find); /** * xas_find_marked() - Find the next marked entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark number to search for. * * If the @xas has not yet been walked to an entry, return the marked entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we return the * first marked entry with an index > xas.xa_index. * * If no marked entry is found and the array is smaller than @max, @xas is * set to the bounds state and xas->xa_index is set to the smallest index * not yet in the array. This allows @xas to be immediately passed to * xas_store(). * * If no entry is found before @max is reached, @xas is set to the restart * state. * * Return: The entry, if found, otherwise %NULL. */ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { bool advance = true; unsigned int offset; void *entry; if (xas_error(xas)) return NULL; if (xas->xa_index > max) goto max; if (!xas->xa_node) { xas->xa_index = 1; goto out; } else if (xas_top(xas->xa_node)) { advance = false; entry = xa_head(xas->xa); xas->xa_node = NULL; if (xas->xa_index > max_index(entry)) goto out; if (!xa_is_node(entry)) { if (xa_marked(xas->xa, mark)) return entry; xas->xa_index = 1; goto out; } xas->xa_node = xa_to_node(entry); xas->xa_offset = xas->xa_index >> xas->xa_node->shift; } while (xas->xa_index <= max) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) break; advance = false; continue; } if (!advance) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_sibling(entry)) { xas->xa_offset = xa_to_sibling(entry); xas_move_index(xas, xas->xa_offset); } } offset = xas_find_chunk(xas, advance, mark); if (offset > xas->xa_offset) { advance = false; xas_move_index(xas, offset); /* Mind the wrap */ if ((xas->xa_index - 1) >= max) goto max; xas->xa_offset = offset; if (offset == XA_CHUNK_SIZE) continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } out: if (xas->xa_index > max) goto max; return set_bounds(xas); max: xas->xa_node = XAS_RESTART; return NULL; } EXPORT_SYMBOL_GPL(xas_find_marked); /** * xas_find_conflict() - Find the next present entry in a range. * @xas: XArray operation state. * * The @xas describes both a range and a position within that range. * * Context: Any context. Expects xa_lock to be held. * Return: The next entry in the range covered by @xas or %NULL. */ void *xas_find_conflict(struct xa_state *xas) { void *curr; if (xas_error(xas)) return NULL; if (!xas->xa_node) return NULL; if (xas_top(xas->xa_node)) { curr = xas_start(xas); if (!curr) return NULL; while (xa_is_node(curr)) { struct xa_node *node = xa_to_node(curr); curr = xas_descend(xas, node); } if (curr) return curr; } if (xas->xa_node->shift > xas->xa_shift) return NULL; for (;;) { if (xas->xa_node->shift == xas->xa_shift) { if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs) break; } else if (xas->xa_offset == XA_CHUNK_MASK) { xas->xa_offset = xas->xa_node->offset; xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); if (!xas->xa_node) break; continue; } curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); if (xa_is_sibling(curr)) continue; while (xa_is_node(curr)) { xas->xa_node = xa_to_node(curr); xas->xa_offset = 0; curr = xa_entry_locked(xas->xa, xas->xa_node, 0); } if (curr) return curr; } xas->xa_offset -= xas->xa_sibs; return NULL; } EXPORT_SYMBOL_GPL(xas_find_conflict); /** * xa_load() - Load an entry from an XArray. * @xa: XArray. * @index: index into array. * * Context: Any context. Takes and releases the RCU lock. * Return: The entry at @index in @xa. */ void *xa_load(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); do { entry = xas_load(&xas); if (xa_is_zero(entry)) entry = NULL; } while (xas_retry(&xas, entry)); rcu_read_unlock(); return entry; } EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { if (xa_is_zero(curr)) return NULL; if (xas_error(xas)) curr = xas->xa_node; return curr; } /** * __xa_erase() - Erase this entry from the XArray while locked. * @xa: XArray. * @index: Index into array. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Expects xa_lock to be held on entry. * Return: The entry which used to be at this index. */ void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); return xas_result(&xas, xas_store(&xas, NULL)); } EXPORT_SYMBOL(__xa_erase); /** * xa_erase() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock. * Return: The entry which used to be at this index. */ void *xa_erase(struct xarray *xa, unsigned long index) { void *entry; xa_lock(xa); entry = __xa_erase(xa, index); xa_unlock(xa); return entry; } EXPORT_SYMBOL(xa_erase); /** * __xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; do { curr = xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_store); /** * xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from this index will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation * failed. */ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock(xa); return