2 1 2 2 1 2 2 2 2 2 2 1 2 2 1 2 2 2 2 2 2 2 2 2 1 2 2 1 2 2 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 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 // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } /** * inode_io_list_del_locked - remove an inode from its bdi_writeback IO list * @inode: inode to be removed * @wb: bdi_writeback @inode is being removed from * * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and * clear %WB_has_dirty_io if all are empty afterwards. */ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_bh(&wb->work_lock); } static void finish_writeback_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(wb, work); spin_unlock_bh(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (page) { memcg_css = mem_cgroup_css_from_page(page); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } EXPORT_SYMBOL_GPL(__inode_attach_wb); /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct inode *inode; struct bdi_writeback *new_wb; struct rcu_head rcu_head; struct work_struct work; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; XA_STATE(xas, &mapping->i_pages, 0); struct page *page; bool switched = false; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING is visible under i_lock, the eviction path owns * the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & I_FREEING)) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to * pages actually under writeback. */ xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (PageDirty(page)) { dec_wb_stat(old_wb, WB_RECLAIMABLE); inc_wb_stat(new_wb, WB_RECLAIMABLE); } } xas_set(&xas, 0); xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { WARN_ON_ONCE(!PageWriteback(page)); dec_wb_stat(old_wb, WB_WRITEBACK); inc_wb_stat(new_wb, WB_WRITEBACK); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. The specific list * @inode was on is ignored and the inode is put on ->b_dirty which * is always correct including from ->b_dirty_time. The transfer * preserves @inode->dirtied_when ordering. */ if (!list_empty(&inode->i_io_list)) { struct inode *pos; inode_io_list_del_locked(inode, old_wb); inode->i_wb = new_wb; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (switched) { wb_wakeup(new_wb); wb_put(old_wb); } wb_put(new_wb); iput(inode); kfree(isw); atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) { struct inode_switch_wbs_context *isw = container_of(rcu_head, struct inode_switch_wbs_context, rcu_head); /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); queue_work(isw_wq, &isw->work); } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(sizeof(*isw), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING) || inode_to_wb(inode) == isw->new_wb) { spin_unlock(&inode->i_lock); goto out_free; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); isw->inode = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight32(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @page: page being written out * @bytes: number of bytes being written out * * @bytes from @page are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_page(page); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * inode_congested - test whether an inode is congested * @inode: inode to test for congestion (may be NULL) * @cong_bits: mask of WB_[a]sync_congested bits to test * * Tests whether @inode is congested. @cong_bits is the mask of congestion * bits to test and the return value is the mask of set bits. * * If cgroup writeback is enabled for @inode, the congestion state is * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg * associated with @inode is congested; otherwise, the root wb's congestion * state is used. * * @inode is allowed to be NULL as this function is often called on * mapping->host which is NULL for the swapper space. */ int inode_congested(struct inode *inode, int cong_bits) { /* * Once set, ->i_wb never becomes NULL while the inode is alive. * Start transaction iff ->i_wb is visible. */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; struct wb_lock_cookie lock_cookie = {}; bool congested; wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } EXPORT_SYMBOL_GPL(inode_congested); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); /* * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ wb_get(wb); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @nr: number of pages to write, 0 for best-effort dirty flushing * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * If @nr is zero, the caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. */ if (!nr) { unsigned long filepages, headroom, dirty, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &dirty, &writeback); nr = dirty * 10 / 8; } /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = nr; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(void) { if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); inode->i_state &= ~I_SYNC_QUEUED; } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Waiters must see I_SYNC cleared before being woken up */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } #define EXPIRE_DIRTY_ATIME 0x0001 /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; list_move(&inode->i_io_list, &tmp); moved++; spin_lock(&inode->i_lock); inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* Move inodes from one superblock together */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ static void __inode_wait_for_writeback(struct inode *inode) __releases(inode->i_lock) __acquires(inode->i_lock) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); wait_queue_head_t *wqh; wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); } } /* * Wait for writeback on an inode to complete. Caller must have inode pinned. */ void inode_wait_for_writeback(struct inode *inode) { spin_lock(&inode->i_lock); __inode_wait_for_writeback(inode); spin_unlock(&inode->i_lock); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { DEFINE_WAIT(wait); wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); int sleep; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); sleep = inode->i_state & I_SYNC; spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wqh, &wait); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * writeback is not making progress due to locked * buffers. Skip this inode for now. */ redirty_tail_locked(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); } } /* * Write out an inode and its dirty pages. Do not update the writeback list * linkage. That is left to the caller. The caller is also responsible for * setting I_SYNC flag and calling inode_sync_complete() to clear it. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Some filesystems may redirty the inode during the writeback * due to delalloc, clear dirty metadata flags right before * write_inode() */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty pages. Either the caller has an active reference * on the inode or the inode has I_WILL_FREE set. * * This function is designed to be called for writing back one inode which * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode() * and does more profound writeback list handling in writeback_sb_inodes(). */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { if (wbc->sync_mode != WB_SYNC_ALL) goto out; /* * It's a data-integrity sync. We must wait. Since callers hold * inode reference or inode has I_WILL_FREE set, it cannot go * away under us. */ __inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * Skip inode if it is clean and we have no outstanding writeback in * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this * function since flusher thread may be doing for example sync in * parallel and if we move the inode, it could get skipped. So here we * make sure inode is on some writeback list and leave it there unless * we have completely cleaned the inode. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If inode is clean, remove it from writeback lists. Otherwise don't * touch it. See comment above for explanation. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_io_list_del_locked(inode, wb); spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long wrote = 0; /* count both pages and inodes */ while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ spin_unlock(&inode->i_lock); requeue_io(inode, wb); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote += write_chunk - wbc.nr_to_write; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) wrote++; requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!trylock_super(sb)) { /* * trylock_super() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; /* * Kupdate and background works are special and we want to * include all inodes that need writing. Livelock avoidance is * handled by these works yielding to any other work so we are * safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); wb_update_bandwidth(wb, wb_start); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress) continue; /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) break; /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); spin_lock(&wb->list_lock); } spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_bh(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_bh(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(wb, work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); current->flags &= ~PF_SWAPWRITE; } /* * Start writeback of `nr_pages' pages on this bdi. If `nr_pages' is zero, * write back the whole world. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ if (blk_needs_flush_plug(current)) blk_schedule_flush_plug(current); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); return 0; } __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) mod_delayed_work(system_wq, &dirtytime_work, 0); return ret; } /** * __mark_inode_dirty - internal function * * @inode: inode to mark * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) * * Mark an inode as dirty. Callers should use mark_inode_dirty or * mark_inode_dirty_sync. * * Put the inode on the super block's dirty list. * * CAREFUL! We mark it dirty unconditionally, but move it onto the * dirty list only if it is hashed or if it refers to a blockdev. * If it was not hashed, it will never be added to the dirty list * even if it is later hashed, as it will have been marked dirty already. * * In short, make sure you hash any inodes _before_ you start marking * them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime; trace_writeback_mark_inode_dirty(inode, flags); /* * Don't do this for I_DIRTY_PAGES - that doesn't actually * dirty the inode itself */ if (flags & (I_DIRTY_INODE | I_DIRTY_TIME)) { trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags); trace_writeback_dirty_inode(inode, flags); } if (flags & I_DIRTY_INODE) flags &= ~I_DIRTY_TIME; dirtytime = flags & I_DIRTY_TIME; /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if (((inode->i_state & flags) == flags) || (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; spin_lock(&inode->i_lock); if (dirtytime && (inode->i_state & I_DIRTY_INODE)) goto out_unlock_inode; if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); if (flags & I_DIRTY_INODE) inode->i_state &= ~I_DIRTY_TIME; inode->i_state |= flags; /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock_inode; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock_inode; } if (inode->i_state & I_FREEING) goto out_unlock_inode; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct bdi_writeback *wb; struct list_head *dirty_list; bool wakeup_bdi = false; wb = locked_inode_to_wb_and_lock_list(inode); WARN((wb->bdi->capabilities & BDI_CAP_WRITEBACK) && !test_bit(WB_registered, &wb->state), "bdi-%s not registered\n", bdi_dev_name(wb->bdi)); inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); spin_unlock(&wb->list_lock); trace_writeback_dirty_inode_enqueue(inode); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); return; } } out_unlock_inode: spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode - write an inode and its pages to disk. * @inode: the inode to sync * @wbc: controls the writeback mode * * sync_inode() will write an inode and its pages to disk. It will also * correctly update the inode on its superblock's dirty inode lists and will * update inode->i_state. * * The caller must have a ref on the inode. */ int sync_inode(struct inode *inode, struct writeback_control *wbc) { return writeback_single_inode(inode, wbc); } EXPORT_SYMBOL(sync_inode); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return sync_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata);
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> */ /* * mballoc.c contains the multiblocks allocation routines */ #include "ext4_jbd2.h" #include "mballoc.h" #include <linux/log2.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/backing-dev.h> #include <trace/events/ext4.h> /* * MUSTDO: * - test ext4_ext_search_left() and ext4_ext_search_right() * - search for metadata in few groups * * TODO v4: * - normalization should take into account whether file is still open * - discard preallocations if no free space left (policy?) * - don't normalize tails * - quota * - reservation for superuser * * TODO v3: * - bitmap read-ahead (proposed by Oleg Drokin aka green) * - track min/max extents in each group for better group selection * - mb_mark_used() may allocate chunk right after splitting buddy * - tree of groups sorted by number of free blocks * - error handling */ /* * The allocation request involve request for multiple number of blocks * near to the goal(block) value specified. * * During initialization phase of the allocator we decide to use the * group preallocation or inode preallocation depending on the size of * the file. The size of the file could be the resulting file size we * would have after allocation, or the current file size, which ever * is larger. If the size is less than sbi->s_mb_stream_request we * select to use the group preallocation. The default value of * s_mb_stream_request is 16 blocks. This can also be tuned via * /sys/fs/ext4/<partition>/mb_stream_req. The value is represented in * terms of number of blocks. * * The main motivation for having small file use group preallocation is to * ensure that we have small files closer together on the disk. * * First stage the allocator looks at the inode prealloc list, * ext4_inode_info->i_prealloc_list, which contains list of prealloc * spaces for this particular inode. The inode prealloc space is * represented as: * * pa_lstart -> the logical start block for this prealloc space * pa_pstart -> the physical start block for this prealloc space * pa_len -> length for this prealloc space (in clusters) * pa_free -> free space available in this prealloc space (in clusters) * * The inode preallocation space is used looking at the _logical_ start * block. If only the logical file block falls within the range of prealloc * space we will consume the particular prealloc space. This makes sure that * we have contiguous physical blocks representing the file blocks * * The important thing to be noted in case of inode prealloc space is that * we don't modify the values associated to inode prealloc space except * pa_free. * * If we are not able to find blocks in the inode prealloc space and if we * have the group allocation flag set then we look at the locality group * prealloc space. These are per CPU prealloc list represented as * * ext4_sb_info.s_locality_groups[smp_processor_id()] * * The reason for having a per cpu locality group is to reduce the contention * between CPUs. It is possible to get scheduled at this point. * * The locality group prealloc space is used looking at whether we have * enough free space (pa_free) within the prealloc space. * * If we can't allocate blocks via inode prealloc or/and locality group * prealloc then we look at the buddy cache. The buddy cache is represented * by ext4_sb_info.s_buddy_cache (struct inode) whose file offset gets * mapped to the buddy and bitmap information regarding different * groups. The buddy information is attached to buddy cache inode so that * we can access them through the page cache. The information regarding * each group is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are stored in the * inode as: * * { page } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. So for each group we * take up 2 blocks. A page can contain blocks_per_page (PAGE_SIZE / * blocksize) blocks. So it can have information regarding groups_per_page * which is blocks_per_page/2 * * The buddy cache inode is not stored on disk. The inode is thrown * away when the filesystem is unmounted. * * We look for count number of blocks in the buddy cache. If we were able * to locate that many free blocks we return with additional information * regarding rest of the contiguous physical block available * * Before allocating blocks via buddy cache we normalize the request * blocks. This ensure we ask for more blocks that we needed. The extra * blocks that we get after allocation is added to the respective prealloc * list. In case of inode preallocation we follow a list of heuristics * based on file size. This can be found in ext4_mb_normalize_request. If * we are doing a group prealloc we try to normalize the request to * sbi->s_mb_group_prealloc. The default value of s_mb_group_prealloc is * dependent on the cluster size; for non-bigalloc file systems, it is * 512 blocks. This can be tuned via * /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in * terms of number of blocks. If we have mounted the file system with -O * stripe=<value> option the group prealloc request is normalized to the * smallest multiple of the stripe value (sbi->s_stripe) which is * greater than the default mb_group_prealloc. * * The regular allocator (using the buddy cache) supports a few tunables. * * /sys/fs/ext4/<partition>/mb_min_to_scan * /sys/fs/ext4/<partition>/mb_max_to_scan * /sys/fs/ext4/<partition>/mb_order2_req * * The regular allocator uses buddy scan only if the request len is power of * 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The * value of s_mb_order2_reqs can be tuned via * /sys/fs/ext4/<partition>/mb_order2_req. If the request len is equal to * stripe size (sbi->s_stripe), we try to search for contiguous block in * stripe size. This should result in better allocation on RAID setups. If * not, we search in the specific group using bitmap for best extents. The * tunable min_to_scan and max_to_scan control the behaviour here. * min_to_scan indicate how long the mballoc __must__ look for a best * extent and max_to_scan indicates how long the mballoc __can__ look for a * best extent in the found extents. Searching for the blocks starts with * the group specified as the goal value in allocation context via * ac_g_ex. Each group is first checked based on the criteria whether it * can be used for allocation. ext4_mb_good_group explains how the groups are * checked. * * Both the prealloc space are getting populated as above. So for the first * request we will hit the buddy cache which will result in this prealloc * space getting filled. The prealloc space is then later used for the * subsequent request. */ /* * mballoc operates on the following data: * - on-disk bitmap * - in-core buddy (actually includes buddy and bitmap) * - preallocation descriptors (PAs) * * there are two types of preallocations: * - inode * assiged to specific inode and can be used for this inode only. * it describes part of inode's space preallocated to specific * physical blocks. any block from that preallocated can be used * independent. the descriptor just tracks number of blocks left * unused. so, before taking some block from descriptor, one must * make sure corresponded logical block isn't allocated yet. this * also means that freeing any block within descriptor's range * must discard all preallocated blocks. * - locality group * assigned to specific locality group which does not translate to * permanent set of inodes: inode can join and leave group. space * from this type of preallocation can be used for any inode. thus * it's consumed from the beginning to the end. * * relation between them can be expressed as: * in-core buddy = on-disk bitmap + preallocation descriptors * * this mean blocks mballoc considers used are: * - allocated blocks (persistent) * - preallocated blocks (non-persistent) * * consistency in mballoc world means that at any time a block is either * free or used in ALL structures. notice: "any time" should not be read * literally -- time is discrete and delimited by locks. * * to keep it simple, we don't use block numbers, instead we count number of * blocks: how many blocks marked used/free in on-disk bitmap, buddy and PA. * * all operations can be expressed as: * - init buddy: buddy = on-disk + PAs * - new PA: buddy += N; PA = N * - use inode PA: on-disk += N; PA -= N * - discard inode PA buddy -= on-disk - PA; PA = 0 * - use locality group PA on-disk += N; PA -= N * - discard locality group PA buddy -= PA; PA = 0 * note: 'buddy -= on-disk - PA' is used to show that on-disk bitmap * is used in real operation because we can't know actual used * bits from PA, only from on-disk bitmap * * if we follow this strict logic, then all operations above should be atomic. * given some of them can block, we'd have to use something like semaphores * killing performance on high-end SMP hardware. let's try to relax it using * the following knowledge: * 1) if buddy is referenced, it's already initialized * 2) while block is used in buddy and the buddy is referenced, * nobody can re-allocate that block * 3) we work on bitmaps and '+' actually means 'set bits'. if on-disk has * bit set and PA claims same block, it's OK. IOW, one can set bit in * on-disk bitmap if buddy has same bit set or/and PA covers corresponded * block * * so, now we're building a concurrency table: * - init buddy vs. * - new PA * blocks for PA are allocated in the buddy, buddy must be referenced * until PA is linked to allocation group to avoid concurrent buddy init * - use inode PA * we need to make sure that either on-disk bitmap or PA has uptodate data * given (3) we care that PA-=N operation doesn't interfere with init * - discard inode PA * the simplest way would be to have buddy initialized by the discard * - use locality group PA * again PA-=N must be serialized with init * - discard locality group PA * the simplest way would be to have buddy initialized by the discard * - new PA vs. * - use inode PA * i_data_sem serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * some mutex should serialize them * - discard locality group PA * discard process must wait until PA isn't used by another process * - use inode PA * - use inode PA * i_data_sem or another mutex should serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * nothing wrong here -- they're different PAs covering different blocks * - discard locality group PA * discard process must wait until PA isn't used by another process * * now we're ready to make few consequences: * - PA is referenced and while it is no discard is possible * - PA is referenced until block isn't marked in on-disk bitmap * - PA changes only after on-disk bitmap * - discard must not compete with init. either init is done before * any discard or they're serialized somehow * - buddy init as sum of on-disk bitmap and PAs is done atomically * * a special case when we've used PA to emptiness. no need to modify buddy * in this case, but we should care about concurrent init * */ /* * Logic in few words: * * - allocation: * load group * find blocks * mark bits in on-disk bitmap * release group * * - use preallocation: * find proper PA (per-inode or group) * load group * mark bits in on-disk bitmap * release group * release PA * * - free: * load group * mark bits in on-disk bitmap * release group * * - discard preallocations in group: * mark PAs deleted * move them onto local list * load on-disk bitmap * load group * remove PA from object (inode or locality group) * mark free blocks in-core * * - discard inode's preallocations: */ /* * Locking rules * * Locks: * - bitlock on a group (group) * - object (inode/locality) (object) * - per-pa lock (pa) * * Paths: * - new pa * object * group * * - find and use pa: * pa * * - release consumed pa: * pa * group * object * * - generate in-core bitmap: * group * pa * * - discard all for given object (inode, locality group): * object * pa * group * * - discard all for given group: * group * pa * group * object * */ static struct kmem_cache *ext4_pspace_cachep; static struct kmem_cache *ext4_ac_cachep; static struct kmem_cache *ext4_free_data_cachep; /* We create slab caches for groupinfo data structures based on the * superblock block size. There will be one per mounted filesystem for * each unique s_blocksize_bits */ #define NR_GRPINFO_CACHES 8 static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES]; static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = { "ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k", "ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k", "ext4_groupinfo_64k", "ext4_groupinfo_128k" }; static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); /* * The algorithm using this percpu seq counter goes below: * 1. We sample the percpu discard_pa_seq counter before trying for block * allocation in ext4_mb_new_blocks(). * 2. We increment this percpu discard_pa_seq counter when we either allocate * or free these blocks i.e. while marking those blocks as used/free in * mb_mark_used()/mb_free_blocks(). * 3. We also increment this percpu seq counter when we successfully identify * that the bb_prealloc_list is not empty and hence proceed for discarding * of those PAs inside ext4_mb_discard_group_preallocations(). * * Now to make sure that the regular fast path of block allocation is not * affected, as a small optimization we only sample the percpu seq counter * on that cpu. Only when the block allocation fails and when freed blocks * found were 0, that is when we sample percpu seq counter for all cpus using * below function ext4_get_discard_pa_seq_sum(). This happens after making * sure that all the PAs on grp->bb_prealloc_list got freed or if it's empty. */ static DEFINE_PER_CPU(u64, discard_pa_seq); static inline u64 ext4_get_discard_pa_seq_sum(void) { int __cpu; u64 __seq = 0; for_each_possible_cpu(__cpu) __seq += per_cpu(discard_pa_seq, __cpu); return __seq; } static inline void *mb_correct_addr_and_bit(int *bit, void *addr) { #if BITS_PER_LONG == 64 *bit += ((unsigned long) addr & 7UL) << 3; addr = (void *) ((unsigned long) addr & ~7UL); #elif BITS_PER_LONG == 32 *bit += ((unsigned long) addr & 3UL) << 3; addr = (void *) ((unsigned long) addr & ~3UL); #else #error "how many bits you are?!" #endif return addr; } static inline int mb_test_bit(int bit, void *addr) { /* * ext4_test_bit on architecture like powerpc * needs unsigned long aligned address */ addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_bit(bit, addr); } static inline void mb_set_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_set_bit(bit, addr); } static inline void mb_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_clear_bit(bit, addr); } static inline int mb_test_and_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_and_clear_bit(bit, addr); } static inline int mb_find_next_zero_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_zero_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static inline int mb_find_next_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max) { char *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(max == NULL); if (order > e4b->bd_blkbits + 1) { *max = 0; return NULL; } /* at order 0 we see each particular block */ if (order == 0) { *max = 1 << (e4b->bd_blkbits + 3); return e4b->bd_bitmap; } bb = e4b->bd_buddy + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order]; *max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order]; return bb; } #ifdef DOUBLE_CHECK static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int i; struct super_block *sb = e4b->bd_sb; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); for (i = 0; i < count; i++) { if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) { ext4_fsblk_t blocknr; blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(EXT4_SB(sb), first + i); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing block already freed " "(bit %u)", first + i); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_clear_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { int i; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); for (i = 0; i < count; i++) { BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap)); mb_set_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; if (memcmp(e4b->bd_info->bb_bitmap, bitmap, e4b->bd_sb->s_blocksize)) { unsigned char *b1, *b2; int i; b1 = (unsigned char *) e4b->bd_info->bb_bitmap; b2 = (unsigned char *) bitmap; for (i = 0; i < e4b->bd_sb->s_blocksize; i++) { if (b1[i] != b2[i]) { ext4_msg(e4b->bd_sb, KERN_ERR, "corruption in group %u " "at byte %u(%u): %x in copy != %x " "on disk/prealloc", e4b->bd_group, i, i * 8, b1[i], b2[i]); BUG(); } } } } static void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { struct buffer_head *bh; grp->bb_bitmap = kmalloc(sb->s_blocksize, GFP_NOFS); if (!grp->bb_bitmap) return; bh = ext4_read_block_bitmap(sb, group); if (IS_ERR_OR_NULL(bh)) { kfree(grp->bb_bitmap); grp->bb_bitmap = NULL; return; } memcpy(grp->bb_bitmap, bh->b_data, sb->s_blocksize); put_bh(bh); } static void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { kfree(grp->bb_bitmap); } #else static inline void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { return; } static inline void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { return; } static inline void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { return; } #endif #ifdef AGGRESSIVE_CHECK #define MB_CHECK_ASSERT(assert) \ do { \ if (!