Eric Lee / smarc-fsl-linux-kernel

slab.c 107 KB
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 
/*
 * 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
 *
 * Cleanup, make the head arrays unconditional, preparation for NUMA
 * 	(c) 2002 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.
 *
 * This means, that your constructor is used only for newly allocated
 * slabs and you must pass objects with the same initializations to
 * kmem_cache_free.
 *
 * 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.
 *
 * 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.
 * The head array is strictly LIFO and should improve the cache hit rates.
 * On SMP, it additionally reduces the spinlock operations.
 *
 * The c_cpuarray may not be read with enabled local interrupts -
 * it's changed with a smp_call_function().
 *
 * SMP synchronization:
 *  constructors and destructors are called without any locking.
 *  Several members in struct kmem_cache and struct slab never change, they
 *	are accessed without any locking.
 *  The per-cpu arrays are never accessed from the wrong cpu, no locking,
 *  	and local interrupts are disabled so slab code is preempt-safe.
 *  The non-constant members are protected with a per-cache irq spinlock.
 *
 * Many thanks to Mark Hemment, who wrote another per-cpu slab patch
 * in 2000 - many ideas in the current implementation are derived from
 * his patch.
 *
 * Further notes from the original documentation:
 *
 * 11 April '97.  Started multi-threading - markhe
 *	The global cache-chain is protected by the mutex 'slab_mutex'.
 *	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()).
 *
 *	At present, each engine can be growing a cache.  This should be blocked.
 *
 * 15 March 2005. NUMA slab allocator.
 *	Shai Fultheim <shai@scalex86.org>.
 *	Shobhit Dayal <shobhit@calsoftinc.com>
 *	Alok N Kataria <alokk@calsoftinc.com>
 *	Christoph Lameter <christoph@lameter.com>
 *
 *	Modified the slab allocator to be node aware on NUMA systems.
 *	Each node has its own list of partial, free and full slabs.
 *	All object allocations for a node occur from node specific slab lists.
 */

#include	<linux/slab.h>
#include	<linux/mm.h>
#include	<linux/poison.h>
#include	<linux/swap.h>
#include	<linux/cache.h>
#include	<linux/interrupt.h>
#include	<linux/init.h>
#include	<linux/compiler.h>
#include	<linux/cpuset.h>
#include	<linux/proc_fs.h>
#include	<linux/seq_file.h>
#include	<linux/notifier.h>
#include	<linux/kallsyms.h>
#include	<linux/cpu.h>
#include	<linux/sysctl.h>
#include	<linux/module.h>
#include	<linux/rcupdate.h>
#include	<linux/string.h>
#include	<linux/uaccess.h>
#include	<linux/nodemask.h>
#include	<linux/kmemleak.h>
#include	<linux/mempolicy.h>
#include	<linux/mutex.h>
#include	<linux/fault-inject.h>
#include	<linux/rtmutex.h>
#include	<linux/reciprocal_div.h>
#include	<linux/debugobjects.h>
#include	<linux/kmemcheck.h>
#include	<linux/memory.h>
#include	<linux/prefetch.h>

#include	<net/sock.h>

#include	<asm/cacheflush.h>
#include	<asm/tlbflush.h>
#include	<asm/page.h>

#include <trace/events/kmem.h>

#include	"internal.h"

#include	"slab.h"

/*
 * DEBUG	- 1 for kmem_cache_create() to honour; 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)
 */

#ifdef CONFIG_DEBUG_SLAB
#define	DEBUG		1
#define	STATS		1
#define	FORCED_DEBUG	1
#else
#define	DEBUG		0
#define	STATS		0
#define	FORCED_DEBUG	0
#endif

/* Shouldn't this be in a header file somewhere? */
#define	BYTES_PER_WORD		sizeof(void *)
#define	REDZONE_ALIGN		max(BYTES_PER_WORD, __alignof__(unsigned long long))

#ifndef ARCH_KMALLOC_FLAGS
#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
#endif

#define FREELIST_BYTE_INDEX (((PAGE_SIZE >> BITS_PER_BYTE) \
				<= SLAB_OBJ_MIN_SIZE) ? 1 : 0)

#if FREELIST_BYTE_INDEX
typedef unsigned char freelist_idx_t;
#else
typedef unsigned short freelist_idx_t;
#endif

#define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1)

/*
 * true if a page was allocated from pfmemalloc reserves for network-based
 * swap
 */
static bool pfmemalloc_active __read_mostly;

/*
 * struct array_cache
 *
 * Purpose:
 * - LIFO ordering, to hand out cache-warm objects from _alloc
 * - reduce the number of linked list operations
 * - reduce spinlock operations
 *
 * The limit is stored in the per-cpu structure to reduce the data cache
 * footprint.
 *
 */
struct array_cache {
	unsigned int avail;
	unsigned int limit;
	unsigned int batchcount;
	unsigned int touched;
	void *entry[];	/*
			 * Must have this definition in here for the proper
			 * alignment of array_cache. Also simplifies accessing
			 * the entries.
			 *
			 * Entries should not be directly dereferenced as
			 * entries belonging to slabs marked pfmemalloc will
			 * have the lower bits set SLAB_OBJ_PFMEMALLOC
			 */
};

struct alien_cache {
	spinlock_t lock;
	struct array_cache ac;
};

#define SLAB_OBJ_PFMEMALLOC	1
static inline bool is_obj_pfmemalloc(void *objp)
{
	return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC;
}

static inline void set_obj_pfmemalloc(void **objp)
{
	*objp = (void *)((unsigned long)*objp | SLAB_OBJ_PFMEMALLOC);
	return;
}

static inline void clear_obj_pfmemalloc(void **objp)
{
	*objp = (void *)((unsigned long)*objp & ~SLAB_OBJ_PFMEMALLOC);
}

/*
 * bootstrap: The caches do not work without cpuarrays anymore, but the
 * cpuarrays are allocated from the generic caches...
 */
#define BOOT_CPUCACHE_ENTRIES	1
struct arraycache_init {
	struct array_cache cache;
	void *entries[BOOT_CPUCACHE_ENTRIES];
};

/*
 * Need this for bootstrapping a per node allocator.
 */
#define NUM_INIT_LISTS (2 * MAX_NUMNODES)
static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS];
#define	CACHE_CACHE 0
#define	SIZE_NODE (MAX_NUMNODES)

static int drain_freelist(struct kmem_cache *cache,
			struct kmem_cache_node *n, int tofree);
static void free_block(struct kmem_cache *cachep, void **objpp, int len,
			int node, struct list_head *list);
static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list);
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp);
static void cache_reap(struct work_struct *unused);

static int slab_early_init = 1;

#define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node))

static void kmem_cache_node_init(struct kmem_cache_node *parent)
{
	INIT_LIST_HEAD(&parent->slabs_full);
	INIT_LIST_HEAD(&parent->slabs_partial);
	INIT_LIST_HEAD(&parent->slabs_free);
	parent->shared = NULL;
	parent->alien = NULL;
	parent->colour_next = 0;
	spin_lock_init(&parent->list_lock);
	parent->free_objects = 0;
	parent->free_touched = 0;
}

#define MAKE_LIST(cachep, listp, slab, nodeid)				\
	do {								\
		INIT_LIST_HEAD(listp);					\
		list_splice(&get_node(cachep, nodeid)->slab, listp);	\
	} while (0)

#define	MAKE_ALL_LISTS(cachep, ptr, nodeid)				\
	do {								\
	MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid);	\
	MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \
	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
	} while (0)

#define CFLGS_OFF_SLAB		(0x80000000UL)
#define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)

#define BATCHREFILL_LIMIT	16
/*
 * Optimization question: fewer reaps means less probability for unnessary
 * cpucache drain/refill cycles.
 *
 * OTOH the cpuarrays can contain lots of objects,
 * which could lock up otherwise freeable slabs.
 */
#define REAPTIMEOUT_AC		(2*HZ)
#define REAPTIMEOUT_NODE	(4*HZ)

#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_ADD_REAPED(x,y)	((x)->reaped += (y))
#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++)
#define	STATS_INC_NODEALLOCS(x)	((x)->node_allocs++)
#define	STATS_INC_NODEFREES(x)	((x)->node_frees++)
#define STATS_INC_ACOVERFLOW(x)   ((x)->node_overflow++)
#define	STATS_SET_FREEABLE(x, i)					\
	do {								\
		if ((x)->max_freeable < i)				\
			(x)->max_freeable = i;				\
	} while (0)
#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_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_ADD_REAPED(x,y)	do { (void)(y); } while (0)
#define	STATS_SET_HIGH(x)	do { } while (0)
#define	STATS_INC_ERR(x)	do { } while (0)
#define	STATS_INC_NODEALLOCS(x)	do { } while (0)
#define	STATS_INC_NODEFREES(x)	do { } while (0)
#define STATS_INC_ACOVERFLOW(x)   do { } while (0)
#define	STATS_SET_FREEABLE(x, i) do { } while (0)
#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

/*
 * memory layout of objects:
 * 0		: objp
 * 0 .. cachep->obj_offset - BYTES_PER_WORD - 1: padding. This ensures that
 * 		the end of an object is aligned with the end of the real
 * 		allocation. Catches writes behind the end of the allocation.
 * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1:
 * 		redzone word.
 * cachep->obj_offset: The real object.
 * cachep->size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
 * cachep->size - 1* BYTES_PER_WORD: last caller address
 *					[BYTES_PER_WORD long]
 */
static int obj_offset(struct kmem_cache *cachep)
{
	return cachep->obj_offset;
}

static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
{
	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
	return (unsigned long long*) (objp + obj_offset(cachep) -
				      sizeof(unsigned long long));
}

static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
{
	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
	if (cachep->flags & SLAB_STORE_USER)
		return (unsigned long long *)(objp + cachep->size -
					      sizeof(unsigned long long) -
					      REDZONE_ALIGN);
	return (unsigned long long *) (objp + cachep->size -
				       sizeof(unsigned long long));
}

static void **dbg_userword(struct kmem_cache *cachep, void *objp)
{
	BUG_ON(!(cachep->flags & SLAB_STORE_USER));
	return (void **)(objp + cachep->size - BYTES_PER_WORD);
}

#else

#define obj_offset(x)			0
#define dbg_redzone1(cachep, objp)	({BUG(); (unsigned long long *)NULL;})
#define dbg_redzone2(cachep, objp)	({BUG(); (unsigned long long *)NULL;})
#define dbg_userword(cachep, objp)	({BUG(); (void **)NULL;})

#endif

#define OBJECT_FREE (0)
#define OBJECT_ACTIVE (1)

#ifdef CONFIG_DEBUG_SLAB_LEAK

static void set_obj_status(struct page *page, int idx, int val)
{
	int freelist_size;
	char *status;
	struct kmem_cache *cachep = page->slab_cache;

	freelist_size = cachep->num * sizeof(freelist_idx_t);
	status = (char *)page->freelist + freelist_size;
	status[idx] = val;
}

static inline unsigned int get_obj_status(struct page *page, int idx)
{
	int freelist_size;
	char *status;
	struct kmem_cache *cachep = page->slab_cache;

	freelist_size = cachep->num * sizeof(freelist_idx_t);
	status = (char *)page->freelist + freelist_size;

	return status[idx];
}

#else
static inline void set_obj_status(struct page *page, int idx, int val) {}

#endif

/*
 * Do not go above this order unless 0 objects fit into the slab or
 * overridden on the command line.
 */
#define	SLAB_MAX_ORDER_HI	1
#define	SLAB_MAX_ORDER_LO	0
static int slab_max_order = SLAB_MAX_ORDER_LO;
static bool slab_max_order_set __initdata;

static inline struct kmem_cache *virt_to_cache(const void *obj)
{
	struct page *page = virt_to_head_page(obj);
	return page->slab_cache;
}

static inline void *index_to_obj(struct kmem_cache *cache, struct page *page,
				 unsigned int idx)
{
	return page->s_mem + cache->size * idx;
}

/*
 * We want to avoid an expensive divide : (offset / cache->size)
 *   Using the fact that size is a constant for a particular cache,
 *   we can replace (offset / cache->size) by
 *   reciprocal_divide(offset, cache->reciprocal_buffer_size)
 */
static inline unsigned int obj_to_index(const struct kmem_cache *cache,
					const struct page *page, void *obj)
{
	u32 offset = (obj - page->s_mem);
	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
}

/* internal cache of cache description objs */
static struct kmem_cache kmem_cache_boot = {
	.batchcount = 1,
	.limit = BOOT_CPUCACHE_ENTRIES,
	.shared = 1,
	.size = sizeof(struct kmem_cache),
	.name = "kmem_cache",
};

#define BAD_ALIEN_MAGIC 0x01020304ul

static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);

static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
{
	return this_cpu_ptr(cachep->cpu_cache);
}

static size_t calculate_freelist_size(int nr_objs, size_t align)
{
	size_t freelist_size;

	freelist_size = nr_objs * sizeof(freelist_idx_t);
	if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
		freelist_size += nr_objs * sizeof(char);

	if (align)
		freelist_size = ALIGN(freelist_size, align);

	return freelist_size;
}

static int calculate_nr_objs(size_t slab_size, size_t buffer_size,
				size_t idx_size, size_t align)
{
	int nr_objs;
	size_t remained_size;
	size_t freelist_size;
	int extra_space = 0;

	if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
		extra_space = sizeof(char);
	/*
	 * Ignore padding for the initial guess. The padding
	 * is at most @align-1 bytes, and @buffer_size is at
	 * least @align. In the worst case, this result will
	 * be one greater than the number of objects that fit
	 * into the memory allocation when taking the padding
	 * into account.
	 */
	nr_objs = slab_size / (buffer_size + idx_size + extra_space);

	/*
	 * This calculated number will be either the right
	 * amount, or one greater than what we want.
	 */
	remained_size = slab_size - nr_objs * buffer_size;
	freelist_size = calculate_freelist_size(nr_objs, align);
	if (remained_size < freelist_size)
		nr_objs--;

	return nr_objs;
}

/*
 * Calculate the number of objects and left-over bytes for a given buffer size.
 */
static void cache_estimate(unsigned long gfporder, size_t buffer_size,
			   size_t align, int flags, size_t *left_over,
			   unsigned int *num)
{
	int nr_objs;
	size_t mgmt_size;
	size_t slab_size = PAGE_SIZE << gfporder;