curr; } EXPORT_SYMBOL(xa_store); /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); do { curr = xas_load(&xas); if (curr == old) { xas_store(&xas, entry); if (xa_track_free(xa) && entry && !curr) xas_clear_mark(&xas, XA_FREE_MARK); } } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_cmpxchg); /** * __xa_insert() - Store this entry in the XArray if no entry is present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { curr = xas_load(&xas); if (!curr) { xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } else { xas_set_err(&xas, -EBUSY); } } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_insert); #ifdef CONFIG_XARRAY_MULTI static void xas_set_range(struct xa_state *xas, unsigned long first, unsigned long last) { unsigned int shift = 0; unsigned long sibs = last - first; unsigned int offset = XA_CHUNK_MASK; xas_set(xas, first); while ((first & XA_CHUNK_MASK) == 0) { if (sibs < XA_CHUNK_MASK) break; if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK)) break; shift += XA_CHUNK_SHIFT; if (offset == XA_CHUNK_MASK) offset = sibs & XA_CHUNK_MASK; sibs >>= XA_CHUNK_SHIFT; first >>= XA_CHUNK_SHIFT; } offset = first & XA_CHUNK_MASK; if (offset + sibs > XA_CHUNK_MASK) sibs = XA_CHUNK_MASK - offset; if ((((first + sibs + 1) << shift) - 1) > last) sibs -= 1; xas->xa_shift = shift; xas->xa_sibs = sibs; } /** * xa_store_range() - Store this entry at a range of indices in the XArray. * @xa: XArray. * @first: First index to affect. * @last: Last index to affect. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from any index between @first and @last, * inclusive will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Process context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in * an XArray, or xa_err(-ENOMEM) if memory allocation failed. */ void *xa_store_range(struct xarray *xa, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_internal(entry))) return XA_ERROR(-EINVAL); if (last < first) return XA_ERROR(-EINVAL); do { xas_lock(&xas); if (entry) { unsigned int order = BITS_PER_LONG; if (last + 1) order = __ffs(last + 1); xas_set_order(&xas, last, order); xas_create(&xas, true); if (xas_error(&xas)) goto unlock; } do { xas_set_range(&xas, first, last); xas_store(&xas, entry); if (xas_error(&xas)) goto unlock; first += xas_size(&xas); } while (first <= last); unlock: xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); return xas_result(&xas, NULL); } EXPORT_SYMBOL(xa_store_range); /** * xa_get_order() - Get the order of an entry. * @xa: XArray. * @index: Index of the entry. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xa_get_order(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; int order = 0; rcu_read_lock(); entry = xas_load(&xas); if (!entry) goto unlock; if (!xas.xa_node) goto unlock; for (;;) { unsigned int slot = xas.xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; if (!xa_is_sibling(xas.xa_node->slots[slot])) break; order++; } order += xas.xa_node->shift; unlock: rcu_read_unlock(); return order; } EXPORT_SYMBOL(xa_get_order); #endif /* CONFIG_XARRAY_MULTI */ /** * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @limit: Range for allocated ID. * @entry: New entry. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ int __xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (WARN_ON_ONCE(!xa_track_free(xa))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { xas.xa_index = limit.min; xas_find_marked(&xas, limit.max, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) xas_set_err(&xas, -EBUSY); else *id = xas.xa_index; xas_store(&xas, entry); xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_alloc); /** * __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { u32 min = limit.min; int ret; limit.min = max(min, *next); ret = __xa_alloc(xa, id, entry, limit, gfp); if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) { xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && limit.min > min) { limit.min = min; ret = __xa_alloc(xa, id, entry, limit, gfp); if (ret == 0) ret = 1; } if (ret >= 0) { *next = *id + 1; if (*next == 0) xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED; } return ret; } EXPORT_SYMBOL(__xa_alloc_cyclic); /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_set_mark(&xas, mark); } EXPORT_SYMBOL(__xa_set_mark); /** * __xa_clear_mark() - Clear this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_clear_mark(&xas, mark); } EXPORT_SYMBOL(__xa_clear_mark); /** * xa_get_mark() - Inquire whether this mark is set on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * This function uses the RCU read lock, so the result may be out of date * by the time it returns. If you need the result to be stable, use a lock. * * Context: Any context. Takes and releases the RCU lock. * Return: True if the entry at @index has this mark set, false if it