(assert)) { \ printk(KERN_EMERG \ "Assertion failure in %s() at %s:%d: \"%s\"\n", \ function, file, line, # assert); \ BUG(); \ } \ } while (0) static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, const char *function, int line) { struct super_block *sb = e4b->bd_sb; int order = e4b->bd_blkbits + 1; int max; int max2; int i; int j; int k; int count; struct ext4_group_info *grp; int fragments = 0; int fstart; struct list_head *cur; void *buddy; void *buddy2; if (e4b->bd_info->bb_check_counter++ % 10) return 0; while (order > 1) { buddy = mb_find_buddy(e4b, order, &max); MB_CHECK_ASSERT(buddy); buddy2 = mb_find_buddy(e4b, order - 1, &max2); MB_CHECK_ASSERT(buddy2); MB_CHECK_ASSERT(buddy != buddy2); MB_CHECK_ASSERT(max * 2 == max2); count = 0; for (i = 0; i < max; i++) { if (mb_test_bit(i, buddy)) { /* only single bit in buddy2 may be 1 */ if (!mb_test_bit(i << 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit((i<<1)+1, buddy2)); } else if (!mb_test_bit((i << 1) + 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit(i << 1, buddy2)); } continue; } /* both bits in buddy2 must be 1 */ MB_CHECK_ASSERT(mb_test_bit(i << 1, buddy2)); MB_CHECK_ASSERT(mb_test_bit((i << 1) + 1, buddy2)); for (j = 0; j < (1 << order); j++) { k = (i * (1 << order)) + j; MB_CHECK_ASSERT( !mb_test_bit(k, e4b->bd_bitmap)); } count++; } MB_CHECK_ASSERT(e4b->bd_info->bb_counters[order] == count); order--; } fstart = -1; buddy = mb_find_buddy(e4b, 0, &max); for (i = 0; i < max; i++) { if (!mb_test_bit(i, buddy)) { MB_CHECK_ASSERT(i >= e4b->bd_info->bb_first_free); if (fstart == -1) { fragments++; fstart = i; } continue; } fstart = -1; /* check used bits only */ for (j = 0; j < e4b->bd_blkbits + 1; j++) { buddy2 = mb_find_buddy(e4b, j, &max2); k = i >> j; MB_CHECK_ASSERT(k < max2); MB_CHECK_ASSERT(mb_test_bit(k, buddy2)); } } MB_CHECK_ASSERT(!EXT4_MB_GRP_NEED_INIT(e4b->bd_info)); MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments); grp = ext4_get_group_info(sb, e4b->bd_group); list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &k); MB_CHECK_ASSERT(groupnr == e4b->bd_group); for (i = 0; i < pa->pa_len; i++) MB_CHECK_ASSERT(mb_test_bit(k + i, buddy)); } return 0; } #undef MB_CHECK_ASSERT #define mb_check_buddy(e4b) __mb_check_buddy(e4b, \ __FILE__, __func__, __LINE__) #else #define mb_check_buddy(e4b) #endif /* * Divide blocks started from @first with length @len into * smaller chunks with power of 2 blocks. * Clear the bits in bitmap which the blocks of the chunk(s) covered, * then increase bb_counters[] for corresponded chunk size. */ static void ext4_mb_mark_free_simple(struct super_block *sb, void *buddy, ext4_grpblk_t first, ext4_grpblk_t len, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t min; ext4_grpblk_t max; ext4_grpblk_t chunk; unsigned int border; BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb)); border = 2 << sb->s_blocksize_bits; while (len > 0) { /* find how many blocks can be covered since this position */ max = ffs(first | border) - 1; /* find how many blocks of power 2 we need to mark */ min = fls(len) - 1; if (max < min) min = max; chunk = 1 << min; /* mark multiblock chunks only */ grp->bb_counters[min]++; if (min > 0) mb_clear_bit(first >> min, buddy + sbi->s_mb_offsets[min]); len -= chunk; first += chunk; } } /* * Cache the order of the largest free extent we have available in this block * group. */ static void mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) { int i; int bits; grp->bb_largest_free_order = -1; /* uninit */ bits = sb->s_blocksize_bits + 1; for (i = bits; i >= 0; i--) { if (grp->bb_counters[i] > 0) { grp->bb_largest_free_order = i; break; } } } static noinline_for_stack void ext4_mb_generate_buddy(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_grpblk_t first; ext4_grpblk_t len; unsigned free = 0; unsigned fragments = 0; unsigned long long period = get_cycles(); /* initialize buddy from bitmap which is aggregation * of on-disk bitmap and preallocations */ i = mb_find_next_zero_bit(bitmap, max, 0); grp->bb_first_free = i; while (i < max) { fragments++; first = i; i = mb_find_next_bit(bitmap, max, i); len = i - first; free += len; if (len > 1) ext4_mb_mark_free_simple(sb, buddy, first, len, grp); else grp->bb_counters[0]++; if (i < max) i = mb_find_next_zero_bit(bitmap, max, i); } grp->bb_fragments = fragments; if (free != grp->bb_free) { ext4_grp_locked_error(sb, group, 0, 0, "block bitmap and bg descriptor " "inconsistent: %u vs %u free clusters", free, grp->bb_free); /* * If we intend to continue, we consider group descriptor * corrupt and update bb_free using bitmap value */ grp->bb_free = free; ext4_mark_group_bitmap_corrupted(sb, group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; spin_lock(&sbi->s_bal_lock); sbi->s_mb_buddies_generated++; sbi->s_mb_generation_time += period; spin_unlock(&sbi->s_bal_lock); } static void mb_regenerate_buddy(struct ext4_buddy *e4b) { int count; int order = 1; void *buddy; while ((buddy = mb_find_buddy(e4b, order++, &count))) { ext4_set_bits(buddy, 0, count); } e4b->bd_info->bb_fragments = 0; memset(e4b->bd_info->bb_counters, 0, sizeof(*e4b->bd_info->bb_counters) * (e4b->bd_sb->s_blocksize_bits + 2)); ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, e4b->bd_bitmap, e4b->bd_group); } /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are * stored in the inode as * * { page } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. * So for each group we take up 2 blocks. A page can * contain blocks_per_page (PAGE_SIZE / blocksize) blocks. * So it can have information regarding groups_per_page which * is blocks_per_page/2 * * Locking note: This routine takes the block group lock of all groups * for this page; do not hold this lock when calling this routine! */ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) { ext4_group_t ngroups; int blocksize; int blocks_per_page; int groups_per_page; int err = 0; int i; ext4_group_t first_group, group; int first_block; struct super_block *sb; struct buffer_head *bhs; struct buffer_head **bh = NULL; struct inode *inode; char *data; char *bitmap; struct ext4_group_info *grinfo; inode = page->mapping->host; sb = inode->i_sb; ngroups = ext4_get_groups_count(sb); blocksize = i_blocksize(inode); blocks_per_page = PAGE_SIZE / blocksize; mb_debug(sb, "init page %lu\n", page->index); groups_per_page = blocks_per_page >> 1; if (groups_per_page == 0) groups_per_page = 1; /* allocate buffer_heads to read bitmaps */ if (groups_per_page > 1) { i = sizeof(struct buffer_head *) * groups_per_page; bh = kzalloc(i, gfp); if (bh == NULL) { err = -ENOMEM; goto out; } } else bh = &bhs; first_group = page->index * blocks_per_page / 2; /* read all groups the page covers into the cache */ for (i = 0, group = first_group; i < groups_per_page; i++, group++) { if (group >= ngroups) break; grinfo = ext4_get_group_info(sb, group); /* * If page is uptodate then we came here after online resize * which added some new uninitialized group info structs, so * we must skip all initialized uptodate buddies on the page, * which may be currently in use by an allocating task. */ if (PageUptodate(page) && !EXT4_MB_GRP_NEED_INIT(grinfo)) { bh[i] = NULL; continue; } bh[i] = ext4_read_block_bitmap_nowait(sb, group, false); if (IS_ERR(bh[i])) { err = PTR_ERR(bh[i]); bh[i] = NULL; goto out; } mb_debug(sb, "read bitmap for group %u\n", group); } /* wait for I/O completion */ for (i = 0, group = first_group; i < groups_per_page; i++, group++) { int err2; if (!bh[i]) continue; err2 = ext4_wait_block_bitmap(sb, group, bh[i]); if (!err) err = err2; } first_block = page->index * blocks_per_page; for (i = 0; i < blocks_per_page; i++) { group = (first_block + i) >> 1; if (group >= ngroups) break; if (!bh[group - first_group]) /* skip initialized uptodate buddy */ continue; if (!buffer_verified(bh[group - first_group])) /* Skip faulty bitmaps */ continue; err = 0; /* * data carry information regarding this * particular group in the format specified * above * */ data = page_address(page) + (i * blocksize); bitmap = bh[group - first_group]->b_data; /* * We place the buddy block and bitmap block * close together */ if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); mb_debug(sb, "put buddy for group %u in page %lu/%x\n", group, page->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); grinfo = ext4_get_group_info(sb, group); grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * (sb->s_blocksize_bits+2)); /* * incore got set to the group block bitmap below */ ext4_lock_group(sb, group); /* init the buddy */ memset(data, 0xff, blocksize); ext4_mb_generate_buddy(sb, data, incore, group); ext4_unlock_group(sb, group); incore = NULL; } else { /* this is block of bitmap */ BUG_ON(incore != NULL); mb_debug(sb, "put bitmap for group %u in page %lu/%x\n", group, page->index, i * blocksize); trace_ext4_mb_bitmap_load(sb, group); /* see comments in ext4_mb_put_pa() */ ext4_lock_group(sb, group); memcpy(data, bitmap, blocksize); /* mark all preallocated blks used in in-core bitmap */ ext4_mb_generate_from_pa(sb, data, group); ext4_mb_generate_from_freelist(sb, data, group); ext4_unlock_group(sb, group); /* set incore so that the buddy information can be * generated using this */ incore = data; } } SetPageUptodate(page); out: if (bh) { for (i = 0; i < groups_per_page; i++) brelse(bh[i]); if (bh != &bhs) kfree(bh); } return err; } /* * Lock the buddy and bitmap pages. This make sure other parallel init_group * on the same buddy page doesn't happen whild holding the buddy page lock. * Return locked buddy and bitmap pages on e4b struct. If buddy and bitmap * are on the same page e4b->bd_buddy_page is NULL and return value is 0. */ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { struct inode *inode = EXT4_SB(sb)->s_buddy_cache; int block, pnum, poff; int blocks_per_page; struct page *page; e4b->bd_buddy_page = NULL; e4b->bd_bitmap_page = NULL; blocks_per_page = PAGE_SIZE / sb->s_blocksize; /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = block / blocks_per_page; poff = block % blocks_per_page; page = find_or_create_page(inode->i_mapping, pnum, gfp); if (!page) return -ENOMEM; BUG_ON(page->mapping != inode->i_mapping); e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); if (blocks_per_page >= 2) { /* buddy and bitmap are on the same page */ return 0; } block++; pnum = block / blocks_per_page; page = find_or_create_page(inode->i_mapping, pnum, gfp); if (!page) return -ENOMEM; BUG_ON(page->mapping != inode->i_mapping); e4b->bd_buddy_page = page; return 0; } static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_page) { unlock_page(e4b->bd_bitmap_page); put_page(e4b->bd_bitmap_page); } if (e4b->bd_buddy_page) { unlock_page(e4b->bd_buddy_page); put_page(e4b->bd_buddy_page); } } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this page; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) { struct ext4_group_info *this_grp; struct ext4_buddy e4b; struct page *page; int ret = 0; might_sleep(); mb_debug(sb, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); /* * This ensures that we don't reinit the buddy cache * page which map to the group from which we are already * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. * The call to ext4_mb_get_buddy_page_lock will mark the * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { /* * somebody initialized the group * return without doing anything */ goto err; } page = e4b.bd_bitmap_page; ret = ext4_mb_init_cache(page, NULL, gfp); if (ret) goto err; if (!PageUptodate(page)) { ret = -EIO; goto err; } if (e4b.bd_buddy_page == NULL) { /* * If both the bitmap and buddy are in * the same page we don't need to force * init the buddy */ ret = 0; goto err; } /* init buddy cache */ page = e4b.bd_buddy_page; ret = ext4_mb_init_cache(page, e4b.bd_bitmap, gfp); if (ret) goto err; if (!PageUptodate(page)) { ret = -EIO; goto err; } err: ext4_mb_put_buddy_page_lock(&e4b); return ret; } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this page; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { int blocks_per_page; int block; int pnum; int poff; struct page *page; int ret; struct ext4_group_info *grp; struct ext4_sb_info *sbi = EXT4_SB(sb); struct inode *inode = sbi->s_buddy_cache; might_sleep(); mb_debug(sb, "load group %u\n", group); blocks_per_page = PAGE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); e4b->bd_blkbits = sb->s_blocksize_bits; e4b->bd_info = grp; e4b->bd_sb = sb; e4b->bd_group = group; e4b->bd_buddy_page = NULL; e4b->bd_bitmap_page = NULL; if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { /* * we need full data about the group * to make a good selection */ ret = ext4_mb_init_group(sb, group, gfp); if (ret) return ret; } /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = block / blocks_per_page; poff = block % blocks_per_page; /* we could use find_or_create_page(), but it locks page * what we'd like to avoid in fast path ... */ page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) /* * drop the page reference and try * to get the page with lock. If we * are not uptodate that implies * somebody just created the page but * is yet to initialize the same. So * wait for it to initialize. */ put_page(page); page = find_or_create_page(inode->i_mapping, pnum, gfp); if (page) { BUG_ON(page->mapping != inode->i_mapping); if (!PageUptodate(page)) { ret = ext4_mb_init_cache(page, NULL, gfp); if (ret) { unlock_page(page); goto err; } mb_cmp_bitmaps(e4b, page_address(page) + (poff * sb->s_blocksize)); } unlock_page(page); } } if (page == NULL) { ret = -ENOMEM; goto err; } if (!PageUptodate(page)) { ret = -EIO; goto err; } /* Pages marked accessed already */ e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) put_page(page); page = find_or_create_page(inode->i_mapping, pnum, gfp); if (page) { BUG_ON(page->mapping != inode->i_mapping); if (!PageUptodate(page)) { ret = ext4_mb_init_cache(page, e4b->bd_bitmap, gfp); if (ret) { unlock_page(page); goto err; } } unlock_page(page); } } if (page == NULL) { ret = -ENOMEM; goto err; } if (!PageUptodate(page)) { ret = -EIO; goto err; } /* Pages marked accessed already */ e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); return 0; err: if (page) put_page(page); if (e4b->bd_bitmap_page) put_page(e4b->bd_bitmap_page); if (e4b->bd_buddy_page) put_page(e4b->bd_buddy_page); e4b->bd_buddy = NULL; e4b->bd_bitmap = NULL; return ret; } static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b) { return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS); } static void ext4_mb_unload_buddy(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_page) put_page(e4b->bd_bitmap_page); if (e4b->bd_buddy_page) put_page(e4b->bd_buddy_page); } static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) { int order = 1; int bb_incr = 1 << (e4b->bd_blkbits - 1); void *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(block >= (1 << (e4b->bd_blkbits + 3))); bb = e4b->bd_buddy; while (order <= e4b->bd_blkbits + 1) { block = block >> 1; if (!mb_test_bit(block, bb)) { /* this block is part of buddy of order 'order' */ return order; } bb += bb_incr; bb_incr >>= 1; order++; } return 0; } static void mb_clear_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); *addr = 0; cur += 32; continue; } mb_clear_bit(cur, bm); cur++; } } /* clear bits in given range * will return first found zero bit if any, -1 otherwise */ static int mb_test_and_clear_bits(void *bm, int cur, int len) { __u32 *addr; int zero_bit = -1; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); if (*addr != (__u32)(-1) && zero_bit == -1) zero_bit = cur + mb_find_next_zero_bit(addr, 32, 0); *addr = 0; cur += 32; continue; } if (!mb_test_and_clear_bit(cur, bm) && zero_bit == -1) zero_bit = cur; cur++; } return zero_bit; } void ext4_set_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: set whole word at once */ addr = bm + (cur >> 3); *addr = 0xffffffff; cur += 32; continue; } mb_set_bit(cur, bm); cur++; } } static inline int mb_buddy_adjust_border(int* bit, void* bitmap, int side) { if (mb_test_bit(*bit + side, bitmap)) { mb_clear_bit(*bit, bitmap); (*bit) -= side; return 1; } else { (*bit) += side; mb_set_bit(*bit, bitmap); return -1; } } static void mb_buddy_mark_free(struct ext4_buddy *e4b, int first, int last) { int max; int order = 1; void *buddy = mb_find_buddy(e4b, order, &max); while (buddy) { void *buddy2; /* Bits in range [first; last] are known to be set since * corresponding blocks were allocated. Bits in range * (first; last) will stay set because they form buddies on * upper layer. We just deal with borders if they don't * align with upper layer and then go up. * Releasing entire group is all about clearing * single bit of highest order buddy. */ /* Example: * --------------------------------- * | 1 | 1 | 1 | 1 | * --------------------------------- * | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | * --------------------------------- * 0 1 2 3 4 5 6 7 * \_____________________/ * * Neither [1] nor [6] is aligned to above layer. * Left neighbour [0] is free, so mark it busy, * decrease bb_counters and extend range to * [0; 6] * Right neighbour [7] is busy. It can't be coaleasced with [6], so * mark [6] free, increase bb_counters and shrink range to * [0; 5]. * Then shift range to [0; 2], go up and do the same. */ if (first & 1) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&first, buddy, -1); if (!(last & 1)) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&last, buddy, 1); if (first > last) break; order++; if (first == last || !(buddy2 = mb_find_buddy(e4b, order, &max))) { mb_clear_bits(buddy, first, last - first + 1); e4b->bd_info->bb_counters[order - 1] += last - first + 1; break; } first >>= 1; last >>= 1; buddy = buddy2; } } static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int left_is_free = 0; int right_is_free = 0; int block; int last = first + count - 1; struct super_block *sb = e4b->bd_sb; if (WARN_ON(count == 0)) return; BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); /* Don't bother if the block group is corrupt. */ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) return; mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free += count; if (first < e4b->bd_info->bb_first_free) e4b->bd_info->bb_first_free = first; /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ if (first != 0) left_is_free = !mb_test_bit(first - 1, e4b->bd_bitmap); block = mb_test_and_clear_bits(e4b->bd_bitmap, first, count); if (last + 1 < EXT4_SB(sb)->s_mb_maxs[0]) right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap); if (unlikely(block != -1)) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing already freed block (bit %u); block bitmap corrupt.", block); ext4_mark_group_bitmap_corrupted( sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_regenerate_buddy(e4b); goto done; } /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; else if (!left_is_free && !right_is_free) e4b->bd_info->bb_fragments++; /* buddy[0] == bd_bitmap is a special case, so handle * it right away and let mb_buddy_mark_free stay free of * zero order checks. * Check if neighbours are to be coaleasced, * adjust bitmap bb_counters and borders appropriately. */ if (first & 1) { first += !left_is_free; e4b->bd_info->bb_counters[0] += left_is_free ? -1 : 1; } if (!(last & 1)) { last -= !right_is_free; e4b->bd_info->bb_counters[0] += right_is_free ? -1 : 1; } if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); done: mb_set_largest_free_order(sb, e4b->bd_info); mb_check_buddy(e4b); } static int mb_find_extent(struct ext4_buddy *e4b, int block, int needed, struct ext4_free_extent *ex) { int next = block; int max, order; void *buddy; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); BUG_ON(ex == NULL); buddy = mb_find_buddy(e4b, 0, &max); BUG_ON(buddy == NULL); BUG_ON(block >= max); if (mb_test_bit(block, buddy)) { ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; return 0; } /* find actual order */ order = mb_find_order_for_block(e4b, block); block = block >> order; ex->fe_len = 1 << order; ex->fe_start = block << order; ex->fe_group = e4b->bd_group; /* calc difference from given start */ next = next - ex->fe_start; ex->fe_len -= next; ex->fe_start += next; while (needed > ex->fe_len && mb_find_buddy(e4b, order, &max)) { if (block + 1 >= max) break; next = (block + 1) * (1 << order); if (mb_test_bit(next, e4b->bd_bitmap)) break; order = mb_find_order_for_block(e4b, next); block = next >> order; ex->fe_len += 1 << order; } if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) { /* Should never happen! (but apparently sometimes does?!?) */ WARN_ON(1); ext4_grp_locked_error(e4b->bd_sb, e4b->bd_group, 0, 0, "corruption or bug in mb_find_extent " "block=%d, order=%d needed=%d ex=%u/%d/%d@%u", block, order, needed, ex->fe_group, ex->fe_start, ex->fe_len, ex->fe_logical); ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; } return ex->fe_len; } static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) { int ord; int mlen = 0; int max = 0; int cur; int start = ex->fe_start; int len = ex->fe_len; unsigned ret = 0; int len0 = len; void *buddy; BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); mb_check_buddy(e4b); mb_mark_used_double(e4b, start, len); this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free -= len; if (e4b->bd_info->bb_first_free == start) e4b->bd_info->bb_first_free += len; /* let's maintain fragments counter */ if (start != 0) mlen = !mb_test_bit(start - 1, e4b->bd_bitmap); if (start + len < EXT4_SB(e4b->bd_sb)->s_mb_maxs[0]) max = !mb_test_bit(start + len, e4b->bd_bitmap); if (mlen && max) e4b->bd_info->bb_fragments++; else if (!mlen && !max) e4b->bd_info->bb_fragments--; /* let's maintain buddy itself */ while (len) { ord = mb_find_order_for_block(e4b, start); if (((start >> ord) << ord) == start && len >= (1 << ord)) { /* the whole chunk may be allocated at once! */ mlen = 1 << ord; buddy = mb_find_buddy(e4b, ord, &max); BUG_ON((start >> ord) >= max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; start += mlen; len -= mlen; BUG_ON(len < 0); continue; } /* store for history */ if (ret == 0) ret = len | (ord << 16); /* we have to split large buddy */ BUG_ON(ord <= 0); buddy = mb_find_buddy(e4b, ord, &max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; ord--; cur = (start >> ord) & ~1U; buddy = mb_find_buddy(e4b, ord, &max); mb_clear_bit(cur, buddy); mb_clear_bit(cur + 1, buddy); e4b->bd_info->bb_counters[ord]++; e4b->bd_info->bb_counters[ord]++; } mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info); ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0); mb_check_buddy(e4b); return ret; } /* * Must be called under group lock! */ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int ret; BUG_ON(ac->ac_b_ex.fe_group != e4b->bd_group); BUG_ON(ac->ac_status == AC_STATUS_FOUND); ac->ac_b_ex.fe_len = min(ac->ac_b_ex.fe_len, ac->ac_g_ex.fe_len); ac->ac_b_ex.fe_logical = ac->ac_g_ex.fe_logical; ret = mb_mark_used(e4b, &ac->ac_b_ex); /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ ac->ac_f_ex = ac->ac_b_ex; ac->ac_status = AC_STATUS_FOUND; ac->ac_tail = ret & 0xffff; ac->ac_buddy = ret >> 16; /* * take the page reference. We want the page to be pinned * so that we don't get a ext4_mb_init_cache_call for this * group until we update the bitmap. That would mean we * double allocate blocks. The reference is dropped * in ext4_mb_release_context */ ac->ac_bitmap_page = e4b->bd_bitmap_page; get_page(ac->ac_bitmap_page); ac->ac_buddy_page = e4b->bd_buddy_page; get_page(ac->ac_buddy_page); /* store last allocated for subsequent stream allocation */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { spin_lock(&sbi->s_md_lock); sbi->s_mb_last_group = ac->ac_f_ex.fe_group; sbi->s_mb_last_start = ac->ac_f_ex.fe_start; spin_unlock(&sbi->s_md_lock); } /* * As we've just preallocated more space than * user requested originally, we store allocated * space in a special descriptor. */ if (ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len) ext4_mb_new_preallocation(ac); } static void ext4_mb_check_limits(struct ext4_allocation_context *ac, struct ext4_buddy *e4b, int finish_group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; struct ext4_free_extent ex; int max; if (ac->ac_status == AC_STATUS_FOUND) return; /* * We don't want to scan for a whole year */ if (ac->ac_found > sbi->s_mb_max_to_scan && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { ac->ac_status = AC_STATUS_BREAK; return; } /* * Haven't found good chunk so far, let's continue */ if (bex->fe_len < gex->fe_len) return; if ((finish_group || ac->ac_found > sbi->s_mb_min_to_scan) && bex->fe_group == e4b->bd_group) { /* recheck chunk's availability - we don't know * when it was found (within this lock-unlock * period or not) */ max = mb_find_extent(e4b, bex->fe_start, gex->fe_len, &ex); if (max >= gex->fe_len) { ext4_mb_use_best_found(ac, e4b); return; } } } /* * The routine checks whether found extent is good enough. If it is, * then the extent gets marked used and flag is set to the context * to stop scanning. Otherwise, the extent is compared with the * previous found extent and if new one is better, then it's stored * in the context. Later, the best found extent will be used, if * mballoc can't find good enough extent. * * FIXME: real allocation policy is to be designed yet! */ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, struct ext4_free_extent *ex, struct ext4_buddy *e4b) { struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; BUG_ON(ex->fe_len <= 0); BUG_ON(ex->fe_len > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ex->fe_start >= EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ac->ac_status != AC_STATUS_CONTINUE); ac->ac_found++; /* * The