	/*
	 * The slab management structure can be either off the slab or
	 * on it. For the latter case, the memory allocated for a
	 * slab is used for:
	 *
	 * - One unsigned int for each object
	 * - Padding to respect alignment of @align
	 * - @buffer_size bytes for each object
	 *
	 * If the slab management structure is off the slab, then the
	 * alignment will already be calculated into the size. Because
	 * the slabs are all pages aligned, the objects will be at the
	 * correct alignment when allocated.
	 */
	if (flags & CFLGS_OFF_SLAB) {
		mgmt_size = 0;
		nr_objs = slab_size / buffer_size;

	} else {
		nr_objs = calculate_nr_objs(slab_size, buffer_size,
					sizeof(freelist_idx_t), align);
		mgmt_size = calculate_freelist_size(nr_objs, align);
	}
	*num = nr_objs;
	*left_over = slab_size - nr_objs*buffer_size - mgmt_size;
}

#if DEBUG
#define slab_error(cachep, msg) __slab_error(__func__, cachep, msg)

static void __slab_error(const char *function, struct kmem_cache *cachep,
			char *msg)
{
	printk(KERN_ERR "slab error in %s(): cache `%s': %s\n",
	       function, cachep->name, msg);
	dump_stack();
	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
#endif

/*
 * By default on NUMA we use alien caches to stage the freeing of
 * objects allocated from other nodes. This causes massive memory
 * inefficiencies when using fake NUMA setup to split memory into a
 * large number of small nodes, so it can be disabled on the command
 * line
  */

static int use_alien_caches __read_mostly = 1;
static int __init noaliencache_setup(char *s)
{
	use_alien_caches = 0;
	return 1;
}
__setup("noaliencache", noaliencache_setup);

static int __init slab_max_order_setup(char *str)
{
	get_option(&str, &slab_max_order);
	slab_max_order = slab_max_order < 0 ? 0 :
				min(slab_max_order, MAX_ORDER - 1);
	slab_max_order_set = true;

	return 1;
}
__setup("slab_max_order=", slab_max_order_setup);

#ifdef CONFIG_NUMA
/*
 * Special reaping functions for NUMA systems called from cache_reap().
 * These take care of doing round robin flushing of alien caches (containing
 * objects freed on different nodes from which they were allocated) and the
 * flushing of remote pcps by calling drain_node_pages.
 */
static DEFINE_PER_CPU(unsigned long, slab_reap_node);

static void init_reap_node(int cpu)
{
	int node;

	node = next_node(cpu_to_mem(cpu), node_online_map);
	if (node == MAX_NUMNODES)
		node = first_node(node_online_map);

	per_cpu(slab_reap_node, cpu) = node;
}

static void next_reap_node(void)
{
	int node = __this_cpu_read(slab_reap_node);

	node = next_node(node, node_online_map);
	if (unlikely(node >= MAX_NUMNODES))
		node = first_node(node_online_map);
	__this_cpu_write(slab_reap_node, node);
}

#else
#define init_reap_node(cpu) do { } while (0)
#define next_reap_node(void) do { } while (0)
#endif

/*
 * Initiate the reap timer running on the target CPU.  We run at around 1 to 2Hz
 * via the workqueue/eventd.
 * Add the CPU number into the expiration time to minimize the possibility of
 * the CPUs getting into lockstep and contending for the global cache chain
 * lock.
 */
static void start_cpu_timer(int cpu)
{
	struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);

	/*
	 * When this gets called from do_initcalls via cpucache_init(),
	 * init_workqueues() has already run, so keventd will be setup
	 * at that time.
	 */
	if (keventd_up() && reap_work->work.func == NULL) {
		init_reap_node(cpu);
		INIT_DEFERRABLE_WORK(reap_work, cache_reap);
		schedule_delayed_work_on(cpu, reap_work,
					__round_jiffies_relative(HZ, cpu));
	}
}

static void init_arraycache(struct array_cache *ac, int limit, int batch)
{
	/*
	 * The array_cache structures contain pointers to free object.
	 * However, when such objects are allocated or transferred to another
	 * cache the pointers are not cleared and they could be counted as
	 * valid references during a kmemleak scan. Therefore, kmemleak must
	 * not scan such objects.
	 */
	kmemleak_no_scan(ac);
	if (ac) {
		ac->avail = 0;
		ac->limit = limit;
		ac->batchcount = batch;
		ac->touched = 0;
	}
}

static struct array_cache *alloc_arraycache(int node, int entries,
					    int batchcount, gfp_t gfp)
{
	size_t memsize = sizeof(void *) * entries + sizeof(struct array_cache);
	struct array_cache *ac = NULL;

	ac = kmalloc_node(memsize, gfp, node);
	init_arraycache(ac, entries, batchcount);
	return ac;
}

static inline bool is_slab_pfmemalloc(struct page *page)
{
	return PageSlabPfmemalloc(page);
}

/* Clears pfmemalloc_active if no slabs have pfmalloc set */
static void recheck_pfmemalloc_active(struct kmem_cache *cachep,
						struct array_cache *ac)
{
	struct kmem_cache_node *n = get_node(cachep, numa_mem_id());
	struct page *page;
	unsigned long flags;

	if (!pfmemalloc_active)
		return;

	spin_lock_irqsave(&n->list_lock, flags);
	list_for_each_entry(page, &n->slabs_full, lru)
		if (is_slab_pfmemalloc(page))
			goto out;

	list_for_each_entry(page, &n->slabs_partial, lru)
		if (is_slab_pfmemalloc(page))
			goto out;

	list_for_each_entry(page, &n->slabs_free, lru)
		if (is_slab_pfmemalloc(page))
			goto out;

	pfmemalloc_active = false;
out:
	spin_unlock_irqrestore(&n->list_lock, flags);
}

static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
						gfp_t flags, bool force_refill)
{
	int i;
	void *objp = ac->entry[--ac->avail];

	/* Ensure the caller is allowed to use objects from PFMEMALLOC slab */
	if (unlikely(is_obj_pfmemalloc(objp))) {
		struct kmem_cache_node *n;

		if (gfp_pfmemalloc_allowed(flags)) {
			clear_obj_pfmemalloc(&objp);
			return objp;
		}

		/* The caller cannot use PFMEMALLOC objects, find another one */
		for (i = 0; i < ac->avail; i++) {
			/* If a !PFMEMALLOC object is found, swap them */
			if (!is_obj_pfmemalloc(ac->entry[i])) {
				objp = ac->entry[i];
				ac->entry[i] = ac->entry[ac->avail];
				ac->entry[ac->avail] = objp;
				return objp;
			}
		}

		/*
		 * If there are empty slabs on the slabs_free list and we are
		 * being forced to refill the cache, mark this one !pfmemalloc.
		 */
		n = get_node(cachep, numa_mem_id());
		if (!list_empty(&n->slabs_free) && force_refill) {
			struct page *page = virt_to_head_page(objp);
			ClearPageSlabPfmemalloc(page);
			clear_obj_pfmemalloc(&objp);
			recheck_pfmemalloc_active(cachep, ac);
			return objp;
		}

		/* No !PFMEMALLOC objects available */
		ac->avail++;
		objp = NULL;
	}

	return objp;
}

static inline void *ac_get_obj(struct kmem_cache *cachep,
			struct array_cache *ac, gfp_t flags, bool force_refill)
{
	void *objp;

	if (unlikely(sk_memalloc_socks()))
		objp = __ac_get_obj(cachep, ac, flags, force_refill);
	else
		objp = ac->entry[--ac->avail];

	return objp;
}

static noinline void *__ac_put_obj(struct kmem_cache *cachep,
			struct array_cache *ac, void *objp)
{
	if (unlikely(pfmemalloc_active)) {
		/* Some pfmemalloc slabs exist, check if this is one */
		struct page *page = virt_to_head_page(objp);
		if (PageSlabPfmemalloc(page))
			set_obj_pfmemalloc(&objp);
	}

	return objp;
}

static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
								void *objp)
{
	if (unlikely(sk_memalloc_socks()))
		objp = __ac_put_obj(cachep, ac, objp);

	ac->entry[ac->avail++] = objp;
}

/*
 * Transfer objects in one arraycache to another.
 * Locking must be handled by the caller.
 *
 * Return the number of entries transferred.
 */
static int transfer_objects(struct array_cache *to,
		struct array_cache *from, unsigned int max)
{
	/* Figure out how many entries to transfer */
	int nr = min3(from->avail, max, to->limit - to->avail);

	if (!nr)
		return 0;

	memcpy(to->entry + to->avail, from->entry + from->avail -nr,
			sizeof(void *) *nr);

	from->avail -= nr;
	to->avail += nr;
	return nr;
}

#ifndef CONFIG_NUMA

#define drain_alien_cache(cachep, alien) do { } while (0)
#define reap_alien(cachep, n) do { } while (0)

static inline struct alien_cache **alloc_alien_cache(int node,
						int limit, gfp_t gfp)
{
	return (struct alien_cache **)BAD_ALIEN_MAGIC;
}

static inline void free_alien_cache(struct alien_cache **ac_ptr)
{
}

static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
	return 0;
}

static inline void *alternate_node_alloc(struct kmem_cache *cachep,
		gfp_t flags)
{
	return NULL;
}

static inline void *____cache_alloc_node(struct kmem_cache *cachep,
		 gfp_t flags, int nodeid)
{
	return NULL;
}

#else	/* CONFIG_NUMA */

static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
static void *alternate_node_alloc(struct kmem_cache *, gfp_t);

static struct alien_cache *__alloc_alien_cache(int node, int entries,
						int batch, gfp_t gfp)
{
	size_t memsize = sizeof(void *) * entries + sizeof(struct alien_cache);
	struct alien_cache *alc = NULL;

	alc = kmalloc_node(memsize, gfp, node);
	init_arraycache(&alc->ac, entries, batch);
	spin_lock_init(&alc->lock);
	return alc;
}

static struct alien_cache **alloc_alien_cache(int node, int limit, gfp_t gfp)
{
	struct alien_cache **alc_ptr;
	size_t memsize = sizeof(void *) * nr_node_ids;
	int i;

	if (limit > 1)
		limit = 12;
	alc_ptr = kzalloc_node(memsize, gfp, node);
	if (!alc_ptr)
		return NULL;

	for_each_node(i) {
		if (i == node || !node_online(i))
			continue;
		alc_ptr[i] = __alloc_alien_cache(node, limit, 0xbaadf00d, gfp);
		if (!alc_ptr[i]) {
			for (i--; i >= 0; i--)
				kfree(alc_ptr[i]);
			kfree(alc_ptr);
			return NULL;
		}
	}
	return alc_ptr;
}

static void free_alien_cache(struct alien_cache **alc_ptr)
{
	int i;

	if (!alc_ptr)
		return;
	for_each_node(i)
	    kfree(alc_ptr[i]);
	kfree(alc_ptr);
}

static void __drain_alien_cache(struct kmem_cache *cachep,
				struct array_cache *ac, int node,
				struct list_head *list)
{
	struct kmem_cache_node *n = get_node(cachep, node);

	if (ac->avail) {
		spin_lock(&n->list_lock);
		/*
		 * Stuff objects into the remote nodes shared array first.
		 * That way we could avoid the overhead of putting the objects
		 * into the free lists and getting them back later.
		 */
		if (n->shared)
			transfer_objects(n->shared, ac, ac->limit);

		free_block(cachep, ac->entry, ac->avail, node, list);
		ac->avail = 0;
		spin_unlock(&n->list_lock);
	}
}

/*
 * Called from cache_reap() to regularly drain alien caches round robin.
 */
static void reap_alien(struct kmem_cache *cachep, struct kmem_cache_node *n)
{
	int node = __this_cpu_read(slab_reap_node);

	if (n->alien) {
		struct alien_cache *alc = n->alien[node];
		struct array_cache *ac;

		if (alc) {
			ac = &alc->ac;
			if (ac->avail && spin_trylock_irq(&alc->lock)) {
				LIST_HEAD(list);

				__drain_alien_cache(cachep, ac, node, &list);
				spin_unlock_irq(&alc->lock);
				slabs_destroy(cachep, &list);
			}
		}
	}
}

static void drain_alien_cache(struct kmem_cache *cachep,
				struct alien_cache **alien)
{
	int i = 0;
	struct alien_cache *alc;
	struct array_cache *ac;
	unsigned long flags;

	for_each_online_node(i) {
		alc = alien[i];
		if (alc) {
			LIST_HEAD(list);

			ac = &alc->ac;
			spin_lock_irqsave(&alc->lock, flags);
			__drain_alien_cache(cachep, ac, i, &list);
			spin_unlock_irqrestore(&alc->lock, flags);
			slabs_destroy(cachep, &list);
		}
	}
}

static int __cache_free_alien(struct kmem_cache *cachep, void *objp,
				int node, int page_node)
{
	struct kmem_cache_node *n;
	struct alien_cache *alien = NULL;
	struct array_cache *ac;
	LIST_HEAD(list);

	n = get_node(cachep, node);
	STATS_INC_NODEFREES(cachep);
	if (n->alien && n->alien[page_node]) {
		alien = n->alien[page_node];
		ac = &alien->ac;
		spin_lock(&alien->lock);
		if (unlikely(ac->avail == ac->limit)) {
			STATS_INC_ACOVERFLOW(cachep);
			__drain_alien_cache(cachep, ac, page_node, &list);
		}
		ac_put_obj(cachep, ac, objp);
		spin_unlock(&alien->lock);
		slabs_destroy(cachep, &list);
	} else {
		n = get_node(cachep, page_node);
		spin_lock(&n->list_lock);
		free_block(cachep, &objp, 1, page_node, &list);
		spin_unlock(&n->list_lock);
		slabs_destroy(cachep, &list);
	}
	return 1;
}

static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
	int page_node = page_to_nid(virt_to_page(objp));
	int node = numa_mem_id();
	/*
	 * Make sure we are not freeing a object from another node to the array
	 * cache on this cpu.
	 */
	if (likely(node == page_node))
		return 0;

	return __cache_free_alien(cachep, objp, node, page_node);
}
#endif

/*
 * Allocates and initializes node for a node on each slab cache, used for
 * either memory or cpu hotplug.  If memory is being hot-added, the kmem_cache_node
 * will be allocated off-node since memory is not yet online for the new node.
 * When hotplugging memory or a cpu, existing node are not replaced if
 * already in use.
 *
 * Must hold slab_mutex.
 */
static int init_cache_node_node(int node)
{
	struct kmem_cache *cachep;
	struct kmem_cache_node *n;
	const size_t memsize = sizeof(struct kmem_cache_node);

	list_for_each_entry(cachep, &slab_caches, list) {
		/*
		 * Set up the kmem_cache_node for cpu before we can
		 * begin anything. Make sure some other cpu on this
		 * node has not already allocated this
		 */
		n = get_node(cachep, node);
		if (!n) {
			n = kmalloc_node(memsize, GFP_KERNEL, node);
			if (!n)
				return -ENOMEM;
			kmem_cache_node_init(n);
			n->next_reap = jiffies + REAPTIMEOUT_NODE +
			    ((unsigned long)cachep) % REAPTIMEOUT_NODE;