doesn't. */ bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); entry = xas_start(&xas); while (xas_get_mark(&xas, mark)) { if (!xa_is_node(entry)) goto found; entry = xas_descend(&xas, xa_to_node(entry)); } rcu_read_unlock(); return false; found: rcu_read_unlock(); return true; } EXPORT_SYMBOL(xa_get_mark); /** * xa_set_mark() - Set this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Process context. Takes and releases the xa_lock. */ void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_set_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_set_mark); /** * xa_clear_mark() - Clear this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Clearing a mark always succeeds. * * Context: Process context. Takes and releases the xa_lock. */ void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_clear_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_clear_mark); /** * xa_find() - Search the XArray for an entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter, and has the lowest * index that is at least @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may not find * entries which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The entry, if found, otherwise %NULL. */ void *xa_find(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find); static bool xas_sibling(struct xa_state *xas) { struct xa_node *node = xas->xa_node; unsigned long mask; if (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !node) return false; mask = (XA_CHUNK_SIZE << node->shift) - 1; return (xas->xa_index & mask) > ((unsigned long)xas->xa_offset << node->shift); } /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter and has the lowest * index that is above @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may miss entries * which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The pointer, if found, otherwise %NULL. */ void *xa_find_after(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp + 1); void *entry; if (xas.xa_index == 0) return NULL; rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); if (xas_invalid(&xas)) break; if (xas_sibling(&xas)) continue; if (!xas_retry(&xas, entry)) break; } rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find_after); static unsigned int xas_extract_present(struct xa_state *xas, void **dst, unsigned long max, unsigned int n) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each(xas, entry, max) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, unsigned long max, unsigned int n, xa_mark_t mark) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each_marked(xas, entry, max, mark) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } /** * xa_extract() - Copy selected entries from the XArray into a normal array. * @xa: The source XArray to copy from. * @dst: The buffer to copy entries into. * @start: The first index in the XArray eligible to be selected. * @max: The last index in the XArray eligible to be selected. * @n: The maximum number of entries to copy. * @filter: Selection criterion. * * Copies up to @n entries that match @filter from the XArray. The * copied entries will have indices between @start and @max, inclusive. * * The @filter may be an XArray mark value, in which case entries which are * marked with that mark will be copied. It may also be %XA_PRESENT, in * which case all entries which are not %NULL will be copied. * * The entries returned may not represent a snapshot of the XArray at a * moment in time. For example, if another thread stores to index 5, then * index 10, calling xa_extract() may return the old contents of index 5 * and the new contents of index 10. Indices not modified while this * function is running will not be skipped. * * If you need stronger guarantees, holding the xa_lock across calls to this * function will prevent concurrent modification. * * Context: Any context. Takes and releases the RCU lock. * Return: The number of entries copied. */ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t filter) { XA_STATE(xas, xa, start); if (!n) return 0; if ((__force unsigned int)filter < XA_MAX_MARKS) return xas_extract_marked(&xas, dst, max, n, filter); return xas_extract_present(&xas, dst, max, n); } EXPORT_SYMBOL(xa_extract); /** * xa_delete_node() - Private interface for workingset code. * @node: Node to be removed from the tree. * @update: Function to call to update ancestor nodes. * * Context: xa_lock must be held on entry and will not be released. */ void xa_delete_node(struct xa_node *node, xa_update_node_t update) { struct xa_state xas = { .xa = node->array, .xa_index = (unsigned long)node->offset << (node->shift + XA_CHUNK_SHIFT), .xa_shift = node->shift + XA_CHUNK_SHIFT, .xa_offset = node->offset, .xa_node = xa_parent_locked(node->array, node), .xa_update = update, }; xas_store(&xas, NULL); } EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */ /** * xa_destroy() - Free all internal data structures. * @xa: XArray. * * After calling this function, the XArray is empty and has freed all memory * allocated for its internal data structures. You are responsible for * freeing the objects referenced by the XArray. * * Context: Any context. Takes and releases the xa_lock, interrupt-safe. */ void xa_destroy(struct xarray *xa) { XA_STATE(xas, xa, 0); unsigned long flags; void *entry; xas.xa_node = NULL; xas_lock_irqsave(&xas, flags); entry = xa_head_locked(xa); RCU_INIT_POINTER(xa->xa_head, NULL); xas_init_marks(&xas); if (xa_zero_busy(xa)) xa_mark_clear(xa, XA_FREE_MARK); /* lockdep checks we're still holding the lock in xas_free_nodes() */ if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry)); xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(xa_destroy); #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { unsigned i, j; if (!node) return; if ((unsigned long)node & 3) { pr_cont("node %px\n", node); return; } pr_cont("node %px %s %d parent %px shift %d count %d values %d " "array %px list %px %px marks", node, node->parent ? "offset" : "max", node->offset, node->parent, node->shift, node->count, node->nr_values, node->array, node->private_list.prev, node->private_list.next); for (i = 0; i < XA_MAX_MARKS; i++) for (j = 0; j < XA_MARK_LONGS; j++) pr_cont(" %lx", node->marks[i][j]); pr_cont("\n"); } void xa_dump_index(unsigned long index, unsigned int shift) { if (!shift) pr_info("%lu: ", index); else if (shift >= BITS_PER_LONG) pr_info("0-%lu: ", ~0UL); else pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1)); } void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) { if (!entry) return; xa_dump_index(index, shift); if (xa_is_node(entry)) { if (shift == 0) { pr_cont("%px\n", entry); } else { unsigned long i; struct xa_node *node = xa_to_node(entry); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) xa_dump_entry(node->slots[i], index + (i << node->shift), node->shift); } } else if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (!xa_is_internal(entry)) pr_cont("%px\n", entry); else if (xa_is_retry(entry)) pr_cont("retry (%ld)\n", xa_to_internal(entry)); else if (xa_is_sibling(entry)) pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else pr_cont("UNKNOWN ENTRY (%px)\n", entry); } void xa_dump(const struct xarray *xa) { void *entry = xa->xa_head; unsigned int shift = 0; pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, xa->xa_flags, xa_marked(xa, XA_MARK_0), xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2)); if (xa_is_node(entry)) shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; xa_dump_entry(entry, 0, shift); } #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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NETLINK_H #define __LINUX_NETLINK_H #include <linux/capability.h> #include <linux/skbuff.h> #include <linux/export.h> #include <net/scm.h> #include <uapi/linux/netlink.h> struct net; static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) { return (struct nlmsghdr *)skb->data; } enum netlink_skb_flags { NETLINK_SKB_DST = 0x8, /* Dst set in sendto or sendmsg */ }; struct netlink_skb_parms { struct scm_creds creds; /* Skb credentials */ __u32 portid; __u32 dst_group; __u32 flags; struct sock *sk; bool nsid_is_set; int nsid; }; #define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb)) #define NETLINK_CREDS(skb) (&NETLINK_CB((skb)).creds) void netlink_table_grab(void); void netlink_table_ungrab(void); #define NL_CFG_F_NONROOT_RECV (1 << 0) #define NL_CFG_F_NONROOT_SEND (1 << 1) /* optional Netlink kernel configuration parameters */ struct netlink_kernel_cfg { unsigned int groups; unsigned int flags; void (*input)(struct sk_buff *skb); struct mutex *cb_mutex; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); bool (*compare)(struct net *net, struct sock *sk); }; struct sock *__netlink_kernel_create(struct net *net, int unit, struct module *module, struct netlink_kernel_cfg *cfg); static inline struct sock * netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) { return __netlink_kernel_create(net, unit, THIS_MODULE, cfg); } /* this can be increased when necessary - don't expose to userland */ #define NETLINK_MAX_COOKIE_LEN 20 /** * struct netlink_ext_ack - netlink extended ACK report struct * @_msg: message string to report - don't access directly, use * %NL_SET_ERR_MSG * @bad_attr: attribute with error * @policy: policy for a bad attribute * @cookie: cookie data to return to userspace (for success) * @cookie_len: actual cookie data length */ struct netlink_ext_ack { const char *_msg; const struct nlattr *bad_attr; const struct nla_policy *policy; u8 cookie[NETLINK_MAX_COOKIE_LEN]; u8 cookie_len; }; /* Always use this macro, this allows later putting the * message into a separate section or such for things * like translation or listing all possible