special case - take what you catch first */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_FIRST)) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * Let's check whether the chuck is good enough */ if (ex->fe_len == gex->fe_len) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * If this is first found extent, just store it in the context */ if (bex->fe_len == 0) { *bex = *ex; return; } /* * If new found extent is better, store it in the context */ if (bex->fe_len < gex->fe_len) { /* if the request isn't satisfied, any found extent * larger than previous best one is better */ if (ex->fe_len > bex->fe_len) *bex = *ex; } else if (ex->fe_len > gex->fe_len) { /* if the request is satisfied, then we try to find * an extent that still satisfy the request, but is * smaller than previous one */ if (ex->fe_len < bex->fe_len) *bex = *ex; } ext4_mb_check_limits(ac, e4b, 0); } static noinline_for_stack int ext4_mb_try_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_free_extent ex = ac->ac_b_ex; ext4_group_t group = ex.fe_group; int max; int err; BUG_ON(ex.fe_len <= 0); err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return err; ext4_lock_group(ac->ac_sb, group); max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); return 0; } static noinline_for_stack int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { ext4_group_t group = ac->ac_g_ex.fe_group; int max; int err; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL)) return 0; if (grp->bb_free == 0) return 0; err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return err; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) { ext4_mb_unload_buddy(e4b); return 0; } ext4_lock_group(ac->ac_sb, group); max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) { ext4_fsblk_t start; start = ext4_group_first_block_no(ac->ac_sb, e4b->bd_group) + ex.fe_start; /* use do_div to get remainder (would be 64-bit modulo) */ if (do_div(start, sbi->s_stripe) == 0) { ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } } else if (max >= ac->ac_g_ex.fe_len) { BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } else if (max > 0 && (ac->ac_flags & EXT4_MB_HINT_MERGE)) { /* Sometimes, caller may want to merge even small * number of blocks to an existing extent */ BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); return 0; } /* * The routine scans buddy structures (not bitmap!) from given order * to max order and tries to find big enough chunk to satisfy the req */ static noinline_for_stack void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_group_info *grp = e4b->bd_info; void *buddy; int i; int k; int max; BUG_ON(ac->ac_2order <= 0); for (i = ac->ac_2order; i <= sb->s_blocksize_bits + 1; i++) { if (grp->bb_counters[i] == 0) continue; buddy = mb_find_buddy(e4b, i, &max); BUG_ON(buddy == NULL); k = mb_find_next_zero_bit(buddy, max, 0); if (k >= max) { ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, "%d free clusters of order %d. But found 0", grp->bb_counters[i], i); ext4_mark_group_bitmap_corrupted(ac->ac_sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); break; } ac->ac_found++; ac->ac_b_ex.fe_len = 1 << i; ac->ac_b_ex.fe_start = k << i; ac->ac_b_ex.fe_group = e4b->bd_group; ext4_mb_use_best_found(ac, e4b); BUG_ON(ac->ac_f_ex.fe_len != ac->ac_g_ex.fe_len); if (EXT4_SB(sb)->s_mb_stats) atomic_inc(&EXT4_SB(sb)->s_bal_2orders); break; } } /* * The routine scans the group and measures all found extents. * In order to optimize scanning, caller must pass number of * free blocks in the group, so the routine can know upper limit. */ static noinline_for_stack void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; int i; int free; free = e4b->bd_info->bb_free; if (WARN_ON(free <= 0)) return; i = e4b->bd_info->bb_first_free; while (free && ac->ac_status == AC_STATUS_CONTINUE) { i = mb_find_next_zero_bit(bitmap, EXT4_CLUSTERS_PER_GROUP(sb), i); if (i >= EXT4_CLUSTERS_PER_GROUP(sb)) { /* * IF we have corrupt bitmap, we won't find any * free blocks even though group info says we * have free blocks */ ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But bitmap says 0", free); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); break; } mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex); if (WARN_ON(ex.fe_len <= 0)) break; if (free < ex.fe_len) { ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But got %d blocks", free, ex.fe_len); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); /* * The number of free blocks differs. This mostly * indicate that the bitmap is corrupt. So exit * without claiming the space. */ break; } ex.fe_logical = 0xDEADC0DE; /* debug value */ ext4_mb_measure_extent(ac, &ex, e4b); i += ex.fe_len; free -= ex.fe_len; } ext4_mb_check_limits(ac, e4b, 1); } /* * This is a special case for storages like raid5 * we try to find stripe-aligned chunks for stripe-size-multiple requests */ static noinline_for_stack void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; ext4_fsblk_t first_group_block; ext4_fsblk_t a; ext4_grpblk_t i; int max; BUG_ON(sbi->s_stripe == 0); /* find first stripe-aligned block in group */ first_group_block = ext4_group_first_block_no(sb, e4b->bd_group); a = first_group_block + sbi->s_stripe - 1; do_div(a, sbi->s_stripe); i = (a * sbi->s_stripe) - first_group_block; while (i < EXT4_CLUSTERS_PER_GROUP(sb)) { if (!mb_test_bit(i, bitmap)) { max = mb_find_extent(e4b, i, sbi->s_stripe, &ex); if (max >= sbi->s_stripe) { ac->ac_found++; ex.fe_logical = 0xDEADF00D; /* debug value */ ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); break; } } i += sbi->s_stripe; } } /* * This is also called BEFORE we load the buddy bitmap. * Returns either 1 or 0 indicating that the group is either suitable * for the allocation or not. */ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ext4_group_t group, int cr) { ext4_grpblk_t free, fragments; int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb)); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); BUG_ON(cr < 0 || cr >= 4); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; free = grp->bb_free; if (free == 0) return false; fragments = grp->bb_fragments; if (fragments == 0) return false; switch (cr) { case 0: BUG_ON(ac->ac_2order == 0); /* Avoid using the first bg of a flexgroup for data files */ if ((ac->ac_flags & EXT4_MB_HINT_DATA) && (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) && ((group % flex_size) == 0)) return false; if (free < ac->ac_g_ex.fe_len) return false; if (ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) return true; if (grp->bb_largest_free_order < ac->ac_2order) return false; return true; case 1: if ((free / fragments) >= ac->ac_g_ex.fe_len) return true; break; case 2: if (free >= ac->ac_g_ex.fe_len) return true; break; case 3: return true; default: BUG(); } return false; } /* * This could return negative error code if something goes wrong * during ext4_mb_init_group(). This should not be called with * ext4_lock_group() held. */ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_group_t group, int cr) { struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK; ext4_grpblk_t free; int ret = 0; if (should_lock) ext4_lock_group(sb, group); free = grp->bb_free; if (free == 0) goto out; if (cr <= 2 && free < ac->ac_g_ex.fe_len) goto out; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) goto out; if (should_lock) ext4_unlock_group(sb, group); /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; /* cr=0/1 is a very optimistic search to find large * good chunks almost for free. If buddy data is not * ready, then this optimization makes no sense. But * we never skip the first block group in a flex_bg, * since this gets used for metadata block allocation, * and we want to make sure we locate metadata blocks * in the first block group in the flex_bg if possible. */ if (cr < 2 && (!sbi->s_log_groups_per_flex || ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) return 0; ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) return ret; } if (should_lock) ext4_lock_group(sb, group); ret = ext4_mb_good_group(ac, group, cr); out: if (should_lock) ext4_unlock_group(sb, group); return ret; } /* * Start prefetching @nr block bitmaps starting at @group. * Return the next group which needs to be prefetched. */ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, unsigned int nr, int *cnt) { ext4_group_t ngroups = ext4_get_groups_count(sb); struct buffer_head *bh; struct blk_plug plug; blk_start_plug(&plug); while (nr-- > 0) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); struct ext4_group_info *grp = ext4_get_group_info(sb, group); /* * Prefetch block groups with free blocks; but don't * bother if it is marked uninitialized on disk, since * it won't require I/O to read. Also only try to * prefetch once, so we avoid getblk() call, which can * be expensive. */ if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { bh = ext4_read_block_bitmap_nowait(sb, group, true); if (bh && !IS_ERR(bh)) { if (!buffer_uptodate(bh) && cnt) (*cnt)++; brelse(bh); } } if (++group >= ngroups) group = 0; } blk_finish_plug(&plug); return group; } /* * Prefetching reads the block bitmap into the buffer cache; but we * need to make sure that the buddy bitmap in the page cache has been * initialized. Note that ext4_mb_init_group() will block if the I/O * is not yet completed, or indeed if it was not initiated by * ext4_mb_prefetch did not start the I/O. * * TODO: We should actually kick off the buddy bitmap setup in a work * queue when the buffer I/O is completed, so that we don't block * waiting for the block allocation bitmap read to finish when * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator(). */ void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, unsigned int nr) { while (nr-- > 0) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); struct ext4_group_info *grp = ext4_get_group_info(sb, group); if (!group) group = ext4_get_groups_count(sb); group--; grp = ext4_get_group_info(sb, group); if (EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { if (ext4_mb_init_group(sb, group, GFP_NOFS)) break; } } } static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t prefetch_grp = 0, ngroups, group, i; int cr = -1; int err = 0, first_err = 0; unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; struct super_block *sb; struct ext4_buddy e4b; int lost; sb = ac->ac_sb; sbi = EXT4_SB(sb); ngroups = ext4_get_groups_count(sb); /* non-extent files are limited to low blocks/groups */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))) ngroups = sbi->s_blockfile_groups; BUG_ON(ac->ac_status == AC_STATUS_FOUND); /* first, try the goal */ err = ext4_mb_find_by_goal(ac, &e4b); if (err || ac->ac_status == AC_STATUS_FOUND) goto out; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) goto out; /* * ac->ac_2order is set only if the fe_len is a power of 2 * if ac->ac_2order is set we also set criteria to 0 so that we * try exact allocation using buddy. */ i = fls(ac->ac_g_ex.fe_len); ac->ac_2order = 0; /* * We search using buddy data only if the order of the request * is greater than equal to the sbi_s_mb_order2_reqs * You can tune it via /sys/fs/ext4/<partition>/mb_order2_req * We also support searching for power-of-two requests only for * requests upto maximum buddy size we have constructed. */ if (i >= sbi->s_mb_order2_reqs && i <= sb->s_blocksize_bits + 2) { /* * This should tell if fe_len is exactly power of 2 */ if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0) ac->ac_2order = array_index_nospec(i - 1, sb->s_blocksize_bits + 2); } /* if stream allocation is enabled, use global goal */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { /* TBD: may be hot point */ spin_lock(&sbi->s_md_lock); ac->ac_g_ex.fe_group = sbi->s_mb_last_group; ac->ac_g_ex.fe_start = sbi->s_mb_last_start; spin_unlock(&sbi->s_md_lock); } /* Let's just scan groups to find more-less suitable blocks */ cr = ac->ac_2order ? 0 : 1; /* * cr == 0 try to get exact allocation, * cr == 3 try to get anything */ repeat: for (; cr < 4 && ac->ac_status == AC_STATUS_CONTINUE; cr++) { ac->ac_criteria = cr; /* * searching for the right group start * from the goal value specified */ group = ac->ac_g_ex.fe_group; prefetch_grp = group; for (i = 0; i < ngroups; group++, i++) { int ret = 0; cond_resched(); /* * Artificially restricted ngroups for non-extent * files makes group > ngroups possible on first loop. */ if (group >= ngroups) group = 0; /* * Batch reads of the block allocation bitmaps * to get multiple READs in flight; limit * prefetching at cr=0/1, otherwise mballoc can * spend a lot of time loading imperfect groups */ if ((prefetch_grp == group) && (cr > 1 || prefetch_ios < sbi->s_mb_prefetch_limit)) { unsigned int curr_ios = prefetch_ios; nr = sbi->s_mb_prefetch; if (ext4_has_feature_flex_bg(sb)) { nr = 1 << sbi->s_log_groups_per_flex; nr -= group & (nr - 1); nr = min(nr, sbi->s_mb_prefetch); } prefetch_grp = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); if (prefetch_ios == curr_ios) nr = 0; } /* This now checks without needing the buddy page */ ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { if (!first_err) first_err = ret; continue; } err = ext4_mb_load_buddy(sb, group, &e4b); if (err) goto out; ext4_lock_group(sb, group); /* * We need to check again after locking the * block group */ ret = ext4_mb_good_group(ac, group, cr); if (ret == 0) { ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); continue; } ac->ac_groups_scanned++; if (cr == 0) ext4_mb_simple_scan_group(ac, &e4b); else if (cr == 1 && sbi->s_stripe && !(ac->ac_g_ex.fe_len % sbi->s_stripe)) ext4_mb_scan_aligned(ac, &e4b); else ext4_mb_complex_scan_group(ac, &e4b); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); if (ac->ac_status != AC_STATUS_CONTINUE) break; } } if (ac->ac_b_ex.fe_len > 0 && ac->ac_status != AC_STATUS_FOUND && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { /* * We've been searching too long. Let's try to allocate * the best chunk we've found so far */ ext4_mb_try_best_found(ac, &e4b); if (ac->ac_status != AC_STATUS_FOUND) { /* * Someone more lucky has already allocated it. * The only thing we can do is just take first * found block(s) */ lost = atomic_inc_return(&sbi->s_mb_lost_chunks); mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n", ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, lost); ac->ac_b_ex.fe_group = 0; ac->ac_b_ex.fe_start = 0; ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; ac->ac_flags |= EXT4_MB_HINT_FIRST; cr = 3; goto repeat; } } out: if (!err && ac->ac_status != AC_STATUS_FOUND && first_err) err = first_err; mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n", ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status, ac->ac_flags, cr, err); if (nr) ext4_mb_prefetch_fini(sb, prefetch_grp, nr); return err; } static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = PDE_DATA(file_inode(seq->file)); ext4_group_t group; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = PDE_DATA(file_inode(seq->file)); ext4_group_t group; ++*pos; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) { struct super_block *sb = PDE_DATA(file_inode(seq->file)); ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i; int err, buddy_loaded = 0; struct ext4_buddy e4b; struct ext4_group_info *grinfo; unsigned char blocksize_bits = min_t(unsigned char, sb->s_blocksize_bits, EXT4_MAX_BLOCK_LOG_SIZE); struct sg { struct ext4_group_info info; ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2]; } sg; group--; if (group == 0) seq_puts(seq, "#group: free frags first [" " 2^0 2^1 2^2 2^3 2^4 2^5 2^6 " " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n"); i = (blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + sizeof(struct ext4_group_info); grinfo = ext4_get_group_info(sb, group); /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { seq_printf(seq, "#%-5u: I/O error\n", group); return 0; } buddy_loaded = 1; } memcpy(&sg, ext4_get_group_info(sb, group), i); if (buddy_loaded) ext4_mb_unload_buddy(&e4b); seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free, sg.info.bb_fragments, sg.info.bb_first_free); for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); seq_puts(seq, " ]\n"); return 0; } static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v) { } const struct seq_operations ext4_mb_seq_groups_ops = { .start = ext4_mb_seq_groups_start, .next = ext4_mb_seq_groups_next, .stop = ext4_mb_seq_groups_stop, .show = ext4_mb_seq_groups_show, }; static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) { int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep = ext4_groupinfo_caches[cache_index]; BUG_ON(!cachep); return cachep; } /* * Allocate the top-level s_group_info array for the specified number * of groups */ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned size; struct ext4_group_info ***old_groupinfo, ***new_groupinfo; size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); if (size <= sbi->s_group_info_size) return 0; size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size); new_groupinfo = kvzalloc(size, GFP_KERNEL); if (!new_groupinfo) { ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } rcu_read_lock(); old_groupinfo = rcu_dereference(sbi->s_group_info); if (old_groupinfo) memcpy(new_groupinfo, old_groupinfo, sbi->s_group_info_size * sizeof(*sbi->s_group_info)); rcu_read_unlock(); rcu_assign_pointer(sbi->s_group_info, new_groupinfo); sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); if (old_groupinfo) ext4_kvfree_array_rcu(old_groupinfo); ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; } /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc) { int i; int metalen = 0; int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); /* * First check if this group is the first of a reserved block. * If it's true, we have to allocate a new table of pointers * to ext4_group_info structures */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { metalen = sizeof(*meta_group_info) << EXT4_DESC_PER_BLOCK_BITS(sb); meta_group_info = kmalloc(metalen, GFP_NOFS); if (meta_group_info == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate mem " "for a buddy group"); goto exit_meta_group_info; } rcu_read_lock(); rcu_dereference(sbi->s_group_info)[idx] = meta_group_info; rcu_read_unlock(); } meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx); i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS); if (meta_group_info[i] == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate buddy mem"); goto exit_group_info; } set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(meta_group_info[i]->bb_state)); /* * initialize bb_free to be able to skip * empty groups without initialization */ if (ext4_has_group_desc_csum(sb) && (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { meta_group_info[i]->bb_free = ext4_free_clusters_after_init(sb, group, desc); } else { meta_group_info[i]->bb_free = ext4_free_group_clusters(sb, desc); } INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list); init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); return 0; exit_group_info: /* If a meta_group_info table has been allocated, release it now */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { struct ext4_group_info ***group_info; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); kfree(group_info[idx]); group_info[idx] = NULL; rcu_read_unlock(); } exit_meta_group_info: return -ENOMEM; } /* ext4_mb_add_groupinfo */ static int ext4_mb_init_backend(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; struct ext4_sb_info *sbi = EXT4_SB(sb); int err; struct ext4_group_desc *desc; struct ext4_group_info ***group_info; struct kmem_cache *cachep; err = ext4_mb_alloc_groupinfo(sb, ngroups); if (err) return err; sbi->s_buddy_cache = new_inode(sb); if (sbi->s_buddy_cache == NULL) { ext4_msg(sb, KERN_ERR, "can't get new inode"); goto err_freesgi; } /* To avoid potentially colliding with an valid on-disk inode number, * use EXT4_BAD_INO for the buddy cache inode number. This inode is * not in the inode hash, so it should never be found by iget(), but * this will avoid confusion if it ever shows up during debugging. */ sbi->s_buddy_cache->i_ino = EXT4_BAD_INO; EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; for (i = 0; i < ngroups; i++) { cond_resched(); desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { ext4_msg(sb, KERN_ERR, "can't read descriptor %u", i); goto err_freebuddy; } if (ext4_mb_add_groupinfo(sb, i, desc) != 0) goto err_freebuddy; } if (ext4_has_feature_flex_bg(sb)) { /* a single flex group is supposed to be read by a single IO. * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is * unsigned integer, so the maximum shift is 32. */ if (sbi->s_es->s_log_groups_per_flex >= 32) { ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group"); goto err_freebuddy; } sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex, BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ } else { sbi->s_mb_prefetch = 32; } if (sbi->s_mb_prefetch > ext4_get_groups_count(sb)) sbi->s_mb_prefetch = ext4_get_groups_count(sb); /* now many real IOs to prefetch within a single allocation at cr=0 * given cr=0 is an CPU-related optimization we shouldn't try to * load too many groups, at some point we should start to use what * we've got in memory. * with an average random access time 5ms, it'd take a second to get * 200 groups (* N with flex_bg), so let's make this limit 4 */ sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4; if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb)) sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb); return 0; err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); while (i-- > 0) kmem_cache_free(cachep, ext4_get_group_info(sb, i)); i = sbi->s_group_info_size; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); while (i-- > 0) kfree(group_info[i]); rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: rcu_read_lock(); kvfree(rcu_dereference(sbi->s_group_info)); rcu_read_unlock(); return -ENOMEM; } static void ext4_groupinfo_destroy_slabs(void) { int i; for (i = 0; i < NR_GRPINFO_CACHES; i++) { kmem_cache_destroy(ext4_groupinfo_caches[i]); ext4_groupinfo_caches[i] = NULL; } } static int ext4_groupinfo_create_slab(size_t size) { static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex); int slab_size; int blocksize_bits = order_base_2(size); int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep; if (cache_index >= NR_GRPINFO_CACHES) return -EINVAL; if (unlikely(cache_index < 0)) cache_index = 0; mutex_lock(&ext4_grpinfo_slab_create_mutex); if (ext4_groupinfo_caches[cache_index]) { mutex_unlock(&ext4_grpinfo_slab_create_mutex); return 0; /* Already created */ } slab_size = offsetof(struct ext4_group_info, bb_counters[blocksize_bits + 2]); cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index], slab_size, 0, SLAB_RECLAIM_ACCOUNT, NULL); ext4_groupinfo_caches[cache_index] = cachep; mutex_unlock(&ext4_grpinfo_slab_create_mutex); if (!cachep) { printk(KERN_EMERG "EXT4-fs: no memory for groupinfo slab cache\n"); return -ENOMEM; } return 0; } int ext4_mb_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned i, j; unsigned offset, offset_incr; unsigned max; int ret; i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { ret = -ENOMEM; goto out; } i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { ret = -ENOMEM; goto out; } ret = ext4_groupinfo_create_slab(sb->s_blocksize); if (ret < 0) goto out; /* order 0 is regular bitmap */ sbi->s_mb_maxs[0] = sb->s_blocksize << 3; sbi->s_mb_offsets[0] = 0; i = 1; offset = 0; offset_incr = 1 << (sb->s_blocksize_bits - 1); max = sb->s_blocksize << 2; do { sbi->s_mb_offsets[i] = offset; sbi->s_mb_maxs[i] = max; offset += offset_incr; offset_incr = offset_incr >> 1; max = max >> 1; i++; } while (i <= sb->s_blocksize_bits + 1); spin_lock_init(&sbi->s_md_lock); spin_lock_init(&sbi->s_bal_lock); sbi->s_mb_free_pending = 0; INIT_LIST_HEAD(&sbi->s_freed_data_list); sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN; sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN; sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; sbi->s_mb_max_inode_prealloc = MB_DEFAULT_MAX_INODE_PREALLOC; /* * The default group preallocation is 512, which for 4k block * sizes translates to 2 megabytes. However for bigalloc file * systems, this is probably too big (i.e, if the cluster size * is 1 megabyte, then group preallocation size becomes half a * gigabyte!). As a default, we will keep a two megabyte * group pralloc size for cluster sizes up to 64k, and after * that, we will force a minimum group preallocation size of * 32 clusters. This translates to 8 megs when the cluster * size is 256k, and 32 megs when the cluster size is 1 meg, * which seems reasonable as a default. */ sbi->s_mb_group_prealloc = max(MB_DEFAULT_GROUP_PREALLOC >> sbi->s_cluster_bits, 32); /* * If there is a s_stripe > 1, then we set the s_mb_group_prealloc * to the lowest multiple of s_stripe which is bigger than * the s_mb_group_prealloc as determined above. We want * the preallocation size to be an exact multiple of the * RAID stripe size so that preallocations don't fragment * the stripes. */ if (sbi->s_stripe > 1) { sbi->s_mb_group_prealloc = roundup( sbi->s_mb_group_prealloc, sbi->s_stripe); } sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); if (sbi->s_locality_groups == NULL) { ret = -ENOMEM; goto out; } for_each_possible_cpu(i) { struct ext4_locality_group *lg; lg = per_cpu_ptr(sbi->s_locality_groups, i); mutex_init(&lg->lg_mutex); for (j = 0; j < PREALLOC_TB_SIZE; j++) INIT_LIST_HEAD(&lg->lg_prealloc_list[j]); spin_lock_init(&lg->lg_prealloc_lock); } /* init file for buddy data */ ret = ext4_mb_init_backend(sb); if (ret != 0) goto out_free_locality_groups; return 0; out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out: kfree(sbi->s_mb_offsets); sbi->s_mb_offsets = NULL; kfree(sbi->s_mb_maxs); sbi->s_mb_maxs = NULL; return ret; } /* need to called with the ext4 group lock held */ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp) { struct ext4_prealloc_space *pa; struct list_head *cur, *tmp; int count = 0; list_for_each_safe(cur, tmp, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); list_del(&pa->pa_group_list); count++; kmem_cache_free(ext4_pspace_cachep, pa); } return count; } int ext4_mb_release(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); int count; if (sbi->s_group_info) { for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); mb_group_bb_bitmap_free(grinfo); ext4_lock_group(sb, i); count = ext4_mb_cleanup_pa(grinfo); if (count) mb_debug(sb, "mballoc: %d PAs left\n", count); ext4_unlock_group(sb, i); kmem_cache_free(cachep, grinfo); } num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) kfree(group_info[i]); kvfree(group_info); rcu_read_unlock(); } kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); iput(sbi->s_buddy_cache); if (sbi->s_mb_stats) { ext4_msg(sb, KERN_INFO, "mballoc: %u blocks %u reqs (%u success)", atomic_read(&sbi->s_bal_allocated), atomic_read(&sbi->s_bal_reqs), atomic_read(&sbi->s_bal_success)); ext4_msg(sb, KERN_INFO, "mballoc: %u extents scanned, %u goal hits, " "%u 2^N hits, %u breaks, %u lost", atomic_read(&sbi->s_bal_ex_scanned), atomic_read(&sbi->s_bal_goals), atomic_read(&sbi->s_bal_2orders), atomic_read(&sbi->s_bal_breaks), atomic_read(&sbi->s_mb_lost_chunks)); ext4_msg(sb, KERN_INFO, "mballoc: %lu generated and it took %Lu", sbi->s_mb_buddies_generated, sbi->s_mb_generation_time); ext4_msg(sb, KERN_INFO, "mballoc: %u preallocated, %u discarded", atomic_read(&sbi->s_mb_preallocated), atomic_read(&sbi->s_mb_discarded)); } free_percpu(sbi->s_locality_groups); return 0; } static inline int ext4_issue_discard(struct super_block *sb, ext4_group_t block_group, ext4_grpblk_t cluster, int count, struct bio **biop) { ext4_fsblk_t