			/*
			 * The kmem_cache_nodes don't come and go as CPUs
			 * come and go.  slab_mutex is sufficient
			 * protection here.
			 */
			cachep->node[node] = n;
		}

		spin_lock_irq(&n->list_lock);
		n->free_limit =
			(1 + nr_cpus_node(node)) *
			cachep->batchcount + cachep->num;
		spin_unlock_irq(&n->list_lock);
	}
	return 0;
}

static inline int slabs_tofree(struct kmem_cache *cachep,
						struct kmem_cache_node *n)
{
	return (n->free_objects + cachep->num - 1) / cachep->num;
}

static void cpuup_canceled(long cpu)
{
	struct kmem_cache *cachep;
	struct kmem_cache_node *n = NULL;
	int node = cpu_to_mem(cpu);
	const struct cpumask *mask = cpumask_of_node(node);

	list_for_each_entry(cachep, &slab_caches, list) {
		struct array_cache *nc;
		struct array_cache *shared;
		struct alien_cache **alien;
		LIST_HEAD(list);

		n = get_node(cachep, node);
		if (!n)
			continue;

		spin_lock_irq(&n->list_lock);

		/* Free limit for this kmem_cache_node */
		n->free_limit -= cachep->batchcount;

		/* cpu is dead; no one can alloc from it. */
		nc = per_cpu_ptr(cachep->cpu_cache, cpu);
		if (nc) {
			free_block(cachep, nc->entry, nc->avail, node, &list);
			nc->avail = 0;
		}

		if (!cpumask_empty(mask)) {
			spin_unlock_irq(&n->list_lock);
			goto free_slab;
		}

		shared = n->shared;
		if (shared) {
			free_block(cachep, shared->entry,
				   shared->avail, node, &list);
			n->shared = NULL;
		}

		alien = n->alien;
		n->alien = NULL;

		spin_unlock_irq(&n->list_lock);

		kfree(shared);
		if (alien) {
			drain_alien_cache(cachep, alien);
			free_alien_cache(alien);
		}

free_slab:
		slabs_destroy(cachep, &list);
	}
	/*
	 * In the previous loop, all the objects were freed to
	 * the respective cache's slabs,  now we can go ahead and
	 * shrink each nodelist to its limit.
	 */
	list_for_each_entry(cachep, &slab_caches, list) {
		n = get_node(cachep, node);
		if (!n)
			continue;
		drain_freelist(cachep, n, slabs_tofree(cachep, n));
	}
}

static int cpuup_prepare(long cpu)
{
	struct kmem_cache *cachep;
	struct kmem_cache_node *n = NULL;
	int node = cpu_to_mem(cpu);
	int err;

	/*
	 * We need to do this right in the beginning since
	 * alloc_arraycache's are going to use this list.
	 * kmalloc_node allows us to add the slab to the right
	 * kmem_cache_node and not this cpu's kmem_cache_node
	 */
	err = init_cache_node_node(node);
	if (err < 0)
		goto bad;

	/*
	 * Now we can go ahead with allocating the shared arrays and
	 * array caches
	 */
	list_for_each_entry(cachep, &slab_caches, list) {
		struct array_cache *shared = NULL;
		struct alien_cache **alien = NULL;

		if (cachep->shared) {
			shared = alloc_arraycache(node,
				cachep->shared * cachep->batchcount,
				0xbaadf00d, GFP_KERNEL);
			if (!shared)
				goto bad;
		}
		if (use_alien_caches) {
			alien = alloc_alien_cache(node, cachep->limit, GFP_KERNEL);
			if (!alien) {
				kfree(shared);
				goto bad;
			}
		}
		n = get_node(cachep, node);
		BUG_ON(!n);

		spin_lock_irq(&n->list_lock);
		if (!n->shared) {
			/*
			 * We are serialised from CPU_DEAD or
			 * CPU_UP_CANCELLED by the cpucontrol lock
			 */
			n->shared = shared;
			shared = NULL;
		}
#ifdef CONFIG_NUMA
		if (!n->alien) {
			n->alien = alien;
			alien = NULL;
		}
#endif
		spin_unlock_irq(&n->list_lock);
		kfree(shared);
		free_alien_cache(alien);
	}

	return 0;
bad:
	cpuup_canceled(cpu);
	return -ENOMEM;
}

static int cpuup_callback(struct notifier_block *nfb,
				    unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	int err = 0;

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		mutex_lock(&slab_mutex);
		err = cpuup_prepare(cpu);
		mutex_unlock(&slab_mutex);
		break;
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		start_cpu_timer(cpu);
		break;
#ifdef CONFIG_HOTPLUG_CPU
  	case CPU_DOWN_PREPARE:
  	case CPU_DOWN_PREPARE_FROZEN:
		/*
		 * Shutdown cache reaper. Note that the slab_mutex is
		 * held so that if cache_reap() is invoked it cannot do
		 * anything expensive but will only modify reap_work
		 * and reschedule the timer.
		*/
		cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
		/* Now the cache_reaper is guaranteed to be not running. */
		per_cpu(slab_reap_work, cpu).work.func = NULL;
  		break;
  	case CPU_DOWN_FAILED:
  	case CPU_DOWN_FAILED_FROZEN:
		start_cpu_timer(cpu);
  		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		/*
		 * Even if all the cpus of a node are down, we don't free the
		 * kmem_cache_node of any cache. This to avoid a race between
		 * cpu_down, and a kmalloc allocation from another cpu for
		 * memory from the node of the cpu going down.  The node
		 * structure is usually allocated from kmem_cache_create() and
		 * gets destroyed at kmem_cache_destroy().
		 */
		/* fall through */
#endif
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
		mutex_lock(&slab_mutex);
		cpuup_canceled(cpu);
		mutex_unlock(&slab_mutex);
		break;
	}
	return notifier_from_errno(err);
}

static struct notifier_block cpucache_notifier = {
	&cpuup_callback, NULL, 0
};

#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
/*
 * Drains freelist for a node on each slab cache, used for memory hot-remove.
 * Returns -EBUSY if all objects cannot be drained so that the node is not
 * removed.
 *
 * Must hold slab_mutex.
 */
static int __meminit drain_cache_node_node(int node)
{
	struct kmem_cache *cachep;
	int ret = 0;

	list_for_each_entry(cachep, &slab_caches, list) {
		struct kmem_cache_node *n;

		n = get_node(cachep, node);
		if (!n)
			continue;

		drain_freelist(cachep, n, slabs_tofree(cachep, n));

		if (!list_empty(&n->slabs_full) ||
		    !list_empty(&n->slabs_partial)) {
			ret = -EBUSY;
			break;
		}
	}
	return ret;
}

static int __meminit slab_memory_callback(struct notifier_block *self,
					unsigned long action, void *arg)
{
	struct memory_notify *mnb = arg;
	int ret = 0;
	int nid;

	nid = mnb->status_change_nid;
	if (nid < 0)
		goto out;

	switch (action) {
	case MEM_GOING_ONLINE:
		mutex_lock(&slab_mutex);
		ret = init_cache_node_node(nid);
		mutex_unlock(&slab_mutex);
		break;
	case MEM_GOING_OFFLINE:
		mutex_lock(&slab_mutex);
		ret = drain_cache_node_node(nid);
		mutex_unlock(&slab_mutex);
		break;
	case MEM_ONLINE:
	case MEM_OFFLINE:
	case MEM_CANCEL_ONLINE:
	case MEM_CANCEL_OFFLINE:
		break;
	}
out:
	return notifier_from_errno(ret);
}
#endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */

/*
 * swap the static kmem_cache_node with kmalloced memory
 */
static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node *list,
				int nodeid)
{
	struct kmem_cache_node *ptr;

	ptr = kmalloc_node(sizeof(struct kmem_cache_node), GFP_NOWAIT, nodeid);
	BUG_ON(!ptr);

	memcpy(ptr, list, sizeof(struct kmem_cache_node));
	/*
	 * Do not assume that spinlocks can be initialized via memcpy:
	 */
	spin_lock_init(&ptr->list_lock);

	MAKE_ALL_LISTS(cachep, ptr, nodeid);
	cachep->node[nodeid] = ptr;
}

/*
 * For setting up all the kmem_cache_node for cache whose buffer_size is same as
 * size of kmem_cache_node.
 */
static void __init set_up_node(struct kmem_cache *cachep, int index)
{
	int node;

	for_each_online_node(node) {
		cachep->node[node] = &init_kmem_cache_node[index + node];
		cachep->node[node]->next_reap = jiffies +
		    REAPTIMEOUT_NODE +
		    ((unsigned long)cachep) % REAPTIMEOUT_NODE;
	}
}

/*
 * Initialisation.  Called after the page allocator have been initialised and
 * before smp_init().
 */
void __init kmem_cache_init(void)
{
	int i;

	BUILD_BUG_ON(sizeof(((struct page *)NULL)->lru) <
					sizeof(struct rcu_head));
	kmem_cache = &kmem_cache_boot;

	if (num_possible_nodes() == 1)
		use_alien_caches = 0;

	for (i = 0; i < NUM_INIT_LISTS; i++)
		kmem_cache_node_init(&init_kmem_cache_node[i]);

	/*
	 * Fragmentation resistance on low memory - only use bigger
	 * page orders on machines with more than 32MB of memory if
	 * not overridden on the command line.
	 */
	if (!slab_max_order_set && totalram_pages > (32 << 20) >> PAGE_SHIFT)
		slab_max_order = SLAB_MAX_ORDER_HI;

	/* Bootstrap is tricky, because several objects are allocated
	 * from caches that do not exist yet:
	 * 1) initialize the kmem_cache cache: it contains the struct
	 *    kmem_cache structures of all caches, except kmem_cache itself:
	 *    kmem_cache is statically allocated.
	 *    Initially an __init data area is used for the head array and the
	 *    kmem_cache_node structures, it's replaced with a kmalloc allocated
	 *    array at the end of the bootstrap.
	 * 2) Create the first kmalloc cache.
	 *    The struct kmem_cache for the new cache is allocated normally.
	 *    An __init data area is used for the head array.
	 * 3) Create the remaining kmalloc caches, with minimally sized
	 *    head arrays.
	 * 4) Replace the __init data head arrays for kmem_cache and the first
	 *    kmalloc cache with kmalloc allocated arrays.
	 * 5) Replace the __init data for kmem_cache_node for kmem_cache and
	 *    the other cache's with kmalloc allocated memory.
	 * 6) Resize the head arrays of the kmalloc caches to their final sizes.
	 */

	/* 1) create the kmem_cache */

	/*
	 * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
	 */
	create_boot_cache(kmem_cache, "kmem_cache",
		offsetof(struct kmem_cache, node) +
				  nr_node_ids * sizeof(struct kmem_cache_node *),
				  SLAB_HWCACHE_ALIGN);
	list_add(&kmem_cache->list, &slab_caches);
	slab_state = PARTIAL;

	/*
	 * Initialize the caches that provide memory for the  kmem_cache_node
	 * structures first.  Without this, further allocations will bug.
	 */
	kmalloc_caches[INDEX_NODE] = create_kmalloc_cache("kmalloc-node",
				kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS);
	slab_state = PARTIAL_NODE;

	slab_early_init = 0;

	/* 5) Replace the bootstrap kmem_cache_node */
	{
		int nid;

		for_each_online_node(nid) {
			init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid);

			init_list(kmalloc_caches[INDEX_NODE],
					  &init_kmem_cache_node[SIZE_NODE + nid], nid);
		}
	}

	create_kmalloc_caches(ARCH_KMALLOC_FLAGS);
}

void __init kmem_cache_init_late(void)
{
	struct kmem_cache *cachep;

	slab_state = UP;

	/* 6) resize the head arrays to their final sizes */
	mutex_lock(&slab_mutex);
	list_for_each_entry(cachep, &slab_caches, list)
		if (enable_cpucache(cachep, GFP_NOWAIT))
			BUG();
	mutex_unlock(&slab_mutex);

	/* Done! */
	slab_state = FULL;

	/*
	 * Register a cpu startup notifier callback that initializes
	 * cpu_cache_get for all new cpus
	 */
	register_cpu_notifier(&cpucache_notifier);

#ifdef CONFIG_NUMA
	/*
	 * Register a memory hotplug callback that initializes and frees
	 * node.
	 */
	hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
#endif

	/*
	 * The reap timers are started later, with a module init call: That part
	 * of the kernel is not yet operational.
	 */
}

static int __init cpucache_init(void)
{
	int cpu;

	/*
	 * Register the timers that return unneeded pages to the page allocator
	 */
	for_each_online_cpu(cpu)
		start_cpu_timer(cpu);

	/* Done! */
	slab_state = FULL;
	return 0;
}
__initcall(cpucache_init);

static noinline void
slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
{
#if DEBUG
	struct kmem_cache_node *n;
	struct page *page;
	unsigned long flags;
	int node;
	static DEFINE_RATELIMIT_STATE(slab_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
				      DEFAULT_RATELIMIT_BURST);

	if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slab_oom_rs))
		return;

	printk(KERN_WARNING
		"SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n",
		nodeid, gfpflags);
	printk(KERN_WARNING "  cache: %s, object size: %d, order: %d\n",
		cachep->name, cachep->size, cachep->gfporder);

	for_each_kmem_cache_node(cachep, node, n) {
		unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
		unsigned long active_slabs = 0, num_slabs = 0;

		spin_lock_irqsave(&n->list_lock, flags);
		list_for_each_entry(page, &n->slabs_full, lru) {
			active_objs += cachep->num;
			active_slabs++;
		}
		list_for_each_entry(page, &n->slabs_partial, lru) {
			active_objs += page->active;
			active_slabs++;
		}
		list_for_each_entry(page, &n->slabs_free, lru)
			num_slabs++;

		free_objects += n->free_objects;
		spin_unlock_irqrestore(&n->list_lock, flags);

		num_slabs += active_slabs;
		num_objs = num_slabs * cachep->num;
		printk(KERN_WARNING
			"  node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
			node, active_slabs, num_slabs, active_objs, num_objs,
			free_objects);
	}
#endif
}