messages. * Currently string formatting is not supported (due * to the lack of an output buffer.) */ #define NL_SET_ERR_MSG(extack, msg) do { \ static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) \ __extack->_msg = __msg; \ } while (0) #define NL_SET_ERR_MSG_MOD(extack, msg) \ NL_SET_ERR_MSG((extack), KBUILD_MODNAME ": " msg) #define NL_SET_BAD_ATTR_POLICY(extack, attr, pol) do { \ if ((extack)) { \ (extack)->bad_attr = (attr); \ (extack)->policy = (pol); \ } \ } while (0) #define NL_SET_BAD_ATTR(extack, attr) NL_SET_BAD_ATTR_POLICY(extack, attr, NULL) #define NL_SET_ERR_MSG_ATTR_POL(extack, attr, pol, msg) do { \ static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) { \ __extack->_msg = __msg; \ __extack->bad_attr = (attr); \ __extack->policy = (pol); \ } \ } while (0) #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) \ NL_SET_ERR_MSG_ATTR_POL(extack, attr, NULL, msg) static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, u64 cookie) { u64 __cookie = cookie; if (!extack) return; memcpy(extack->cookie, &__cookie, sizeof(__cookie)); extack->cookie_len = sizeof(__cookie); } static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack, u32 cookie) { u32 __cookie = cookie; if (!extack) return; memcpy(extack->cookie, &__cookie, sizeof(__cookie)); extack->cookie_len = sizeof(__cookie); } void netlink_kernel_release(struct sock *sk); int __netlink_change_ngroups(struct sock *sk, unsigned int groups); int netlink_change_ngroups(struct sock *sk, unsigned int groups); void __netlink_clear_multicast_users(struct sock *sk, unsigned int group); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack); int netlink_has_listeners(struct sock *sk, unsigned int group); bool netlink_strict_get_check(struct sk_buff *skb); int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation, int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), void *filter_data); int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code); int netlink_register_notifier(struct notifier_block *nb); int netlink_unregister_notifier(struct notifier_block *nb); /* finegrained unicast helpers: */ struct sock *netlink_getsockbyfilp(struct file *filp); int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk); void netlink_detachskb(struct sock *sk, struct sk_buff *skb); int netlink_sendskb(struct sock *sk, struct sk_buff *skb); static inline struct sk_buff * netlink_skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *nskb; nskb = skb_clone(skb, gfp_mask); if (!nskb) return NULL; /* This is a large skb, set destructor callback to release head */ if (is_vmalloc_addr(skb->head)) nskb->destructor = skb->destructor; return nskb; } /* * skb should fit one page. This choice is good for headerless malloc. * But we should limit to 8K so that userspace does not have to * use enormous buffer sizes on recvmsg() calls just to avoid * MSG_TRUNC when PAGE_SIZE is very large. */ #if PAGE_SIZE < 8192UL #define NLMSG_GOODSIZE SKB_WITH_OVERHEAD(PAGE_SIZE) #else #define NLMSG_GOODSIZE SKB_WITH_OVERHEAD(8192UL) #endif #define NLMSG_DEFAULT_SIZE (NLMSG_GOODSIZE - NLMSG_HDRLEN) struct netlink_callback { struct sk_buff *skb; const struct nlmsghdr *nlh; int (*dump)(struct sk_buff * skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); void *data; /* the module that dump function belong to */ struct module *module; struct netlink_ext_ack *extack; u16 family; u16 answer_flags; u32 min_dump_alloc; unsigned int prev_seq, seq; bool strict_check; union { u8 ctx[48]; /* args is deprecated. Cast a struct over ctx instead * for proper type safety. */ long args[6]; }; }; struct netlink_notify { struct net *net; u32 portid; int protocol; }; struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags); struct netlink_dump_control { int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff *skb, struct netlink_callback *); int (*done)(struct netlink_callback *); void *data; struct module *module; u32 min_dump_alloc; }; int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control); static inline int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { if (!control->module) control->module = THIS_MODULE; return __netlink_dump_start(ssk, skb, nlh, control); } struct netlink_tap { struct net_device *dev; struct module *module; struct list_head list; }; int netlink_add_tap(struct netlink_tap *nt); int netlink_remove_tap(struct netlink_tap *nt); bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *ns, int cap); bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *ns, int cap); bool netlink_capable(const struct sk_buff *skb, int cap); bool netlink_net_capable(const struct sk_buff *skb, int cap); #endif /* __LINUX_NETLINK_H */
