Loading...
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 | /* * linux/mm/slab.c * Written by Mark Hemment, 1996/97. * (markhe@nextd.demon.co.uk) * * kmem_cache_destroy() + some cleanup - 1999 Andrea Arcangeli * * Major cleanup, different bufctl logic, per-cpu arrays * (c) 2000 Manfred Spraul * * An implementation of the Slab Allocator as described in outline in; * UNIX Internals: The New Frontiers by Uresh Vahalia * Pub: Prentice Hall ISBN 0-13-101908-2 * or with a little more detail in; * The Slab Allocator: An Object-Caching Kernel Memory Allocator * Jeff Bonwick (Sun Microsystems). * Presented at: USENIX Summer 1994 Technical Conference * * * The memory is organized in caches, one cache for each object type. * (e.g. inode_cache, dentry_cache, buffer_head, vm_area_struct) * Each cache consists out of many slabs (they are small (usually one * page long) and always contiguous), and each slab contains multiple * initialized objects. * * Each cache can only support one memory type (GFP_DMA, GFP_HIGHMEM, * normal). If you need a special memory type, then must create a new * cache for that memory type. * * In order to reduce fragmentation, the slabs are sorted in 3 groups: * full slabs with 0 free objects * partial slabs * empty slabs with no allocated objects * * If partial slabs exist, then new allocations come from these slabs, * otherwise from empty slabs or new slabs are allocated. * * kmem_cache_destroy() CAN CRASH if you try to allocate from the cache * during kmem_cache_destroy(). The caller must prevent concurrent allocs. * * On SMP systems, each cache has a short per-cpu head array, most allocs * and frees go into that array, and if that array overflows, then 1/2 * of the entries in the array are given back into the global cache. * This reduces the number of spinlock operations. * * The c_cpuarray may not be read with enabled local interrupts. * * SMP synchronization: * constructors and destructors are called without any locking. * Several members in kmem_cache_t and slab_t never change, they * are accessed without any locking. * The per-cpu arrays are never accessed from the wrong cpu, no locking. * The non-constant members are protected with a per-cache irq spinlock. * * Further notes from the original documentation: * * 11 April '97. Started multi-threading - markhe * The global cache-chain is protected by the semaphore 'cache_chain_sem'. * The sem is only needed when accessing/extending the cache-chain, which * can never happen inside an interrupt (kmem_cache_create(), * kmem_cache_shrink() and kmem_cache_reap()). * * To prevent kmem_cache_shrink() trying to shrink a 'growing' cache (which * maybe be sleeping and therefore not holding the semaphore/lock), the * growing field is used. This also prevents reaping from a cache. * * At present, each engine can be growing a cache. This should be blocked. * */ #include <linux/__KEEPIDENTS__B.h> #include <linux/__KEEPIDENTS__C.h> #include <linux/__KEEPIDENTS__D.h> #include <linux/__KEEPIDENTS__E.h> #include <asm/uaccess.h> /* * DEBUG - 1 for kmem_cache_create() to honour; SLAB_DEBUG_INITIAL, * SLAB_RED_ZONE & SLAB_POISON. * 0 for faster, smaller code (especially in the critical paths). * * STATS - 1 to collect stats for /proc/slabinfo. * 0 for faster, smaller code (especially in the critical paths). * * FORCED_DEBUG - 1 enables SLAB_RED_ZONE and SLAB_POISON (if possible) */ #define DEBUG 0 #define STATS 0 #define FORCED_DEBUG 0 /* * Parameters for kmem_cache_reap */ #define REAP_SCANLEN 10 #define REAP_PERFECT 10 /* Shouldn't this be in a header file somewhere? */ #define BYTES_PER_WORD sizeof(void *) /* Legal flag mask for kmem_cache_create(). */ #if DEBUG # define CREATE_MASK (SLAB_DEBUG_INITIAL | SLAB_RED_ZONE | \ SLAB_POISON | SLAB_HWCACHE_ALIGN | \ SLAB_NO_REAP | SLAB_CACHE_DMA) #else # define CREATE_MASK (SLAB_HWCACHE_ALIGN | SLAB_NO_REAP | SLAB_CACHE_DMA) #endif /* * kmem_bufctl_t: * * Bufctl's are used for linking objs within a slab * linked offsets. * * This implementaion relies on "struct page" for locating the cache & * slab an object belongs to. * This allows the bufctl structure to be small (one int), but limits * the number of objects a slab (not a cache) can contain when off-slab * bufctls are used. The limit is the size of the largest general cache * that does not use off-slab slabs. * For 32bit archs with 4 kB pages, is this 56. * This is not serious, as it is only for large objects, when it is unwise * to have too many per slab. * Note: This limit can be raised by introducing a general cache whose size * is less than 512 (PAGE_SIZE<<3), but greater than 256. */ #define BUFCTL_END 0xffffFFFF #define SLAB_LIMIT 0xffffFFFE typedef unsigned int kmem_bufctl_t; /* Max number of objs-per-slab for caches which use off-slab slabs. * Needed to avoid a possible looping condition in kmem_cache_grow(). */ static unsigned long offslab_limit; /* * slab_t * * Manages the objs in a slab. Placed either at the beginning of mem allocated * for a slab, or allocated from an general cache. * Slabs are chained into one ordered list: fully used, partial, then fully * free slabs. */ typedef struct slab_s { struct list_head list; unsigned long colouroff; void *s_mem; /* including colour offset */ unsigned int inuse; /* num of objs active in slab */ kmem_bufctl_t free; } slab_t; #define slab_bufctl(slabp) \ ((kmem_bufctl_t *)(((slab_t*)slabp)+1)) /* * cpucache_t * * Per cpu structures * The limit is stored in the per-cpu structure to reduce the data cache * footprint. */ typedef struct cpucache_s { unsigned int avail; unsigned int limit; } cpucache_t; #define cc_entry(cpucache) \ ((void **)(((cpucache_t*)cpucache)+1)) #define cc_data(cachep) \ ((cachep)->cpudata[smp_processor_id()]) /* * kmem_cache_t * * manages a cache. */ #define CACHE_NAMELEN 20 /* max name length for a slab cache */ struct kmem_cache_s { /* 1) each alloc & free */ /* full, partial first, then free */ struct list_head slabs; struct list_head *firstnotfull; unsigned int objsize; unsigned int flags; /* constant flags */ unsigned int num; /* # of objs per slab */ spinlock_t spinlock; #ifdef CONFIG_SMP unsigned int batchcount; #endif /* 2) slab additions /removals */ /* order of pgs per slab (2^n) */ unsigned int gfporder; /* force GFP flags, e.g. GFP_DMA */ unsigned int gfpflags; size_t colour; /* cache colouring range */ unsigned int colour_off; /* colour offset */ unsigned int colour_next; /* cache colouring */ kmem_cache_t *slabp_cache; unsigned int growing; unsigned int dflags; /* dynamic flags */ /* constructor func */ void (*ctor)(void *, kmem_cache_t *, unsigned long); /* de-constructor func */ void (*dtor)(void *, kmem_cache_t *, unsigned long); unsigned long failures; /* 3) cache creation/removal */ char name[CACHE_NAMELEN]; struct list_head next; #ifdef CONFIG_SMP /* 4) per-cpu data */ cpucache_t *cpudata[NR_CPUS]; #endif #if STATS unsigned long num_active; unsigned long num_allocations; unsigned long high_mark; unsigned long grown; unsigned long reaped; unsigned long errors; #ifdef CONFIG_SMP atomic_t allochit; atomic_t allocmiss; atomic_t freehit; atomic_t freemiss; #endif #endif }; /* internal c_flags */ #define CFLGS_OFF_SLAB 0x010000UL /* slab management in own cache */ #define CFLGS_OPTIMIZE 0x020000UL /* optimized slab lookup */ /* c_dflags (dynamic flags). Need to hold the spinlock to access this member */ #define DFLGS_GROWN 0x000001UL /* don't reap a recently grown */ #define OFF_SLAB(x) ((x)->flags & CFLGS_OFF_SLAB) #define OPTIMIZE(x) ((x)->flags & CFLGS_OPTIMIZE) #define GROWN(x) ((x)->dlags & DFLGS_GROWN) #if STATS #define STATS_INC_ACTIVE(x) ((x)->num_active++) #define STATS_DEC_ACTIVE(x) ((x)->num_active--) #define STATS_INC_ALLOCED(x) ((x)->num_allocations++) #define STATS_INC_GROWN(x) ((x)->grown++) #define STATS_INC_REAPED(x) ((x)->reaped++) #define STATS_SET_HIGH(x) do { if ((x)->num_active > (x)->high_mark) \ (x)->high_mark = (x)->num_active; \ } while (0) #define STATS_INC_ERR(x) ((x)->errors++) #else #define STATS_INC_ACTIVE(x) do { } while (0) #define STATS_DEC_ACTIVE(x) do { } while (0) #define STATS_INC_ALLOCED(x) do { } while (0) #define STATS_INC_GROWN(x) do { } while (0) #define STATS_INC_REAPED(x) do { } while (0) #define STATS_SET_HIGH(x) do { } while (0) #define STATS_INC_ERR(x) do { } while (0) #endif #if STATS && defined(CONFIG_SMP) #define STATS_INC_ALLOCHIT(x) atomic_inc(&(x)->allochit) #define STATS_INC_ALLOCMISS(x) atomic_inc(&(x)->allocmiss) #define STATS_INC_FREEHIT(x) atomic_inc(&(x)->freehit) #define STATS_INC_FREEMISS(x) atomic_inc(&(x)->freemiss) #else #define STATS_INC_ALLOCHIT(x) do { } while (0) #define STATS_INC_ALLOCMISS(x) do { } while (0) #define STATS_INC_FREEHIT(x) do { } while (0) #define STATS_INC_FREEMISS(x) do { } while (0) #endif #if DEBUG /* Magic nums for obj red zoning. * Placed in the first word before and the first word after an obj. */ #define RED_MAGIC1 0x5A2CF071UL /* when obj is active */ #define RED_MAGIC2 0x170FC2A5UL /* when obj is inactive */ /* ...and for poisoning */ #define POISON_BYTE 0x5a /* byte value for poisoning */ #define POISON_END 0xa5 /* end-byte of poisoning */ #endif /* maximum size of an obj (in 2^order pages) */ #define MAX_OBJ_ORDER 5 /* 32 pages */ /* * Do not go above this order unless 0 objects fit into the slab. */ #define BREAK_GFP_ORDER_HI 2 #define BREAK_GFP_ORDER_LO 1 static int slab_break_gfp_order = BREAK_GFP_ORDER_LO; /* * Absolute limit for the gfp order */ #define MAX_GFP_ORDER 5 /* 32 pages */ /* Macros for storing/retrieving the cachep and or slab from the * global 'mem_map'. These are used to find the slab an obj belongs to. * With kfree(), these are used to find the cache which an obj belongs to. */ #define SET_PAGE_CACHE(pg,x) ((pg)->list.next = (struct list_head *)(x)) #define GET_PAGE_CACHE(pg) ((kmem_cache_t *)(pg)->list.next) #define SET_PAGE_SLAB(pg,x) ((pg)->list.prev = (struct list_head *)(x)) #define GET_PAGE_SLAB(pg) ((slab_t *)(pg)->list.prev) /* Size description struct for general caches. */ typedef struct cache_sizes { size_t cs_size; kmem_cache_t *cs_cachep; kmem_cache_t *cs_dmacachep; } cache_sizes_t; static cache_sizes_t cache_sizes[] = { #if PAGE_SIZE == 4096 { 32, NULL, NULL}, #endif { 64, NULL, NULL}, { 128, NULL, NULL}, { 256, NULL, NULL}, { 512, NULL, NULL}, { 1024, NULL, NULL}, { 2048, NULL, NULL}, { 4096, NULL, NULL}, { 8192, NULL, NULL}, { 16384, NULL, NULL}, { 32768, NULL, NULL}, { 65536, NULL, NULL}, {131072, NULL, NULL}, { 0, NULL, NULL} }; /* internal cache of cache description objs */ static kmem_cache_t cache_cache = { slabs: LIST_HEAD_INIT(cache_cache.slabs), firstnotfull: &cache_cache.slabs, objsize: sizeof(kmem_cache_t), flags: SLAB_NO_REAP, spinlock: SPIN_LOCK_UNLOCKED, colour_off: L1_CACHE_BYTES, name: "kmem_cache", }; /* Guard access to the cache-chain. */ static struct semaphore cache_chain_sem; /* Place maintainer for reaping. */ static kmem_cache_t *clock_searchp = &cache_cache; #define cache_chain (cache_cache.next) #ifdef CONFIG_SMP /* * chicken and egg problem: delay the per-cpu array allocation * until the general caches are up. */ static int g_cpucache_up; static void enable_cpucache (kmem_cache_t *cachep); static void enable_all_cpucaches (void); #endif /* Cal the num objs, wastage, and bytes left over for a given slab size. */ static void kmem_cache_estimate (unsigned long gfporder, size_t size, int flags, size_t *left_over, unsigned int *num) { int i; size_t wastage = PAGE_SIZE<<gfporder; size_t extra = 0; size_t base = 0; if (!