/*
 * Interface to system's page allocator. No need to hold the
 * kmem_cache_node ->list_lock.
 *
 * 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.
 */
static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
								int nodeid)
{
	struct page *page;
	int nr_pages;

	flags |= cachep->allocflags;
	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
		flags |= __GFP_RECLAIMABLE;

	if (memcg_charge_slab(cachep, flags, cachep->gfporder))
		return NULL;

	page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
	if (!page) {
		memcg_uncharge_slab(cachep, cachep->gfporder);
		slab_out_of_memory(cachep, flags, nodeid);
		return NULL;
	}

	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
	if (unlikely(page->pfmemalloc))
		pfmemalloc_active = true;

	nr_pages = (1 << cachep->gfporder);
	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
		add_zone_page_state(page_zone(page),
			NR_SLAB_RECLAIMABLE, nr_pages);
	else
		add_zone_page_state(page_zone(page),
			NR_SLAB_UNRECLAIMABLE, nr_pages);
	__SetPageSlab(page);
	if (page->pfmemalloc)
		SetPageSlabPfmemalloc(page);

	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
		kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);

		if (cachep->ctor)
			kmemcheck_mark_uninitialized_pages(page, nr_pages);
		else
			kmemcheck_mark_unallocated_pages(page, nr_pages);
	}

	return page;
}

/*
 * Interface to system's page release.
 */
static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
{
	const unsigned long nr_freed = (1 << cachep->gfporder);

	kmemcheck_free_shadow(page, cachep->gfporder);

	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
		sub_zone_page_state(page_zone(page),
				NR_SLAB_RECLAIMABLE, nr_freed);
	else
		sub_zone_page_state(page_zone(page),
				NR_SLAB_UNRECLAIMABLE, nr_freed);

	BUG_ON(!PageSlab(page));
	__ClearPageSlabPfmemalloc(page);
	__ClearPageSlab(page);
	page_mapcount_reset(page);
	page->mapping = NULL;

	if (current->reclaim_state)
		current->reclaim_state->reclaimed_slab += nr_freed;
	__free_pages(page, cachep->gfporder);
	memcg_uncharge_slab(cachep, cachep->gfporder);
}

static void kmem_rcu_free(struct rcu_head *head)
{
	struct kmem_cache *cachep;
	struct page *page;

	page = container_of(head, struct page, rcu_head);
	cachep = page->slab_cache;

	kmem_freepages(cachep, page);
}

#if DEBUG

#ifdef CONFIG_DEBUG_PAGEALLOC
static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
			    unsigned long caller)
{
	int size = cachep->object_size;

	addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];

	if (size < 5 * sizeof(unsigned long))
		return;

	*addr++ = 0x12345678;
	*addr++ = caller;
	*addr++ = smp_processor_id();
	size -= 3 * sizeof(unsigned long);
	{
		unsigned long *sptr = &caller;
		unsigned long svalue;

		while (!kstack_end(sptr)) {
			svalue = *sptr++;
			if (kernel_text_address(svalue)) {
				*addr++ = svalue;
				size -= sizeof(unsigned long);
				if (size <= sizeof(unsigned long))
					break;
			}
		}

	}
	*addr++ = 0x87654321;
}
#endif

static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
{
	int size = cachep->object_size;
	addr = &((char *)addr)[obj_offset(cachep)];

	memset(addr, val, size);
	*(unsigned char *)(addr + size - 1) = POISON_END;
}

static void dump_line(char *data, int offset, int limit)
{
	int i;
	unsigned char error = 0;
	int bad_count = 0;

	printk(KERN_ERR "%03x: ", offset);
	for (i = 0; i < limit; i++) {
		if (data[offset + i] != POISON_FREE) {
			error = data[offset + i];
			bad_count++;
		}
	}
	print_hex_dump(KERN_CONT, "", 0, 16, 1,
			&data[offset], limit, 1);

	if (bad_count == 1) {
		error ^= POISON_FREE;
		if (!(error & (error - 1))) {
			printk(KERN_ERR "Single bit error detected. Probably "
					"bad RAM.\n");
#ifdef CONFIG_X86
			printk(KERN_ERR "Run memtest86+ or a similar memory "
					"test tool.\n");
#else
			printk(KERN_ERR "Run a memory test tool.\n");
#endif
		}
	}
}
#endif

#if DEBUG

static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
{
	int i, size;
	char *realobj;

	if (cachep->flags & SLAB_RED_ZONE) {
		printk(KERN_ERR "Redzone: 0x%llx/0x%llx.\n",
			*dbg_redzone1(cachep, objp),
			*dbg_redzone2(cachep, objp));
	}

	if (cachep->flags & SLAB_STORE_USER) {
		printk(KERN_ERR "Last user: [<%p>](%pSR)\n",
		       *dbg_userword(cachep, objp),
		       *dbg_userword(cachep, objp));
	}
	realobj = (char *)objp + obj_offset(cachep);
	size = cachep->object_size;
	for (i = 0; i < size && lines; i += 16, lines--) {
		int limit;
		limit = 16;
		if (i + limit > size)
			limit = size - i;
		dump_line(realobj, i, limit);
	}
}

static void check_poison_obj(struct kmem_cache *cachep, void *objp)
{
	char *realobj;
	int size, i;
	int lines = 0;

	realobj = (char *)objp + obj_offset(cachep);
	size = cachep->object_size;

	for (i = 0; i < size; i++) {
		char exp = POISON_FREE;
		if (i == size - 1)
			exp = POISON_END;
		if (realobj[i] != exp) {
			int limit;
			/* Mismatch ! */
			/* Print header */
			if (lines == 0) {
				printk(KERN_ERR
					"Slab corruption (%s): %s start=%p, len=%d\n",
					print_tainted(), cachep->name, realobj, size);
				print_objinfo(cachep, objp, 0);
			}
			/* Hexdump the affected line */
			i = (i / 16) * 16;
			limit = 16;
			if (i + limit > size)
				limit = size - i;
			dump_line(realobj, i, limit);
			i += 16;
			lines++;
			/* Limit to 5 lines */
			if (lines > 5)
				break;
		}
	}
	if (lines != 0) {
		/* Print some data about the neighboring objects, if they
		 * exist:
		 */
		struct page *page = virt_to_head_page(objp);
		unsigned int objnr;

		objnr = obj_to_index(cachep, page, objp);
		if (objnr) {
			objp = index_to_obj(cachep, page, objnr - 1);
			realobj = (char *)objp + obj_offset(cachep);
			printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
			       realobj, size);
			print_objinfo(cachep, objp, 2);
		}
		if (objnr + 1 < cachep->num) {
			objp = index_to_obj(cachep, page, objnr + 1);
			realobj = (char *)objp + obj_offset(cachep);
			printk(KERN_ERR "Next obj: start=%p, len=%d\n",
			       realobj, size);
			print_objinfo(cachep, objp, 2);
		}
	}
}
#endif

#if DEBUG
static void slab_destroy_debugcheck(struct kmem_cache *cachep,
						struct page *page)
{
	int i;
	for (i = 0; i < cachep->num; i++) {
		void *objp = index_to_obj(cachep, page, i);

		if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
			if (cachep->size % PAGE_SIZE == 0 &&
					OFF_SLAB(cachep))
				kernel_map_pages(virt_to_page(objp),
					cachep->size / PAGE_SIZE, 1);
			else
				check_poison_obj(cachep, objp);
#else
			check_poison_obj(cachep, objp);
#endif
		}
		if (cachep->flags & SLAB_RED_ZONE) {
			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "start of a freed object "
					   "was overwritten");
			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "end of a freed object "
					   "was overwritten");
		}
	}
}
#else
static void slab_destroy_debugcheck(struct kmem_cache *cachep,
						struct page *page)
{
}
#endif

/**
 * slab_destroy - destroy and release all objects in a slab
 * @cachep: cache pointer being destroyed
 * @page: page pointer being destroyed
 *
 * Destroy all the objs in a slab page, and release the mem back to the system.
 * Before calling the slab page must have been unlinked from the cache. The
 * kmem_cache_node ->list_lock is not held/needed.
 */
static void slab_destroy(struct kmem_cache *cachep, struct page *page)
{
	void *freelist;

	freelist = page->freelist;
	slab_destroy_debugcheck(cachep, page);
	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
		struct rcu_head *head;

		/*
		 * RCU free overloads the RCU head over the LRU.
		 * slab_page has been overloeaded over the LRU,
		 * however it is not used from now on so that
		 * we can use it safely.
		 */
		head = (void *)&page->rcu_head;
		call_rcu(head, kmem_rcu_free);

	} else {
		kmem_freepages(cachep, page);
	}

	/*
	 * From now on, we don't use freelist
	 * although actual page can be freed in rcu context
	 */
	if (OFF_SLAB(cachep))
		kmem_cache_free(cachep->freelist_cache, freelist);
}

static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list)
{
	struct page *page, *n;

	list_for_each_entry_safe(page, n, list, lru) {
		list_del(&page->lru);
		slab_destroy(cachep, page);
	}
}

/**
 * calculate_slab_order - calculate size (page order) of slabs
 * @cachep: pointer to the cache that is being created
 * @size: size of objects to be created in this cache.
 * @align: required alignment for the objects.
 * @flags: slab allocation flags
 *
 * Also calculates the number of objects per slab.
 *
 * This could be made much more intelligent.  For now, try to avoid using
 * high order pages for slabs.  When the gfp() functions are more friendly
 * towards high-order requests, this should be changed.
 */
static size_t calculate_slab_order(struct kmem_cache *cachep,
			size_t size, size_t align, unsigned long flags)
{
	unsigned long offslab_limit;
	size_t left_over = 0;
	int gfporder;

	for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) {
		unsigned int num;
		size_t remainder;

		cache_estimate(gfporder, size, align, flags, &remainder, &num);
		if (!num)
			continue;

		/* Can't handle number of objects more than SLAB_OBJ_MAX_NUM */
		if (num > SLAB_OBJ_MAX_NUM)
			break;

		if (flags & CFLGS_OFF_SLAB) {
			size_t freelist_size_per_obj = sizeof(freelist_idx_t);
			/*
			 * Max number of objs-per-slab for caches which
			 * use off-slab slabs. Needed to avoid a possible
			 * looping condition in cache_grow().
			 */
			if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
				freelist_size_per_obj += sizeof(char);
			offslab_limit = size;
			offslab_limit /= freelist_size_per_obj;

 			if (num > offslab_limit)
				break;
		}

		/* Found something acceptable - save it away */
		cachep->num = num;
		cachep->gfporder = gfporder;
		left_over = remainder;

		/*
		 * A VFS-reclaimable slab tends to have most allocations
		 * as GFP_NOFS and we really don't want to have to be allocating
		 * higher-order pages when we are unable to shrink dcache.
		 */
		if (flags & SLAB_RECLAIM_ACCOUNT)
			break;

		/*
		 * Large number of objects is good, but very large slabs are
		 * currently bad for the gfp()s.
		 */
		if (gfporder >= slab_max_order)
			break;

		/*
		 * Acceptable internal fragmentation?
		 */
		if (left_over * 8 <= (PAGE_SIZE << gfporder))
			break;
	}
	return left_over;
}

static struct array_cache __percpu *alloc_kmem_cache_cpus(
		struct kmem_cache *cachep, int entries, int batchcount)
{
	int cpu;
	size_t size;
	struct array_cache __percpu *cpu_cache;

	size = sizeof(void *) * entries + sizeof(struct array_cache);
	cpu_cache = __alloc_percpu(size, sizeof(void *));

	if (!cpu_cache)
		return NULL;

	for_each_possible_cpu(cpu) {
		init_arraycache(per_cpu_ptr(cpu_cache, cpu),
				entries, batchcount);
	}

	return cpu_cache;
}

static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
{
	if (slab_state >= FULL)
		return enable_cpucache(cachep, gfp);

	cachep->cpu_cache = alloc_kmem_cache_cpus(cachep, 1, 1);
	if (!cachep->cpu_cache)
		return 1;

	if (slab_state == DOWN) {
		/* Creation of first cache (kmem_cache). */
		set_up_node(kmem_cache, CACHE_CACHE);
	} else if (slab_state == PARTIAL) {
		/* For kmem_cache_node */
		set_up_node(cachep, SIZE_NODE);
	} else {
		int node;

		for_each_online_node(node) {
			cachep->node[node] = kmalloc_node(
				sizeof(struct kmem_cache_node), gfp, node);
			BUG_ON(!cachep->node[node]);
			kmem_cache_node_init(cachep->node[node]);
		}
	}

	cachep->node[numa_mem_id()]->next_reap =
			jiffies + REAPTIMEOUT_NODE +
			((unsigned long)cachep) % REAPTIMEOUT_NODE;

	cpu_cache_get(cachep)->avail = 0;
	cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
	cpu_cache_get(cachep)->batchcount = 1;
	cpu_cache_get(cachep)->touched = 0;
	cachep->batchcount = 1;
	cachep->limit = BOOT_CPUCACHE_ENTRIES;
	return 0;
}

unsigned long kmem_cache_flags(unsigned long object_size,
	unsigned long flags, const char *name,
	void (*ctor)(void *))
{
	return flags;
}

struct kmem_cache *
__kmem_cache_alias(const char *name, size_t size, size_t align,
		   unsigned long flags, void (*ctor)(void *))
{
	struct kmem_cache *cachep;

	cachep = find_mergeable(size, align, flags, name, ctor);
	if (cachep) {
		cachep->refcount++;

		/*
		 * Adjust the object sizes so that we clear
		 * the complete object on kzalloc.
		 */
		cachep->object_size = max_t(int, cachep->object_size, size);
	}
	return cachep;
}