9 9 9 9 9 1 3 1 2 4 4 22 16 16 3 3 3 3 3 9 9 9 1 3 3 9 9 3 9 9 9 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 // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? */ int page_cluster; /* Protecting only lru_rotate.pvec which requires disabling interrupts */ struct lru_rotate { local_lock_t lock; struct pagevec pvec; }; static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * The following struct pagevec are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ struct lru_pvecs { local_lock_t lock; struct pagevec lru_add; struct pagevec lru_deactivate_file; struct pagevec lru_deactivate; struct pagevec lru_lazyfree; #ifdef CONFIG_SMP struct pagevec activate_page; #endif }; static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * This path almost never happens for VM activity - pages are normally * freed via pagevecs. But it gets used by networking. */ static void __page_cache_release(struct page *page) { if (PageLRU(page)) { pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; unsigned long flags; spin_lock_irqsave(&pgdat->lru_lock, flags); lruvec = mem_cgroup_page_lruvec(page, pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); spin_unlock_irqrestore(&pgdat->lru_lock, flags); } __ClearPageWaiters(page); } static void __put_single_page(struct page *page) { __page_cache_release(page); mem_cgroup_uncharge(page); free_unref_page(page); } static void __put_compound_page(struct page *page) { /* * __page_cache_release() is supposed to be called for thp, not for * hugetlb. This is because hugetlb page does never have PageLRU set * (it's never listed to any LRU lists) and no memcg routines should * be called for hugetlb (it has a separate hugetlb_cgroup.) */ if (!PageHuge(page)) __page_cache_release(page); destroy_compound_page(page); } void __put_page(struct page *page) { if (is_zone_device_page(page)) { put_dev_pagemap(page->pgmap); /* * The page belongs to the device that created pgmap. Do * not return it to page allocator. */ return; } if (unlikely(PageCompound(page))) __put_compound_page(page); else __put_single_page(page); } EXPORT_SYMBOL(__put_page); /** * put_pages_list() - release a list of pages * @pages: list of pages threaded on page->lru * * Release a list of pages which are strung together on page.lru. Currently * used by read_cache_pages() and related error recovery code. */ void put_pages_list(struct list_head *pages) { while (!list_empty(pages)) { struct page *victim; victim = lru_to_page(pages); list_del(&victim->lru); put_page(victim); } } EXPORT_SYMBOL(put_pages_list); /* * get_kernel_pages() - pin kernel pages in memory * @kiov: An array of struct kvec structures * @nr_segs: number of segments to pin * @write: pinning for read/write, currently ignored * @pages: array that receives pointers to the pages pinned. * Should be at least nr_segs long. * * 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. Each page returned must be released * with a put_page() call when it is finished with. */ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, struct page **pages) { int seg; for (seg = 0; seg < nr_segs; seg++) { if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) return seg; pages[seg] = kmap_to_page(kiov[seg].iov_base); get_page(pages[seg]); } return seg; } EXPORT_SYMBOL_GPL(get_kernel_pages); /* * get_kernel_page() - pin a kernel page in memory * @start: starting kernel address * @write: pinning for read/write, currently ignored * @pages: array that receives pointer to the page pinned. * Must be at least nr_segs long. * * Returns 1 if page is pinned. If the page was not pinned, returns * -errno. The page returned must be released with a put_page() call * when it is finished with. */ int get_kernel_page(unsigned long start, int write, struct page **pages) { const struct kvec kiov = { .iov_base = (void *)start, .iov_len = PAGE_SIZE }; return get_kernel_pages(&kiov, 1, write, pages); } EXPORT_SYMBOL_GPL(get_kernel_page); static void pagevec_lru_move_fn(struct pagevec *pvec, void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg), void *arg) { int i; struct pglist_data *pgdat = NULL; struct lruvec *lruvec; unsigned long flags = 0; for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; struct pglist_data *pagepgdat = page_pgdat(page); if (pagepgdat != pgdat) { if (pgdat) spin_unlock_irqrestore(&pgdat->lru_lock, flags); pgdat = pagepgdat; spin_lock_irqsave(&pgdat->lru_lock, flags); } lruvec = mem_cgroup_page_lruvec(page, pgdat); (*move_fn)(page, lruvec, arg); } if (pgdat) spin_unlock_irqrestore(&pgdat->lru_lock, flags); release_pages(pvec->pages, pvec->nr); pagevec_reinit(pvec); } static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec, void *arg) { int *pgmoved = arg; if (PageLRU(page) && !PageUnevictable(page)) { del_page_from_lru_list(page, lruvec, page_lru(page)); ClearPageActive(page); add_page_to_lru_list_tail(page, lruvec, page_lru(page)); (*pgmoved) += thp_nr_pages(page); } } /* * pagevec_move_tail() must be called with IRQ disabled. * Otherwise this may cause nasty races. */ static void