discard_block; discard_block = (EXT4_C2B(EXT4_SB(sb), cluster) + ext4_group_first_block_no(sb, block_group)); count = EXT4_C2B(EXT4_SB(sb), count); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); if (biop) { return __blkdev_issue_discard(sb->s_bdev, (sector_t)discard_block << (sb->s_blocksize_bits - 9), (sector_t)count << (sb->s_blocksize_bits - 9), GFP_NOFS, 0, biop); } else return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } static void ext4_free_data_in_buddy(struct super_block *sb, struct ext4_free_data *entry) { struct ext4_buddy e4b; struct ext4_group_info *db; int err, count = 0, count2 = 0; mb_debug(sb, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); /* we expect to find existing buddy because it's pinned */ BUG_ON(err != 0); spin_lock(&EXT4_SB(sb)->s_md_lock); EXT4_SB(sb)->s_mb_free_pending -= entry->efd_count; spin_unlock(&EXT4_SB(sb)->s_md_lock); db = e4b.bd_info; /* there are blocks to put in buddy to make them really free */ count += entry->efd_count; count2++; ext4_lock_group(sb, entry->efd_group); /* Take it out of per group rb tree */ rb_erase(&entry->efd_node, &(db->bb_free_root)); mb_free_blocks(NULL, &e4b, entry->efd_start_cluster, entry->efd_count); /* * Clear the trimmed flag for the group so that the next * ext4_trim_fs can trim it. * If the volume is mounted with -o discard, online discard * is supported and the free blocks will be trimmed online. */ if (!test_opt(sb, DISCARD)) EXT4_MB_GRP_CLEAR_TRIMMED(db); if (!db->bb_free_root.rb_node) { /* No more items in the per group rb tree * balance refcounts from ext4_mb_free_metadata() */ put_page(e4b.bd_buddy_page); put_page(e4b.bd_bitmap_page); } ext4_unlock_group(sb, entry->efd_group); kmem_cache_free(ext4_free_data_cachep, entry); ext4_mb_unload_buddy(&e4b); mb_debug(sb, "freed %d blocks in %d structures\n", count, count2); } /* * This function is called by the jbd2 layer once the commit has finished, * so we know we can free the blocks that were released with that commit. */ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_free_data *entry, *tmp; struct bio *discard_bio = NULL; struct list_head freed_data_list; struct list_head *cut_pos = NULL; int err; INIT_LIST_HEAD(&freed_data_list); spin_lock(&sbi->s_md_lock); list_for_each_entry(entry, &sbi->s_freed_data_list, efd_list) { if (entry->efd_tid != commit_tid) break; cut_pos = &entry->efd_list; } if (cut_pos) list_cut_position(&freed_data_list, &sbi->s_freed_data_list, cut_pos); spin_unlock(&sbi->s_md_lock); if (test_opt(sb, DISCARD)) { list_for_each_entry(entry, &freed_data_list, efd_list) { err = ext4_issue_discard(sb, entry->efd_group, entry->efd_start_cluster, entry->efd_count, &discard_bio); if (err && err != -EOPNOTSUPP) { ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%d failed" " with %d", entry->efd_group, entry->efd_start_cluster, entry->efd_count, err); } else if (err == -EOPNOTSUPP) break; } if (discard_bio) { submit_bio_wait(discard_bio); bio_put(discard_bio); } } list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list) ext4_free_data_in_buddy(sb, entry); } int __init ext4_init_mballoc(void) { ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space, SLAB_RECLAIM_ACCOUNT); if (ext4_pspace_cachep == NULL) goto out; ext4_ac_cachep = KMEM_CACHE(ext4_allocation_context, SLAB_RECLAIM_ACCOUNT); if (ext4_ac_cachep == NULL) goto out_pa_free; ext4_free_data_cachep = KMEM_CACHE(ext4_free_data, SLAB_RECLAIM_ACCOUNT); if (ext4_free_data_cachep == NULL) goto out_ac_free; return 0; out_ac_free: kmem_cache_destroy(ext4_ac_cachep); out_pa_free: kmem_cache_destroy(ext4_pspace_cachep); out: return -ENOMEM; } void ext4_exit_mballoc(void) { /* * Wait for completion of call_rcu()'s on ext4_pspace_cachep * before destroying the slab cache. */ rcu_barrier(); kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_data_cachep); ext4_groupinfo_destroy_slabs(); } /* * Check quota and mark chosen space (ac->ac_b_ex) non-free in bitmaps * Returns 0 if success or error code */ static noinline_for_stack int ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, handle_t *handle, unsigned int reserv_clstrs) { struct buffer_head *bitmap_bh = NULL; struct ext4_group_desc *gdp; struct buffer_head *gdp_bh; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block; int err, len; BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(ac->ac_b_ex.fe_len <= 0); sb = ac->ac_sb; sbi = EXT4_SB(sb); bitmap_bh = ext4_read_block_bitmap(sb, ac->ac_b_ex.fe_group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto out_err; } BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, bitmap_bh); if (err) goto out_err; err = -EIO; gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, &gdp_bh); if (!gdp) goto out_err; ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group, ext4_free_group_clusters(sb, gdp)); BUFFER_TRACE(gdp_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdp_bh); if (err) goto out_err; block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error * Fix the bitmap and return EFSCORRUPTED * We leak some of the blocks here. */ ext4_lock_group(sb, ac->ac_b_ex.fe_group); ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!err) err = -EFSCORRUPTED; goto out_err; } ext4_lock_group(sb, ac->ac_b_ex.fe_group); #ifdef AGGRESSIVE_CHECK { int i; for (i = 0; i < ac->ac_b_ex.fe_len; i++) { BUG_ON(mb_test_bit(ac->ac_b_ex.fe_start + i, bitmap_bh->b_data)); } } #endif ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, ac->ac_b_ex.fe_group, gdp)); } len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len; ext4_free_group_clusters_set(sb, gdp, len); ext4_block_bitmap_csum_set(sb, ac->ac_b_ex.fe_group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, ac->ac_b_ex.fe_group, gdp); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative */ if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED)) /* release all the reserved blocks if non delalloc */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, ac->ac_b_ex.fe_group); atomic64_sub(ac->ac_b_ex.fe_len, &sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (err) goto out_err; err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); out_err: brelse(bitmap_bh); return err; } /* * Idempotent helper for Ext4 fast commit replay path to set the state of * blocks in bitmaps and update counters. */ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, int len, int state) { struct buffer_head *bitmap_bh = NULL; struct ext4_group_desc *gdp; struct buffer_head *gdp_bh; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; int i, clen, err; int already; clen = EXT4_B2C(sbi, len); ext4_get_group_no_and_offset(sb, block, &group, &blkoff); bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto out_err; } err = -EIO; gdp = ext4_get_group_desc(sb, group, &gdp_bh); if (!gdp) goto out_err; ext4_lock_group(sb, group); already = 0; for (i = 0; i < clen; i++) if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state) already++; if (state) ext4_set_bits(bitmap_bh->b_data, blkoff, clen); else mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); } if (state) clen = ext4_free_group_clusters(sb, gdp) - clen + already; else clen = ext4_free_group_clusters(sb, gdp) + clen - already; ext4_free_group_clusters_set(sb, gdp, clen); ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); ext4_unlock_group(sb, group); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, group); atomic64_sub(len, &sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_clusters); } err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); if (err) goto out_err; sync_dirty_buffer(bitmap_bh); err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); sync_dirty_buffer(gdp_bh); out_err: brelse(bitmap_bh); } /* * here we normalize request for locality group * Group request are normalized to s_mb_group_prealloc, which goes to * s_strip if we set the same via mount option. * s_mb_group_prealloc can be configured via * /sys/fs/ext4/<partition>/mb_group_prealloc * * XXX: should we try to preallocate more than the group has now? */ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; BUG_ON(lg == NULL); ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; mb_debug(sb, "goal %u blocks for locality group\n", ac->ac_g_ex.fe_len); } /* * Normalization means making request better in terms of * size and alignment */ static noinline_for_stack void ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits, max; ext4_lblk_t end; loff_t size, start_off; loff_t orig_size __maybe_unused; ext4_lblk_t start; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_prealloc_space *pa; /* do normalize only data requests, metadata requests do not need preallocation */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; /* sometime caller may want exact blocks */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; /* caller may indicate that preallocation isn't * required (it's a tail, for example) */ if (ac->ac_flags & EXT4_MB_HINT_NOPREALLOC) return; if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) { ext4_mb_normalize_group_request(ac); return ; } bsbits = ac->ac_sb->s_blocksize_bits; /* first, let's learn actual file size * given current request is allocated */ size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); size = size << bsbits; if (size < i_size_read(ac->ac_inode)) size = i_size_read(ac->ac_inode); orig_size = size; /* max size of free chunks */ max = 2 << bsbits; #define NRL_CHECK_SIZE(req, size, max, chunk_size) \ (req <= (size) || max <= (chunk_size)) /* first, try to predict filesize */ /* XXX: should this table be tunable? */ start_off = 0; if (size <= 16 * 1024) { size = 16 * 1024; } else if (size <= 32 * 1024) { size = 32 * 1024; } else if (size <= 64 * 1024) { size = 64 * 1024; } else if (size <= 128 * 1024) { size = 128 * 1024; } else if (size <= 256 * 1024) { size = 256 * 1024; } else if (size <= 512 * 1024) { size = 512 * 1024; } else if (size <= 1024 * 1024) { size = 1024 * 1024; } else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, 2 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (21 - bsbits)) << 21; size = 2 * 1024 * 1024; } else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, 4 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (22 - bsbits)) << 22; size = 4 * 1024 * 1024; } else if (NRL_CHECK_SIZE(ac->ac_o_ex.fe_len, (8<<20)>>bsbits, max, 8 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (23 - bsbits)) << 23; size = 8 * 1024 * 1024; } else { start_off = (loff_t) ac->ac_o_ex.fe_logical << bsbits; size = (loff_t) EXT4_C2B(EXT4_SB(ac->ac_sb), ac->ac_o_ex.fe_len) << bsbits; } size = size >> bsbits; start = start_off >> bsbits; /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; start = ar->lleft + 1; } if (ar->pright && start + size - 1 >= ar->lright) size -= start + size - ar->lright; /* * Trim allocation request for filesystems with artificially small * groups. */ if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)) size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb); end = start + size; /* check we don't cross already preallocated blocks */ rcu_read_lock(); list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) { ext4_lblk_t pa_end; if (pa->pa_deleted) continue; spin_lock(&pa->pa_lock); if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb), pa->pa_len); /* PA must not overlap original request */ BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end || ac->ac_o_ex.fe_logical < pa->pa_lstart)); /* skip PAs this normalized request doesn't overlap with */ if (pa->pa_lstart >= end || pa_end <= start) { spin_unlock(&pa->pa_lock); continue; } BUG_ON(pa->pa_lstart <= start && pa_end >= end); /* adjust start or end to be adjacent to this pa */ if (pa_end <= ac->ac_o_ex.fe_logical) { BUG_ON(pa_end < start); start = pa_end; } else if (pa->pa_lstart > ac->ac_o_ex.fe_logical) { BUG_ON(pa->pa_lstart > end); end = pa->pa_lstart; } spin_unlock(&pa->pa_lock); } rcu_read_unlock(); size = end - start; /* XXX: extra loop to check we really don't overlap preallocations */ rcu_read_lock(); list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) { ext4_lblk_t pa_end; spin_lock(&pa->pa_lock); if (pa->pa_deleted == 0) { pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb), pa->pa_len); BUG_ON(!(start >= pa_end || end <= pa->pa_lstart)); } spin_unlock(&pa->pa_lock); } rcu_read_unlock(); if (start + size <= ac->ac_o_ex.fe_logical && start > ac->ac_o_ex.fe_logical) { ext4_msg(ac->ac_sb, KERN_ERR, "start %lu, size %lu, fe_logical %lu", (unsigned long) start, (unsigned long) size, (unsigned long) ac->ac_o_ex.fe_logical); BUG(); } BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); /* now prepare goal request */ /* XXX: is it better to align blocks WRT to logical * placement or satisfy big request as is */ ac->ac_g_ex.fe_logical = start; ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size); /* define goal start in order to merge */ if (ar->pright && (ar->lright == (start + size))) { /* merge to the right */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size, &ac->ac_f_ex.fe_group, &ac->ac_f_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } if (ar->pleft && (ar->lleft + 1 == start)) { /* merge to the left */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1, &ac->ac_f_ex.fe_group, &ac->ac_f_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } mb_debug(ac->ac_sb, "goal: %lld(was %lld) blocks at %u\n", size, orig_size, start); } static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); if (sbi->s_mb_stats && ac->ac_g_ex.fe_len > 1) { atomic_inc(&sbi->s_bal_reqs); atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated); if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len) atomic_inc(&sbi->s_bal_success); atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned); if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start && ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group) atomic_inc(&sbi->s_bal_goals); if (ac->ac_found > sbi->s_mb_max_to_scan) atomic_inc(&sbi->s_bal_breaks); } if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) trace_ext4_mballoc_alloc(ac); else trace_ext4_mballoc_prealloc(ac); } /* * Called on failure; free up any blocks from the inode PA for this * context. We don't need this for MB_GROUP_PA because we only change * pa_free in ext4_mb_release_context(), but on failure, we've already * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed. */ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; struct ext4_buddy e4b; int err; if (pa == NULL) { if (ac->ac_f_ex.fe_len == 0) return; err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b); if (err) { /* * This should never happen since we pin the * pages in the ext4_allocation_context so * ext4_mb_load_buddy() should never fail. */ WARN(1, "mb_load_buddy failed (%d)", err); return; } ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group); mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start, ac->ac_f_ex.fe_len); ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group); ext4_mb_unload_buddy(&e4b); return; } if (pa->pa_type == MB_INODE_PA) pa->pa_free += ac->ac_b_ex.fe_len; } /* * use blocks preallocated to inode */ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_fsblk_t start; ext4_fsblk_t end; int len; /* found preallocated blocks, use them */ start = pa->pa_pstart + (ac->ac_o_ex.fe_logical - pa->pa_lstart); end = min(pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len), start + EXT4_C2B(sbi, ac->ac_o_ex.fe_len)); len = EXT4_NUM_B2C(sbi, end - start); ext4_get_group_no_and_offset(ac->ac_sb, start, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; BUG_ON(start < pa->pa_pstart); BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len)); BUG_ON(pa->pa_free < len); pa->pa_free -= len; mb_debug(ac->ac_sb, "use %llu/%d from inode pa %p\n", start, len, pa); } /* * use blocks preallocated to locality group */ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { unsigned int len = ac->ac_o_ex.fe_len; ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; /* we don't correct pa_pstart or pa_plen here to avoid * possible race when the group is being loaded concurrently * instead we correct pa later, after blocks are marked * in on-disk bitmap -- see ext4_mb_release_context() * Other CPUs are prevented from allocating from this pa by lg_mutex */ mb_debug(ac->ac_sb, "use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa); } /* * Return the prealloc space that have minimal distance * from the goal block. @cpa is the prealloc * space that is having currently known minimal distance * from the goal block. */ static struct ext4_prealloc_space * ext4_mb_check_group_pa(ext4_fsblk_t goal_block, struct ext4_prealloc_space *pa, struct ext4_prealloc_space *cpa) { ext4_fsblk_t cur_distance, new_distance; if (cpa == NULL) { atomic_inc(&pa->pa_count); return pa; } cur_distance = abs(goal_block - cpa->pa_pstart); new_distance = abs(goal_block - pa->pa_pstart); if (cur_distance <= new_distance) return cpa; /* drop the previous reference */ atomic_dec(&cpa->pa_count); atomic_inc(&pa->pa_count); return pa; } /* * search goal blocks in preallocated space */ static noinline_for_stack bool ext4_mb_use_preallocated(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int order, i; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_locality_group *lg; struct ext4_prealloc_space *pa, *cpa = NULL; ext4_fsblk_t goal_block; /* only data can be preallocated */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return false; /* first, try per-file preallocation */ rcu_read_lock(); list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) { /* all fields in this condition don't change, * so we can skip locking for them */ if (ac->ac_o_ex.fe_logical < pa->pa_lstart || ac->ac_o_ex.fe_logical >= (pa->pa_lstart + EXT4_C2B(sbi, pa->pa_len))) continue; /* non-extent files can't have physical blocks past 2^32 */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) && (pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len) > EXT4_MAX_BLOCK_FILE_PHYS)) continue; /* found preallocated blocks, use them */ spin_lock(&pa->pa_lock); if (pa->pa_deleted == 0 && pa->pa_free) { atomic_inc(&pa->pa_count); ext4_mb_use_inode_pa(ac, pa); spin_unlock(&pa->pa_lock); ac->ac_criteria = 10; rcu_read_unlock(); return true; } spin_unlock(&pa->pa_lock); } rcu_read_unlock(); /* can we use group allocation? */ if (!(ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)) return false; /* inode may have no locality group for some reason */ lg = ac->ac_lg; if (lg == NULL) return false; order = fls(ac->ac_o_ex.fe_len) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; goal_block = ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex); /* * search for the prealloc space that is having * minimal distance from the goal block. */ for (i = order; i < PREALLOC_TB_SIZE; i++) { rcu_read_lock(); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[i], pa_inode_list) { spin_lock(&pa->pa_lock); if (pa->pa_deleted == 0 && pa->pa_free >= ac->ac_o_ex.fe_len) { cpa = ext4_mb_check_group_pa(goal_block, pa, cpa); } spin_unlock(&pa->pa_lock); } rcu_read_unlock(); } if (cpa) { ext4_mb_use_group_pa(ac, cpa); ac->ac_criteria = 20; return true; } return false; } /* * the function goes through all block freed in the group * but not yet committed and marks them used in in-core bitmap. * buddy must be generated from this bitmap * Need to be called with the ext4 group lock held */ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group) { struct rb_node *n; struct ext4_group_info *grp; struct ext4_free_data *entry; grp = ext4_get_group_info(sb, group); n = rb_first(&(grp->bb_free_root)); while (n) { entry = rb_entry(n, struct ext4_free_data, efd_node); ext4_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); n = rb_next(n); } return; } /* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap * Need to be called with ext4 group lock held */ static noinline_for_stack void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_prealloc_space *pa; struct list_head *cur; ext4_group_t groupnr; ext4_grpblk_t start; int preallocated = 0; int len; /* all form of preallocation discards first load group, * so the only competing code is preallocation use. * we don't need any locking here * notice we do NOT ignore preallocations with pa_deleted * otherwise we could leave used blocks available for * allocation in buddy when concurrent ext4_mb_put_pa() * is dropping preallocation */ list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &start); len = pa->pa_len; spin_unlock(&pa->pa_lock); if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); ext4_set_bits(bitmap, start, len); preallocated += len; } mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); } static void ext4_mb_mark_pa_deleted(struct super_block *sb, struct ext4_prealloc_space *pa) { struct ext4_inode_info *ei; if (pa->pa_deleted) { ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n", pa->pa_type, pa->pa_pstart, pa->pa_lstart, pa->pa_len); return; } pa->pa_deleted = 1; if (pa->pa_type == MB_INODE_PA) { ei = EXT4_I(pa->pa_inode); atomic_dec(&ei->i_prealloc_active); } } static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu); BUG_ON(atomic_read(&pa->pa_count)); BUG_ON(pa->pa_deleted == 0); kmem_cache_free(ext4_pspace_cachep, pa); } /* * drops a reference to preallocated space descriptor * if this was the last reference and the space is consumed */ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, struct super_block *sb, struct ext4_prealloc_space *pa) { ext4_group_t grp; ext4_fsblk_t grp_blk; /* in this short window concurrent discard can set pa_deleted */ spin_lock(&pa->pa_lock); if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) { spin_unlock(&pa->pa_lock); return; } if (pa->pa_deleted == 1) { spin_unlock(&pa->pa_lock); return; } ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); grp_blk = pa->pa_pstart; /* * If doing group-based preallocation, pa_pstart may be in the * next group when pa is used up */ if (pa->pa_type == MB_GROUP_PA) grp_blk--; grp = ext4_get_group_number(sb, grp_blk); /* * possible race: * * P1 (buddy init) P2 (regular allocation) * find block B in PA * copy on-disk bitmap to buddy * mark B in on-disk bitmap * drop PA from group * mark all PAs in buddy * * thus, P1 initializes buddy with B available. to prevent this * we make "copy" and "mark all PAs" atomic and serialize "drop PA" * against that pair */ ext4_lock_group(sb, grp); list_del(&pa->pa_group_list); ext4_unlock_group(sb, grp); spin_lock(pa->pa_obj_lock); list_del_rcu(&pa->pa_inode_list); spin_unlock(pa->pa_obj_lock); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } /* * creates new preallocated space for given inode */ static noinline_for_stack void ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_prealloc_space *pa; struct ext4_group_info *grp; struct ext4_inode_info *ei; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) { int winl; int wins; int win; int offs; /* we can't allocate as much as normalizer wants. * so, found space must get proper lstart * to cover original request */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); /* we're limited by original request in that * logical block must be covered any way * winl is window we can move our chunk within */ winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical; /* also, we should cover whole original request */ wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len); /* the smallest one defines real window */ win = min(winl, wins); offs = ac->ac_o_ex.fe_logical % EXT4_C2B(sbi, ac->ac_b_ex.fe_len); if (offs && offs < win) win = offs; ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical - EXT4_NUM_B2C(sbi, win); BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); } /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ ac->ac_f_ex = ac->ac_b_ex; pa->pa_lstart = ac->ac_b_ex.fe_logical; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_inode_list); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_INODE_PA; mb_debug(sb, "new inode pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_inode_pa(ac, pa); ext4_mb_use_inode_pa(ac, pa); atomic_add(pa->pa_free, &sbi->s_mb_preallocated); ei = EXT4_I(ac->ac_inode); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); pa->pa_obj_lock = &ei->i_prealloc_lock; pa->pa_inode = ac->ac_inode; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); spin_lock(pa->pa_obj_lock); list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); atomic_inc(&ei->i_prealloc_active); } /* * creates new preallocated space for locality group inodes belongs to */ static noinline_for_stack void ext4_mb_new_group_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg; struct ext4_prealloc_space *pa; struct ext4_group_info *grp; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ ac->ac_f_ex = ac->ac_b_ex; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_lstart = pa->pa_pstart; pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_inode_list); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_GROUP_PA; mb_debug(sb, "new group pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_group_pa(ac, pa); ext4_mb_use_group_pa(ac, pa); atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); lg = ac->ac_lg; BUG_ON(lg == NULL); pa->pa_obj_lock = &lg->lg_prealloc_lock; pa->pa_inode = NULL; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); /* * We will later add the new pa to the right bucket * after updating the pa_free in ext4_mb_release_context */ } static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac) { if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) ext4_mb_new_group_pa(ac); else ext4_mb_new_inode_pa(ac); } /* * finds all unused blocks in on-disk bitmap, frees them in * in-core bitmap and buddy. * @pa must be unlinked from inode and group lists, so that * nobody else can find/use it. * the caller MUST hold group/inode locks. * TODO: optimize the case when there are no in-core structures yet */ static noinline_for_stack int ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned int end; unsigned int next; ext4_group_t group; ext4_grpblk_t bit; unsigned long long grp_blk_start; int free = 0; BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); grp_blk_start = pa->pa_pstart - EXT4_C2B(sbi, bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); end = bit + pa->pa_len; while (bit < end) { bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit); if (bit >= end) break; next = mb_find_next_bit(bitmap_bh->b_data, end, bit); mb_debug(sb, "free preallocated %u/%u in group %u\n", (unsigned) ext4_group_first_block_no(sb, group) + bit, (unsigned) next - bit, (unsigned) group); free += next - bit; trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit); trace_ext4_mb_release_inode_pa(pa, (grp_blk_start + EXT4_C2B(sbi, bit)), next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; } if (free != pa->pa_free) { ext4_msg(e4b->bd_sb, KERN_CRIT, "pa %p: logic %lu, phys. %lu, len %d", pa, (unsigned long) pa->pa_lstart, (unsigned long) pa->pa_pstart, pa->pa_len); ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u", free, pa->pa_free); /* * pa is already deleted so we use the value obtained * from the bitmap and continue. */ } atomic_add(free, &sbi->s_mb_discarded); return 0; } static noinline_for_stack int ext4_mb_release_group_pa(struct ext4_buddy *e4b, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; ext4_group_t group; ext4_grpblk_t bit; trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); return 0; } /* * releases all preallocations in given group * * first, we need to decide discard policy: * - when do we discard * 1) ENOSPC * - how many do we discard * 1) how many requested */ static noinline_for_stack int ext4_mb_discard_group_preallocations(struct super_block *sb, ext4_group_t group, int needed) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; struct list_head