/**
 * __kmem_cache_create - Create a cache.
 * @cachep: cache management descriptor
 * @flags: SLAB flags
 *
 * 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.
 *
 * 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_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.
 */
int
__kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
{
	size_t left_over, freelist_size;
	size_t ralign = BYTES_PER_WORD;
	gfp_t gfp;
	int err;
	size_t size = cachep->size;

#if DEBUG
#if FORCED_DEBUG
	/*
	 * Enable redzoning and last user accounting, except for caches with
	 * large objects, if the increased size would increase the object size
	 * above the next power of two: caches with object sizes just above a
	 * power of two have a significant amount of internal fragmentation.
	 */
	if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
						2 * sizeof(unsigned long long)))
		flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
	if (!(flags & SLAB_DESTROY_BY_RCU))
		flags |= SLAB_POISON;
#endif
	if (flags & SLAB_DESTROY_BY_RCU)
		BUG_ON(flags & SLAB_POISON);
#endif

	/*
	 * 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);
	}

	if (flags & SLAB_RED_ZONE) {
		ralign = REDZONE_ALIGN;
		/* If redzoning, ensure that the second redzone is suitably
		 * aligned, by adjusting the object size accordingly. */
		size += REDZONE_ALIGN - 1;
		size &= ~(REDZONE_ALIGN - 1);
	}

	/* 3) caller mandated alignment */
	if (ralign < cachep->align) {
		ralign = cachep->align;
	}
	/* disable debug if necessary */
	if (ralign > __alignof__(unsigned long long))
		flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
	/*
	 * 4) Store it.
	 */
	cachep->align = ralign;

	if (slab_is_available())
		gfp = GFP_KERNEL;
	else
		gfp = GFP_NOWAIT;

#if DEBUG

	/*
	 * Both debugging options require word-alignment which is calculated
	 * into align above.
	 */
	if (flags & SLAB_RED_ZONE) {
		/* add space for red zone words */
		cachep->obj_offset += sizeof(unsigned long long);
		size += 2 * sizeof(unsigned long long);
	}
	if (flags & SLAB_STORE_USER) {
		/* user store requires one word storage behind the end of
		 * the real object. But if the second red zone needs to be
		 * aligned to 64 bits, we must allow that much space.
		 */
		if (flags & SLAB_RED_ZONE)
			size += REDZONE_ALIGN;
		else
			size += BYTES_PER_WORD;
	}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
	if (size >= kmalloc_size(INDEX_NODE + 1)
	    && cachep->object_size > cache_line_size()
	    && ALIGN(size, cachep->align) < PAGE_SIZE) {
		cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
		size = PAGE_SIZE;
	}
#endif
#endif

	/*
	 * Determine if the slab management is 'on' or 'off' slab.
	 * (bootstrapping cannot cope with offslab caches so don't do
	 * it too early on. Always use on-slab management when
	 * SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak)
	 */
	if ((size >= (PAGE_SIZE >> 5)) && !slab_early_init &&
	    !(flags & SLAB_NOLEAKTRACE))
		/*
		 * Size is large, assume best to place the slab management obj
		 * off-slab (should allow better packing of objs).
		 */
		flags |= CFLGS_OFF_SLAB;

	size = ALIGN(size, cachep->align);
	/*
	 * We should restrict the number of objects in a slab to implement
	 * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition.
	 */
	if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
		size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);

	left_over = calculate_slab_order(cachep, size, cachep->align, flags);

	if (!cachep->num)
		return -E2BIG;

	freelist_size = calculate_freelist_size(cachep->num, cachep->align);

	/*
	 * 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 >= freelist_size) {
		flags &= ~CFLGS_OFF_SLAB;
		left_over -= freelist_size;
	}

	if (flags & CFLGS_OFF_SLAB) {
		/* really off slab. No need for manual alignment */
		freelist_size = calculate_freelist_size(cachep->num, 0);

#ifdef CONFIG_PAGE_POISONING
		/* If we're going to use the generic kernel_map_pages()
		 * poisoning, then it's going to smash the contents of
		 * the redzone and userword anyhow, so switch them off.
		 */
		if (size % PAGE_SIZE == 0 && flags & SLAB_POISON)
			flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
#endif
	}

	cachep->colour_off = cache_line_size();
	/* Offset must be a multiple of the alignment. */
	if (cachep->colour_off < cachep->align)
		cachep->colour_off = cachep->align;
	cachep->colour = left_over / cachep->colour_off;
	cachep->freelist_size = freelist_size;
	cachep->flags = flags;
	cachep->allocflags = __GFP_COMP;
	if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
		cachep->allocflags |= GFP_DMA;
	cachep->size = size;
	cachep->reciprocal_buffer_size = reciprocal_value(size);

	if (flags & CFLGS_OFF_SLAB) {
		cachep->freelist_cache = kmalloc_slab(freelist_size, 0u);
		/*
		 * This is a possibility for one of the kmalloc_{dma,}_caches.
		 * But since we go off slab only for object size greater than
		 * PAGE_SIZE/8, and kmalloc_{dma,}_caches get created
		 * in ascending order,this should not happen at all.
		 * But leave a BUG_ON for some lucky dude.
		 */
		BUG_ON(ZERO_OR_NULL_PTR(cachep->freelist_cache));
	}

	err = setup_cpu_cache(cachep, gfp);
	if (err) {
		__kmem_cache_shutdown(cachep);
		return err;
	}

	return 0;
}

#if DEBUG
static void check_irq_off(void)
{
	BUG_ON(!irqs_disabled());
}

static void check_irq_on(void)
{
	BUG_ON(irqs_disabled());
}

static void check_spinlock_acquired(struct kmem_cache *cachep)
{
#ifdef CONFIG_SMP
	check_irq_off();
	assert_spin_locked(&get_node(cachep, numa_mem_id())->list_lock);
#endif
}

static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
{
#ifdef CONFIG_SMP
	check_irq_off();
	assert_spin_locked(&get_node(cachep, node)->list_lock);
#endif
}

#else
#define check_irq_off()	do { } while(0)
#define check_irq_on()	do { } while(0)
#define check_spinlock_acquired(x) do { } while(0)
#define check_spinlock_acquired_node(x, y) do { } while(0)
#endif

static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n,
			struct array_cache *ac,
			int force, int node);

static void do_drain(void *arg)
{
	struct kmem_cache *cachep = arg;
	struct array_cache *ac;
	int node = numa_mem_id();
	struct kmem_cache_node *n;
	LIST_HEAD(list);

	check_irq_off();
	ac = cpu_cache_get(cachep);
	n = get_node(cachep, node);
	spin_lock(&n->list_lock);
	free_block(cachep, ac->entry, ac->avail, node, &list);
	spin_unlock(&n->list_lock);
	slabs_destroy(cachep, &list);
	ac->avail = 0;
}

static void drain_cpu_caches(struct kmem_cache *cachep)
{
	struct kmem_cache_node *n;
	int node;

	on_each_cpu(do_drain, cachep, 1);
	check_irq_on();
	for_each_kmem_cache_node(cachep, node, n)
		if (n->alien)
			drain_alien_cache(cachep, n->alien);

	for_each_kmem_cache_node(cachep, node, n)
		drain_array(cachep, n, n->shared, 1, node);
}

/*
 * Remove slabs from the list of free slabs.
 * Specify the number of slabs to drain in tofree.
 *
 * Returns the actual number of slabs released.
 */
static int drain_freelist(struct kmem_cache *cache,
			struct kmem_cache_node *n, int tofree)
{
	struct list_head *p;
	int nr_freed;
	struct page *page;

	nr_freed = 0;
	while (nr_freed < tofree && !list_empty(&n->slabs_free)) {

		spin_lock_irq(&n->list_lock);
		p = n->slabs_free.prev;
		if (p == &n->slabs_free) {
			spin_unlock_irq(&n->list_lock);
			goto out;
		}

		page = list_entry(p, struct page, lru);
#if DEBUG
		BUG_ON(page->active);
#endif
		list_del(&page->lru);
		/*
		 * Safe to drop the lock. The slab is no longer linked
		 * to the cache.
		 */
		n->free_objects -= cache->num;
		spin_unlock_irq(&n->list_lock);
		slab_destroy(cache, page);
		nr_freed++;
	}
out:
	return nr_freed;
}

int __kmem_cache_shrink(struct kmem_cache *cachep)
{
	int ret = 0;
	int node;
	struct kmem_cache_node *n;

	drain_cpu_caches(cachep);

	check_irq_on();
	for_each_kmem_cache_node(cachep, node, n) {
		drain_freelist(cachep, n, slabs_tofree(cachep, n));

		ret += !list_empty(&n->slabs_full) ||
			!list_empty(&n->slabs_partial);
	}
	return (ret ? 1 : 0);
}

int __kmem_cache_shutdown(struct kmem_cache *cachep)
{
	int i;
	struct kmem_cache_node *n;
	int rc = __kmem_cache_shrink(cachep);

	if (rc)
		return rc;

	free_percpu(cachep->cpu_cache);

	/* NUMA: free the node structures */
	for_each_kmem_cache_node(cachep, i, n) {
		kfree(n->shared);
		free_alien_cache(n->alien);
		kfree(n);
		cachep->node[i] = NULL;
	}
	return 0;
}

/*
 * Get the memory for a slab management obj.
 *
 * For a slab cache when the slab descriptor is off-slab, the
 * slab descriptor can't come from the same cache which is being created,
 * Because if it is the case, that means we defer the creation of
 * the kmalloc_{dma,}_cache of size sizeof(slab descriptor) to this point.
 * And we eventually call down to __kmem_cache_create(), which
 * in turn looks up in the kmalloc_{dma,}_caches for the disired-size one.
 * This is a "chicken-and-egg" problem.
 *
 * So the off-slab slab descriptor shall come from the kmalloc_{dma,}_caches,
 * which are all initialized during kmem_cache_init().
 */
static void *alloc_slabmgmt(struct kmem_cache *cachep,
				   struct page *page, int colour_off,
				   gfp_t local_flags, int nodeid)
{
	void *freelist;
	void *addr = page_address(page);

	if (OFF_SLAB(cachep)) {
		/* Slab management obj is off-slab. */
		freelist = kmem_cache_alloc_node(cachep->freelist_cache,
					      local_flags, nodeid);
		if (!freelist)
			return NULL;
	} else {
		freelist = addr + colour_off;
		colour_off += cachep->freelist_size;
	}
	page->active = 0;
	page->s_mem = addr + colour_off;
	return freelist;
}

static inline freelist_idx_t get_free_obj(struct page *page, unsigned int idx)
{
	return ((freelist_idx_t *)page->freelist)[idx];
}

static inline void set_free_obj(struct page *page,
					unsigned int idx, freelist_idx_t val)
{
	((freelist_idx_t *)(page->freelist))[idx] = val;
}

static void cache_init_objs(struct kmem_cache *cachep,
			    struct page *page)
{
	int i;

	for (i = 0; i < cachep->num; i++) {
		void *objp = index_to_obj(cachep, page, i);
#if DEBUG
		/* need to poison the objs? */
		if (cachep->flags & SLAB_POISON)
			poison_obj(cachep, objp, POISON_FREE);
		if (cachep->flags & SLAB_STORE_USER)
			*dbg_userword(cachep, objp) = NULL;

		if (cachep->flags & SLAB_RED_ZONE) {
			*dbg_redzone1(cachep, objp) = RED_INACTIVE;
			*dbg_redzone2(cachep, objp) = RED_INACTIVE;
		}
		/*
		 * 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->flags & SLAB_POISON))
			cachep->ctor(objp + obj_offset(cachep));

		if (cachep->flags & SLAB_RED_ZONE) {
			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "constructor overwrote the"
					   " end of an object");
			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "constructor overwrote the"
					   " start of an object");
		}
		if ((cachep->size % PAGE_SIZE) == 0 &&
			    OFF_SLAB(cachep) && cachep->flags & SLAB_POISON)
			kernel_map_pages(virt_to_page(objp),
					 cachep->size / PAGE_SIZE, 0);
#else
		if (cachep->ctor)
			cachep->ctor(objp);
#endif
		set_obj_status(page, i, OBJECT_FREE);
		set_free_obj(page, i, i);
	}
}

static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
{
	if (CONFIG_ZONE_DMA_FLAG) {
		if (flags & GFP_DMA)
			BUG_ON(!(cachep->allocflags & GFP_DMA));
		else
			BUG_ON(cachep->allocflags & GFP_DMA);
	}
}

static void *slab_get_obj(struct kmem_cache *cachep, struct page *page,
				int nodeid)
{
	void *objp;

	objp = index_to_obj(cachep, page, get_free_obj(page, page->active));
	page->active++;
#if DEBUG
	WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
#endif

	return objp;
}

static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
				void *objp, int nodeid)
{
	unsigned int objnr = obj_to_index(cachep, page, objp);
#if DEBUG
	unsigned int i;

	/* Verify that the slab belongs to the intended node */
	WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);

	/* Verify double free bug */
	for (i = page->active; i < cachep->num; i++) {
		if (get_free_obj(page, i) == objnr) {
			printk(KERN_ERR "slab: double free detected in cache "
					"'%s', objp %p\n", cachep->name, objp);
			BUG();
		}
	}
#endif
	page->active--;
	set_free_obj(page, page->active, objnr);
}

/*
 * Map pages beginning at addr to the given cache and slab. This is required
 * for the slab allocator to be able to lookup the cache and slab of a
 * virtual address for kfree, ksize, and slab debugging.
 */
static void slab_map_pages(struct kmem_cache *cache, struct page *page,
			   void *freelist)
{
	page->slab_cache = cache;
	page->freelist = freelist;
}

/*
 * 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 cache_grow(struct kmem_cache *cachep,
		gfp_t flags, int nodeid, struct page *page)
{
	void *freelist;
	size_t offset;
	gfp_t local_flags;
	struct kmem_cache_node *n;

	/*
	 * Be lazy and only check for valid flags here,  keeping it out of the
	 * critical path in kmem_cache_alloc().
	 */
	BUG_ON(flags & GFP_SLAB_BUG_MASK);
	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);

	/* Take the node list lock to change the colour_next on this node */
	check_irq_off();
	n = get_node(cachep, nodeid);
	spin_lock(&n->list_lock);