(flags & CFLGS_OFF_SLAB)) { base = sizeof(slab_t); extra = sizeof(kmem_bufctl_t); } i = 0; while (i*size + L1_CACHE_ALIGN(base+i*extra) <= wastage) i++; if (i > 0) i--; if (i > SLAB_LIMIT) i = SLAB_LIMIT; *num = i; wastage -= i*size; wastage -= L1_CACHE_ALIGN(base+i*extra); *left_over = wastage; } /* Initialisation - setup the `cache' cache. */ void __init kmem_cache_init(void) { size_t left_over; init_MUTEX(&cache_chain_sem); INIT_LIST_HEAD(&cache_chain); kmem_cache_estimate(0, cache_cache.objsize, 0, &left_over, &cache_cache.num); if (!cache_cache.num) BUG(); cache_cache.colour = left_over/cache_cache.colour_off; cache_cache.colour_next = 0; } /* Initialisation - setup remaining internal and general caches. * Called after the gfp() functions have been enabled, and before smp_init(). */ void __init kmem_cache_sizes_init(void) { cache_sizes_t *sizes = cache_sizes; char name[20]; /* * Fragmentation resistance on low memory - only use bigger * page orders on machines with more than 32MB of memory. */ if (num_physpages > (32 << 20) >> PAGE_SHIFT) slab_break_gfp_order = BREAK_GFP_ORDER_HI; do { /* For performance, all the general caches are L1 aligned. * This should be particularly beneficial on SMP boxes, as it * eliminates "false sharing". * Note for systems short on memory removing the alignment will * allow tighter packing of the smaller caches. */ sprintf(name,"size-%Zd",sizes->cs_size); if (!(sizes->cs_cachep = kmem_cache_create(name, sizes->cs_size, 0, SLAB_HWCACHE_ALIGN, NULL, NULL))) { BUG(); } /* Inc off-slab bufctl limit until the ceiling is hit. */ if (!(OFF_SLAB(sizes->cs_cachep))) { offslab_limit = sizes->cs_size-sizeof(slab_t); offslab_limit /= 2; } sprintf(name, "size-%Zd(DMA)",sizes->cs_size); sizes->cs_dmacachep = kmem_cache_create(name, sizes->cs_size, 0, SLAB_CACHE_DMA|SLAB_HWCACHE_ALIGN, NULL, NULL); if (!sizes->cs_dmacachep) BUG(); sizes++; } while (sizes->cs_size); } int __init kmem_cpucache_init(void) { #ifdef CONFIG_SMP g_cpucache_up = 1; enable_all_cpucaches(); #endif return 0; } __initcall(kmem_cpucache_init); /* Interface to system's page allocator. No need to hold the cache-lock. */ static inline void * kmem_getpages (kmem_cache_t *cachep, unsigned long flags) { void *addr; /* * If we requested dmaable memory, we will get it. Even if we * did not request dmaable memory, we might get it, but that * would be relatively rare and ignorable. */ flags |= cachep->gfpflags; addr = (void*) __get_free_pages(flags, cachep->gfporder); /* Assume that now we have the pages no one else can legally * messes with the 'struct page's. * However vm_scan() might try to test the structure to see if * it is a named-page or buffer-page. The members it tests are * of no interest here..... */ return addr; } /* Interface to system's page release. */ static inline void kmem_freepages (kmem_cache_t *cachep, void *addr) { unsigned long i = (1<<cachep->gfporder); struct page *page = virt_to_page(addr); /* free_pages() does not clear the type bit - we do that. * The pages have been unlinked from their cache-slab, * but their 'struct page's might be accessed in * vm_scan(). Shouldn't be a worry. */ while (i--) { PageClearSlab(page); page++; } free_pages((unsigned long)addr, cachep->gfporder); } #if DEBUG static inline void kmem_poison_obj (kmem_cache_t *cachep, void *addr) { int size = cachep->objsize; if (cachep->flags & SLAB_RED_ZONE) { addr += BYTES_PER_WORD; size -= 2*BYTES_PER_WORD; } memset(addr, POISON_BYTE, size); *(unsigned char *)(addr+size-1) = POISON_END; } static inline int kmem_check_poison_obj (kmem_cache_t *cachep, void *addr) { int size = cachep->objsize; void *end; if (cachep->flags & SLAB_RED_ZONE) { addr += BYTES_PER_WORD; size -= 2*BYTES_PER_WORD; } end = memchr(addr, POISON_END, size); if (end != (addr+size-1)) return 1; return 0; } #endif /* Destroy all the objs in a slab, and release the mem back to the system. * Before calling the slab must have been unlinked from the cache. * The cache-lock is not held/needed. */ static void kmem_slab_destroy (kmem_cache_t *cachep, slab_t *slabp) { if (cachep->dtor #if DEBUG || cachep->flags & (SLAB_POISON | SLAB_RED_ZONE) #endif ) { int i; for (i = 0; i < cachep->num; i++) { void* objp = slabp->s_mem+cachep->objsize*i; #if DEBUG if (cachep->flags & SLAB_RED_ZONE) { if (*((unsigned long*)(objp)) != RED_MAGIC1) BUG(); if (*((unsigned long*)(objp + cachep->objsize -BYTES_PER_WORD)) != RED_MAGIC1) BUG(); objp += BYTES_PER_WORD; } #endif if (cachep->dtor) (cachep->dtor)(objp, cachep, 0); #if DEBUG if (cachep->flags & SLAB_RED_ZONE) { objp -= BYTES_PER_WORD; } if ((cachep->flags & SLAB_POISON) && kmem_check_poison_obj(cachep, objp)) BUG(); #endif } } kmem_freepages(cachep, slabp->s_mem-slabp->colouroff); if (OFF_SLAB(cachep)) kmem_cache_free(cachep->slabp_cache, slabp); } /** * kmem_cache_create - Create a cache. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @offset: The offset to use within the page. * @flags: SLAB flags * @ctor: A constructor for the objects. * @dtor: A destructor for the objects. * * Returns a ptr to the cache on success, NULL on failure. * Cannot be called within a int, but can be interrupted. * The @ctor is run when new pages are allocated by the cache * and the @dtor is run before the pages are handed back. * The flags are * * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) * to catch references to uninitialised memory. * * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check * for buffer overruns. * * %SLAB_NO_REAP - Don't automatically reap this cache when we're under * memory pressure. * * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware * cacheline. This can be beneficial if you're counting cycles as closely * as davem. */ kmem_cache_t * kmem_cache_create (const char *name, size_t size, size_t offset, unsigned long flags, void (*ctor)(void*, kmem_cache_t *, unsigned long), void (*dtor)(void*, kmem_cache_t *, unsigned long)) { const char *func_nm = KERN_ERR "kmem_create: "; size_t left_over, align, slab_size; kmem_cache_t *cachep = NULL; /* * Sanity checks... these are all serious usage bugs. */ if ((!name) || ((strlen(name) >= CACHE_NAMELEN - 1)) || in_interrupt() || (size < BYTES_PER_WORD) || (size > (1<<MAX_OBJ_ORDER)*PAGE_SIZE) || (dtor && !ctor) || (offset < 0 || offset > size)) BUG(); #if DEBUG if ((flags & SLAB_DEBUG_INITIAL) && !ctor) { /* No constructor, but inital state check requested */ printk("%sNo con, but init state check requested - %s\n", func_nm, name); flags &= ~SLAB_DEBUG_INITIAL; } if ((flags & SLAB_POISON) && ctor) { /* request for poisoning, but we can't do that with a constructor */ printk("%sPoisoning requested, but con given - %s\n", func_nm, name); flags &= ~SLAB_POISON; } #if FORCED_DEBUG if (size < (PAGE_SIZE>>3)) /* * do not red zone large object, causes severe * fragmentation. */ flags |= SLAB_RED_ZONE; if (!ctor) flags |= SLAB_POISON; #endif #endif /* * Always checks flags, a caller might be expecting debug * support which isn't available. */ if (flags & ~CREATE_MASK) BUG(); /* Get cache's description obj. */ cachep = (kmem_cache_t *) kmem_cache_alloc(&cache_cache, SLAB_KERNEL); if (!cachep) goto opps; memset(cachep, 0, sizeof(kmem_cache_t)); /* Check that size is in terms of words. This is needed to avoid * unaligned accesses for some archs when redzoning is used, and makes * sure any on-slab bufctl's are also correctly aligned. */ if (size & (BYTES_PER_WORD-1)) { size += (BYTES_PER_WORD-1); size &= ~(BYTES_PER_WORD-1); printk("%sForcing size word alignment - %s\n", func_nm, name); } #if DEBUG if (flags & SLAB_RED_ZONE) { /* * There is no point trying to honour cache alignment * when redzoning. */ flags &= ~SLAB_HWCACHE_ALIGN; size += 2*BYTES_PER_WORD; /* words for redzone */ } #endif align = BYTES_PER_WORD; if (flags & SLAB_HWCACHE_ALIGN) align = L1_CACHE_BYTES; /* Determine if the slab management is 'on' or 'off' slab. */ if (size >= (PAGE_SIZE>>3)) /* * Size is large, assume best to place the slab management obj * off-slab (should allow better packing of objs). */ flags |= CFLGS_OFF_SLAB; if (flags & SLAB_HWCACHE_ALIGN) { /* Need to adjust size so that objs are cache aligned. */ /* Small obj size, can get at least two per cache line. */ /* FIXME: only power of 2 supported, was better */ while (size < align/2) align /= 2; size = (size+align-1)&(~(align-1)); } /* Cal size (in pages) of slabs, and the num of objs per slab. * This could be made much more intelligent. For now, try to avoid * using high page-orders for slabs. When the gfp() funcs are more * friendly towards high-order requests, this should be changed. */ do { unsigned int break_flag = 0; cal_wastage: kmem_cache_estimate(cachep->gfporder, size, flags, &left_over, &cachep->num); if (break_flag) break; if (cachep->gfporder >= MAX_GFP_ORDER) break; if (!cachep->num) goto next; if (flags & CFLGS_OFF_SLAB && cachep->num > offslab_limit) { /* Oops, this num of objs will cause problems. */ cachep->gfporder--; break_flag++; goto cal_wastage; } /* * Large num of objs is good, but v. large slabs are currently * bad for the gfp()s. */ if (cachep->gfporder >= slab_break_gfp_order) break; if ((left_over*8) <= (PAGE_SIZE<<cachep->gfporder)) break; /* Acceptable internal fragmentation. */ next: cachep->gfporder++; } while (1); if (!cachep->num) { printk("kmem_cache_create: couldn't create cache %s.\n", name); kmem_cache_free(&cache_cache, cachep); cachep = NULL; goto opps; } slab_size = L1_CACHE_ALIGN(cachep->num*sizeof(kmem_bufctl_t)+sizeof(slab_t)); /* * If the slab has been placed off-slab, and we have enough space then * move it on-slab. This is at the expense of any extra colouring. */ if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) { flags &= ~CFLGS_OFF_SLAB; left_over -= slab_size; } /* Offset must be a multiple of the alignment. */ offset += (align-1); offset &= ~(align-1); if (!offset) offset = L1_CACHE_BYTES; cachep->colour_off = offset; cachep->colour = left_over/offset; /* init remaining fields */ if (!cachep->gfporder && !(flags & CFLGS_OFF_SLAB)) flags |= CFLGS_OPTIMIZE; cachep->flags = flags; cachep->gfpflags = 0; if (flags & SLAB_CACHE_DMA) cachep->gfpflags |= GFP_DMA; spin_lock_init(&cachep->spinlock); cachep->objsize = size; INIT_LIST_HEAD(&cachep->slabs); cachep->firstnotfull = &cachep->slabs; if (flags & CFLGS_OFF_SLAB) cachep->slabp_cache = kmem_find_general_cachep(slab_size,0); cachep->ctor = ctor; cachep->dtor = dtor; /* Copy name over so we don't have problems with unloaded modules */ strcpy(cachep->name, name); #ifdef CONFIG_SMP if (g_cpucache_up) enable_cpucache(cachep); #endif /* Need the semaphore to access the chain. */ down(&cache_chain_sem); { struct list_head *p; list_for_each(p, &cache_chain) { kmem_cache_t *pc = list_entry(p, kmem_cache_t, next); /* The name field is constant - no lock needed. */ if (!strcmp(pc->name, name)) BUG(); } } /* There is no reason to lock our new cache before we * link it in - no one knows about it yet... */ list_add(&cachep->next, &cache_chain); up(&cache_chain_sem); opps: return cachep; } #ifdef CONFIG_SMP /* * Waits for all CPUs to execute func(). */ static void smp_call_function_all_cpus(void (*func) (void *arg), void *arg) { local_irq_disable(); func(arg); local_irq_enable(); if (smp_call_function(func, arg, 1, 1)) BUG(); } typedef struct ccupdate_struct_s { kmem_cache_t *cachep; cpucache_t *new[NR_CPUS]; } ccupdate_struct_t; static void do_ccupdate_local(void *info) { ccupdate_struct_t *new = (ccupdate_struct_t *)info; cpucache_t *old = cc_data(new->cachep); cc_data(new->cachep) = new->new[smp_processor_id()]; new->new[smp_processor_id()] = old; } static void free_block (kmem_cache_t* cachep, void** objpp, int len); static void drain_cpu_caches(kmem_cache_t *cachep) { ccupdate_struct_t new; int i; memset(&new.new,0,sizeof(new.new)); new.cachep = cachep; down(&cache_chain_sem); smp_call_function_all_cpus(do_ccupdate_local, (void *)&new); for (i = 0; i < smp_num_cpus; i++) { cpucache_t* ccold = new.new[cpu_logical_map(i)]; if (!ccold || (ccold->avail == 0)) continue; local_irq_disable(); free_block(cachep, cc_entry(ccold), ccold->avail); local_irq_enable(); ccold->avail = 0; } smp_call_function_all_cpus(do_ccupdate_local, (void *)&new); up(&cache_chain_sem); } #else #define drain_cpu_caches(cachep) do { } while (0) #endif static int __kmem_cache_shrink(kmem_cache_t *cachep) { slab_t *slabp; int ret; drain_cpu_caches(cachep); spin_lock_irq(&cachep->spinlock); /* If the cache is growing, stop shrinking. */ while (!cachep->growing) { struct list_head *p; p = cachep->slabs.prev; if (p == &cachep->slabs) break; slabp = list_entry(cachep->slabs.prev, slab_t, list); if (slabp->inuse) break; list_del(&slabp->list); if (cachep->firstnotfull == &slabp->list) cachep->firstnotfull = &cachep->slabs; spin_unlock_irq(&cachep->spinlock); kmem_slab_destroy(cachep, slabp); spin_lock_irq(&cachep->spinlock); } ret = !list_empty(&cachep->slabs); spin_unlock_irq(&cachep->spinlock); return ret; } /** * kmem_cache_shrink - Shrink a cache. * @cachep: The cache to shrink. * * Releases as many slabs as possible for a cache. * To help debugging, a zero exit status indicates all slabs were released. */ int kmem_cache_shrink(kmem_cache_t *cachep) { if (!cachep || in_interrupt()) BUG(); return __kmem_cache_shrink(cachep); } /** * kmem_cache_destroy - delete a cache * @cachep: the cache to destroy * * Remove a kmem_cache_t object from the slab cache. * Returns 0 on success. * * It is expected this function will be called by a module when it is * unloaded. This will remove the cache completely, and avoid a duplicate * cache being allocated each time a module is loaded and unloaded, if the * module doesn't have persistent in-kernel storage across loads and unloads. * * The caller must guarantee that noone will allocate memory from the cache * during the kmem_cache_destroy(). */ int kmem_cache_destroy (kmem_cache_t * cachep) { if (!cachep || in_interrupt() || cachep->growing) BUG(); /* Find the cache in the chain of caches. */ down(&cache_chain_sem); /* the chain is never empty, cache_cache is never destroyed */ if (clock_searchp == cachep) clock_searchp = list_entry(cachep->next.next, kmem_cache_t, next); list_del(&cachep->next); up(&cache_chain_sem); if (__kmem_cache_shrink(cachep)) { printk(KERN_ERR "kmem_cache_destroy: Can't free all objects %p\n", cachep); down(&cache_chain_sem); list_add(&cachep->next,&cache_chain); up(&cache_chain_sem); return 1; } #ifdef CONFIG_SMP { int i; for (i = 0; i < NR_CPUS; i++) kfree(cachep->cpudata[i]); } #endif kmem_cache_free(&cache_cache, cachep); return 0; } /* Get the memory for a slab management obj. */ static inline slab_t * kmem_cache_slabmgmt (kmem_cache_t *cachep, void *objp, int colour_off, int local_flags) { slab_t *slabp; if (OFF_SLAB(cachep)) { /* Slab management obj is off-slab. */ slabp = kmem_cache_alloc(cachep->slabp_cache, local_flags); if (!slabp) return NULL; } else { /* FIXME: change to slabp = objp * if you enable OPTIMIZE */ slabp = objp+colour_off; colour_off += L1_CACHE_ALIGN(cachep->num * sizeof(kmem_bufctl_t) + sizeof(slab_t)); } slabp->inuse = 0; slabp->colouroff = colour_off; slabp->s_mem = objp+colour_off; return slabp; } static inline void kmem_cache_init_objs (kmem_cache_t * cachep, slab_t * slabp, unsigned long ctor_flags) { int i; for (i = 0; i < cachep->num; i++) { void* objp = slabp->s_mem+cachep->objsize*i; #if DEBUG if (cachep->flags & SLAB_RED_ZONE) { *((unsigned long*)(objp)) = RED_MAGIC1; *((unsigned long*)(objp + cachep->objsize - BYTES_PER_WORD)) = RED_MAGIC1; objp += BYTES_PER_WORD; } #endif /* * Constructors are not allowed to allocate memory from * the same cache which they are a constructor for. * Otherwise, deadlock. They must also be threaded. */ if (cachep->ctor) cachep->ctor(objp, cachep, ctor_flags); #if DEBUG if (cachep->flags & SLAB_RED_ZONE) objp -= BYTES_PER_WORD; if (cachep->flags & SLAB_POISON) /* need to poison the objs */ kmem_poison_obj(cachep, objp); if (cachep->flags & SLAB_RED_ZONE) { if (*((unsigned long*)(objp)) != RED_MAGIC1) BUG(); if (*((unsigned long*)(objp + cachep->objsize - BYTES_PER_WORD)) != RED_MAGIC1) BUG(); } #endif slab_bufctl(slabp)[i] = i+1; } slab_bufctl(slabp)[i-1] = BUFCTL_END; slabp->free = 0; } /* * Grow (by 1) the number of slabs within a cache. This is called by * kmem_cache_alloc() when there are no active objs left in a cache. */ static int kmem_cache_grow (kmem_cache_t * cachep, int flags) { slab_t *slabp; struct page *page; void *objp; size_t offset; unsigned int i, local_flags; unsigned long ctor_flags; unsigned long save_flags; /* Be lazy and only check for valid flags here, * keeping it out of the critical path in kmem_cache_alloc(). */ if (flags & ~(SLAB_DMA|SLAB_LEVEL_MASK|SLAB_NO_GROW)) BUG(); if (flags & SLAB_NO_GROW) return 0; /* * The test for missing atomic flag is performed here, rather than * the more obvious place, simply to reduce the critical path length * in kmem_cache_alloc(). If a caller is seriously mis-behaving they * will eventually be caught here (where it matters). */ if (in_interrupt() && (flags & SLAB_LEVEL_MASK) != SLAB_ATOMIC) BUG(); ctor_flags = SLAB_CTOR_CONSTRUCTOR; local_flags = (flags & SLAB_LEVEL_MASK); if (local_flags == SLAB_ATOMIC) /* * Not allowed to sleep. Need to tell a constructor about * this - it might need to know... */ ctor_flags |= SLAB_CTOR_ATOMIC; /* About to mess with non-constant members - lock. */ spin_lock_irqsave(&cachep->spinlock, save_flags); /* Get colour for the slab, and cal the next value. */ offset = cachep->colour_next; cachep->colour_next++; if (cachep->colour_next >= cachep->colour) cachep->colour_next = 0; offset *= cachep->colour_off; cachep->dflags |= DFLGS_GROWN; cachep->growing++; spin_unlock_irqrestore(&cachep->spinlock, save_flags); /* A series of memory allocations for a new slab. * Neither the cache-chain semaphore, or cache-lock, are * held, but the incrementing c_growing prevents this * cache from being reaped or shrunk. * Note: The cache could be selected in for reaping in * kmem_cache_reap(), but when the final test is made the * growing value will be seen. */ /* Get mem for the objs. */ if (!(objp = kmem_getpages(cachep, flags))) goto failed; /* Get slab management. */ if (!