list; struct ext4_buddy e4b; int err; int busy = 0; int free, free_total = 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) goto out_dbg; bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); goto out_dbg; } err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { ext4_warning(sb, "Error %d loading buddy information for %u", err, group); put_bh(bitmap_bh); goto out_dbg; } if (needed == 0) needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1; INIT_LIST_HEAD(&list); repeat: free = 0; ext4_lock_group(sb, group); list_for_each_entry_safe(pa, tmp, &grp->bb_prealloc_list, pa_group_list) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { spin_unlock(&pa->pa_lock); busy = 1; continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); if (!free) this_cpu_inc(discard_pa_seq); /* we can trust pa_free ... */ free += pa->pa_free; spin_unlock(&pa->pa_lock); list_del(&pa->pa_group_list); list_add(&pa->u.pa_tmp_list, &list); } /* now free all selected PAs */ list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { /* remove from object (inode or locality group) */ spin_lock(pa->pa_obj_lock); list_del_rcu(&pa->pa_inode_list); spin_unlock(pa->pa_obj_lock); if (pa->pa_type == MB_GROUP_PA) ext4_mb_release_group_pa(&e4b, pa); else ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } free_total += free; /* if we still need more blocks and some PAs were used, try again */ if (free_total < needed && busy) { ext4_unlock_group(sb, group); cond_resched(); busy = 0; goto repeat; } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); out_dbg: mb_debug(sb, "discarded (%d) blocks preallocated for group %u bb_free (%d)\n", free_total, group, grp->bb_free); return free_total; } /* * releases all non-used preallocated blocks for given inode * * It's important to discard preallocations under i_data_sem * We don't want another block to be served from the prealloc * space when we are discarding the inode prealloc space. * * FIXME!! Make sure it is valid at all the call sites */ void ext4_discard_preallocations(struct inode *inode, unsigned int needed) { struct ext4_inode_info *ei = EXT4_I(inode); struct super_block *sb = inode->i_sb; struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; ext4_group_t group = 0; struct list_head list; struct ext4_buddy e4b; int err; if (!S_ISREG(inode->i_mode)) { /*BUG_ON(!list_empty(&ei->i_prealloc_list));*/ return; } if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) return; mb_debug(sb, "discard preallocation for inode %lu\n", inode->i_ino); trace_ext4_discard_preallocations(inode, atomic_read(&ei->i_prealloc_active), needed); INIT_LIST_HEAD(&list); if (needed == 0) needed = UINT_MAX; repeat: /* first, collect all pa's in the inode */ spin_lock(&ei->i_prealloc_lock); while (!list_empty(&ei->i_prealloc_list) && needed) { pa = list_entry(ei->i_prealloc_list.prev, struct ext4_prealloc_space, pa_inode_list); BUG_ON(pa->pa_obj_lock != &ei->i_prealloc_lock); spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* this shouldn't happen often - nobody should * use preallocation while we're discarding it */ spin_unlock(&pa->pa_lock); spin_unlock(&ei->i_prealloc_lock); ext4_msg(sb, KERN_ERR, "uh-oh! used pa while discarding"); WARN_ON(1); schedule_timeout_uninterruptible(HZ); goto repeat; } if (pa->pa_deleted == 0) { ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); list_add(&pa->u.pa_tmp_list, &list); needed--; continue; } /* someone is deleting pa right now */ spin_unlock(&pa->pa_lock); spin_unlock(&ei->i_prealloc_lock); /* we have to wait here because pa_deleted * doesn't mean pa is already unlinked from * the list. as we might be called from * ->clear_inode() the inode will get freed * and concurrent thread which is unlinking * pa from inode's list may access already * freed memory, bad-bad-bad */ /* XXX: if this happens too often, we can * add a flag to force wait only in case * of ->clear_inode(), but not in case of * regular truncate */ schedule_timeout_uninterruptible(HZ); goto repeat; } spin_unlock(&ei->i_prealloc_lock); list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { BUG_ON(pa->pa_type != MB_INODE_PA); group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); ext4_mb_unload_buddy(&e4b); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } static int ext4_mb_pa_alloc(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa; BUG_ON(ext4_pspace_cachep == NULL); pa = kmem_cache_zalloc(ext4_pspace_cachep, GFP_NOFS); if (!pa) return -ENOMEM; atomic_set(&pa->pa_count, 1); ac->ac_pa = pa; return 0; } static void ext4_mb_pa_free(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; BUG_ON(!pa); ac->ac_pa = NULL; WARN_ON(!atomic_dec_and_test(&pa->pa_count)); kmem_cache_free(ext4_pspace_cachep, pa); } #ifdef CONFIG_EXT4_DEBUG static inline void ext4_mb_show_pa(struct super_block *sb) { ext4_group_t i, ngroups; if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; ngroups = ext4_get_groups_count(sb); mb_debug(sb, "groups: "); for (i = 0; i < ngroups; i++) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); struct ext4_prealloc_space *pa; ext4_grpblk_t start; struct list_head *cur; ext4_lock_group(sb, i); list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, NULL, &start); spin_unlock(&pa->pa_lock); mb_debug(sb, "PA:%u:%d:%d\n", i, start, pa->pa_len); } ext4_unlock_group(sb, i); mb_debug(sb, "%u: %d/%d\n", i, grp->bb_free, grp->bb_fragments); } } static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; mb_debug(sb, "Can't allocate:" " Allocation context details:"); mb_debug(sb, "status %u flags 0x%x", ac->ac_status, ac->ac_flags); mb_debug(sb, "orig %lu/%lu/%lu@%lu, " "goal %lu/%lu/%lu@%lu, " "best %lu/%lu/%lu@%lu cr %d", (unsigned long)ac->ac_o_ex.fe_group, (unsigned long)ac->ac_o_ex.fe_start, (unsigned long)ac->ac_o_ex.fe_len, (unsigned long)ac->ac_o_ex.fe_logical, (unsigned long)ac->ac_g_ex.fe_group, (unsigned long)ac->ac_g_ex.fe_start, (unsigned long)ac->ac_g_ex.fe_len, (unsigned long)ac->ac_g_ex.fe_logical, (unsigned long)ac->ac_b_ex.fe_group, (unsigned long)ac->ac_b_ex.fe_start, (unsigned long)ac->ac_b_ex.fe_len, (unsigned long)ac->ac_b_ex.fe_logical, (int)ac->ac_criteria); mb_debug(sb, "%u found", ac->ac_found); ext4_mb_show_pa(sb); } #else static inline void ext4_mb_show_pa(struct super_block *sb) { return; } static inline void ext4_mb_show_ac(struct ext4_allocation_context *ac) { ext4_mb_show_pa(ac->ac_sb); return; } #endif /* * We use locality group preallocation for small size file. The size of the * file is determined by the current size or the resulting size after * allocation which ever is larger * * One can tune this size via /sys/fs/ext4/<partition>/mb_stream_req */ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; if ((size == isize) && !ext4_fs_is_busy(sbi) && !inode_is_open_for_write(ac->ac_inode)) { ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } if (sbi->s_mb_group_prealloc <= 0) { ac->ac_flags |= EXT4_MB_STREAM_ALLOC; return; } /* don't use group allocation for large files */ size = max(size, isize); if (size > sbi->s_mb_stream_request) { ac->ac_flags |= EXT4_MB_STREAM_ALLOC; return; } BUG_ON(ac->ac_lg != NULL); /* * locality group prealloc space are per cpu. The reason for having * per cpu locality group is to reduce the contention between block * request from multiple CPUs. */ ac->ac_lg = raw_cpu_ptr(sbi->s_locality_groups); /* we're going to use group allocation */ ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC; /* serialize all allocations in the group */ mutex_lock(&ac->ac_lg->lg_mutex); } static noinline_for_stack int ext4_mb_initialize_context(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct super_block *sb = ar->inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_group_t group; unsigned int len; ext4_fsblk_t goal; ext4_grpblk_t block; /* we can't allocate > group size */ len = ar->len; /* just a dirty hack to filter too big requests */ if (len >= EXT4_CLUSTERS_PER_GROUP(sb)) len = EXT4_CLUSTERS_PER_GROUP(sb); /* start searching from the goal */ goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical); ac->ac_status = AC_STATUS_CONTINUE; ac->ac_sb = sb; ac->ac_inode = ar->inode; ac->ac_o_ex.fe_logical = ac->ac_b_ex.fe_logical; ac->ac_o_ex.fe_group = group; ac->ac_o_ex.fe_start = block; ac->ac_o_ex.fe_len = len; ac->ac_g_ex = ac->ac_o_ex; ac->ac_flags = ar->flags; /* we have to define context: we'll work with a file or * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); mb_debug(sb, "init ac: %u blocks @ %u, goal %u, flags 0x%x, 2^%d, " "left: %u/%u, right %u/%u to %swritable\n", (unsigned) ar->len, (unsigned) ar->logical, (unsigned) ar->goal, ac->ac_flags, ac->ac_2order, (unsigned) ar->lleft, (unsigned) ar->pleft, (unsigned) ar->lright, (unsigned) ar->pright, inode_is_open_for_write(ar->inode) ? "" : "non-"); return 0; } static noinline_for_stack void ext4_mb_discard_lg_preallocations(struct super_block *sb, struct ext4_locality_group *lg, int order, int total_entries) { ext4_group_t group = 0; struct ext4_buddy e4b; struct list_head discard_list; struct ext4_prealloc_space *pa, *tmp; mb_debug(sb, "discard locality group preallocation\n"); INIT_LIST_HEAD(&discard_list); spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order], pa_inode_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* * This is the pa that we just used * for block allocation. So don't * free that */ spin_unlock(&pa->pa_lock); continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* only lg prealloc space */ BUG_ON(pa->pa_type != MB_GROUP_PA); /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); list_add(&pa->u.pa_tmp_list, &discard_list); total_entries--; if (total_entries <= 5) { /* * we want to keep only 5 entries * allowing it to grow to 8. This * mak sure we don't call discard * soon for this list. */ break; } } spin_unlock(&lg->lg_prealloc_lock); list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) { int err; group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_group_pa(&e4b, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } /* * We have incremented pa_count. So it cannot be freed at this * point. Also we hold lg_mutex. So no parallel allocation is * possible from this lg. That means pa_free cannot be updated. * * A parallel ext4_mb_discard_group_preallocations is possible. * which can cause the lg_prealloc_list to be updated. */ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) { int order, added = 0, lg_prealloc_count = 1; struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; struct ext4_prealloc_space *tmp_pa, *pa = ac->ac_pa; order = fls(pa->pa_free) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; /* Add the prealloc space to lg */ spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order], pa_inode_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted) { spin_unlock(&tmp_pa->pa_lock); continue; } if (!added && pa->pa_free < tmp_pa->pa_free) { /* Add to the tail of the previous entry */ list_add_tail_rcu(&pa->pa_inode_list, &tmp_pa->pa_inode_list); added = 1; /* * we want to count the total * number of entries in the list */ } spin_unlock(&tmp_pa->pa_lock); lg_prealloc_count++; } if (!added) list_add_tail_rcu(&pa->pa_inode_list, &lg->lg_prealloc_list[order]); spin_unlock(&lg->lg_prealloc_lock); /* Now trim the list to be not more than 8 elements */ if (lg_prealloc_count > 8) { ext4_mb_discard_lg_preallocations(sb, lg, order, lg_prealloc_count); return; } return ; } /* * if per-inode prealloc list is too long, trim some PA */ static void ext4_mb_trim_inode_pa(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int count, delta; count = atomic_read(&ei->i_prealloc_active); delta = (sbi->s_mb_max_inode_prealloc >> 2) + 1; if (count > sbi->s_mb_max_inode_prealloc + delta) { count -= sbi->s_mb_max_inode_prealloc; ext4_discard_preallocations(inode, count); } } /* * release all resource we used in allocation */ static int ext4_mb_release_context(struct ext4_allocation_context *ac) { struct inode *inode = ac->ac_inode; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *pa = ac->ac_pa; if (pa) { if (pa->pa_type == MB_GROUP_PA) { /* see comment in ext4_mb_use_group_pa() */ spin_lock(&pa->pa_lock); pa->pa_pstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_lstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_free -= ac->ac_b_ex.fe_len; pa->pa_len -= ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); /* * We want to add the pa to the right bucket. * Remove it from the list and while adding * make sure the list to which we are adding * doesn't grow big. */ if (likely(pa->pa_free)) { spin_lock(pa->pa_obj_lock); list_del_rcu(&pa->pa_inode_list); spin_unlock(pa->pa_obj_lock); ext4_mb_add_n_trim(ac); } } if (pa->pa_type == MB_INODE_PA) { /* * treat per-inode prealloc list as a lru list, then try * to trim the least recently used PA. */ spin_lock(pa->pa_obj_lock); list_move(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); } ext4_mb_put_pa(ac, ac->ac_sb, pa); } if (ac->ac_bitmap_page) put_page(ac->ac_bitmap_page); if (ac->ac_buddy_page) put_page(ac->ac_buddy_page); if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); ext4_mb_trim_inode_pa(inode); return 0; } static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) { ext4_group_t i, ngroups = ext4_get_groups_count(sb); int ret; int freed = 0; trace_ext4_mb_discard_preallocations(sb, needed); for (i = 0; i < ngroups && needed > 0; i++) { ret = ext4_mb_discard_group_preallocations(sb, i, needed); freed += ret; needed -= ret; } return freed; } static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb, struct ext4_allocation_context *ac, u64 *seq) { int freed; u64 seq_retry = 0; bool ret = false; freed = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len); if (freed) { ret = true; goto out_dbg; } seq_retry = ext4_get_discard_pa_seq_sum(); if (!(ac->ac_flags & EXT4_MB_STRICT_CHECK) || seq_retry != *seq) { ac->ac_flags |= EXT4_MB_STRICT_CHECK; *seq = seq_retry; ret = true; } out_dbg: mb_debug(sb, "freed %d, retry ? %s\n", freed, ret ? "yes" : "no"); return ret; } static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct ext4_allocation_request *ar, int *errp); /* * Main entry point into mballoc to allocate blocks * it tries to use preallocation first, then falls back * to usual allocation */ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, struct ext4_allocation_request *ar, int *errp) { struct ext4_allocation_context *ac = NULL; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; u64 seq; might_sleep(); sb = ar->inode->i_sb; sbi = EXT4_SB(sb); trace_ext4_request_blocks(ar); if (sbi->s_mount_state & EXT4_FC_REPLAY) return ext4_mb_new_blocks_simple(handle, ar, errp); /* Allow to use superuser reservation for quota file */ if (ext4_is_quota_file(ar->inode)) ar->flags |= EXT4_MB_USE_ROOT_BLOCKS; if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) { /* Without delayed allocation we need to verify * there is enough free blocks to do block allocation * and verify allocation doesn't exceed the quota limits. */ while (ar->len && ext4_claim_free_clusters(sbi, ar->len, ar->flags)) { /* let others to free the space */ cond_resched(); ar->len = ar->len >> 1; } if (!ar->len) { ext4_mb_show_pa(sb); *errp = -ENOSPC; return 0; } reserv_clstrs = ar->len; if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) { dquot_alloc_block_nofail(ar->inode, EXT4_C2B(sbi, ar->len)); } else { while (ar->len && dquot_alloc_block(ar->inode, EXT4_C2B(sbi, ar->len))) { ar->flags |= EXT4_MB_HINT_NOPREALLOC; ar->len--; } } inquota = ar->len; if (ar->len == 0) { *errp = -EDQUOT; goto out; } } ac = kmem_cache_zalloc(ext4_ac_cachep, GFP_NOFS); if (!ac) { ar->len = 0; *errp = -ENOMEM; goto out; } *errp = ext4_mb_initialize_context(ac, ar); if (*errp) { ar->len = 0; goto out; } ac->ac_op = EXT4_MB_HISTORY_PREALLOC; seq = this_cpu_read(discard_pa_seq); if (!ext4_mb_use_preallocated(ac)) { ac->ac_op = EXT4_MB_HISTORY_ALLOC; ext4_mb_normalize_request(ac, ar); *errp = ext4_mb_pa_alloc(ac); if (*errp) goto errout; repeat: /* allocate space in core */ *errp = ext4_mb_regular_allocator(ac); /* * pa allocated above is added to grp->bb_prealloc_list only * when we were able to allocate some block i.e. when * ac->ac_status == AC_STATUS_FOUND. * And error from above mean ac->ac_status != AC_STATUS_FOUND * So we have to free this pa here itself. */ if (*errp) { ext4_mb_pa_free(ac); ext4_discard_allocated_blocks(ac); goto errout; } if (ac->ac_status == AC_STATUS_FOUND && ac->ac_o_ex.fe_len >= ac->ac_f_ex.fe_len) ext4_mb_pa_free(ac); } if (likely(ac->ac_status == AC_STATUS_FOUND)) { *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs); if (*errp) { ext4_discard_allocated_blocks(ac); goto errout; } else { block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); ar->len = ac->ac_b_ex.fe_len; } } else { if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above * needs to be freed here itself. */ ext4_mb_pa_free(ac); *errp = -ENOSPC; } errout: if (*errp) { ac->ac_b_ex.fe_len = 0; ar->len = 0; ext4_mb_show_ac(ac); } ext4_mb_release_context(ac); out: if (ac) kmem_cache_free(ext4_ac_cachep, ac); if (inquota && ar->len < inquota) dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len)); if (!ar->len) { if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) /* release all the reserved blocks if non delalloc */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); } trace_ext4_allocate_blocks(ar, (unsigned long long)block); return block; } /* * We can merge two free data extents only if the physical blocks * are contiguous, AND the extents were freed by the same transaction, * AND the blocks are associated with the same group. */ static void ext4_try_merge_freed_extent(struct ext4_sb_info *sbi, struct ext4_free_data *entry, struct ext4_free_data *new_entry, struct rb_root *entry_rb_root) { if ((entry->efd_tid != new_entry->efd_tid) || (entry->efd_group != new_entry->efd_group)) return; if (entry->efd_start_cluster + entry->efd_count == new_entry->efd_start_cluster) { new_entry->efd_start_cluster = entry->efd_start_cluster; new_entry->efd_count += entry->efd_count; } else if (new_entry->efd_start_cluster + new_entry->efd_count == entry->efd_start_cluster) { new_entry->efd_count += entry->efd_count; } else return; spin_lock(&sbi->s_md_lock); list_del(&entry->efd_list); spin_unlock(&sbi->s_md_lock); rb_erase(&entry->efd_node, entry_rb_root); kmem_cache_free(ext4_free_data_cachep, entry); } static noinline_for_stack int ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, struct ext4_free_data *new_entry) { ext4_group_t group = e4b->bd_group; ext4_grpblk_t cluster; ext4_grpblk_t clusters = new_entry->efd_count; struct ext4_free_data *entry; struct ext4_group_info *db = e4b->bd_info; struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct rb_node **n = &db->bb_free_root.rb_node, *node; struct rb_node *parent = NULL, *new_node; BUG_ON(!ext4_handle_valid(handle)); BUG_ON(e4b->bd_bitmap_page == NULL); BUG_ON(e4b->bd_buddy_page == NULL); new_node = &new_entry->efd_node; cluster = new_entry->efd_start_cluster; if (!*n) { /* first free block exent. We need to protect buddy cache from being freed, * otherwise we'll refresh it from * on-disk bitmap and lose not-yet-available * blocks */ get_page(e4b->bd_buddy_page); get_page(e4b->bd_bitmap_page); } while (*n) { parent = *n; entry = rb_entry(parent, struct ext4_free_data, efd_node); if (cluster < entry->efd_start_cluster) n = &(*n)->rb_left; else if (cluster >= (entry->efd_start_cluster + entry->efd_count)) n = &(*n)->rb_right; else { ext4_grp_locked_error(sb, group, 0, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, cluster), "Block already on to-be-freed list"); kmem_cache_free(ext4_free_data_cachep, new_entry); return 0; } } rb_link_node(new_node, parent, n); rb_insert_color(new_node, &db->bb_free_root); /* Now try to see the extent can be merged to left and right */ node = rb_prev(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); ext4_try_merge_freed_extent(sbi, entry, new_entry, &(db->bb_free_root)); } node = rb_next(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); ext4_try_merge_freed_extent(sbi, entry, new_entry, &(db->bb_free_root)); } spin_lock(&sbi->s_md_lock); list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list); sbi->s_mb_free_pending += clusters; spin_unlock(&sbi->s_md_lock); return 0; } /* * Simple allocator for Ext4 fast commit replay path. It searches for blocks * linearly starting at the goal block and also excludes the blocks which * are going to be in use after fast commit replay. */ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct ext4_allocation_request *ar, int *errp) { struct buffer_head *bitmap_bh; struct super_block *sb = ar->inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; int i = sb->s_blocksize; ext4_fsblk_t goal, block; struct ext4_super_block *es = EXT4_SB(sb)->s_es; goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ar->len = 0; ext4_get_group_no_and_offset(sb, goal, &group, &blkoff); for (; group < ext4_get_groups_count(sb); group++) { bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { *errp = PTR_ERR(bitmap_bh); pr_warn("Failed to read block bitmap\n"); return 0; } ext4_get_group_no_and_offset(sb, max(ext4_group_first_block_no(sb, group), goal), NULL, &blkoff); i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize, blkoff); brelse(bitmap_bh); if (i >= sb->s_blocksize) continue; if (ext4_fc_replay_check_excluded(sb, ext4_group_first_block_no(sb, group) + i)) continue; break; } if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize) return 0; block = ext4_group_first_block_no(sb, group) + i; ext4_mb_mark_bb(sb, block, 1, 1); ar->len = 1; return block; } static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, unsigned long count) { struct buffer_head *bitmap_bh; struct super_block *sb = inode->i_sb; struct ext4_group_desc *gdp; struct buffer_head *gdp_bh; ext4_group_t group; ext4_grpblk_t blkoff; int already_freed = 0, err, i; ext4_get_group_no_and_offset(sb, block, &group, &blkoff); bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); pr_warn("Failed to read block bitmap\n"); return; } gdp = ext4_get_group_desc(sb, group, &gdp_bh); if (!gdp) return; for (i = 0; i < count; i++) { if (!mb_test_bit(blkoff + i, bitmap_bh->b_data)) already_freed++; } mb_clear_bits(bitmap_bh->b_data, blkoff, count); err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); if (err) return; ext4_free_group_clusters_set( sb, gdp, ext4_free_group_clusters(sb, gdp) + count - already_freed); ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); sync_dirty_buffer(bitmap_bh); sync_dirty_buffer(gdp_bh); brelse(bitmap_bh); } /** * ext4_free_blocks() -- Free given blocks and update quota * @handle: handle for this transaction * @inode: inode * @bh: optional buffer of the block to be freed * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags) { struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; struct ext4_group_desc *gdp; unsigned int overflow; ext4_grpblk_t bit; struct buffer_head *gd_bh; ext4_group_t block_group; struct ext4_sb_info *sbi; struct ext4_buddy e4b; unsigned int count_clusters; int err = 0; int ret; sbi = EXT4_SB(sb); if (sbi->s_mount_state & EXT4_FC_REPLAY) { ext4_free_blocks_simple(inode, block, count); return; } might_sleep(); if (bh) { if (block) BUG_ON(block != bh->b_blocknr); else block = bh->b_blocknr; } if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); goto error_return; } ext4_debug("freeing block %llu\n", block); trace_ext4_free_blocks(inode, block, count, flags); if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { BUG_ON(count > 1); ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, inode, bh, block); } /* * If the extent to be freed does not begin on a cluster * boundary, we need to deal with partial clusters at the * beginning and end of the extent. Normally we will free * blocks at the beginning or the end unless we are explicitly * requested to avoid doing so. */ overflow = EXT4_PBLK_COFF(sbi, block); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { overflow = sbi->s_cluster_ratio - overflow; block += overflow; if (count > overflow) count -= overflow; else return; } else { block -= overflow; count += overflow; } } overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { if (count > overflow) count -= overflow; else return; } else count += sbi->s_cluster_ratio - overflow; } if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { int i; int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; for (i = 0; i < count; i++) { cond_resched(); if (is_metadata) bh = sb_find_get_block(inode->i_sb, block + i); ext4_forget(handle, is_metadata, inode, bh, block + i); } } do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT( ext4_get_group_info(sb, block_group)))) return; /* * Check to see if we are freeing blocks across a group * boundary. */ if (EXT4_C2B(sbi, bit) + count > EXT4_BLOCKS_PER_GROUP(sb)) { overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; } count_clusters = EXT4_NUM_B2C(sbi, count); bitmap_bh = ext4_read_block_bitmap(sb, block_group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto error_return; } gdp = ext4_get_group_desc(sb, block_group, &gd_bh); if (!gdp) { err = -EIO; goto error_return; } if (in_range(ext4_block_bitmap(sb, gdp), block, count) || in_range(ext4_inode_bitmap(sb, gdp), block, count) || in_range(block, ext4_inode_table(sb, gdp), sbi->s_itb_per_group) || in_range(block + count - 1, ext4_inode_table(sb, gdp), sbi->s_itb_per_group)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ goto error_return; } BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, bitmap_bh); if (err) goto error_return; /* * We are about to modify some metadata. Call the journal APIs * to unshare ->b_data if a currently-committing transaction is * using it */ BUFFER_TRACE(gd_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gd_bh); if (err) goto error_return; #ifdef AGGRESSIVE_CHECK { int i; for (i = 0; i < count_clusters; i++) BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data)); } #endif trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */ err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) goto error_return; /* * We need to make sure we don't reuse the freed block until after the * transaction is committed. We make an exception if the inode is to be * written in writeback mode since writeback mode has weak data * consistency guarantees. */ if (ext4_handle_valid(handle) && ((flags & EXT4_FREE_BLOCKS_METADATA) || !ext4_should_writeback_data(inode))) { struct ext4_free_data *new_entry; /* * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed * to fail. */ new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS|__GFP_NOFAIL); new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; new_entry->efd_count = count_clusters; new_entry->efd_tid = handle->h_transaction->t_tid; ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); ext4_mb_free_metadata(handle, &e4b, new_entry); } else { /* need to update group_info->bb_free and bitmap * with group lock held. generate_buddy look at * them with group lock_held */ if (test_opt(sb, DISCARD)) { err = ext4_issue_discard(sb, block_group, bit, count, NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%lu failed" " with %d", block_group, bit, count, err); } else EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info); ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); mb_free_blocks(inode, &e4b, bit, count_clusters); } ret = ext4_free_group_clusters(sb, gdp) + count_clusters; ext4_free_group_clusters_set(sb, gdp, ret); ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(count_clusters, &sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_clusters); } /* * on a bigalloc file system, defer the s_freeclusters_counter * update to the caller (ext4_remove_space and friends) so they * can determine if a cluster freed here should be rereserved */ if (!(flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)) { if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); } ext4_mb_unload_buddy(&e4b); /* We dirtied the bitmap block */ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); /* And the group descriptor block */ BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh); if (!err) err = ret; if (overflow && !err) { block += count; count = overflow; put_bh(bitmap_bh); goto do_more; } error_return: brelse(bitmap_bh); ext4_std_error(sb, err); return; } /** * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block * @block: start physical block to add to the block group * @count: number of blocks to free * * This marks the blocks as free in the bitmap and buddy. */ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count) { struct buffer_head *bitmap_bh = NULL; struct buffer_head *gd_bh; ext4_group_t block_group; ext4_grpblk_t bit; unsigned int i; struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_buddy e4b; int err = 0, ret, free_clusters_count; ext4_grpblk_t clusters_freed; ext4_fsblk_t first_cluster = EXT4_B2C(sbi, block); ext4_fsblk_t last_cluster = EXT4_B2C(sbi, block + count - 1); unsigned long cluster_count = last_cluster - first_cluster + 1; ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1); if (count == 0) return 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); /* * Check to see if we are freeing blocks across a group * boundary. */ if (bit + cluster_count > EXT4_CLUSTERS_PER_GROUP(sb)) { ext4_warning(sb, "too many blocks added to group %u", block_group); err = -EINVAL; goto error_return; } bitmap_bh = ext4_read_block_bitmap(sb, block_group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto error_return; } desc = ext4_get_group_desc(sb, block_group, &gd_bh); if (!desc) { err = -EIO; goto error_return; } if (in_range(ext4_block_bitmap(sb, desc), block, count) || in_range(ext4_inode_bitmap(sb, desc), block, count) || in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) || in_range(block + count - 1, ext4_inode_table(sb, desc), sbi->s_itb_per_group)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); err = -EINVAL; goto error_return; } BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, bitmap_bh); if (err) goto error_return; /* * We are about to modify some metadata. Call the journal APIs * to unshare ->b_data if a currently-committing transaction is * using it */ BUFFER_TRACE(gd_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gd_bh); if (err) goto error_return; for (i = 0, clusters_freed = 0; i < cluster_count; i++) { BUFFER_TRACE(bitmap_bh, "clear bit"); if (!mb_test_bit(bit + i, bitmap_bh->b_data)) { ext4_error(sb, "bit already cleared for block %llu", (ext4_fsblk_t)(block + i)); BUFFER_TRACE(bitmap_bh, "bit already cleared"); } else { clusters_freed++; } } err = ext4_mb_load_buddy(sb, block_group, &e4b); if (err) goto error_return; /* * need to update group_info->bb_free and bitmap * with group lock held. generate_buddy look at * them with group lock_held */ ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, cluster_count); mb_free_blocks(NULL, &e4b, bit, cluster_count); free_clusters_count = clusters_freed + ext4_free_group_clusters(sb, desc); ext4_free_group_clusters_set(sb, desc, free_clusters_count); ext4_block_bitmap_csum_set(sb, block_group, desc, bitmap_bh); ext4_group_desc_csum_set(sb, block_group, desc); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, clusters_freed); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(clusters_freed, &sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_clusters); } ext4_mb_unload_buddy(&e4b); /* We dirtied the bitmap block */ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); /* And the group descriptor block */ BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh); if (!err) err = ret; error_return: brelse(bitmap_bh); ext4_std_error(sb, err); return err; } /** * ext4_trim_extent -- function to TRIM one single free extent in the group * @sb: super block for the file system * @start: starting block of the free extent in the alloc. group * @count: number of blocks to TRIM * @group: alloc. group we are working with * @e4b: ext4 buddy for the group * * Trim "count" blocks starting at "start" in the "group". To assure that no * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ static int ext4_trim_extent(struct super_block *sb, int start, int count, ext4_group_t group, struct ext4_buddy *e4b) __releases(bitlock) __acquires(bitlock) { struct ext4_free_extent ex; int ret = 0; trace_ext4_trim_extent(sb, group, start, count); assert_spin_locked(ext4_group_lock_ptr(sb, group)); ex.fe_start = start; ex.fe_group = group; ex.fe_len = count; /* * Mark blocks used, so no one can reuse them while * being trimmed. */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); ret = ext4_issue_discard(sb, group, start, count, NULL); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); return ret; } /** * ext4_trim_all_free -- function to trim all free space in alloc. group * @sb: super block for file system * @group: group to be trimmed * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count * * ext4_trim_all_free walks through group's buddy bitmap searching for free * extents. When the free block is found, ext4_trim_extent is called to TRIM * the extent. * * * ext4_trim_all_free walks through group's block bitmap searching for free * extents. When the free extent is found, mark it as used in group buddy * bitmap. Then issue a TRIM command on this extent and free the extent in * the group buddy bitmap. This is done until whole group is scanned. */ static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { void *bitmap; ext4_grpblk_t next, count = 0, free_count = 0; struct ext4_buddy e4b; int ret = 0; trace_ext4_trim_all_free(sb, group, start, max); ret = ext4_mb_load_buddy(sb, group, &e4b); if (ret) { ext4_warning(sb, "Error %d loading buddy information for %u", ret, group); return ret; } bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) && minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) goto out; start = (e4b.bd_info->bb_first_free > start) ? e4b.bd_info->bb_first_free : start; while (start <= max) { start = mb_find_next_zero_bit(bitmap, max + 1, start); if (start > max) break; next = mb_find_next_bit(bitmap, max + 1, start); if ((next - start) >= minblocks) { ret = ext4_trim_extent(sb, start, next - start, group, &e4b); if (ret && ret != -EOPNOTSUPP) break; ret = 0; count += next - start; } free_count += next - start; start = next + 1; if (fatal_signal_pending(current)) { count = -ERESTARTSYS; break; } if (need_resched()) { ext4_unlock_group(sb, group); cond_resched(); ext4_lock_group(sb, group); } if ((e4b.bd_info->bb_free - free_count) < minblocks) break; } if (!ret) { ret = count; EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); } out: ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); ext4_debug("trimmed %d blocks in the group %d\n", count, group); return ret; } /** * ext4_trim_fs() -- trim ioctl handle function * @sb: superblock for filesystem * @range: fstrim_range structure * * start: First Byte to trim * len: number of Bytes to trim from start * minlen: minimum extent length in Bytes * ext4_trim_fs goes through all allocation groups containing Bytes from * start to start+len. For each such a group ext4_trim_all_free function * is invoked to trim all free space. */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; uint64_t start, end, minlen, trimmed = 0; ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); int ret = 0; start = range->start >> sb->s_blocksize_bits; end = start + (range->len >> sb->s_blocksize_bits) - 1; minlen = EXT4_NUM_B2C(EXT4_SB(sb), range->minlen >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb) || start >= max_blks || range->len < sb->s_blocksize) return -EINVAL; if (end >= max_blks) end = max_blks - 1; if (end <= first_data_blk) goto out; if (start < first_data_blk) start = first_data_blk; /* Determine first and last group to examine based on start and end */ ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start, &first_group, &first_cluster); ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) end, &last_group, &last_cluster); /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) break; } /* * For all the groups except the last one, last cluster will * always be EXT4_CLUSTERS_PER_GROUP(sb)-1, so we only need to * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ if (group == last_group) end = last_cluster; if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, end, minlen); if (cnt < 0) { ret = cnt; break; } trimmed += cnt; } /* * For every group except the first one, we are sure * that the first cluster to discard will be cluster #0. */ first_cluster = 0; } if (!ret) atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; return ret; } /* Iterate all the free extents in the group. */ int ext4_mballoc_query_range( struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t end, ext4_mballoc_query_range_fn formatter, void *priv) { void *bitmap; ext4_grpblk_t next; struct ext4_buddy e4b; int error; error = ext4_mb_load_buddy(sb, group, &e4b); if (error) return error; bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); start = (e4b.bd_info->bb_first_free > start) ? e4b.bd_info->bb_first_free : start; if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; while (start <= end) { start = mb_find_next_zero_bit(bitmap, end + 1, start); if (start > end) break; next = mb_find_next_bit(bitmap, end + 1, start); ext4_unlock_group(sb, group); error = formatter(sb, group, start, next - start, priv); if (error) goto out_unload; ext4_lock_group(sb, group); start = next + 1; } ext4_unlock_group(sb, group); out_unload: ext4_mb_unload_buddy(&e4b); return error; }
1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SIGNAL_H #define _LINUX_SIGNAL_H #include <linux/bug.h> #include <linux/signal_types.h> #include <linux/string.h> struct task_struct; /* for sysctl */ extern int print_fatal_signals; static inline void copy_siginfo(kernel_siginfo_t *to, const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*to)); } static inline void clear_siginfo(kernel_siginfo_t *info) { memset(info, 0, sizeof(*info)); } #define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo)) static inline void copy_siginfo_to_external(siginfo_t *to, const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*from)); memset(((char *)to) + sizeof(struct kernel_siginfo), 0, SI_EXPANSION_SIZE); } int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); enum siginfo_layout { SIL_KILL, SIL_TIMER, SIL_POLL, SIL_FAULT, SIL_FAULT_MCEERR, SIL_FAULT_BNDERR, SIL_FAULT_PKUERR, SIL_CHLD, SIL_RT, SIL_SYS, }; enum siginfo_layout siginfo_layout(unsigned sig, int si_code); /* * Define some primitives to manipulate sigset_t. */ #ifndef __HAVE_ARCH_SIG_BITOPS #include <linux/bitops.h> /* We don't use <linux/bitops.h> for these because there is no need to be atomic. */ static inline void sigaddset(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) set->sig[0] |= 1UL << sig; else set->sig[sig / _NSIG_BPW] |= 1UL << (sig % _NSIG_BPW); } static inline void sigdelset(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) set->sig[0] &= ~(1UL << sig); else set->sig[sig / _NSIG_BPW] &= ~(1UL << (sig % _NSIG_BPW)); } static inline int sigismember(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) return 1 & (set->sig[0] >> sig); else return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW)); } #endif /* __HAVE_ARCH_SIG_BITOPS */ static inline int sigisemptyset(sigset_t *set) { switch (_NSIG_WORDS) { case 4: return (set->sig[3] | set->sig[2] | set->sig[1] | set->sig[0]) == 0; case 2: return (set->sig[1] | set->sig[0]) == 0; case 1: return set->sig[0] == 0; default: BUILD_BUG(); return 0; } } static inline int sigequalsets(const sigset_t *set1, const sigset_t *set2) { switch (_NSIG_WORDS) { case 4: return (set1->sig[3] == set2->sig[3]) && (set1->sig[2] == set2->sig[2]) && (set1->sig[1] == set2->sig[1]) && (set1->sig[0] == set2->sig[0]); case 2: return (set1->sig[1] == set2->sig[1]) && (set1->sig[0] == set2->sig[0]); case 1: return set1->sig[0] == set2->sig[0]; } return 0; } #define sigmask(sig) (1UL << ((sig) - 1)) #ifndef __HAVE_ARCH_SIG_SETOPS #include <linux/string.h> #define _SIG_SET_BINOP(name, op) \ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ { \ unsigned long a0, a1, a2, a3, b0, b1, b2, b3; \ \ switch (_NSIG_WORDS) { \ case 4: \ a3 = a->sig[3]; a2 = a->sig[2]; \ b3 = b->sig[3]; b2 = b->sig[2]; \ r->sig[3] = op(a3, b3); \ r->sig[2] = op(a2, b2); \ fallthrough; \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ fallthrough; \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ break; \ default: \ BUILD_BUG(); \ } \ } #define _sig_or(x,y) ((x) | (y)) _SIG_SET_BINOP(sigorsets, _sig_or) #define _sig_and(x,y) ((x) & (y)) _SIG_SET_BINOP(sigandsets, _sig_and) #define _sig_andn(x,y) ((x) & ~(y)) _SIG_SET_BINOP(sigandnsets, _sig_andn) #undef _SIG_SET_BINOP #undef _sig_or #undef _sig_and #undef _sig_andn #define _SIG_SET_OP(name, op) \ static inline void name(sigset_t *set) \ { \ switch (_NSIG_WORDS) { \ case 4: set->sig[3] = op(set->sig[3]); \ set->sig[2] = op(set->sig[2]); \ fallthrough; \ case 2: set->sig[1] = op(set->sig[1]); \ fallthrough; \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ BUILD_BUG(); \ } \ } #define _sig_not(x) (~(x)) _SIG_SET_OP(signotset, _sig_not) #undef _SIG_SET_OP #undef _sig_not static inline void sigemptyset(sigset_t *set) { switch (_NSIG_WORDS) { default: memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; fallthrough; case 1: set->sig[0] = 0; break; } } static inline void sigfillset(sigset_t *set) { switch (_NSIG_WORDS) { default: memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; fallthrough; case 1: set->sig[0] = -1; break; } } /* Some extensions for manipulating the low 32 signals in particular. */ static inline void sigaddsetmask(sigset_t *set, unsigned long mask) { set->sig[0] |= mask; } static inline void sigdelsetmask(sigset_t *set, unsigned long mask) { set->sig[0] &= ~mask; } static inline int sigtestsetmask(sigset_t *set, unsigned long mask) { return (set->sig[0] & mask) != 0; } static inline void siginitset(sigset_t *set, unsigned long mask) { set->sig[0] = mask; switch (_NSIG_WORDS) { default: memset(&set->sig[1], 0, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = 0; break; case 1: ; } } static inline void siginitsetinv(sigset_t *set, unsigned long mask) { set->sig[0] = ~mask; switch (_NSIG_WORDS) { default: memset(&set->sig[1], -1, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = -1; break; case 1: ; } } #endif /* __HAVE_ARCH_SIG_SETOPS */ static inline void init_sigpending(struct sigpending *sig) { sigemptyset(&sig->signal); INIT_LIST_HEAD(&sig->list); } extern void flush_sigqueue(struct sigpending *queue); /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ static inline int valid_signal(unsigned long sig) { return sig <= _NSIG ? 1 : 0; } struct timespec; struct pt_regs; enum pid_type; extern int next_signal(struct sigpending *pending, sigset_t *mask); extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; extern bool get_signal(struct ksignal *ksig); extern void signal_setup_done(int failed, struct ksignal *ksig, int stepping); extern void exit_signals(struct task_struct *tsk); extern void kernel_sigaction(int, __sighandler_t); #define SIG_KTHREAD ((__force __sighandler_t)2) #define SIG_KTHREAD_KERNEL ((__force __sighandler_t)3) static inline void allow_signal(int sig) { /* * Kernel threads handle their own signals. Let the signal code * know it'll be handled, so that they don't get converted to * SIGKILL or just silently dropped. */ kernel_sigaction(sig, SIG_KTHREAD); } static inline void allow_kernel_signal(int sig) { /* * Kernel threads handle their own signals. Let the signal code * know signals sent by the kernel will be handled, so that they * don't get silently dropped. */ kernel_sigaction(sig, SIG_KTHREAD_KERNEL); } static inline void disallow_signal(int sig) { kernel_sigaction(sig, SIG_IGN); } extern struct kmem_cache *sighand_cachep; extern bool unhandled_signal(struct task_struct *tsk, int sig); /* * In POSIX a signal is sent either to a specific thread (Linux task) * or to the process as a whole (Linux thread group). How the signal * is sent determines whether it's to one thread or the whole group, * which determines which signal mask(s) are involved in blocking it * from being delivered until later. When the signal is delivered, * either it's caught or ignored by a user handler or it has a default * effect that applies to the whole thread group (POSIX process). * * The possible effects an unblocked signal set to SIG_DFL can have are: * ignore - Nothing Happens * terminate - kill the process, i.e. all threads in the group, * similar to exit_group. The group leader (only) reports * WIFSIGNALED status to its parent. * coredump - write a core dump file describing all threads using * the same mm and then kill all those threads * stop - stop all the threads in the group, i.e. TASK_STOPPED state * * SIGKILL and SIGSTOP cannot be caught, blocked, or ignored. * Other signals when not blocked and set to SIG_DFL behaves as follows. * The job control signals also have other special effects. * * +--------------------+------------------+ * | POSIX signal | default action | * +--------------------+------------------+ * | SIGHUP | terminate | * | SIGINT | terminate | * | SIGQUIT | coredump | * | SIGILL | coredump | * | SIGTRAP | coredump | * | SIGABRT/SIGIOT | coredump | * | SIGBUS | coredump | * | SIGFPE | coredump | * | SIGKILL | terminate(+) | * | SIGUSR1 | terminate | * | SIGSEGV | coredump | * | SIGUSR2 | terminate | * | SIGPIPE | terminate | * | SIGALRM | terminate | * | SIGTERM | terminate | * | SIGCHLD | ignore | * | SIGCONT | ignore(*) | * | SIGSTOP | stop(*)(+) | * | SIGTSTP | stop(*) | * | SIGTTIN | stop(*) | * | SIGTTOU | stop(*) | * | SIGURG | ignore | * | SIGXCPU | coredump | * | SIGXFSZ | coredump | * | SIGVTALRM | terminate | * | SIGPROF | terminate | * | SIGPOLL/SIGIO | terminate | * | SIGSYS/SIGUNUSED | coredump | * | SIGSTKFLT | terminate | * | SIGWINCH | ignore | * | SIGPWR | terminate | * | SIGRTMIN-SIGRTMAX | terminate | * +--------------------+------------------+ * | non-POSIX signal | default action | * +--------------------+------------------+ * | SIGEMT | coredump | * +--------------------+------------------+ * * (+) For SIGKILL and SIGSTOP the action is "always", not just "default". * (*) Special job control effects: * When SIGCONT is sent, it resumes the process (all threads in the group) * from TASK_STOPPED state and also clears any pending/queued stop signals * (any of those marked with "stop(*)"). This happens regardless of blocking, * catching, or ignoring SIGCONT. When any stop signal is sent, it clears * any pending/queued SIGCONT signals; this happens regardless of blocking, * catching, or ignored the stop signal, though (except for SIGSTOP) the * default action of stopping the process may happen later or never. */ #ifdef SIGEMT #define SIGEMT_MASK rt_sigmask(SIGEMT) #else #define SIGEMT_MASK 0 #endif #if SIGRTMIN > BITS_PER_LONG #define rt_sigmask(sig) (1ULL << ((sig)-1)) #else #define rt_sigmask(sig) sigmask(sig) #endif #define siginmask(sig, mask) \ ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) #define SIG_KERNEL_STOP_MASK (\ rt_sigmask(SIGSTOP) | rt_sigmask(SIGTSTP) | \ rt_sigmask(SIGTTIN) | rt_sigmask(SIGTTOU) ) #define SIG_KERNEL_COREDUMP_MASK (\ rt_sigmask(SIGQUIT) | rt_sigmask(SIGILL) | \ rt_sigmask(SIGTRAP) | rt_sigmask(SIGABRT) | \ rt_sigmask(SIGFPE) | rt_sigmask(SIGSEGV) | \ rt_sigmask(SIGBUS) | rt_sigmask(SIGSYS) | \ rt_sigmask(SIGXCPU) | rt_sigmask(SIGXFSZ) | \ SIGEMT_MASK ) #define SIG_KERNEL_IGNORE_MASK (\ rt_sigmask(SIGCONT) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGWINCH) | rt_sigmask(SIGURG) ) #define SIG_SPECIFIC_SICODES_MASK (\ rt_sigmask(SIGILL) | rt_sigmask(SIGFPE) | \ rt_sigmask(SIGSEGV) | rt_sigmask(SIGBUS) | \ rt_sigmask(SIGTRAP) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGPOLL) | rt_sigmask(SIGSYS) | \ SIGEMT_MASK ) #define sig_kernel_only(sig) siginmask(sig, SIG_KERNEL_ONLY_MASK) #define sig_kernel_coredump(sig) siginmask(sig, SIG_KERNEL_COREDUMP_MASK) #define sig_kernel_ignore(sig) siginmask(sig, SIG_KERNEL_IGNORE_MASK) #define sig_kernel_stop(sig) siginmask(sig, SIG_KERNEL_STOP_MASK) #define sig_specific_sicodes(sig) siginmask(sig, SIG_SPECIFIC_SICODES_MASK) #define sig_fatal(t, signr) \ (!siginmask(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \ (t)->sighand->action[(signr)-1].sa.sa_handler == SIG_DFL) void signals_init(void); int restore_altstack(const stack_t __user *); int __save_altstack(stack_t __user *, unsigned long); #define unsafe_save_altstack(uss, sp, label) do { \ stack_t __user *__uss = uss; \ struct task_struct *t = current; \ unsafe_put_user((void __user *)t->sas_ss_sp, &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ if (t->sas_ss_flags & SS_AUTODISARM) \ sas_ss_reset(t); \ } while (0); #ifdef CONFIG_PROC_FS struct seq_file; extern void render_sigset_t(struct seq_file *, const char *, sigset_t *); #endif #endif /* _LINUX_SIGNAL_H */
1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 /* SPDX-License-Identifier: GPL-2.0 */ /* * A security context is a set of security attributes * associated with each subject and object controlled * by the security policy. Security contexts are * externally represented as variable-length strings * that can be interpreted by a user or application * with an understanding of the security policy. * Internally, the security server uses a simple * structure. This structure is private to the * security server and can be changed without affecting * clients of the security server. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ #ifndef _SS_CONTEXT_H_ #define _SS_CONTEXT_H_ #include "ebitmap.h" #include "mls_types.h" #include "security.h" /* * A security context consists of an authenticated user * identity, a role, a type and a MLS range. */ struct context { u32 user; u32 role; u32 type; u32 len; /* length of string in bytes */ struct mls_range range; char *str; /* string representation if context cannot be mapped. */ }; static inline void mls_context_init(struct context *c) { memset(&c->range, 0, sizeof(c->range)); } static inline int mls_context_cpy(struct context *dst, struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the low level of 'src'. */ static inline int mls_context_cpy_low(struct context *dst, struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[0].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the high level of 'src'. */ static inline int mls_context_cpy_high(struct context *dst, struct context *src) { int rc; dst->range.level[0].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[1].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } static inline int mls_context_glblub(struct context *dst, struct context *c1, struct context *c2) { struct mls_range *dr = &dst->range, *r1 = &c1->range, *r2 = &c2->range; int rc = 0; if (r1->level[1].sens < r2->level[0].sens || r2->level[1].sens < r1->level[0].sens) /* These ranges have no common sensitivities */ return -EINVAL; /* Take the greatest of the low */ dr->level[0].sens = max(r1->level[0].sens, r2->level[0].sens); /* Take the least of the high */ dr->level[1].sens = min(r1->level[1].sens, r2->level[1].sens); rc = ebitmap_and(&dr->level[0].cat, &r1->level[0].cat, &r2->level[0].cat); if (rc) goto out; rc = ebitmap_and(&dr->level[1].cat, &r1->level[1].cat, &r2->level[1].cat); if (rc) goto out; out: return rc; } static inline int mls_context_cmp(struct context *c1, struct context *c2) { return ((c1->range.level[0].sens == c2->range.level[0].sens) && ebitmap_cmp(&c1->range.level[0].cat, &c2->range.level[0].cat) && (c1->range.level[1].sens == c2->range.level[1].sens) && ebitmap_cmp(&c1->range.level[1].cat, &c2->range.level[1].cat)); } static inline void mls_context_destroy(struct context *c) { ebitmap_destroy(&c->range.level[0].cat); ebitmap_destroy(&c->range.level[1].cat); mls_context_init(c); } static inline void context_init(struct context *c) { memset(c, 0, sizeof(*c)); } static inline int context_cpy(struct context *dst, struct context *src) { int rc; dst->user = src->user; dst->role = src->role; dst->type = src->type; if (src->str) { dst->str = kstrdup(src->str, GFP_ATOMIC); if (!dst->str) return -ENOMEM; dst->len = src->len; } else { dst->str = NULL; dst->len = 0; } rc = mls_context_cpy(dst, src); if (rc) { kfree(dst->str); return rc; } return 0; } static inline void context_destroy(struct context *c) { c->user = c->role = c->type = 0; kfree(c->str); c->str = NULL; c->len = 0; mls_context_destroy(c); } static inline int context_cmp(struct context *c1, struct context *c2) { if (c1->len && c2->len) return (c1->len == c2->len && !strcmp(c1->str, c2->str)); if (c1->len || c2->len) return 0; return ((c1->user == c2->user) && (c1->role == c2->role) && (c1->type == c2->type) && mls_context_cmp(c1, c2)); } u32 context_compute_hash(const struct context *c); #endif /* _SS_CONTEXT_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 /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef LLIST_H #define LLIST_H /* * Lock-less NULL terminated single linked list * * Cases where locking is not needed: * If there are multiple producers and multiple consumers, llist_add can be * used in producers and llist_del_all can be used in consumers simultaneously * without locking. Also a single consumer can use llist_del_first while * multiple producers simultaneously use llist_add, without any locking. * * Cases where locking is needed: * If we have multiple consumers with llist_del_first used in one consumer, and * llist_del_first or llist_del_all used in other consumers, then a lock is * needed. This is because llist_del_first depends on list->first->next not * changing, but without lock protection, there's no way to be sure about that * if a preemption happens in the middle of the delete operation and on being * preempted back, the list->first is the same as before causing the cmpxchg in * llist_del_first to succeed. For example, while a llist_del_first operation * is in progress in one consumer, then a llist_del_first, llist_add, * llist_add (or llist_del_all, llist_add, llist_add) sequence in another * consumer may cause violations. * * This can be summarized as follows: * * | add | del_first | del_all * add | - | - | - * del_first | | L | L * del_all | | | - * * Where, a particular row's operation can happen concurrently with a column's * operation, with "-" being no lock needed, while "L" being lock is needed. * * The list entries deleted via llist_del_all can be traversed with * traversing function such as llist_for_each etc. But the list * entries can not be traversed safely before deleted from the list. * The order of deleted entries is from the newest to the oldest added * one. If you want to traverse from the oldest to the newest, you * must reverse the order by yourself before traversing. * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/atomic.h> #include <linux/kernel.h> struct llist_head { struct llist_node *first; }; struct llist_node { struct llist_node *next; }; #define LLIST_HEAD_INIT(name) { NULL } #define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name) /** * init_llist_head - initialize lock-less list head * @head: the head for your lock-less list */ static inline void init_llist_head(struct llist_head *list) { list->first = NULL; } /** * llist_entry - get the struct of this entry * @ptr: the &struct llist_node pointer. * @type: the type of the struct this is embedded in. * @member: the name of the llist_node within the struct. */ #define llist_entry(ptr, type, member) \ container_of(ptr, type, member) /** * member_address_is_nonnull - check whether the member address is not NULL * @ptr: the object pointer (struct type * that contains the llist_node) * @member: the name of the llist_node within the struct. * * This macro is conceptually the same as * &ptr->member != NULL * but it works around the fact that compilers can decide that taking a member * address is never a NULL pointer. * * Real objects that start at a high address and have a member at NULL are * unlikely to exist, but such pointers may be returned e.g. by the * container_of() macro. */ #define member_address_is_nonnull(ptr, member) \ ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) /** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each(pos, node) \ for ((pos) = (node); pos; (pos) = (pos)->next) /** * llist_for_each_safe - iterate over some deleted entries of a lock-less list * safe against removal of list entry * @pos: the &struct llist_node to use as a loop cursor * @n: another &struct llist_node to use as temporary storage * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_safe(pos, n, node) \ for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n)) /** * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type * @pos: the type * to use as a loop cursor. * @node: the fist entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** * llist_for_each_entry_safe - iterate over some deleted entries of lock-less list of given type * safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @node: the first entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test * * Not guaranteed to be accurate or up to date. Just a quick way to * test whether the list is empty without deleting something from the * list. */ static inline bool llist_empty(const struct llist_head *head) { return READ_ONCE(head->first) == NULL; } static inline struct llist_node *llist_next(struct llist_node *node) { return node->next; } extern bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head); /** * llist_add - add a new entry * @new: new entry to be added * @head: the head for your lock-less list * * Returns true if the list was empty prior to adding this entry. */ static inline bool llist_add(struct llist_node *new, struct llist_head *head) { return llist_add_batch(new, new, head); } /** * llist_del_all - delete all entries from lock-less list * @head: the head of lock-less list to delete all entries * * If list is empty, return NULL, otherwise, delete all entries and * return the pointer to the first entry. The order of entries * deleted is from the newest to the oldest added one. */ static inline struct llist_node *llist_del_all(struct llist_head *head) { return xchg(&head->first, NULL); } extern struct llist_node *llist_del_first(struct llist_head *head); struct llist_node *llist_reverse_order(struct llist_node *head); #endif /* LLIST_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Resizable, Scalable, Concurrent Hash Table * * Copyright (c) 2015-2016 Herbert Xu <herbert@gondor.apana.org.au> * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * * Code partially derived from nft_hash * Rewritten with rehash code from br_multicast plus single list * pointer as suggested by Josh Triplett * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H #include <linux/err.h> #include <linux/errno.h> #include <linux/jhash.h> #include <linux/list_nulls.h> #include <linux/workqueue.h> #include <linux/rculist.h> #include <linux/bit_spinlock.h> #include <linux/rhashtable-types.h> /* * Objects in an rhashtable have an embedded struct rhash_head * which is linked into as hash chain from the hash table - or one * of two or more hash tables when the rhashtable is being resized. * The end of the chain is marked with a special nulls marks which has * the least significant bit set but otherwise stores the address of * the hash bucket. This allows us to be sure we've found the end * of the right list. * The value stored in the hash bucket has BIT(0) used as a lock bit. * This bit must be atomically set before any changes are made to * the chain. To avoid dereferencing this pointer without clearing * the bit first, we use an opaque 'struct rhash_lock_head *' for the * pointer stored in the bucket. This struct needs to be defined so * that rcu_dereference() works on it, but it has no content so a * cast is needed for it to be useful. This ensures it isn't * used by mistake with clearing the lock bit first. */ struct rhash_lock_head {}; /* Maximum chain length before rehash * * The maximum (not average) chain length grows with the size of the hash * table, at a rate of (log N)/(log log N). * * The value of 16 is selected so that even if the hash table grew to * 2^32 you would not expect the maximum chain length to exceed it * unless we are under attack (or extremely unlucky). * * As this limit is only to detect attacks, we don't need to set it to a * lower value as you'd need the chain length to vastly exceed 16 to have * any real effect on the system. */ #define RHT_ELASTICITY 16u /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets * @nest: Number of bits of first-level nested table. * @rehash: Current bucket being rehashed * @hash_rnd: Random seed to fold into hash * @walkers: List of active walkers * @rcu: RCU structure for freeing the table * @future_tbl: Table under construction during rehashing * @ntbl: Nested table used when out of memory. * @buckets: size * hash buckets */ struct bucket_table { unsigned int size; unsigned int nest; u32 hash_rnd; struct list_head walkers; struct rcu_head rcu; struct bucket_table __rcu *future_tbl; struct lockdep_map dep_map; struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; /* * NULLS_MARKER() expects a hash value with the low * bits mostly likely to be significant, and it discards * the msb. * We give it an address, in which the bottom bit is * always 0, and the msb might be significant. * So we shift the address down one bit to align with * expectations and avoid losing a significant bit. * * We never store the NULLS_MARKER in the hash table * itself as we need the lsb for locking. * Instead we store a NULL */ #define RHT_NULLS_MARKER(ptr) \ ((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1)) #define INIT_RHT_NULLS_HEAD(ptr) \ ((ptr) = NULL) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { return ((unsigned long) ptr & 1); } static inline void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he) { return (char *)he - ht->p.head_offset; } static inline unsigned int rht_bucket_index(const struct bucket_table *tbl, unsigned int hash) { return hash & (tbl->size - 1); } static inline unsigned int rht_key_get_hash(struct rhashtable *ht, const void *key, const struct rhashtable_params params, unsigned int hash_rnd) { unsigned int hash; /* params must be equal to ht->p if it isn't constant. */ if (!__builtin_constant_p(params.key_len)) hash = ht->p.hashfn(key, ht->key_len, hash_rnd); else if (params.key_len) { unsigned int key_len = params.key_len; if (params.hashfn) hash = params.hashfn(key, key_len, hash_rnd); else if (key_len & (sizeof(u32) - 1)) hash = jhash(key, key_len, hash_rnd); else hash = jhash2(key, key_len / sizeof(u32), hash_rnd); } else { unsigned int key_len = ht->p.key_len; if (params.hashfn) hash = params.hashfn(key, key_len, hash_rnd); else hash = jhash(key, key_len, hash_rnd); } return hash; } static inline unsigned int rht_key_hashfn( struct rhashtable *ht, const struct bucket_table *tbl, const void *key, const struct rhashtable_params params) { unsigned int hash = rht_key_get_hash(ht, key, params, tbl->hash_rnd); return rht_bucket_index(tbl, hash); } static inline unsigned int rht_head_hashfn( struct rhashtable *ht, const struct bucket_table *tbl, const struct rhash_head *he, const struct rhashtable_params params) { const char *ptr = rht_obj(ht, he); return likely(params.obj_hashfn) ? rht_bucket_index(tbl, params.obj_hashfn(ptr, params.key_len ?: ht->p.key_len, tbl->hash_rnd)) : rht_key_hashfn(ht, tbl, ptr + params.key_offset, params); } /** * rht_grow_above_75 - returns true if nelems > 0.75 * table-size * @ht: hash table * @tbl: current table */ static inline bool rht_grow_above_75(const struct rhashtable *ht, const struct bucket_table *tbl) { /* Expand table when exceeding 75% load */ return atomic_read(&ht->nelems) > (tbl->size / 4 * 3) && (!ht->p.max_size || tbl->size < ht->p.max_size); } /** * rht_shrink_below_30 - returns true if nelems < 0.3 * table-size * @ht: hash table * @tbl: current table */ static inline bool rht_shrink_below_30(const struct rhashtable *ht, const struct bucket_table *tbl) { /* Shrink table beneath 30% load */ return atomic_read(&ht->nelems) < (tbl->size * 3 / 10) && tbl->size > ht->p.min_size; } /** * rht_grow_above_100 - returns true if nelems > table-size * @ht: hash table * @tbl: current table */ static inline bool rht_grow_above_100(const struct rhashtable *ht, const struct bucket_table *tbl) { return atomic_read(&ht->nelems) > tbl->size && (!ht->p.max_size || tbl->size < ht->p.max_size); } /** * rht_grow_above_max - returns true if table is above maximum * @ht: hash table * @tbl: current table */ static inline bool rht_grow_above_max(const struct rhashtable *ht, const struct bucket_table *tbl) { return atomic_read(&ht->nelems) >= ht->max_elems; } #ifdef CONFIG_PROVE_LOCKING int lockdep_rht_mutex_is_held(struct rhashtable *ht); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); #else static inline int lockdep_rht_mutex_is_held(struct rhashtable *ht) { return 1; } static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash) { return 1; } #endif /* CONFIG_PROVE_LOCKING */ void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj); void rhashtable_walk_enter(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); int rhashtable_walk_start_check(struct rhashtable_iter *iter) __acquires(RCU); static inline void rhashtable_walk_start(struct rhashtable_iter *iter) { (void)rhashtable_walk_start_check(iter); } void *rhashtable_walk_next(struct rhashtable_iter *iter); void *rhashtable_walk_peek(struct rhashtable_iter *iter); void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU); void rhashtable_free_and_destroy(struct rhashtable *ht, void (*free_fn)(void *ptr, void *arg), void *arg); void rhashtable_destroy(struct rhashtable *ht); struct rhash_lock_head __rcu **rht_bucket_nested( const struct bucket_table *tbl, unsigned int hash); struct rhash_lock_head __rcu **__rht_bucket_nested( const struct bucket_table *tbl, unsigned int hash); struct rhash_lock_head __rcu **rht_bucket_nested_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash); #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) #define rht_dereference_rcu(p, ht) \ rcu_dereference_check(p, lockdep_rht_mutex_is_held(ht)) #define rht_dereference_bucket(p, tbl, hash) \ rcu_dereference_protected(p, lockdep_rht_bucket_is_held(tbl, hash)) #define rht_dereference_bucket_rcu(p, tbl, hash) \ rcu_dereference_check(p, lockdep_rht_bucket_is_held(tbl, hash)) #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) static inline struct rhash_lock_head __rcu *const *rht_bucket( const struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } static inline struct rhash_lock_head __rcu **rht_bucket_var( struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } static inline struct rhash_lock_head __rcu **rht_bucket_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : &tbl->buckets[hash]; } /* * We lock a bucket by setting BIT(0) in the pointer - this is always * zero in real pointers. The NULLS mark is never stored in the bucket, * rather we store NULL if the bucket is empty. * bit_spin_locks do not handle contention well, but the whole point * of the hashtable design is to achieve minimum per-bucket contention. * A nested hash table might not have a bucket pointer. In that case * we cannot get a lock. For remove and replace the bucket cannot be * interesting and doesn't need locking. * For insert we allocate the bucket if this is the last bucket_table, * and then take the lock. * Sometimes we unlock a bucket by writing a new pointer there. In that * case we don't need to unlock, but we do need to reset state such as * local_bh. For that we have rht_assign_unlock(). As rcu_assign_pointer() * provides the same release semantics that bit_spin_unlock() provides, * this is safe. * When we write to a bucket without unlocking, we use rht_assign_locked(). */ static inline void rht_lock(struct bucket_table *tbl, struct rhash_lock_head __rcu **bkt) { local_bh_disable(); bit_spin_lock(0, (unsigned long *)bkt); lock_map_acquire(&tbl->dep_map); } static inline void rht_lock_nested(struct bucket_table *tbl, struct rhash_lock_head __rcu **bucket, unsigned int subclass) { local_bh_disable(); bit_spin_lock(0, (unsigned long *)bucket); lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_); } static inline void rht_unlock(struct bucket_table *tbl, struct rhash_lock_head __rcu **bkt) { lock_map_release(&tbl->dep_map); bit_spin_unlock(0, (unsigned long *)bkt); local_bh_enable(); } static inline struct rhash_head *__rht_ptr( struct rhash_lock_head *p, struct rhash_lock_head __rcu *const *bkt) { return (struct rhash_head *) ((unsigned long)p & ~BIT(0) ?: (unsigned long)RHT_NULLS_MARKER(bkt)); } /* * Where 'bkt' is a bucket and might be locked: * rht_ptr_rcu() dereferences that pointer and clears the lock bit. * rht_ptr() dereferences in a context where the bucket is locked. * rht_ptr_exclusive() dereferences in a context where exclusive * access is guaranteed, such as when destroying the table. */ static inline struct rhash_head *rht_ptr_rcu( struct rhash_lock_head __rcu *const *bkt) { return __rht_ptr(rcu_dereference(*bkt), bkt); } static inline struct rhash_head *rht_ptr( struct rhash_lock_head __rcu *const *bkt, struct bucket_table *tbl, unsigned int hash) { return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt); } static inline struct rhash_head *rht_ptr_exclusive( struct rhash_lock_head __rcu *const *bkt) { return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt); } static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { if (rht_is_a_nulls(obj)) obj = NULL; rcu_assign_pointer(*bkt, (void *)((unsigned long)obj | BIT(0))); } static inline void rht_assign_unlock(struct bucket_table *tbl, struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { if (rht_is_a_nulls(obj)) obj = NULL; lock_map_release(&tbl->dep_map); rcu_assign_pointer(*bkt, (void *)obj); preempt_enable(); __release(bitlock); local_bh_enable(); } /** * rht_for_each_from - iterate over hash chain from given head * @pos: the &struct rhash_head to use as a loop cursor. * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index */ #define rht_for_each_from(pos, head, tbl, hash) \ for (pos = head; \ !rht_is_a_nulls(pos); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) /** * rht_for_each - iterate over hash chain * @pos: the &struct rhash_head to use as a loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index */ #define rht_for_each(pos, tbl, hash) \ rht_for_each_from(pos, rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ tbl, hash) /** * rht_for_each_entry_from - iterate over hash chain from given head * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry_from(tpos, pos, head, tbl, hash, member) \ for (pos = head; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) /** * rht_for_each_entry - iterate over hash chain of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. */ #define rht_for_each_entry(tpos, pos, tbl, hash, member) \ rht_for_each_entry_from(tpos, pos, \ rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ tbl, hash, member) /** * rht_for_each_entry_safe - safely iterate over hash chain of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @next: the &struct rhash_head to use as next in loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. * * This hash chain list-traversal primitive allows for the looped code to * remove the loop cursor from the list. */ #define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ for (pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ next = !rht_is_a_nulls(pos) ? \ rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = next, \ next = !rht_is_a_nulls(pos) ? \ rht_dereference_bucket(pos->next, tbl, hash) : NULL) /** * rht_for_each_rcu_from - iterate over rcu hash chain from given head * @pos: the &struct rhash_head to use as a loop cursor. * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * * This hash chain list-traversal primitive may safely run concurrently with * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_rcu_from(pos, head, tbl, hash) \ for (({barrier(); }), \ pos = head; \ !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) /** * rht_for_each_rcu - iterate over rcu hash chain * @pos: the &struct rhash_head to use as a loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * * This hash chain list-traversal primitive may safely run concurrently with * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_rcu(pos, tbl, hash) \ for (({barrier(); }), \ pos = rht_ptr_rcu(rht_bucket(tbl, hash)); \ !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) /** * rht_for_each_entry_rcu_from - iterated over rcu hash chain from given head * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @head: the &struct rhash_head to start from * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. * * This hash chain list-traversal primitive may safely run concurrently with * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_entry_rcu_from(tpos, pos, head, tbl, hash, member) \ for (({barrier(); }), \ pos = head; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket_rcu(pos->next, tbl, hash)) /** * rht_for_each_entry_rcu - iterate over rcu hash chain of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct rhash_head to use as a loop cursor. * @tbl: the &struct bucket_table * @hash: the hash value / bucket index * @member: name of the &struct rhash_head within the hashable struct. * * This hash chain list-traversal primitive may safely run concurrently with * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ rht_for_each_entry_rcu_from(tpos, pos, \ rht_ptr_rcu(rht_bucket(tbl, hash)), \ tbl, hash, member) /** * rhl_for_each_rcu - iterate over rcu hash table list * @pos: the &struct rlist_head to use as a loop cursor. * @list: the head of the list * * This hash chain list-traversal primitive should be used on the * list returned by rhltable_lookup. */ #define rhl_for_each_rcu(pos, list) \ for (pos = list; pos; pos = rcu_dereference_raw(pos->next)) /** * rhl_for_each_entry_rcu - iterate over rcu hash table list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct rlist_head to use as a loop cursor. * @list: the head of the list * @member: name of the &struct rlist_head within the hashable struct. * * This hash chain list-traversal primitive should be used on the * list returned by rhltable_lookup. */ #define rhl_for_each_entry_rcu(tpos, pos, list, member) \ for (pos = list; pos && rht_entry(tpos, pos, member); \ pos = rcu_dereference_raw(pos->next)) static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, const void *obj) { struct rhashtable *ht = arg->ht; const char *ptr = obj; return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len); } /* Internal function, do not use. */ static inline struct rhash_head *__rhashtable_lookup( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { struct rhashtable_compare_arg arg = { .ht = ht, .key = key, }; struct rhash_lock_head __rcu *const *bkt; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); bkt = rht_bucket(tbl, hash); do { rht_for_each_rcu_from(he, rht_ptr_rcu(bkt), tbl, hash) { if (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) continue; return he; } /* An object might have been moved to a different hash chain, * while we walk along it - better check and retry. */ } while (he != RHT_NULLS_MARKER(bkt)); /* Ensure we see any new tables. */ smp_rmb(); tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(tbl)) goto restart; return NULL; } /** * rhashtable_lookup - search hash table * @ht: hash table * @key: the pointer to the key * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking * for a entry with an identical key. The first matching entry is returned. * * This must only be called under the RCU read lock. * * Returns the first entry on which the compare function returned true. */ static inline void *rhashtable_lookup( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { struct rhash_head *he = __rhashtable_lookup(ht, key, params); return he ? rht_obj(ht, he) : NULL; } /** * rhashtable_lookup_fast - search hash table, without RCU read lock * @ht: hash table * @key: the pointer to the key * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking * for a entry with an identical key. The first matching entry is returned. * * Only use this function when you have other mechanisms guaranteeing * that the object won't go away after the RCU read lock is released. * * Returns the first entry on which the compare function returned true. */ static inline void *rhashtable_lookup_fast( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { void *obj; rcu_read_lock(); obj = rhashtable_lookup(ht, key, params); rcu_read_unlock(); return obj; } /** * rhltable_lookup - search hash list table * @hlt: hash table * @key: the pointer to the key * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking * for a entry with an identical key. All matching entries are returned * in a list. * * This must only be called under the RCU read lock. * * Returns the list of entries that match the given key. */ static inline struct rhlist_head *rhltable_lookup( struct rhltable *hlt, const void *key, const struct rhashtable_params params) { struct rhash_head *he = __rhashtable_lookup(&hlt->ht, key, params); return he ? container_of(he, struct rhlist_head, rhead) : NULL; } /* Internal function, please use rhashtable_insert_fast() instead. This * function returns the existing element already in hashes in there is a clash, * otherwise it returns an error via ERR_PTR(). */ static inline void *__rhashtable_insert_fast( struct rhashtable *ht, const void *key, struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { struct rhashtable_compare_arg arg = { .ht = ht, .key = key, }; struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct bucket_table *tbl; struct rhash_head *head; unsigned int hash; int elasticity; void *data; rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); hash = rht_head_hashfn(ht, tbl, obj, params); elasticity = RHT_ELASTICITY; bkt = rht_bucket_insert(ht, tbl, hash); data = ERR_PTR(-ENOMEM); if (!bkt) goto out; pprev = NULL; rht_lock(tbl, bkt); if (unlikely(rcu_access_pointer(tbl->future_tbl))) { slow_path: rht_unlock(tbl, bkt); rcu_read_unlock(); return rhashtable_insert_slow(ht, key, obj); } rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *plist; struct rhlist_head *list; elasticity--; if (!key || (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, head)) : rhashtable_compare(&arg, rht_obj(ht, head)))) { pprev = &head->next; continue; } data = rht_obj(ht, head); if (!rhlist) goto out_unlock; list = container_of(obj, struct rhlist_head, rhead); plist = container_of(head, struct rhlist_head, rhead); RCU_INIT_POINTER(list->next, plist); head = rht_dereference_bucket(head->next, tbl, hash); RCU_INIT_POINTER(list->rhead.next, head); if (pprev) { rcu_assign_pointer(*pprev, obj); rht_unlock(tbl, bkt); } else rht_assign_unlock(tbl, bkt, obj); data = NULL; goto out; } if (elasticity <= 0) goto slow_path; data = ERR_PTR(-E2BIG); if (unlikely(rht_grow_above_max(ht, tbl))) goto out_unlock; if (unlikely(rht_grow_above_100(ht, tbl))) goto slow_path; /* Inserting at head of list makes unlocking free. */ head = rht_ptr(bkt, tbl, hash); RCU_INIT_POINTER(obj->next, head); if (rhlist) { struct rhlist_head *list; list = container_of(obj, struct rhlist_head, rhead); RCU_INIT_POINTER(list->next, NULL); } atomic_inc(&ht->nelems); rht_assign_unlock(tbl, bkt, obj); if (rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); data = NULL; out: rcu_read_unlock(); return data; out_unlock: rht_unlock(tbl, bkt); goto out; } /** * rhashtable_insert_fast - insert object into hash table * @ht: hash table * @obj: pointer to hash head inside object * @params: hash table parameters * * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless * they map to the same bucket. * * It is safe to call this function from atomic context. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. */ static inline int rhashtable_insert_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { void *ret; ret = __rhashtable_insert_fast(ht, NULL, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); return ret == NULL ? 0 : -EEXIST; } /** * rhltable_insert_key - insert object into hash list table * @hlt: hash list table * @key: the pointer to the key * @list: pointer to hash list head inside object * @params: hash table parameters * * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless * they map to the same bucket. * * It is safe to call this function from atomic context. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. */ static inline int rhltable_insert_key( struct rhltable *hlt, const void *key, struct rhlist_head *list, const struct rhashtable_params params) { return PTR_ERR(__rhashtable_insert_fast(&hlt->ht, key, &list->rhead, params, true)); } /** * rhltable_insert - insert object into hash list table * @hlt: hash list table * @list: pointer to hash list head inside object * @params: hash table parameters * * Will take the per bucket bitlock to protect against mutual mutations * on the same bucket. Multiple insertions may occur in parallel unless * they map to the same bucket. * * It is safe to call this function from atomic context. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. */ static inline int rhltable_insert( struct rhltable *hlt, struct rhlist_head *list, const struct rhashtable_params params) { const char *key = rht_obj(&hlt->ht, &list->rhead); key += params.key_offset; return rhltable_insert_key(hlt, key, list, params); } /** * rhashtable_lookup_insert_fast - lookup and insert object into hash table * @ht: hash table * @obj: pointer to hash head inside object * @params: hash table parameters * * This lookup function may only be used for fixed key hash table (key_len * parameter set). It will BUG() if used inappropriately. * * It is safe to call this function from atomic context. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. */ static inline int rhashtable_lookup_insert_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { const char *key = rht_obj(ht, obj); void *ret; BUG_ON(ht->p.obj_hashfn); ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); return ret == NULL ? 0 : -EEXIST; } /** * rhashtable_lookup_get_insert_fast - lookup and insert object into hash table * @ht: hash table * @obj: pointer to hash head inside object * @params: hash table parameters * * Just like rhashtable_lookup_insert_fast(), but this function returns the * object if it exists, NULL if it did not and the insertion was successful, * and an ERR_PTR otherwise. */ static inline void *rhashtable_lookup_get_insert_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { const char *key = rht_obj(ht, obj); BUG_ON(ht->p.obj_hashfn); return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, false); } /** * rhashtable_lookup_insert_key - search and insert object to hash table * with explicit key * @ht: hash table * @key: key * @obj: pointer to hash head inside object * @params: hash table parameters * * Lookups may occur in parallel with hashtable mutations and resizing. * * Will trigger an automatic deferred table resizing if residency in the * table grows beyond 70%. * * Returns zero on success. */ static inline int rhashtable_lookup_insert_key( struct rhashtable *ht, const void *key, struct rhash_head *obj, const struct rhashtable_params params) { void *ret; BUG_ON(!ht->p.obj_hashfn || !key); ret = __rhashtable_insert_fast(ht, key, obj, params, false); if (IS_ERR(ret)) return PTR_ERR(ret); return ret == NULL ? 