	/* Get colour for the slab, and cal the next value. */
	offset = n->colour_next;
	n->colour_next++;
	if (n->colour_next >= cachep->colour)
		n->colour_next = 0;
	spin_unlock(&n->list_lock);

	offset *= cachep->colour_off;

	if (local_flags & __GFP_WAIT)
		local_irq_enable();

	/*
	 * 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).
	 */
	kmem_flagcheck(cachep, flags);

	/*
	 * Get mem for the objs.  Attempt to allocate a physical page from
	 * 'nodeid'.
	 */
	if (!page)
		page = kmem_getpages(cachep, local_flags, nodeid);
	if (!page)
		goto failed;

	/* Get slab management. */
	freelist = alloc_slabmgmt(cachep, page, offset,
			local_flags & ~GFP_CONSTRAINT_MASK, nodeid);
	if (!freelist)
		goto opps1;

	slab_map_pages(cachep, page, freelist);

	cache_init_objs(cachep, page);

	if (local_flags & __GFP_WAIT)
		local_irq_disable();
	check_irq_off();
	spin_lock(&n->list_lock);

	/* Make slab active. */
	list_add_tail(&page->lru, &(n->slabs_free));
	STATS_INC_GROWN(cachep);
	n->free_objects += cachep->num;
	spin_unlock(&n->list_lock);
	return 1;
opps1:
	kmem_freepages(cachep, page);
failed:
	if (local_flags & __GFP_WAIT)
		local_irq_disable();
	return 0;
}

#if DEBUG

/*
 * Perform extra freeing checks:
 * - detect bad pointers.
 * - POISON/RED_ZONE checking
 */
static void kfree_debugcheck(const void *objp)
{
	if (!virt_addr_valid(objp)) {
		printk(KERN_ERR "kfree_debugcheck: out of range ptr %lxh.\n",
		       (unsigned long)objp);
		BUG();
	}
}

static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
{
	unsigned long long redzone1, redzone2;

	redzone1 = *dbg_redzone1(cache, obj);
	redzone2 = *dbg_redzone2(cache, obj);

	/*
	 * Redzone is ok.
	 */
	if (redzone1 == RED_ACTIVE && redzone2 == RED_ACTIVE)
		return;

	if (redzone1 == RED_INACTIVE && redzone2 == RED_INACTIVE)
		slab_error(cache, "double free detected");
	else
		slab_error(cache, "memory outside object was overwritten");

	printk(KERN_ERR "%p: redzone 1:0x%llx, redzone 2:0x%llx.\n",
			obj, redzone1, redzone2);
}

static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
				   unsigned long caller)
{
	unsigned int objnr;
	struct page *page;

	BUG_ON(virt_to_cache(objp) != cachep);

	objp -= obj_offset(cachep);
	kfree_debugcheck(objp);
	page = virt_to_head_page(objp);

	if (cachep->flags & SLAB_RED_ZONE) {
		verify_redzone_free(cachep, objp);
		*dbg_redzone1(cachep, objp) = RED_INACTIVE;
		*dbg_redzone2(cachep, objp) = RED_INACTIVE;
	}
	if (cachep->flags & SLAB_STORE_USER)
		*dbg_userword(cachep, objp) = (void *)caller;

	objnr = obj_to_index(cachep, page, objp);

	BUG_ON(objnr >= cachep->num);
	BUG_ON(objp != index_to_obj(cachep, page, objnr));

	set_obj_status(page, objnr, OBJECT_FREE);
	if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
		if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
			store_stackinfo(cachep, objp, caller);
			kernel_map_pages(virt_to_page(objp),
					 cachep->size / PAGE_SIZE, 0);
		} else {
			poison_obj(cachep, objp, POISON_FREE);
		}
#else
		poison_obj(cachep, objp, POISON_FREE);
#endif
	}
	return objp;
}

#else
#define kfree_debugcheck(x) do { } while(0)
#define cache_free_debugcheck(x,objp,z) (objp)
#endif

static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
							bool force_refill)
{
	int batchcount;
	struct kmem_cache_node *n;
	struct array_cache *ac;
	int node;

	check_irq_off();
	node = numa_mem_id();
	if (unlikely(force_refill))
		goto force_grow;
retry:
	ac = cpu_cache_get(cachep);
	batchcount = ac->batchcount;
	if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
		/*
		 * If there was little recent activity on this cache, then
		 * perform only a partial refill.  Otherwise we could generate
		 * refill bouncing.
		 */
		batchcount = BATCHREFILL_LIMIT;
	}
	n = get_node(cachep, node);

	BUG_ON(ac->avail > 0 || !n);
	spin_lock(&n->list_lock);

	/* See if we can refill from the shared array */
	if (n->shared && transfer_objects(ac, n->shared, batchcount)) {
		n->shared->touched = 1;
		goto alloc_done;
	}

	while (batchcount > 0) {
		struct list_head *entry;
		struct page *page;
		/* Get slab alloc is to come from. */
		entry = n->slabs_partial.next;
		if (entry == &n->slabs_partial) {
			n->free_touched = 1;
			entry = n->slabs_free.next;
			if (entry == &n->slabs_free)
				goto must_grow;
		}

		page = list_entry(entry, struct page, lru);
		check_spinlock_acquired(cachep);

		/*
		 * The slab was either on partial or free list so
		 * there must be at least one object available for
		 * allocation.
		 */
		BUG_ON(page->active >= cachep->num);

		while (page->active < cachep->num && batchcount--) {
			STATS_INC_ALLOCED(cachep);
			STATS_INC_ACTIVE(cachep);
			STATS_SET_HIGH(cachep);

			ac_put_obj(cachep, ac, slab_get_obj(cachep, page,
									node));
		}

		/* move slabp to correct slabp list: */
		list_del(&page->lru);
		if (page->active == cachep->num)
			list_add(&page->lru, &n->slabs_full);
		else
			list_add(&page->lru, &n->slabs_partial);
	}

must_grow:
	n->free_objects -= ac->avail;
alloc_done:
	spin_unlock(&n->list_lock);

	if (unlikely(!ac->avail)) {
		int x;
force_grow:
		x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL);

		/* cache_grow can reenable interrupts, then ac could change. */
		ac = cpu_cache_get(cachep);
		node = numa_mem_id();

		/* no objects in sight? abort */
		if (!x && (ac->avail == 0 || force_refill))
			return NULL;

		if (!ac->avail)		/* objects refilled by interrupt? */
			goto retry;
	}
	ac->touched = 1;

	return ac_get_obj(cachep, ac, flags, force_refill);
}

static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
						gfp_t flags)
{
	might_sleep_if(flags & __GFP_WAIT);
#if DEBUG
	kmem_flagcheck(cachep, flags);
#endif
}

#if DEBUG
static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
				gfp_t flags, void *objp, unsigned long caller)
{
	struct page *page;

	if (!objp)
		return objp;
	if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
		if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep))
			kernel_map_pages(virt_to_page(objp),
					 cachep->size / PAGE_SIZE, 1);
		else
			check_poison_obj(cachep, objp);
#else
		check_poison_obj(cachep, objp);
#endif
		poison_obj(cachep, objp, POISON_INUSE);
	}
	if (cachep->flags & SLAB_STORE_USER)
		*dbg_userword(cachep, objp) = (void *)caller;

	if (cachep->flags & SLAB_RED_ZONE) {
		if (*dbg_redzone1(cachep, objp) != RED_INACTIVE ||
				*dbg_redzone2(cachep, objp) != RED_INACTIVE) {
			slab_error(cachep, "double free, or memory outside"
						" object was overwritten");
			printk(KERN_ERR
				"%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
				objp, *dbg_redzone1(cachep, objp),
				*dbg_redzone2(cachep, objp));
		}
		*dbg_redzone1(cachep, objp) = RED_ACTIVE;
		*dbg_redzone2(cachep, objp) = RED_ACTIVE;
	}

	page = virt_to_head_page(objp);
	set_obj_status(page, obj_to_index(cachep, page, objp), OBJECT_ACTIVE);
	objp += obj_offset(cachep);
	if (cachep->ctor && cachep->flags & SLAB_POISON)
		cachep->ctor(objp);
	if (ARCH_SLAB_MINALIGN &&
	    ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) {
		printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n",
		       objp, (int)ARCH_SLAB_MINALIGN);
	}
	return objp;
}
#else
#define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
#endif

static bool slab_should_failslab(struct kmem_cache *cachep, gfp_t flags)
{
	if (unlikely(cachep == kmem_cache))
		return false;

	return should_failslab(cachep->object_size, flags, cachep->flags);
}

static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
	void *objp;
	struct array_cache *ac;
	bool force_refill = false;

	check_irq_off();

	ac = cpu_cache_get(cachep);
	if (likely(ac->avail)) {
		ac->touched = 1;
		objp = ac_get_obj(cachep, ac, flags, false);

		/*
		 * Allow for the possibility all avail objects are not allowed
		 * by the current flags
		 */
		if (objp) {
			STATS_INC_ALLOCHIT(cachep);
			goto out;
		}
		force_refill = true;
	}

	STATS_INC_ALLOCMISS(cachep);
	objp = cache_alloc_refill(cachep, flags, force_refill);
	/*
	 * the 'ac' may be updated by cache_alloc_refill(),
	 * and kmemleak_erase() requires its correct value.
	 */
	ac = cpu_cache_get(cachep);

out:
	/*
	 * To avoid a false negative, if an object that is in one of the
	 * per-CPU caches is leaked, we need to make sure kmemleak doesn't
	 * treat the array pointers as a reference to the object.
	 */
	if (objp)
		kmemleak_erase(&ac->entry[ac->avail]);
	return objp;
}

#ifdef CONFIG_NUMA
/*
 * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set.
 *
 * If we are in_interrupt, then process context, including cpusets and
 * mempolicy, may not apply and should not be used for allocation policy.
 */
static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
{
	int nid_alloc, nid_here;

	if (in_interrupt() || (flags & __GFP_THISNODE))
		return NULL;
	nid_alloc = nid_here = numa_mem_id();
	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
		nid_alloc = cpuset_slab_spread_node();
	else if (current->mempolicy)
		nid_alloc = mempolicy_slab_node();
	if (nid_alloc != nid_here)
		return ____cache_alloc_node(cachep, flags, nid_alloc);
	return NULL;
}

/*
 * Fallback function if there was no memory available and no objects on a
 * certain node and fall back is permitted. First we scan all the
 * available node for available objects. If that fails then we
 * perform an allocation without specifying a node. This allows the page
 * allocator to do its reclaim / fallback magic. We then insert the
 * slab into the proper nodelist and then allocate from it.
 */
static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
{
	struct zonelist *zonelist;
	gfp_t local_flags;
	struct zoneref *z;
	struct zone *zone;
	enum zone_type high_zoneidx = gfp_zone(flags);
	void *obj = NULL;
	int nid;
	unsigned int cpuset_mems_cookie;

	if (flags & __GFP_THISNODE)
		return NULL;

	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);

retry_cpuset:
	cpuset_mems_cookie = read_mems_allowed_begin();
	zonelist = node_zonelist(mempolicy_slab_node(), flags);

retry:
	/*
	 * Look through allowed nodes for objects available
	 * from existing per node queues.
	 */
	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
		nid = zone_to_nid(zone);

		if (cpuset_zone_allowed_hardwall(zone, flags) &&
			get_node(cache, nid) &&
			get_node(cache, nid)->free_objects) {
				obj = ____cache_alloc_node(cache,
					flags | GFP_THISNODE, nid);
				if (obj)
					break;
		}
	}

	if (!obj) {
		/*
		 * This allocation will be performed within the constraints
		 * of the current cpuset / memory policy requirements.
		 * We may trigger various forms of reclaim on the allowed
		 * set and go into memory reserves if necessary.
		 */
		struct page *page;

		if (local_flags & __GFP_WAIT)
			local_irq_enable();
		kmem_flagcheck(cache, flags);
		page = kmem_getpages(cache, local_flags, numa_mem_id());
		if (local_flags & __GFP_WAIT)
			local_irq_disable();
		if (page) {
			/*
			 * Insert into the appropriate per node queues
			 */
			nid = page_to_nid(page);
			if (cache_grow(cache, flags, nid, page)) {
				obj = ____cache_alloc_node(cache,
					flags | GFP_THISNODE, nid);
				if (!obj)
					/*
					 * Another processor may allocate the
					 * objects in the slab since we are
					 * not holding any locks.
					 */
					goto retry;
			} else {
				/* cache_grow already freed obj */
				obj = NULL;
			}
		}
	}

	if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie)))
		goto retry_cpuset;
	return obj;
}

/*
 * A interface to enable slab creation on nodeid
 */
static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
				int nodeid)
{
	struct list_head *entry;
	struct page *page;
	struct kmem_cache_node *n;
	void *obj;
	int x;

	VM_BUG_ON(nodeid > num_online_nodes());
	n = get_node(cachep, nodeid);
	BUG_ON(!n);

retry:
	check_irq_off();
	spin_lock(&n->list_lock);
	entry = n->slabs_partial.next;
	if (entry == &n->slabs_partial) {
		n->free_touched = 1;
		entry = n->slabs_free.next;
		if (entry == &n->slabs_free)
			goto must_grow;
	}

	page = list_entry(entry, struct page, lru);
	check_spinlock_acquired_node(cachep, nodeid);

	STATS_INC_NODEALLOCS(cachep);
	STATS_INC_ACTIVE(cachep);
	STATS_SET_HIGH(cachep);