(slabp = kmem_cache_slabmgmt(cachep, objp, offset, local_flags))) goto opps1; /* Nasty!!!!!! I hope this is OK. */ i = 1 << cachep->gfporder; page = virt_to_page(objp); do { SET_PAGE_CACHE(page, cachep); SET_PAGE_SLAB(page, slabp); PageSetSlab(page); page++; } while (--i); kmem_cache_init_objs(cachep, slabp, ctor_flags); spin_lock_irqsave(&cachep->spinlock, save_flags); cachep->growing--; /* Make slab active. */ list_add_tail(&slabp->list,&cachep->slabs); if (cachep->firstnotfull == &cachep->slabs) cachep->firstnotfull = &slabp->list; STATS_INC_GROWN(cachep); cachep->failures = 0; spin_unlock_irqrestore(&cachep->spinlock, save_flags); return 1; opps1: kmem_freepages(cachep, objp); failed: spin_lock_irqsave(&cachep->spinlock, save_flags); cachep->growing--; spin_unlock_irqrestore(&cachep->spinlock, save_flags); return 0; } /* * Perform extra freeing checks: * - detect double free * - detect bad pointers. * Called with the cache-lock held. */ #if DEBUG static int kmem_extra_free_checks (kmem_cache_t * cachep, slab_t *slabp, void * objp) { int i; unsigned int objnr = (objp-slabp->s_mem)/cachep->objsize; if (objnr >= cachep->num) BUG(); if (objp != slabp->s_mem + objnr*cachep->objsize) BUG(); /* Check slab's freelist to see if this obj is there. */ for (i = slabp->free; i != BUFCTL_END; i = slab_bufctl(slabp)[i]) { if (i == objnr) BUG(); } return 0; } #endif static inline void kmem_cache_alloc_head(kmem_cache_t *cachep, int flags) { #if DEBUG if (flags & SLAB_DMA) { if (!(cachep->gfpflags & GFP_DMA)) BUG(); } else { if (cachep->gfpflags & GFP_DMA) BUG(); } #endif } static inline void * kmem_cache_alloc_one_tail (kmem_cache_t *cachep, slab_t *slabp) { void *objp; STATS_INC_ALLOCED(cachep); STATS_INC_ACTIVE(cachep); STATS_SET_HIGH(cachep); /* get obj pointer */ slabp->inuse++; objp = slabp->s_mem + slabp->free*cachep->objsize; slabp->free=slab_bufctl(slabp)[slabp->free]; if (slabp->free == BUFCTL_END) /* slab now full: move to next slab for next alloc */ cachep->firstnotfull = slabp->list.next; #if DEBUG if (cachep->flags & SLAB_POISON) if (kmem_check_poison_obj(cachep, objp)) BUG(); if (cachep->flags & SLAB_RED_ZONE) { /* Set alloc red-zone, and check old one. */ if (xchg((unsigned long *)objp, RED_MAGIC2) != RED_MAGIC1) BUG(); if (xchg((unsigned long *)(objp+cachep->objsize - BYTES_PER_WORD), RED_MAGIC2) != RED_MAGIC1) BUG(); objp += BYTES_PER_WORD; } #endif return objp; } /* * Returns a ptr to an obj in the given cache. * caller must guarantee synchronization * #define for the goto optimization 8-) */ #define kmem_cache_alloc_one(cachep) \ ({ \ slab_t *slabp; \ \ /* Get slab alloc is to come from. */ \ { \ struct list_head* p = cachep->firstnotfull; \ if (p == &cachep->slabs) \ goto alloc_new_slab; \ slabp = list_entry(p,slab_t, list); \ } \ kmem_cache_alloc_one_tail(cachep, slabp); \ }) #ifdef CONFIG_SMP void* kmem_cache_alloc_batch(kmem_cache_t* cachep, int flags) { int batchcount = cachep->batchcount; cpucache_t* cc = cc_data(cachep); spin_lock(&cachep->spinlock); while (batchcount--) { /* Get slab alloc is to come from. */ struct list_head *p = cachep->firstnotfull; slab_t *slabp; if (p == &cachep->slabs) break; slabp = list_entry(p,slab_t, list); cc_entry(cc)[cc->avail++] = kmem_cache_alloc_one_tail(cachep, slabp); } spin_unlock(&cachep->spinlock); if (cc->avail) return cc_entry(cc)[--cc->avail]; return NULL; } #endif static inline void * __kmem_cache_alloc (kmem_cache_t *cachep, int flags) { unsigned long save_flags; void* objp; kmem_cache_alloc_head(cachep, flags); try_again: local_irq_save(save_flags); #ifdef CONFIG_SMP { cpucache_t *cc = cc_data(cachep); if (cc) { if (cc->avail) { STATS_INC_ALLOCHIT(cachep); objp = cc_entry(cc)[--cc->avail]; } else { STATS_INC_ALLOCMISS(cachep); objp = kmem_cache_alloc_batch(cachep,flags); if (!objp) goto alloc_new_slab_nolock; } } else { spin_lock(&cachep->spinlock); objp = kmem_cache_alloc_one(cachep); spin_unlock(&cachep->spinlock); } } #else objp = kmem_cache_alloc_one(cachep); #endif local_irq_restore(save_flags); return objp; alloc_new_slab: #ifdef CONFIG_SMP spin_unlock(&cachep->spinlock); alloc_new_slab_nolock: #endif local_irq_restore(save_flags); if (kmem_cache_grow(cachep, flags)) /* Someone may have stolen our objs. Doesn't matter, we'll * just come back here again. */ goto try_again; return NULL; } /* * Release an obj back to its cache. If the obj has a constructed * state, it should be in this state _before_ it is released. * - caller is responsible for the synchronization */ #if DEBUG # define CHECK_NR(pg) \ do { \ if (!VALID_PAGE(pg)) { \ printk(KERN_ERR "kfree: out of range ptr %lxh.\n", \ (unsigned long)objp); \ BUG(); \ } \ } while (0) # define CHECK_PAGE(page) \ do { \ CHECK_NR(page); \ if (!PageSlab(page)) { \ printk(KERN_ERR "kfree: bad ptr %lxh.\n", \ (unsigned long)objp); \ BUG(); \ } \ } while (0) #else # define CHECK_PAGE(pg) do { } while (0) #endif static inline void kmem_cache_free_one(kmem_cache_t *cachep, void *objp) { slab_t* slabp; CHECK_PAGE(virt_to_page(objp)); /* reduces memory footprint * if (OPTIMIZE(cachep)) slabp = (void*)((unsigned long)objp&(~(PAGE_SIZE-1))); else */ slabp = GET_PAGE_SLAB(virt_to_page(objp)); #if DEBUG if (cachep->flags & SLAB_DEBUG_INITIAL) /* Need to call the slab's constructor so the * caller can perform a verify of its state (debugging). * Called without the cache-lock held. */ cachep->ctor(objp, cachep, SLAB_CTOR_CONSTRUCTOR|SLAB_CTOR_VERIFY); if (cachep->flags & SLAB_RED_ZONE) { objp -= BYTES_PER_WORD; if (xchg((unsigned long *)objp, RED_MAGIC1) != RED_MAGIC2) /* Either write before start, or a double free. */ BUG(); if (xchg((unsigned long *)(objp+cachep->objsize - BYTES_PER_WORD), RED_MAGIC1) != RED_MAGIC2) /* Either write past end, or a double free. */ BUG(); } if (cachep->flags & SLAB_POISON) kmem_poison_obj(cachep, objp); if (kmem_extra_free_checks(cachep, slabp, objp)) return; #endif { unsigned int objnr = (objp-slabp->s_mem)/cachep->objsize; slab_bufctl(slabp)[objnr] = slabp->free; slabp->free = objnr; } STATS_DEC_ACTIVE(cachep); /* fixup slab chain */ if (slabp->inuse-- == cachep->num) goto moveslab_partial; if (!slabp->inuse) goto moveslab_free; return; moveslab_partial: /* was full. * Even if the page is now empty, we can set c_firstnotfull to * slabp: there are no partial slabs in this case */ { struct list_head *t = cachep->firstnotfull; cachep->firstnotfull = &slabp->list; if (slabp->list.next == t) return; list_del(&slabp->list); list_add_tail(&slabp->list, t); return; } moveslab_free: /* * was partial, now empty. * c_firstnotfull might point to slabp * FIXME: optimize */ { struct list_head *t = cachep->firstnotfull->prev; list_del(&slabp->list); list_add_tail(&slabp->list, &cachep->slabs); if (cachep->firstnotfull == &slabp->list) cachep->firstnotfull = t->next; return; } } #ifdef CONFIG_SMP static inline void __free_block (kmem_cache_t* cachep, void** objpp, int len) { for ( ; len > 0; len--, objpp++) kmem_cache_free_one(cachep, *objpp); } static void free_block (kmem_cache_t* cachep, void** objpp, int len) { spin_lock(&cachep->spinlock); __free_block(cachep, objpp, len); spin_unlock(&cachep->spinlock); } #endif /* * __kmem_cache_free * called with disabled ints */ static inline void __kmem_cache_free (kmem_cache_t *cachep, void* objp) { #ifdef CONFIG_SMP cpucache_t *cc = cc_data(cachep); CHECK_PAGE(virt_to_page(objp)); if (cc) { int batchcount; if (cc->avail < cc->limit) { STATS_INC_FREEHIT(cachep); cc_entry(cc)[cc->avail++] = objp; return; } STATS_INC_FREEMISS(cachep); batchcount = cachep->batchcount; cc->avail -= batchcount; free_block(cachep, &cc_entry(cc)[cc->avail],batchcount); cc_entry(cc)[cc->avail++] = objp; return; } else { free_block(cachep, &objp, 1); } #else kmem_cache_free_one(cachep, objp); #endif } /** * kmem_cache_alloc - Allocate an object * @cachep: The cache to allocate from. * @flags: See kmalloc(). * * Allocate an object from this cache. The flags are only relevant * if the cache has no available objects. */ void * kmem_cache_alloc (kmem_cache_t *cachep, int flags) { return __kmem_cache_alloc(cachep, flags); } /** * 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 * in the kernel. The @flags argument may be one of: * * %GFP_BUFFER - XXX * * %GFP_ATOMIC - allocation will not sleep. Use inside interrupt handlers. * * %GFP_USER - allocate memory on behalf of user. May sleep. * * %GFP_KERNEL - allocate normal kernel ram. May sleep. * * %GFP_NFS - has a slightly lower probability of sleeping than %GFP_KERNEL. * Don't use unless you're in the NFS code. * * %GFP_KSWAPD - Don't use unless you're modifying kswapd. */ void * kmalloc (size_t size, int flags) { cache_sizes_t *csizep = cache_sizes; for (; csizep->cs_size; csizep++) { if (size > csizep->cs_size) continue; return __kmem_cache_alloc(flags & GFP_DMA ? csizep->cs_dmacachep : csizep->cs_cachep, flags); } return NULL; } /** * kmem_cache_free - Deallocate an object * @cachep: The cache the allocation was from. * @objp: The previously allocated object. * * Free an object which was previously allocated from this * cache. */ void kmem_cache_free (kmem_cache_t *cachep, void *objp) { unsigned long flags; #if DEBUG CHECK_PAGE(virt_to_page(objp)); if (cachep != GET_PAGE_CACHE(virt_to_page(objp))) BUG(); #endif local_irq_save(flags); __kmem_cache_free(cachep, objp); local_irq_restore(flags); } /** * kfree - free previously allocated memory * @objp: pointer returned by kmalloc. * * Don't free memory not originally allocated by kmalloc() * or you will run into trouble. */ void kfree (const void *objp) { kmem_cache_t *c; unsigned long flags; if (!objp) return; local_irq_save(flags); CHECK_PAGE(virt_to_page(objp)); c = GET_PAGE_CACHE(virt_to_page(objp)); __kmem_cache_free(c, (void*)objp); local_irq_restore(flags); } kmem_cache_t * kmem_find_general_cachep (size_t size, int gfpflags) { cache_sizes_t *csizep = cache_sizes; /* This function could be moved to the header file, and * made inline so consumers can quickly determine what * cache pointer they require. */ for ( ; csizep->cs_size; csizep++) { if (size > csizep->cs_size) continue; break; } return (gfpflags & GFP_DMA) ? csizep->cs_dmacachep : csizep->cs_cachep; } #ifdef CONFIG_SMP /* called with cache_chain_sem acquired. */ static int kmem_tune_cpucache (kmem_cache_t* cachep, int limit, int batchcount) { ccupdate_struct_t new; int i; /* * These are admin-provided, so we are more graceful. */ if (limit < 0) return -EINVAL; if (batchcount < 0) return -EINVAL; if (batchcount > limit) return -EINVAL; if (limit != 0 && !batchcount) return -EINVAL; memset(&new.new,0,sizeof(new.new)); if (limit) { for (i = 0; i< smp_num_cpus; i++) { cpucache_t* ccnew; ccnew = kmalloc(sizeof(void*)*limit+ sizeof(cpucache_t), GFP_KERNEL); if (!ccnew) goto oom; ccnew->limit = limit; ccnew->avail = 0; new.new[cpu_logical_map(i)] = ccnew; } } new.cachep = cachep; spin_lock_irq(&cachep->spinlock); cachep->batchcount = batchcount; spin_unlock_irq(&cachep->spinlock); smp_call_function_all_cpus(do_ccupdate_local, (void *)&new); for (i = 0; i < smp_num_cpus; i++) { cpucache_t* ccold = new.new[cpu_logical_map(i)]; if (!ccold) continue; local_irq_disable(); free_block(cachep, cc_entry(ccold), ccold->avail); local_irq_enable(); kfree(ccold); } return 0; oom: for (i--; i >= 0; i--) kfree(new.new[cpu_logical_map(i)]); return -ENOMEM; } static void enable_cpucache (kmem_cache_t *cachep) { int err; int limit; /* FIXME: optimize */ if (cachep->objsize > PAGE_SIZE) return; if (cachep->objsize > 1024) limit = 60; else if (cachep->objsize > 256) limit = 124; else limit = 252; err = kmem_tune_cpucache(cachep, limit, limit/2); if (err) printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n", cachep->name, -err); } static void enable_all_cpucaches (void) { struct list_head* p; down(&cache_chain_sem); p = &cache_cache.next; do { kmem_cache_t* cachep = list_entry(p, kmem_cache_t, next); enable_cpucache(cachep); p = cachep->next.next; } while (p != &cache_cache.next); up(&cache_chain_sem); } #endif /** * kmem_cache_reap - Reclaim memory from caches. * @gfp_mask: the type of memory required. * * Called from do_try_to_free_pages() and __alloc_pages() */ void kmem_cache_reap (int gfp_mask) { slab_t *slabp; kmem_cache_t *searchp; kmem_cache_t *best_cachep; unsigned int best_pages; unsigned int best_len; unsigned int scan; if (gfp_mask & __GFP_WAIT) down(&cache_chain_sem); else if (down_trylock(&cache_chain_sem)) return; scan = REAP_SCANLEN; best_len = 0; best_pages = 0; best_cachep = NULL; searchp = clock_searchp; do { unsigned int pages; struct list_head* p; unsigned int full_free; /* It's safe to test this without holding the cache-lock. */ if (searchp->flags & SLAB_NO_REAP) goto next; spin_lock_irq(&searchp->spinlock); if (searchp->growing) goto next_unlock; if (searchp->dflags & DFLGS_GROWN) { searchp->dflags &= ~DFLGS_GROWN; goto