0 : -EEXIST; } /** * rhashtable_lookup_get_insert_key - lookup and insert object into hash table * @ht: hash table * @key: key * @obj: pointer to hash head inside object * @params: hash table parameters * * Just like rhashtable_lookup_insert_key(), but this function returns the * object if it exists, NULL if it does not and the insertion was successful, * and an ERR_PTR otherwise. */ static inline void *rhashtable_lookup_get_insert_key( struct rhashtable *ht, const void *key, struct rhash_head *obj, const struct rhashtable_params params) { BUG_ON(!ht->p.obj_hashfn || !key); return __rhashtable_insert_fast(ht, key, obj, params, false); } /* Internal function, please use rhashtable_remove_fast() instead */ static inline int __rhashtable_remove_fast_one( struct rhashtable *ht, struct bucket_table *tbl, struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; int err = -ENOENT; hash = rht_head_hashfn(ht, tbl, obj, params); bkt = rht_bucket_var(tbl, hash); if (!bkt) return -ENOENT; pprev = NULL; rht_lock(tbl, bkt); rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *list; list = container_of(he, struct rhlist_head, rhead); if (he != obj) { struct rhlist_head __rcu **lpprev; pprev = &he->next; if (!rhlist) continue; do { lpprev = &list->next; list = rht_dereference_bucket(list->next, tbl, hash); } while (list && obj != &list->rhead); if (!list) continue; list = rht_dereference_bucket(list->next, tbl, hash); RCU_INIT_POINTER(*lpprev, list); err = 0; break; } obj = rht_dereference_bucket(obj->next, tbl, hash); err = 1; if (rhlist) { list = rht_dereference_bucket(list->next, tbl, hash); if (list) { RCU_INIT_POINTER(list->rhead.next, obj); obj = &list->rhead; err = 0; } } if (pprev) { rcu_assign_pointer(*pprev, obj); rht_unlock(tbl, bkt); } else { rht_assign_unlock(tbl, bkt, obj); } goto unlocked; } rht_unlock(tbl, bkt); unlocked: if (err > 0) { atomic_dec(&ht->nelems); if (unlikely(ht->p.automatic_shrinking && rht_shrink_below_30(ht, tbl))) schedule_work(&ht->run_work); err = 0; } return err; } /* Internal function, please use rhashtable_remove_fast() instead */ static inline int __rhashtable_remove_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { struct bucket_table *tbl; int err; rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); /* Because we have already taken (and released) the bucket * lock in old_tbl, if we find that future_tbl is not yet * visible then that guarantees the entry to still be in * the old tbl if it exists. */ while ((err = __rhashtable_remove_fast_one(ht, tbl, obj, params, rhlist)) && (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) ; rcu_read_unlock(); return err; } /** * rhashtable_remove_fast - remove object from hash table * @ht: hash table * @obj: pointer to hash head inside object * @params: hash table parameters * * Since the hash chain is single linked, the removal operation needs to * walk the bucket chain upon removal. The removal operation is thus * considerable slow if the hash table is not correctly sized. * * Will automatically shrink the table if permitted when residency drops * below 30%. * * Returns zero on success, -ENOENT if the entry could not be found. */ static inline int rhashtable_remove_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { return __rhashtable_remove_fast(ht, obj, params, false); } /** * rhltable_remove - remove object from hash list table * @hlt: hash list table * @list: pointer to hash list head inside object * @params: hash table parameters * * Since the hash chain is single linked, the removal operation needs to * walk the bucket chain upon removal. The removal operation is thus * considerable slow if the hash table is not correctly sized. * * Will automatically shrink the table if permitted when residency drops * below 30% * * Returns zero on success, -ENOENT if the entry could not be found. */ static inline int rhltable_remove( struct rhltable *hlt, struct rhlist_head *list, const struct rhashtable_params params) { return __rhashtable_remove_fast(&hlt->ht, &list->rhead, params, true); } /* Internal function, please use rhashtable_replace_fast() instead */ static inline int __rhashtable_replace_fast( struct rhashtable *ht, struct bucket_table *tbl, struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; int err = -ENOENT; /* Minimally, the old and new objects must have same hash * (which should mean identifiers are the same). */ hash = rht_head_hashfn(ht, tbl, obj_old, params); if (hash != rht_head_hashfn(ht, tbl, obj_new, params)) return -EINVAL; bkt = rht_bucket_var(tbl, hash); if (!bkt) return -ENOENT; pprev = NULL; rht_lock(tbl, bkt); rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { if (he != obj_old) { pprev = &he->next; continue; } rcu_assign_pointer(obj_new->next, obj_old->next); if (pprev) { rcu_assign_pointer(*pprev, obj_new); rht_unlock(tbl, bkt); } else { rht_assign_unlock(tbl, bkt, obj_new); } err = 0; goto unlocked; } rht_unlock(tbl, bkt); unlocked: return err; } /** * rhashtable_replace_fast - replace an object in hash table * @ht: hash table * @obj_old: pointer to hash head inside object being replaced * @obj_new: pointer to hash head inside object which is new * @params: hash table parameters * * Replacing an object doesn't affect the number of elements in the hash table * or bucket, so we don't need to worry about shrinking or expanding the * table here. * * Returns zero on success, -ENOENT if the entry could not be found, * -EINVAL if hash is not the same for the old and new objects. */ static inline int rhashtable_replace_fast( struct rhashtable *ht, struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { struct bucket_table *tbl; int err; rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); /* Because we have already taken (and released) the bucket * lock in old_tbl, if we find that future_tbl is not yet * visible then that guarantees the entry to still be in * the old tbl if it exists. */ while ((err = __rhashtable_replace_fast(ht, tbl, obj_old, obj_new, params)) && (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) ; rcu_read_unlock(); return err; } /** * rhltable_walk_enter - Initialise an iterator * @hlt: Table to walk over * @iter: Hash table Iterator * * This function prepares a hash table walk. * * Note that if you restart a walk after rhashtable_walk_stop you * may see the same object twice. Also, you may miss objects if * there are removals in between rhashtable_walk_stop and the next * call to rhashtable_walk_start. * * For a completely stable walk you should construct your own data * structure outside the hash table. * * This function may be called from any process context, including * non-preemptable context, but cannot be called from softirq or * hardirq context. * * You must call rhashtable_walk_exit after this function returns. */ static inline void rhltable_walk_enter(struct rhltable *hlt, struct rhashtable_iter *iter) { return rhashtable_walk_enter(&hlt->ht, iter); } /** * rhltable_free_and_destroy - free elements and destroy hash list table * @hlt: the hash list table to destroy * @free_fn: callback to release resources of element * @arg: pointer passed to free_fn * * See documentation for rhashtable_free_and_destroy. */ static inline void rhltable_free_and_destroy(struct rhltable *hlt, void (*free_fn)(void *ptr, void *arg), void *arg) { return rhashtable_free_and_destroy(&hlt->ht, free_fn, arg); } static inline void rhltable_destroy(struct rhltable *hlt) { return rhltable_free_and_destroy(hlt, NULL, NULL); } #endif /* _LINUX_RHASHTABLE_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_CPUTIME_H #define _LINUX_SCHED_CPUTIME_H #include <linux/sched/signal.h> /* * cputime accounting APIs: */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <asm/cputime.h> #ifndef cputime_to_nsecs # define cputime_to_nsecs(__ct) \ (cputime_to_usecs(__ct) * NSEC_PER_USEC) #endif #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void task_cputime(struct task_struct *t, u64 *utime, u64 *stime); extern u64 task_gtime(struct task_struct *t); #else static inline void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { *utime = t->utime; *stime = t->stime; } static inline u64 task_gtime(struct task_struct *t) { return t->gtime; } #endif #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME static inline void task_cputime_scaled(struct task_struct *t, u64 *utimescaled, u64 *stimescaled) { *utimescaled = t->utimescaled; *stimescaled = t->stimescaled; } #else static inline void task_cputime_scaled(struct task_struct *t, u64 *utimescaled, u64 *stimescaled) { task_cputime(t, utimescaled, stimescaled); } #endif extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); extern void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev, u64 *ut, u64 *st); /* * Thread group CPU time accounting. */ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples); /* * The following are functions that support scheduler-internal time accounting. * These functions are generally called at the timer tick. None of this depends * on CONFIG_SCHEDSTATS. */ /** * get_running_cputimer - return &tsk->signal->cputimer if cputimers are active * * @tsk: Pointer to target task. */ #ifdef CONFIG_POSIX_TIMERS static inline struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; /* * Check whether posix CPU timers are active. If not the thread * group accounting is not active either. Lockless check. */ if (!READ_ONCE(tsk->signal->posix_cputimers.timers_active)) return NULL; /* * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime * in __exit_signal(), we won't account to the signal struct further * cputime consumed by that task, even though the task can still be * ticking after __exit_signal(). * * In order to keep a consistent behaviour between thread group cputime * and thread group cputimer accounting, lets also ignore the cputime * elapsing after __exit_signal() in any thread group timer running. * * This makes sure that POSIX CPU clocks and timers are synchronized, so * that a POSIX CPU timer won't expire while the corresponding POSIX CPU * clock delta is behind the expiring timer value. */ if (unlikely(!tsk->sighand)) return NULL; return cputimer; } #else static inline struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) { return NULL; } #endif /** * account_group_user_time - Maintain utime for a thread group. * * @tsk: Pointer to task structure. * @cputime: Time value by which to increment the utime field of the * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the utime field there. */ static inline void account_group_user_time(struct task_struct *tsk, u64 cputime) { struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.utime); } /** * account_group_system_time - Maintain stime for a thread group. * * @tsk: Pointer to task structure. * @cputime: Time value by which to increment the stime field of the * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the stime field there. */ static inline void account_group_system_time(struct task_struct *tsk, u64 cputime) { struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.stime); } /** * account_group_exec_runtime - Maintain exec runtime for a thread group. * * @tsk: Pointer to task structure. * @ns: Time value by which to increment the sum_exec_runtime field * of the thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the sum_exec_runtime field there. */ static inline void account_group_exec_runtime(struct task_struct *tsk, unsigned long long ns) { struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); if (!cputimer) return; atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime); } static inline void prev_cputime_init(struct prev_cputime *prev) { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE prev->utime = prev->stime = 0; raw_spin_lock_init(&prev->lock); #endif } extern unsigned long long task_sched_runtime(struct task_struct *task); #endif /* _LINUX_SCHED_CPUTIME_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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Common values for SHA algorithms */ #ifndef _CRYPTO_SHA_H #define _CRYPTO_SHA_H #include <linux/types.h> #define SHA1_DIGEST_SIZE 20 #define SHA1_BLOCK_SIZE 64 #define SHA224_DIGEST_SIZE 28 #define SHA224_BLOCK_SIZE 64 #define SHA256_DIGEST_SIZE 32 #define SHA256_BLOCK_SIZE 64 #define SHA384_DIGEST_SIZE 48 #define SHA384_BLOCK_SIZE 128 #define SHA512_DIGEST_SIZE 64 #define SHA512_BLOCK_SIZE 128 #define SHA1_H0 0x67452301UL #define SHA1_H1 0xefcdab89UL #define SHA1_H2 0x98badcfeUL #define SHA1_H3 0x10325476UL #define SHA1_H4 0xc3d2e1f0UL #define SHA224_H0 0xc1059ed8UL #define SHA224_H1 0x367cd507UL #define SHA224_H2 0x3070dd17UL #define SHA224_H3 0xf70e5939UL #define SHA224_H4 0xffc00b31UL #define SHA224_H5 0x68581511UL #define SHA224_H6 0x64f98fa7UL #define SHA224_H7 0xbefa4fa4UL #define SHA256_H0 0x6a09e667UL #define SHA256_H1 0xbb67ae85UL #define SHA256_H2 0x3c6ef372UL #define SHA256_H3 0xa54ff53aUL #define SHA256_H4 0x510e527fUL #define SHA256_H5 0x9b05688cUL #define SHA256_H6 0x1f83d9abUL #define SHA256_H7 0x5be0cd19UL #define SHA384_H0 0xcbbb9d5dc1059ed8ULL #define SHA384_H1 0x629a292a367cd507ULL #define SHA384_H2 0x9159015a3070dd17ULL #define SHA384_H3 0x152fecd8f70e5939ULL #define SHA384_H4 0x67332667ffc00b31ULL #define SHA384_H5 0x8eb44a8768581511ULL #define SHA384_H6 0xdb0c2e0d64f98fa7ULL #define SHA384_H7 0x47b5481dbefa4fa4ULL #define SHA512_H0 0x6a09e667f3bcc908ULL #define SHA512_H1 0xbb67ae8584caa73bULL #define SHA512_H2 0x3c6ef372fe94f82bULL #define SHA512_H3 0xa54ff53a5f1d36f1ULL #define SHA512_H4 0x510e527fade682d1ULL #define SHA512_H5 0x9b05688c2b3e6c1fULL #define SHA512_H6 0x1f83d9abfb41bd6bULL #define SHA512_H7 0x5be0cd19137e2179ULL extern const u8 sha1_zero_message_hash[SHA1_DIGEST_SIZE]; extern const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE]; extern const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE]; extern const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE]; extern const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE]; struct sha1_state { u32 state[SHA1_DIGEST_SIZE / 4]; u64 count; u8 buffer[SHA1_BLOCK_SIZE]; }; struct sha256_state { u32 state[SHA256_DIGEST_SIZE / 4]; u64 count; u8 buf[SHA256_BLOCK_SIZE]; }; struct sha512_state { u64 state[SHA512_DIGEST_SIZE / 8]; u64 count[2]; u8 buf[SHA512_BLOCK_SIZE]; }; struct shash_desc; extern int crypto_sha1_update(struct shash_desc *desc, const u8 *data, unsigned int len); extern int crypto_sha1_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *hash); extern int crypto_sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len); extern int crypto_sha256_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *hash); extern int crypto_sha512_update(struct shash_desc *desc, const u8 *data, unsigned int len); extern int crypto_sha512_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *hash); /* * An implementation of SHA-1's compression function. Don't use in new code! * You shouldn't be using SHA-1, and even if you *have* to use SHA-1, this isn't * the correct way to hash something with SHA-1 (use crypto_shash instead). */ #define SHA1_DIGEST_WORDS (SHA1_DIGEST_SIZE / 4) #define SHA1_WORKSPACE_WORDS 16 void sha1_init(__u32 *buf); void sha1_transform(__u32 *digest, const char *data, __u32 *W); /* * Stand-alone implementation of the SHA256 algorithm. It is designed to * have as little dependencies as possible so it can be used in the * kexec_file purgatory. In other cases you should generally use the * hash APIs from include/crypto/hash.h. Especially when hashing large * amounts of data as those APIs may be hw-accelerated. * * For details see lib/crypto/sha256.c */ static inline void sha256_init(struct sha256_state *sctx) { sctx->state[0] = SHA256_H0; sctx->state[1] = SHA256_H1; sctx->state[2] = SHA256_H2; sctx->state[3] = SHA256_H3; sctx->state[4] = SHA256_H4; sctx->state[5] = SHA256_H5; sctx->state[6] = SHA256_H6; sctx->state[7] = SHA256_H7; sctx->count = 0; } void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len); void sha256_final(struct sha256_state *sctx, u8 *out); void sha256(const u8 *data, unsigned int len, u8 *out); static inline void sha224_init(struct sha256_state *sctx) { sctx->state[0] = SHA224_H0; sctx->state[1] = SHA224_H1; sctx->state[2] = SHA224_H2; sctx->state[3] = SHA224_H3; sctx->state[4] = SHA224_H4; sctx->state[5] = SHA224_H5; sctx->state[6] = SHA224_H6; sctx->state[7] = SHA224_H7; sctx->count = 0; } void sha224_update(struct sha256_state *sctx, const u8 *data, unsigned int len); void sha224_final(struct sha256_state *sctx, u8 *out); #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. * (C) Linux Foundation 2008-2013 * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set. */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS ((slab_flags_t __force)0x00000100U) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE ((slab_flags_t __force)0x00000400U) /* DEBUG: Poison objects */ #define SLAB_POISON ((slab_flags_t __force)0x00000800U) /* Align objs on cache lines */ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC ((slab_flags_t __force)0x00040000U) /* * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() * that memory location is free to be reused at any time. Thus it may * be possible to see another object there in the same RCU grace period. * * This feature only ensures the memory location backing the object * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * * rcu_read_lock() * again: * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * goto again; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * goto again; * } * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, * from its address obtained without the usual locking. We can lock * the structure to stabilize it and check it's still at the given address, * only if we can be sure that the memory has not been meanwhile reused * for some other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ /* Defer freeing slabs to RCU */ #define SLAB_TYPESAFE_BY_RCU ((slab_flags_t __force)0x00080000U) /* Spread some memory over cpuset */ #define SLAB_MEM_SPREAD ((slab_flags_t __force)0x00100000U) /* Trace allocations and frees */ #define SLAB_TRACE ((slab_flags_t __force)0x00200000U) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS ((slab_flags_t __force)0x00400000U) #else # define SLAB_DEBUG_OBJECTS 0 #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE ((slab_flags_t __force)0x00800000U) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB ((slab_flags_t __force)0x02000000U) #else # define SLAB_FAILSLAB 0 #endif /* Account to memcg */ #ifdef CONFIG_MEMCG_KMEM # define SLAB_ACCOUNT ((slab_flags_t __force)0x04000000U) #else # define SLAB_ACCOUNT 0 #endif #ifdef CONFIG_KASAN #define SLAB_KASAN ((slab_flags_t __force)0x08000000U) #else #define SLAB_KASAN 0 #endif /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab deactivation flag */ #define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U) /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. * * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. * Both make kfree a no-op. */ #define ZERO_SIZE_PTR ((void *)16) #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) #include <linux/kasan.h> struct mem_cgroup; /* * struct kmem_cache related prototypes */ void __init kmem_cache_init(void); bool slab_is_available(void); extern bool usercopy_fallback; struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); struct kmem_cache *kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. * * The alignment of the struct determines object alignment. If you * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ #define KMEM_CACHE(__struct, __flags) \ kmem_cache_create(#__struct, sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), NULL) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ #define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ kmem_cache_create_usercopy(#__struct, \ sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), \ offsetof(struct __struct, __field), \ sizeof_field(struct __struct, __field), NULL) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); void kfree_sensitive(const void *); size_t __ksize(const void *); size_t ksize(const void *); #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user); #else static inline void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user) { } #endif /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. */ #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN) #else #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer * aligned buffers. */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif /* * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN * aligned pointers. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) #define __assume_page_alignment __assume_aligned(PAGE_SIZE) /* * Kmalloc array related definitions */ #ifdef CONFIG_SLAB /* * The largest kmalloc size supported by the SLAB allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is * less than 32 MB. * * WARNING: Its not easy to increase this value since the allocators have * to do various tricks to work around compiler limitations in order to * ensure proper constant folding. */ #define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ (MAX_ORDER + PAGE_SHIFT - 1) : 25) #define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif #endif #ifdef CONFIG_SLUB /* * SLUB directly allocates requests fitting in to an order-1 page * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif #ifdef CONFIG_SLOB /* * SLOB passes all requests larger than one page to the page allocator. * No kmalloc array is necessary since objects of different sizes can * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) /* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. */ #ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif /* * This restriction comes from byte sized index implementation. * Page size is normally 2^12 bytes and, in this case, if we want to use * byte sized index which can represent 2^8 entries, the size of the object * should be equal or greater to 2^12 / 2^8 = 2^4 = 16. * If minimum size of kmalloc is less than 16, we use it as minimum object * size and give up to use byte sized index. */ #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif NR_KMALLOC_TYPES }; #ifndef CONFIG_SLOB extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { #ifdef CONFIG_ZONE_DMA /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for both flags. */ if (likely((flags & (__GFP_DMA | __GFP_RECLAIMABLE)) == 0)) return KMALLOC_NORMAL; /* * At least one of the flags has to be set. If both are, __GFP_DMA * is more important. */ return flags & __GFP_DMA ? KMALLOC_DMA : KMALLOC_RECLAIM; #else return flags & __GFP_RECLAIMABLE ? KMALLOC_RECLAIM : KMALLOC_NORMAL; #endif } /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n */ static __always_inline unsigned int kmalloc_index(size_t size) { if (!size) return 0; if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) return 1; if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) return 2; if (size <= 8) return 3; if (size <= 16) return 4; if (size <= 32) return 5; if (size <= 64) return 6; if (size <= 128) return 7; if (size <= 256) return 8; if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; if (size <= 32 * 1024) return 15; if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; if (size <= 4 * 1024 * 1024) return 22; if (size <= 8 * 1024 * 1024) return 23; if (size <= 16 * 1024 * 1024) return 24; if (size <= 32 * 1024 * 1024) return 25; if (size <= 64 * 1024 * 1024) return 26; BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *, void *); /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); /* * Caller must not use kfree_bulk() on memory not originally allocated * by kmalloc(), because the SLOB allocator cannot handle this. */ static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __kmalloc(size, flags); } static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) { return kmem_cache_alloc(s, flags); } #endif #ifdef CONFIG_TRACING extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc; #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_slab_alignment __malloc; #else static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) { void *ret = kmem_cache_alloc(s, flags); ret = kasan_kmalloc(s, ret, size, flags); return ret; } static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { void *ret = kmem_cache_alloc_node(s, gfpflags, node); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; } #endif /* CONFIG_TRACING */ extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #ifdef CONFIG_TRACING extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #else static __always_inline void * kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { return kmalloc_order(size, flags, order); } #endif static __always_inline void *kmalloc_large(size_t size, gfp_t flags) { unsigned int order = get_order(size); return kmalloc_order_trace(size, flags, order); } /** * kmalloc - allocate memory * @size: how many bytes of memory are required. * @flags: the type of memory to allocate. * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed * to be at least to the size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at * :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>` * * Below is a brief outline of the most useful GFP flags * * %GFP_KERNEL * Allocate normal kernel ram. May sleep. * * %GFP_NOWAIT * Allocation will not sleep. * * %GFP_ATOMIC * Allocation will not sleep. May use emergency pools. * * %GFP_HIGHUSER * Allocate memory from high memory on behalf of user. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_HIGH * This allocation has high priority and may use emergency pools. * * %__GFP_NOFAIL * Indicate that this allocation is in no way allowed to fail * (think twice before using). * * %__GFP_NORETRY * If memory is not immediately available, * then give up at once. * * %__GFP_NOWARN * If allocation fails, don't issue any warnings. * * %__GFP_RETRY_MAYFAIL * Try really hard to succeed the allocation but fail * eventually. */ static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { #ifndef CONFIG_SLOB unsigned int index; #endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB index = kmalloc_index(size); if (!index) return ZERO_SIZE_PTR; return kmem_cache_alloc_trace( kmalloc_caches[kmalloc_type(flags)][index], flags, size); #endif } return __kmalloc(size, flags); } static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; return kmem_cache_alloc_node_trace( kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif return __kmalloc_node(size, flags, node); } /** * kmalloc_array - allocate memory for an array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc(bytes, flags); return __kmalloc(bytes, flags); } /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) { return kmalloc_array(n, size, flags | __GFP_ZERO); } /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead * of just the calling function (confusing, eh?). * It's useful when the call to kmalloc comes from a widely-used standard * allocator where we care about the real place the memory allocation * request comes from. */ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_node(bytes, flags, node); return __kmalloc_node(bytes, flags, node); } static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) { return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } #ifdef CONFIG_NUMA extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) #else /* CONFIG_NUMA */ #define kmalloc_node_track_caller(size, flags, node) \ kmalloc_track_caller(size, flags) #endif /* CONFIG_NUMA */ /* * Shortcuts */ stat