	BUG_ON(page->active == cachep->num);

	obj = slab_get_obj(cachep, page, nodeid);
	n->free_objects--;
	/* move slabp to correct slabp list: */
	list_del(&page->lru);

	if (page->active == cachep->num)
		list_add(&page->lru, &n->slabs_full);
	else
		list_add(&page->lru, &n->slabs_partial);

	spin_unlock(&n->list_lock);
	goto done;

must_grow:
	spin_unlock(&n->list_lock);
	x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL);
	if (x)
		goto retry;

	return fallback_alloc(cachep, flags);

done:
	return obj;
}

static __always_inline void *
slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
		   unsigned long caller)
{
	unsigned long save_flags;
	void *ptr;
	int slab_node = numa_mem_id();

	flags &= gfp_allowed_mask;

	lockdep_trace_alloc(flags);

	if (slab_should_failslab(cachep, flags))
		return NULL;

	cachep = memcg_kmem_get_cache(cachep, flags);

	cache_alloc_debugcheck_before(cachep, flags);
	local_irq_save(save_flags);

	if (nodeid == NUMA_NO_NODE)
		nodeid = slab_node;

	if (unlikely(!get_node(cachep, nodeid))) {
		/* Node not bootstrapped yet */
		ptr = fallback_alloc(cachep, flags);
		goto out;
	}

	if (nodeid == slab_node) {
		/*
		 * Use the locally cached objects if possible.
		 * However ____cache_alloc does not allow fallback
		 * to other nodes. It may fail while we still have
		 * objects on other nodes available.
		 */
		ptr = ____cache_alloc(cachep, flags);
		if (ptr)
			goto out;
	}
	/* ___cache_alloc_node can fall back to other nodes */
	ptr = ____cache_alloc_node(cachep, flags, nodeid);
  out:
	local_irq_restore(save_flags);
	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
	kmemleak_alloc_recursive(ptr, cachep->object_size, 1, cachep->flags,
				 flags);

	if (likely(ptr)) {
		kmemcheck_slab_alloc(cachep, flags, ptr, cachep->object_size);
		if (unlikely(flags & __GFP_ZERO))
			memset(ptr, 0, cachep->object_size);
	}

	return ptr;
}

static __always_inline void *
__do_cache_alloc(struct kmem_cache *cache, gfp_t flags)
{
	void *objp;

	if (current->mempolicy || cpuset_do_slab_mem_spread()) {
		objp = alternate_node_alloc(cache, flags);
		if (objp)
			goto out;
	}
	objp = ____cache_alloc(cache, flags);

	/*
	 * We may just have run out of memory on the local node.
	 * ____cache_alloc_node() knows how to locate memory on other nodes
	 */
	if (!objp)
		objp = ____cache_alloc_node(cache, flags, numa_mem_id());

  out:
	return objp;
}
#else

static __always_inline void *
__do_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
	return ____cache_alloc(cachep, flags);
}

#endif /* CONFIG_NUMA */

static __always_inline void *
slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
{
	unsigned long save_flags;
	void *objp;

	flags &= gfp_allowed_mask;

	lockdep_trace_alloc(flags);

	if (slab_should_failslab(cachep, flags))
		return NULL;

	cachep = memcg_kmem_get_cache(cachep, flags);

	cache_alloc_debugcheck_before(cachep, flags);
	local_irq_save(save_flags);
	objp = __do_cache_alloc(cachep, flags);
	local_irq_restore(save_flags);
	objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
	kmemleak_alloc_recursive(objp, cachep->object_size, 1, cachep->flags,
				 flags);
	prefetchw(objp);

	if (likely(objp)) {
		kmemcheck_slab_alloc(cachep, flags, objp, cachep->object_size);
		if (unlikely(flags & __GFP_ZERO))
			memset(objp, 0, cachep->object_size);
	}

	return objp;
}

/*
 * Caller needs to acquire correct kmem_cache_node's list_lock
 * @list: List of detached free slabs should be freed by caller
 */
static void free_block(struct kmem_cache *cachep, void **objpp,
			int nr_objects, int node, struct list_head *list)
{
	int i;
	struct kmem_cache_node *n = get_node(cachep, node);

	for (i = 0; i < nr_objects; i++) {
		void *objp;
		struct page *page;

		clear_obj_pfmemalloc(&objpp[i]);
		objp = objpp[i];

		page = virt_to_head_page(objp);
		list_del(&page->lru);
		check_spinlock_acquired_node(cachep, node);
		slab_put_obj(cachep, page, objp, node);
		STATS_DEC_ACTIVE(cachep);
		n->free_objects++;

		/* fixup slab chains */
		if (page->active == 0) {
			if (n->free_objects > n->free_limit) {
				n->free_objects -= cachep->num;
				list_add_tail(&page->lru, list);
			} else {
				list_add(&page->lru, &n->slabs_free);
			}
		} else {
			/* Unconditionally move a slab to the end of the
			 * partial list on free - maximum time for the
			 * other objects to be freed, too.
			 */
			list_add_tail(&page->lru, &n->slabs_partial);
		}
	}
}

static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
{
	int batchcount;
	struct kmem_cache_node *n;
	int node = numa_mem_id();
	LIST_HEAD(list);

	batchcount = ac->batchcount;
#if DEBUG
	BUG_ON(!batchcount || batchcount > ac->avail);
#endif
	check_irq_off();
	n = get_node(cachep, node);
	spin_lock(&n->list_lock);
	if (n->shared) {
		struct array_cache *shared_array = n->shared;
		int max = shared_array->limit - shared_array->avail;
		if (max) {
			if (batchcount > max)
				batchcount = max;
			memcpy(&(shared_array->entry[shared_array->avail]),
			       ac->entry, sizeof(void *) * batchcount);
			shared_array->avail += batchcount;
			goto free_done;
		}
	}

	free_block(cachep, ac->entry, batchcount, node, &list);
free_done:
#if STATS
	{
		int i = 0;
		struct list_head *p;

		p = n->slabs_free.next;
		while (p != &(n->slabs_free)) {
			struct page *page;

			page = list_entry(p, struct page, lru);
			BUG_ON(page->active);

			i++;
			p = p->next;
		}
		STATS_SET_FREEABLE(cachep, i);
	}
#endif
	spin_unlock(&n->list_lock);
	slabs_destroy(cachep, &list);
	ac->avail -= batchcount;
	memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail);
}

/*
 * Release an obj back to its cache. If the obj has a constructed state, it must
 * be in this state _before_ it is released.  Called with disabled ints.
 */
static inline void __cache_free(struct kmem_cache *cachep, void *objp,
				unsigned long caller)
{
	struct array_cache *ac = cpu_cache_get(cachep);

	check_irq_off();
	kmemleak_free_recursive(objp, cachep->flags);
	objp = cache_free_debugcheck(cachep, objp, caller);

	kmemcheck_slab_free(cachep, objp, cachep->object_size);

	/*
	 * Skip calling cache_free_alien() when the platform is not numa.
	 * This will avoid cache misses that happen while accessing slabp (which
	 * is per page memory  reference) to get nodeid. Instead use a global
	 * variable to skip the call, which is mostly likely to be present in
	 * the cache.
	 */
	if (nr_online_nodes > 1 && cache_free_alien(cachep, objp))
		return;

	if (ac->avail < ac->limit) {
		STATS_INC_FREEHIT(cachep);
	} else {
		STATS_INC_FREEMISS(cachep);
		cache_flusharray(cachep, ac);
	}

	ac_put_obj(cachep, ac, objp);
}

/**
 * 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(struct kmem_cache *cachep, gfp_t flags)
{
	void *ret = slab_alloc(cachep, flags, _RET_IP_);

	trace_kmem_cache_alloc(_RET_IP_, ret,
			       cachep->object_size, cachep->size, flags);

	return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc);

#ifdef CONFIG_TRACING
void *
kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size)
{
	void *ret;

	ret = slab_alloc(cachep, flags, _RET_IP_);

	trace_kmalloc(_RET_IP_, ret,
		      size, cachep->size, flags);
	return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_trace);
#endif

#ifdef CONFIG_NUMA
/**
 * kmem_cache_alloc_node - Allocate an object on the specified node
 * @cachep: The cache to allocate from.
 * @flags: See kmalloc().
 * @nodeid: node number of the target node.
 *
 * Identical to kmem_cache_alloc but it will allocate memory on the given
 * node, which can improve the performance for cpu bound structures.
 *
 * Fallback to other node is possible if __GFP_THISNODE is not set.
 */
void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
{
	void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);

	trace_kmem_cache_alloc_node(_RET_IP_, ret,
				    cachep->object_size, cachep->size,
				    flags, nodeid);

	return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node);

#ifdef CONFIG_TRACING
void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep,
				  gfp_t flags,
				  int nodeid,
				  size_t size)
{
	void *ret;

	ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);

	trace_kmalloc_node(_RET_IP_, ret,
			   size, cachep->size,
			   flags, nodeid);
	return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
#endif

static __always_inline void *
__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
{
	struct kmem_cache *cachep;

	cachep = kmalloc_slab(size, flags);
	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
		return cachep;
	return kmem_cache_alloc_node_trace(cachep, flags, node, size);
}

void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
	return __do_kmalloc_node(size, flags, node, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc_node);

void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
		int node, unsigned long caller)
{
	return __do_kmalloc_node(size, flags, node, caller);
}
EXPORT_SYMBOL(__kmalloc_node_track_caller);
#endif /* CONFIG_NUMA */

/**
 * __do_kmalloc - allocate memory
 * @size: how many bytes of memory are required.
 * @flags: the type of memory to allocate (see kmalloc).
 * @caller: function caller for debug tracking of the caller
 */
static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
					  unsigned long caller)
{
	struct kmem_cache *cachep;
	void *ret;

	cachep = kmalloc_slab(size, flags);
	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
		return cachep;
	ret = slab_alloc(cachep, flags, caller);

	trace_kmalloc(caller, ret,
		      size, cachep->size, flags);

	return ret;
}

void *__kmalloc(size_t size, gfp_t flags)
{
	return __do_kmalloc(size, flags, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc);

void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller)
{
	return __do_kmalloc(size, flags, caller);
}
EXPORT_SYMBOL(__kmalloc_track_caller);

/**
 * 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(struct kmem_cache *cachep, void *objp)
{
	unsigned long flags;
	cachep = cache_from_obj(cachep, objp);
	if (!cachep)
		return;

	local_irq_save(flags);
	debug_check_no_locks_freed(objp, cachep->object_size);
	if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
		debug_check_no_obj_freed(objp, cachep->object_size);
	__cache_free(cachep, objp, _RET_IP_);
	local_irq_restore(flags);

	trace_kmem_cache_free(_RET_IP_, objp);
}
EXPORT_SYMBOL(kmem_cache_free);

/**
 * kfree - free previously allocated memory
 * @objp: pointer returned by kmalloc.
 *
 * If @objp is NULL, no operation is performed.
 *
 * Don't free memory not originally allocated by kmalloc()
 * or you will run into trouble.
 */
void kfree(const void *objp)
{
	struct kmem_cache *c;
	unsigned long flags;

	trace_kfree(_RET_IP_, objp);

	if (unlikely(ZERO_OR_NULL_PTR(objp)))
		return;
	local_irq_save(flags);
	kfree_debugcheck(objp);
	c = virt_to_cache(objp);
	debug_check_no_locks_freed(objp, c->object_size);

	debug_check_no_obj_freed(objp, c->object_size);
	__cache_free(c, (void *)objp, _RET_IP_);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(kfree);

/*
 * This initializes kmem_cache_node or resizes various caches for all nodes.
 */
static int alloc_kmem_cache_node(struct kmem_cache *cachep, gfp_t gfp)
{
	int node;
	struct kmem_cache_node *n;
	struct array_cache *new_shared;
	struct alien_cache **new_alien = NULL;

	for_each_online_node(node) {

                if (use_alien_caches) {
                        new_alien = alloc_alien_cache(node, cachep->limit, gfp);
                        if (!new_alien)
                                goto fail;
                }

		new_shared = NULL;
		if (cachep->shared) {
			new_shared = alloc_arraycache(node,
				cachep->shared*cachep->batchcount,
					0xbaadf00d, gfp);
			if (!new_shared) {
				free_alien_cache(new_alien);
				goto fail;
			}
		}

		n = get_node(cachep, node);
		if (n) {
			struct array_cache *shared = n->shared;
			LIST_HEAD(list);

			spin_lock_irq(&n->list_lock);

			if (shared)
				free_block(cachep, shared->entry,
						shared->avail, node, &list);

			n->shared = new_shared;
			if (!n->alien) {
				n->alien = new_alien;
				new_alien = NULL;
			}
			n->free_limit = (1 + nr_cpus_node(node)) *
					cachep->batchcount + cachep->num;
			spin_unlock_irq(&n->list_lock);
			slabs_destroy(cachep, &list);
			kfree(shared);
			free_alien_cache(new_alien);
			continue;
		}
		n = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node);
		if (!n) {
			free_alien_cache(new_alien);
			kfree(new_shared);
			goto fail;
		}

		kmem_cache_node_init(n);
		n->next_reap = jiffies + REAPTIMEOUT_NODE +
				((unsigned long)cachep) % REAPTIMEOUT_NODE;
		n->shared = new_shared;
		n->alien = new_alien;
		n->free_limit = (1 + nr_cpus_node(node)) *
					cachep->batchcount + cachep->num;
		cachep->node[node] = n;
	}
	return 0;

fail:
	if (!cachep->list.next) {
		/* Cache is not active yet. Roll back what we did */
		node--;
		while (node >= 0) {
			n = get_node(cachep, node);
			if (n) {
				kfree(n->shared);
				free_alien_cache(n->alien);
				kfree(n);
				cachep->node[node] = NULL;
			}
			node--;
		}
	}
	return -ENOMEM;
}

/* Always called with the slab_mutex held */
static int __do_tune_cpucache(struct kmem_cache *cachep, int limit,
				int batchcount, int shared, gfp_t gfp)
{
	struct array_cache __percpu *cpu_cache, *prev;
	int cpu;

	cpu_cache = alloc_kmem_cache_cpus(cachep, limit, batchcount);
	if (!cpu_cache)
		return -ENOMEM;

	prev = cachep->cpu_cache;
	cachep->cpu_cache = cpu_cache;
	kick_all_cpus_sync();

	check_irq_on();
	cachep->batchcount = batchcount;
	cachep->limit = limit;
	cachep->shared = shared;

	if (!prev)
		goto alloc_node;

	for_each_online_cpu(cpu) {
		LIST_HEAD(list);
		int node;
		struct kmem_cache_node *n;
		struct array_cache *ac = per_cpu_ptr(prev, cpu);

		node = cpu_to_mem(cpu);
		n = get_node(cachep, node);
		spin_lock_irq(&n->list_lock);
		free_block(cachep, ac->entry, ac->avail, node, &list);
		spin_unlock_irq(&n->list_lock);
		slabs_destroy(cachep, &list);
	}
	free_percpu(prev);

alloc_node:
	return alloc_kmem_cache_node(cachep, gfp);
}

static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
				int batchcount, int shared, gfp_t gfp)
{
	int ret;
	struct kmem_cache *c = NULL;
	int i = 0;

	ret = __do_tune_cpucache(cachep, limit, batchcount, shared, gfp);

	if (slab_state < FULL)
		return ret;

	if ((ret < 0) || !is_root_cache(cachep))
		return ret;