next_unlock; } #ifdef CONFIG_SMP { cpucache_t *cc = cc_data(searchp); if (cc && cc->avail) { __free_block(searchp, cc_entry(cc), cc->avail); cc->avail = 0; } } #endif full_free = 0; p = searchp->slabs.prev; while (p != &searchp->slabs) { slabp = list_entry(p, slab_t, list); if (slabp->inuse) break; full_free++; p = p->prev; } /* * Try to avoid slabs with constructors and/or * more than one page per slab (as it can be difficult * to get high orders from gfp()). */ pages = full_free * (1<<searchp->gfporder); if (searchp->ctor) pages = (pages*4+1)/5; if (searchp->gfporder) pages = (pages*4+1)/5; if (pages > best_pages) { best_cachep = searchp; best_len = full_free; best_pages = pages; if (full_free >= REAP_PERFECT) { clock_searchp = list_entry(searchp->next.next, kmem_cache_t,next); goto perfect; } } next_unlock: spin_unlock_irq(&searchp->spinlock); next: searchp = list_entry(searchp->next.next,kmem_cache_t,next); } while (--scan && searchp != clock_searchp); clock_searchp = searchp; if (!best_cachep) /* couldn't find anything to reap */ goto out; spin_lock_irq(&best_cachep->spinlock); perfect: /* free only 80% of the free slabs */ best_len = (best_len*4 + 1)/5; for (scan = 0; scan < best_len; scan++) { struct list_head *p; if (best_cachep->growing) break; p = best_cachep->slabs.prev; if (p == &best_cachep->slabs) break; slabp = list_entry(p,slab_t,list); if (slabp->inuse) break; list_del(&slabp->list); if (best_cachep->firstnotfull == &slabp->list) best_cachep->firstnotfull = &best_cachep->slabs; STATS_INC_REAPED(best_cachep); /* Safe to drop the lock. The slab is no longer linked to the * cache. */ spin_unlock_irq(&best_cachep->spinlock); kmem_slab_destroy(best_cachep, slabp); spin_lock_irq(&best_cachep->spinlock); } spin_unlock_irq(&best_cachep->spinlock); out: up(&cache_chain_sem); return; } #ifdef CONFIG_PROC_FS /* /proc/slabinfo * cache-name num-active-objs total-objs * obj-size num-active-slabs total-slabs * num-pages-per-slab */ #define FIXUP(t) \ do { \ if (len <= off) { \ off -= len; \ len = 0; \ } else { \ if (len-off > count) \ goto t; \ } \ } while (0) static int proc_getdata (char*page, char**start, off_t off, int count) { struct list_head *p; int len = 0; /* Output format version, so at least we can change it without _too_ * many complaints. */ len += sprintf(page+len, "slabinfo - version: 1.1" #if STATS " (statistics)" #endif #ifdef CONFIG_SMP " (SMP)" #endif "\n"); FIXUP(got_data); down(&cache_chain_sem); p = &cache_cache.next; do { kmem_cache_t *cachep; struct list_head *q; slab_t *slabp; unsigned long active_objs; unsigned long num_objs; unsigned long active_slabs = 0; unsigned long num_slabs; cachep = list_entry(p, kmem_cache_t, next); spin_lock_irq(&cachep->spinlock); active_objs = 0; num_slabs = 0; list_for_each(q,&cachep->slabs) { slabp = list_entry(q, slab_t, list); active_objs += slabp->inuse; num_objs += cachep->num; if (slabp->inuse) active_slabs++; else num_slabs++; } num_slabs+=active_slabs; num_objs = num_slabs*cachep->num; len += sprintf(page+len, "%-17s %6lu %6lu %6u %4lu %4lu %4u", cachep->name, active_objs, num_objs, cachep->objsize, active_slabs, num_slabs, (1<<cachep->gfporder)); #if STATS { unsigned long errors = cachep->errors; unsigned long high = cachep->high_mark; unsigned long grown = cachep->grown; unsigned long reaped = cachep->reaped; unsigned long allocs = cachep->num_allocations; len += sprintf(page+len, " : %6lu %7lu %5lu %4lu %4lu", high, allocs, grown, reaped, errors); } #endif #ifdef CONFIG_SMP { unsigned int batchcount = cachep->batchcount; unsigned int limit; if (cc_data(cachep)) limit = cc_data(cachep)->limit; else limit = 0; len += sprintf(page+len, " : %4u %4u", limit, batchcount); } #endif #if STATS && defined(CONFIG_SMP) { unsigned long allochit = atomic_read(&cachep->allochit); unsigned long allocmiss = atomic_read(&cachep->allocmiss); unsigned long freehit = atomic_read(&cachep->freehit); unsigned long freemiss = atomic_read(&cachep->freemiss); len += sprintf(page+len, " : %6lu %6lu %6lu %6lu", allochit, allocmiss, freehit, freemiss); } #endif len += sprintf(page+len,"\n"); spin_unlock_irq(&cachep->spinlock); FIXUP(got_data_up); p = cachep->next.next; } while (p != &cache_cache.next); got_data_up: up(&cache_chain_sem); got_data: *start = page+off; return len; } /** * slabinfo_read_proc - generates /proc/slabinfo * @page: scratch area, one page long * @start: pointer to the pointer to the output buffer * @off: offset within /proc/slabinfo the caller is interested in * @count: requested len in bytes * @eof: eof marker * @data: unused * * The contents of the buffer are * cache-name * num-active-objs * total-objs * object size * num-active-slabs * total-slabs * num-pages-per-slab * + further values on SMP and with statistics enabled */ int slabinfo_read_proc (char *page, char **start, off_t off, int count, int *eof, void *data) { int len = proc_getdata(page, start, off, count); len -= (*start-page); if (len <= count) *eof = 1; if (len>count) len = count; if (len<0) len = 0; return len; } #define MAX_SLABINFO_WRITE 128 /** * slabinfo_write_proc - SMP tuning for the slab allocator * @file: unused * @buffer: user buffer * @count: data len * @data: unused */ int slabinfo_write_proc (struct file *file, const char *buffer, unsigned long count, void *data) { #ifdef CONFIG_SMP char kbuf[MAX_SLABINFO_WRITE+1], *tmp; int limit, batchcount, res; struct list_head *p; if (count > MAX_SLABINFO_WRITE) return -EINVAL; if (copy_from_user(&kbuf, buffer, count)) return -EFAULT; kbuf[MAX_SLABINFO_WRITE] = '\0'; tmp = strchr(kbuf, ' '); if (!tmp) return -EINVAL; *tmp = '\0'; tmp++; limit = simple_strtol(tmp, &tmp, 10); while (*tmp == ' ') tmp++; batchcount = simple_strtol(tmp, &tmp, 10); /* Find the cache in the chain of caches. */ down(&cache_chain_sem); res = -EINVAL; list_for_each(p,&cache_chain) { kmem_cache_t *cachep = list_entry(p, kmem_cache_t, next); if (!strcmp(cachep->name, kbuf)) { res = kmem_tune_cpucache(cachep, limit, batchcount); break; } } up(&cache_chain_sem); if (res >= 0) res = count; return res; #else return -EINVAL; #endif } #endif |