pagevec_move_tail(struct pagevec *pvec) { int pgmoved = 0; pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved); __count_vm_events(PGROTATED, pgmoved); } /* * Writeback is about to end against a page which has been marked for immediate * reclaim. If it still appears to be reclaimable, move it to the tail of the * inactive list. */ void rotate_reclaimable_page(struct page *page) { if (!PageLocked(page) && !PageDirty(page) && !PageUnevictable(page) && PageLRU(page)) { struct pagevec *pvec; unsigned long flags; get_page(page); local_lock_irqsave(&lru_rotate.lock, flags); pvec = this_cpu_ptr(&lru_rotate.pvec); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_move_tail(pvec); local_unlock_irqrestore(&lru_rotate.lock, flags); } } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) { do { unsigned long lrusize; /* Record cost event */ if (file) lruvec->file_cost += nr_pages; else lruvec->anon_cost += nr_pages; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } } while ((lruvec = parent_lruvec(lruvec))); } void lru_note_cost_page(struct page *page) { lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)), page_is_file_lru(page), thp_nr_pages(page)); } static void __activate_page(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, lru); SetPageActive(page); lru += LRU_ACTIVE; add_page_to_lru_list(page, lruvec, lru); trace_mm_lru_activate(page); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } } #ifdef CONFIG_SMP static void activate_page_drain(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, __activate_page, NULL); } static bool need_activate_page_drain(int cpu) { return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0; } static void activate_page(struct page *page) { page = compound_head(page); if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.activate_page); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); local_unlock(&lru_pvecs.lock); } } #else static inline void activate_page_drain(int cpu) { } static void activate_page(struct page *page) { pg_data_t *pgdat = page_pgdat(page); page = compound_head(page); spin_lock_irq(&pgdat->lru_lock); __activate_page(page, mem_cgroup_page_lruvec(page, pgdat), NULL); spin_unlock_irq(&pgdat->lru_lock); } #endif static void __lru_cache_activate_page(struct page *page) { struct pagevec *pvec; int i; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); /* * Search backwards on the optimistic assumption that the page being * activated has just been added to this pagevec. Note that only * the local pagevec is examined as a !PageLRU page could be in the * process of being released, reclaimed, migrated or on a remote * pagevec that is currently being drained. Furthermore, marking * a remote pagevec's page PageActive potentially hits a race where * a page is marked PageActive just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = pagevec_count(pvec) - 1; i >= 0; i--) { struct page *pagevec_page = pvec->pages[i]; if (pagevec_page == page) { SetPageActive(page); break; } } local_unlock(&lru_pvecs.lock); } /* * Mark a page as having seen activity. * * inactive,unreferenced -> inactive,referenced * inactive,referenced -> active,unreferenced * active,unreferenced -> active,referenced * * When a newly allocated page is not yet visible, so safe for non-atomic ops, * __SetPageReferenced(page) may be substituted for mark_page_accessed(page). */ void mark_page_accessed(struct page *page) { page = compound_head(page); if (!PageReferenced(page)) { SetPageReferenced(page); } else if (PageUnevictable(page)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * evictable page accessed has no effect. */ } else if (!PageActive(page)) { /* * If the page is on the LRU, queue it for activation via * lru_pvecs.activate_page. Otherwise, assume the page is on a * pagevec, mark it active and it'll be moved to the active * LRU on the next drain. */ if (PageLRU(page)) activate_page(page); else __lru_cache_activate_page(page); ClearPageReferenced(page); workingset_activation(page); } if (page_is_idle(page)) clear_page_idle(page); } EXPORT_SYMBOL(mark_page_accessed); /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. * * Queue the page for addition to the LRU via pagevec. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * pagevec is drained. This gives a chance for the caller of lru_cache_add() * have the page added to the active list using mark_page_accessed(). */ void lru_cache_add(struct page *page) { struct pagevec *pvec; VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); get_page(page); local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); if (!pagevec_add(pvec, page) || PageCompound(page)) __pagevec_lru_add(pvec); local_unlock(&lru_pvecs.lock); } EXPORT_SYMBOL(lru_cache_add); /** * lru_cache_add_inactive_or_unevictable * @page: the page to be added to LRU * @vma: vma in which page is mapped for determining reclaimability * * Place @page on the inactive or unevictable LRU list, depending on its * evictability. */ void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma) { bool unevictable; VM_BUG_ON_PAGE(PageLRU(page), page); unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED; if (unlikely(unevictable) && !TestSetPageMlocked(page)) { int nr_pages = thp_nr_pages(page); /* * We use the irq-unsafe __mod_zone_page_stat because this * counter is not modified from interrupt context, and the pte * lock is held(spinlock), which implies preemption disabled. */ __mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } lru_cache_add(page); } /* * If the page can not be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the page isn't page_mapped and dirty/writeback, the page * could reclaim asap using PG_reclaim. * * 1. active, mapped page -> none * 2. active, dirty/writeback page -> inactive, head, PG_reclaim * 3. inactive, mapped page -> none * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, why it moves inactive's head, the VM expects the page would * be write it out by flusher threads as this is much more effective * than the single-page writeout from reclaim. */ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, void *arg) { int lru; bool active; int nr_pages = thp_nr_pages(page); if (!PageLRU(page)) return; if (PageUnevictable(page)) return; /* Some processes are using the page */ if (page_mapped(page)) return; active = PageActive(page); lru = page_lru_base_type(page); del_page_from_lru_list(page, lruvec, lru + active); ClearPageActive(page); ClearPageReferenced(page); if (PageWriteback(page) || PageDirty(page)) { /* * PG_reclaim could be raced with end_page_writeback * It can make readahead confusing. But race window * is _really_ small and it's non-critical problem. */ add_page_to_lru_list(page, lruvec, lru); SetPageReclaim(page); } else { /* * The page's writeback ends up during pagevec * We moves tha page into tail of inactive. */ add_page_to_lru_list_tail(page, lruvec, lru); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); ClearPageActive(page); ClearPageReferenced(page); add_page_to_lru_list(page, lruvec, lru); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { bool active = PageActive(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, LRU_INACTIVE_ANON + active); ClearPageActive(page); ClearPageReferenced(page); /* * Lazyfree pages are clean anonymous pages. They have * PG_swapbacked flag cleared, to distinguish them from normal * anonymous pages */ ClearPageSwapBacked(page); add_page_to_lru_list(page, lruvec, LRU_INACTIVE_FILE); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } } /* * Drain pages out of the cpu's pagevecs. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add, cpu); if (pagevec_count(pvec)) __pagevec_lru_add(pvec); pvec = &per_cpu(lru_rotate.pvec, cpu); /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(pagevec_count(pvec))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&lru_rotate.lock, flags); pagevec_move_tail(pvec); local_unlock_irqrestore(&lru_rotate.lock, flags); } pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); activate_page_drain(cpu); } /** * deactivate_file_page - forcefully deactivate a file page * @page: page to deactivate * * This function hints the VM that @page is a good reclaim candidate, * for example if its invalidation fails due to the page being dirty * or under writeback. */ void deactivate_file_page(struct page *page) { /* * In a workload with many unevictable page such as mprotect, * unevictable page deactivation for accelerating reclaim is pointless. */ if (PageUnevictable(page)) return; if (likely(get_page_unless_zero(page))) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); local_unlock(&lru_pvecs.lock); } } /* * deactivate_page - deactivate a page * @page: page to deactivate * * deactivate_page() moves @page to the inactive list if @page was on the active * list and was not an unevictable page. This is done to accelerate the reclaim * of @page. */ void deactivate_page(struct page *page) { if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); local_unlock(&lru_pvecs.lock); } } /** * mark_page_lazyfree - make an anon page lazyfree * @page: page to deactivate * * mark_page_lazyfree() moves @page to the inactive file list. * This is done to accelerate the reclaim of @page. */ void mark_page_lazyfree(struct page *page) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); local_unlock(&lru_pvecs.lock); } } void lru_add_drain(void) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&lru_pvecs.lock); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&lru_pvecs.lock); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_drain(); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ void lru_add_drain_all(void) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody trig