	VM_BUG_ON(!mutex_is_locked(&slab_mutex));
	for_each_memcg_cache_index(i) {
		c = cache_from_memcg_idx(cachep, i);
		if (c)
			/* return value determined by the parent cache only */
			__do_tune_cpucache(c, limit, batchcount, shared, gfp);
	}

	return ret;
}

/* Called with slab_mutex held always */
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
{
	int err;
	int limit = 0;
	int shared = 0;
	int batchcount = 0;

	if (!is_root_cache(cachep)) {
		struct kmem_cache *root = memcg_root_cache(cachep);
		limit = root->limit;
		shared = root->shared;
		batchcount = root->batchcount;
	}

	if (limit && shared && batchcount)
		goto skip_setup;
	/*
	 * The head array serves three purposes:
	 * - create a LIFO ordering, i.e. return objects that are cache-warm
	 * - reduce the number of spinlock operations.
	 * - reduce the number of linked list operations on the slab and
	 *   bufctl chains: array operations are cheaper.
	 * The numbers are guessed, we should auto-tune as described by
	 * Bonwick.
	 */
	if (cachep->size > 131072)
		limit = 1;
	else if (cachep->size > PAGE_SIZE)
		limit = 8;
	else if (cachep->size > 1024)
		limit = 24;
	else if (cachep->size > 256)
		limit = 54;
	else
		limit = 120;

	/*
	 * CPU bound tasks (e.g. network routing) can exhibit cpu bound
	 * allocation behaviour: Most allocs on one cpu, most free operations
	 * on another cpu. For these cases, an efficient object passing between
	 * cpus is necessary. This is provided by a shared array. The array
	 * replaces Bonwick's magazine layer.
	 * On uniprocessor, it's functionally equivalent (but less efficient)
	 * to a larger limit. Thus disabled by default.
	 */
	shared = 0;
	if (cachep->size <= PAGE_SIZE && num_possible_cpus() > 1)
		shared = 8;

#if DEBUG
	/*
	 * With debugging enabled, large batchcount lead to excessively long
	 * periods with disabled local interrupts. Limit the batchcount
	 */
	if (limit > 32)
		limit = 32;
#endif
	batchcount = (limit + 1) / 2;
skip_setup:
	err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
	if (err)
		printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n",
		       cachep->name, -err);
	return err;
}

/*
 * Drain an array if it contains any elements taking the node lock only if
 * necessary. Note that the node listlock also protects the array_cache
 * if drain_array() is used on the shared array.
 */
static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n,
			 struct array_cache *ac, int force, int node)
{
	LIST_HEAD(list);
	int tofree;

	if (!ac || !ac->avail)
		return;
	if (ac->touched && !force) {
		ac->touched = 0;
	} else {
		spin_lock_irq(&n->list_lock);
		if (ac->avail) {
			tofree = force ? ac->avail : (ac->limit + 4) / 5;
			if (tofree > ac->avail)
				tofree = (ac->avail + 1) / 2;
			free_block(cachep, ac->entry, tofree, node, &list);
			ac->avail -= tofree;
			memmove(ac->entry, &(ac->entry[tofree]),
				sizeof(void *) * ac->avail);
		}
		spin_unlock_irq(&n->list_lock);
		slabs_destroy(cachep, &list);
	}
}

/**
 * cache_reap - Reclaim memory from caches.
 * @w: work descriptor
 *
 * Called from workqueue/eventd every few seconds.
 * Purpose:
 * - clear the per-cpu caches for this CPU.
 * - return freeable pages to the main free memory pool.
 *
 * If we cannot acquire the cache chain mutex then just give up - we'll try
 * again on the next iteration.
 */
static void cache_reap(struct work_struct *w)
{
	struct kmem_cache *searchp;
	struct kmem_cache_node *n;
	int node = numa_mem_id();
	struct delayed_work *work = to_delayed_work(w);

	if (!mutex_trylock(&slab_mutex))
		/* Give up. Setup the next iteration. */
		goto out;

	list_for_each_entry(searchp, &slab_caches, list) {
		check_irq_on();

		/*
		 * We only take the node lock if absolutely necessary and we
		 * have established with reasonable certainty that
		 * we can do some work if the lock was obtained.
		 */
		n = get_node(searchp, node);

		reap_alien(searchp, n);

		drain_array(searchp, n, cpu_cache_get(searchp), 0, node);

		/*
		 * These are racy checks but it does not matter
		 * if we skip one check or scan twice.
		 */
		if (time_after(n->next_reap, jiffies))
			goto next;

		n->next_reap = jiffies + REAPTIMEOUT_NODE;

		drain_array(searchp, n, n->shared, 0, node);

		if (n->free_touched)
			n->free_touched = 0;
		else {
			int freed;

			freed = drain_freelist(searchp, n, (n->free_limit +
				5 * searchp->num - 1) / (5 * searchp->num));
			STATS_ADD_REAPED(searchp, freed);
		}
next:
		cond_resched();
	}
	check_irq_on();
	mutex_unlock(&slab_mutex);
	next_reap_node();
out:
	/* Set up the next iteration */
	schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_AC));
}

#ifdef CONFIG_SLABINFO
void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
{
	struct page *page;
	unsigned long active_objs;
	unsigned long num_objs;
	unsigned long active_slabs = 0;
	unsigned long num_slabs, free_objects = 0, shared_avail = 0;
	const char *name;
	char *error = NULL;
	int node;
	struct kmem_cache_node *n;

	active_objs = 0;
	num_slabs = 0;
	for_each_kmem_cache_node(cachep, node, n) {

		check_irq_on();
		spin_lock_irq(&n->list_lock);

		list_for_each_entry(page, &n->slabs_full, lru) {
			if (page->active != cachep->num && !error)
				error = "slabs_full accounting error";
			active_objs += cachep->num;
			active_slabs++;
		}
		list_for_each_entry(page, &n->slabs_partial, lru) {
			if (page->active == cachep->num && !error)
				error = "slabs_partial accounting error";
			if (!page->active && !error)
				error = "slabs_partial accounting error";
			active_objs += page->active;
			active_slabs++;
		}
		list_for_each_entry(page, &n->slabs_free, lru) {
			if (page->active && !error)
				error = "slabs_free accounting error";
			num_slabs++;
		}
		free_objects += n->free_objects;
		if (n->shared)
			shared_avail += n->shared->avail;

		spin_unlock_irq(&n->list_lock);
	}
	num_slabs += active_slabs;
	num_objs = num_slabs * cachep->num;
	if (num_objs - active_objs != free_objects && !error)
		error = "free_objects accounting error";

	name = cachep->name;
	if (error)
		printk(KERN_ERR "slab: cache %s error: %s\n", name, error);

	sinfo->active_objs = active_objs;
	sinfo->num_objs = num_objs;
	sinfo->active_slabs = active_slabs;
	sinfo->num_slabs = num_slabs;
	sinfo->shared_avail = shared_avail;
	sinfo->limit = cachep->limit;
	sinfo->batchcount = cachep->batchcount;
	sinfo->shared = cachep->shared;
	sinfo->objects_per_slab = cachep->num;
	sinfo->cache_order = cachep->gfporder;
}

void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
{
#if STATS
	{			/* node stats */
		unsigned long high = cachep->high_mark;
		unsigned long allocs = cachep->num_allocations;
		unsigned long grown = cachep->grown;
		unsigned long reaped = cachep->reaped;
		unsigned long errors = cachep->errors;
		unsigned long max_freeable = cachep->max_freeable;
		unsigned long node_allocs = cachep->node_allocs;
		unsigned long node_frees = cachep->node_frees;
		unsigned long overflows = cachep->node_overflow;

		seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu "
			   "%4lu %4lu %4lu %4lu %4lu",
			   allocs, high, grown,
			   reaped, errors, max_freeable, node_allocs,
			   node_frees, overflows);
	}
	/* cpu stats */
	{
		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);

		seq_printf(m, " : cpustat %6lu %6lu %6lu %6lu",
			   allochit, allocmiss, freehit, freemiss);
	}
#endif
}

#define MAX_SLABINFO_WRITE 128
/**
 * slabinfo_write - Tuning for the slab allocator
 * @file: unused
 * @buffer: user buffer
 * @count: data length
 * @ppos: unused
 */
ssize_t slabinfo_write(struct file *file, const char __user *buffer,
		       size_t count, loff_t *ppos)
{
	char kbuf[MAX_SLABINFO_WRITE + 1], *tmp;
	int limit, batchcount, shared, res;
	struct kmem_cache *cachep;

	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++;
	if (sscanf(tmp, " %d %d %d", &limit, &batchcount, &shared) != 3)
		return -EINVAL;

	/* Find the cache in the chain of caches. */
	mutex_lock(&slab_mutex);
	res = -EINVAL;
	list_for_each_entry(cachep, &slab_caches, list) {
		if (!strcmp(cachep->name, kbuf)) {
			if (limit < 1 || batchcount < 1 ||
					batchcount > limit || shared < 0) {
				res = 0;
			} else {
				res = do_tune_cpucache(cachep, limit,
						       batchcount, shared,
						       GFP_KERNEL);
			}
			break;
		}
	}
	mutex_unlock(&slab_mutex);
	if (res >= 0)
		res = count;
	return res;
}

#ifdef CONFIG_DEBUG_SLAB_LEAK

static void *leaks_start(struct seq_file *m, loff_t *pos)
{
	mutex_lock(&slab_mutex);
	return seq_list_start(&slab_caches, *pos);
}

static inline int add_caller(unsigned long *n, unsigned long v)
{
	unsigned long *p;
	int l;
	if (!v)
		return 1;
	l = n[1];
	p = n + 2;
	while (l) {
		int i = l/2;
		unsigned long *q = p + 2 * i;
		if (*q == v) {
			q[1]++;
			return 1;
		}
		if (*q > v) {
			l = i;
		} else {
			p = q + 2;
			l -= i + 1;
		}
	}
	if (++n[1] == n[0])
		return 0;
	memmove(p + 2, p, n[1] * 2 * sizeof(unsigned long) - ((void *)p - (void *)n));
	p[0] = v;
	p[1] = 1;
	return 1;
}

static void handle_slab(unsigned long *n, struct kmem_cache *c,
						struct page *page)
{
	void *p;
	int i;

	if (n[0] == n[1])
		return;
	for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) {
		if (get_obj_status(page, i) != OBJECT_ACTIVE)
			continue;

		if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
			return;
	}
}

static void show_symbol(struct seq_file *m, unsigned long address)
{
#ifdef CONFIG_KALLSYMS
	unsigned long offset, size;
	char modname[MODULE_NAME_LEN], name[KSYM_NAME_LEN];

	if (lookup_symbol_attrs(address, &size, &offset, modname, name) == 0) {
		seq_printf(m, "%s+%#lx/%#lx", name, offset, size);
		if (modname[0])
			seq_printf(m, " [%s]", modname);
		return;
	}
#endif
	seq_printf(m, "%p", (void *)address);
}

static int leaks_show(struct seq_file *m, void *p)
{
	struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
	struct page *page;
	struct kmem_cache_node *n;
	const char *name;
	unsigned long *x = m->private;
	int node;
	int i;

	if (!(cachep->flags & SLAB_STORE_USER))
		return 0;
	if (!(cachep->flags & SLAB_RED_ZONE))
		return 0;

	/* OK, we can do it */

	x[1] = 0;

	for_each_kmem_cache_node(cachep, node, n) {

		check_irq_on();
		spin_lock_irq(&n->list_lock);

		list_for_each_entry(page, &n->slabs_full, lru)
			handle_slab(x, cachep, page);
		list_for_each_entry(page, &n->slabs_partial, lru)
			handle_slab(x, cachep, page);
		spin_unlock_irq(&n->list_lock);
	}
	name = cachep->name;
	if (x[0] == x[1]) {
		/* Increase the buffer size */
		mutex_unlock(&slab_mutex);
		m->private = kzalloc(x[0] * 4 * sizeof(unsigned long), GFP_KERNEL);
		if (!m->private) {
			/* Too bad, we are really out */
			m->private = x;
			mutex_lock(&slab_mutex);
			return -ENOMEM;
		}
		*(unsigned long *)m->private = x[0] * 2;
		kfree(x);
		mutex_lock(&slab_mutex);
		/* Now make sure this entry will be retried */
		m->count = m->size;
		return 0;
	}
	for (i = 0; i < x[1]; i++) {
		seq_printf(m, "%s: %lu ", name, x[2*i+3]);
		show_symbol(m, x[2*i+2]);
		seq_putc(m, '\n');
	}

	return 0;
}

static const struct seq_operations slabstats_op = {
	.start = leaks_start,
	.next = slab_next,
	.stop = slab_stop,
	.show = leaks_show,
};

static int slabstats_open(struct inode *inode, struct file *file)
{
	unsigned long *n;

	n = __seq_open_private(file, &slabstats_op, PAGE_SIZE);
	if (!n)
		return -ENOMEM;

	*n = PAGE_SIZE / (2 * sizeof(unsigned long));

	return 0;
}

static const struct file_operations proc_slabstats_operations = {
	.open		= slabstats_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};
#endif

static int __init slab_proc_init(void)
{
#ifdef CONFIG_DEBUG_SLAB_LEAK
	proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations);
#endif
	return 0;
}
module_init(slab_proc_init);
#endif

/**
 * ksize - get the actual amount of memory allocated for a given object
 * @objp: Pointer to the object
 *
 * kmalloc may internally round up allocations and return more memory
 * than requested. ksize() can be used to determine the actual amount of
 * memory allocated. The caller may use this additional memory, even though
 * a smaller amount of memory was initially specified with the kmalloc call.
 * The caller must guarantee that objp points to a valid object previously
 * allocated with either kmalloc() or kmem_cache_alloc(). The object
 * must not be freed during the duration of the call.
 */
size_t ksize(const void *objp)
{
	BUG_ON(!objp);
	if (unlikely(objp == ZERO_SIZE_PTR))
		return 0;

	return virt_to_cache(objp)->object_size;
}
EXPORT_SYMBOL(ksize);