aboutsummaryrefslogtreecommitdiffstats
path: root/lib/genalloc.c
Commit message (Expand)AuthorAge
* Slab allocators: Replace explicit zeroing with __GFP_ZEROChristoph Lameter2007-07-17
* [PATCH] genalloc warning fixesAndrew Morton2007-02-20
* [PATCH] make genpool allocator adhere to kernel-doc standardsDean Nelson2006-10-02
* [PATCH] LIB: add gen_pool_destroy()Steve Wise2006-10-02
* [PATCH] change gen_pool allocator to not touch managed memoryDean Nelson2006-06-23
* [PATCH] fix broken lib/genalloc.cChris Humbert2005-11-28
* [PATCH] ia64 uncached allocJes Sorensen2005-06-21
/a> 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841
/*
 *  Generic process-grouping system.
 *
 *  Based originally on the cpuset system, extracted by Paul Menage
 *  Copyright (C) 2006 Google, Inc
 *
 *  Notifications support
 *  Copyright (C) 2009 Nokia Corporation
 *  Author: Kirill A. Shutemov
 *
 *  Copyright notices from the original cpuset code:
 *  --------------------------------------------------
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
 *
 *  Portions derived from Patrick Mochel's sysfs code.
 *  sysfs is Copyright (c) 2001-3 Patrick Mochel
 *
 *  2003-10-10 Written by Simon Derr.
 *  2003-10-22 Updates by Stephen Hemminger.
 *  2004 May-July Rework by Paul Jackson.
 *  ---------------------------------------------------
 *
 *  This file is subject to the terms and conditions of the GNU General Public
 *  License.  See the file COPYING in the main directory of the Linux
 *  distribution for more details.
 */

#include <linux/cgroup.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/backing-dev.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/magic.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
#include <linux/module.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hash.h>
#include <linux/namei.h>
#include <linux/smp_lock.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <linux/eventfd.h>
#include <linux/poll.h>

#include <asm/atomic.h>

static DEFINE_MUTEX(cgroup_mutex);

/*
 * Generate an array of cgroup subsystem pointers. At boot time, this is
 * populated up to CGROUP_BUILTIN_SUBSYS_COUNT, and modular subsystems are
 * registered after that. The mutable section of this array is protected by
 * cgroup_mutex.
 */
#define SUBSYS(_x) &_x ## _subsys,
static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = {
#include <linux/cgroup_subsys.h>
};

#define MAX_CGROUP_ROOT_NAMELEN 64

/*
 * A cgroupfs_root represents the root of a cgroup hierarchy,
 * and may be associated with a superblock to form an active
 * hierarchy
 */
struct cgroupfs_root {
	struct super_block *sb;

	/*
	 * The bitmask of subsystems intended to be attached to this
	 * hierarchy
	 */
	unsigned long subsys_bits;

	/* Unique id for this hierarchy. */
	int hierarchy_id;

	/* The bitmask of subsystems currently attached to this hierarchy */
	unsigned long actual_subsys_bits;

	/* A list running through the attached subsystems */
	struct list_head subsys_list;

	/* The root cgroup for this hierarchy */
	struct cgroup top_cgroup;

	/* Tracks how many cgroups are currently defined in hierarchy.*/
	int number_of_cgroups;

	/* A list running through the active hierarchies */
	struct list_head root_list;

	/* Hierarchy-specific flags */
	unsigned long flags;

	/* The path to use for release notifications. */
	char release_agent_path[PATH_MAX];

	/* The name for this hierarchy - may be empty */
	char name[MAX_CGROUP_ROOT_NAMELEN];
};

/*
 * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
 * subsystems that are otherwise unattached - it never has more than a
 * single cgroup, and all tasks are part of that cgroup.
 */
static struct cgroupfs_root rootnode;

/*
 * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
 * cgroup_subsys->use_id != 0.
 */
#define CSS_ID_MAX	(65535)
struct css_id {
	/*
	 * The css to which this ID points. This pointer is set to valid value
	 * after cgroup is populated. If cgroup is removed, this will be NULL.
	 * This pointer is expected to be RCU-safe because destroy()
	 * is called after synchronize_rcu(). But for safe use, css_is_removed()
	 * css_tryget() should be used for avoiding race.
	 */
	struct cgroup_subsys_state *css;
	/*
	 * ID of this css.
	 */
	unsigned short id;
	/*
	 * Depth in hierarchy which this ID belongs to.
	 */
	unsigned short depth;
	/*
	 * ID is freed by RCU. (and lookup routine is RCU safe.)
	 */
	struct rcu_head rcu_head;
	/*
	 * Hierarchy of CSS ID belongs to.
	 */
	unsigned short stack[0]; /* Array of Length (depth+1) */
};

/*
 * cgroup_event represents events which userspace want to recieve.
 */
struct cgroup_event {
	/*
	 * Cgroup which the event belongs to.
	 */
	struct cgroup *cgrp;
	/*
	 * Control file which the event associated.
	 */
	struct cftype *cft;
	/*
	 * eventfd to signal userspace about the event.
	 */
	struct eventfd_ctx *eventfd;
	/*
	 * Each of these stored in a list by the cgroup.
	 */
	struct list_head list;
	/*
	 * All fields below needed to unregister event when
	 * userspace closes eventfd.
	 */
	poll_table pt;
	wait_queue_head_t *wqh;
	wait_queue_t wait;
	struct work_struct remove;
};

/* The list of hierarchy roots */

static LIST_HEAD(roots);
static int root_count;

static DEFINE_IDA(hierarchy_ida);
static int next_hierarchy_id;
static DEFINE_SPINLOCK(hierarchy_id_lock);

/* dummytop is a shorthand for the dummy hierarchy's top cgroup */
#define dummytop (&rootnode.top_cgroup)

/* This flag indicates whether tasks in the fork and exit paths should
 * check for fork/exit handlers to call. This avoids us having to do
 * extra work in the fork/exit path if none of the subsystems need to
 * be called.
 */
static int need_forkexit_callback __read_mostly;

#ifdef CONFIG_PROVE_LOCKING
int cgroup_lock_is_held(void)
{
	return lockdep_is_held(&cgroup_mutex);
}
#else /* #ifdef CONFIG_PROVE_LOCKING */
int cgroup_lock_is_held(void)
{
	return mutex_is_locked(&cgroup_mutex);
}
#endif /* #else #ifdef CONFIG_PROVE_LOCKING */

EXPORT_SYMBOL_GPL(cgroup_lock_is_held);

/* convenient tests for these bits */
inline int cgroup_is_removed(const struct cgroup *cgrp)
{
	return test_bit(CGRP_REMOVED, &cgrp->flags);
}

/* bits in struct cgroupfs_root flags field */
enum {
	ROOT_NOPREFIX, /* mounted subsystems have no named prefix */
};

static int cgroup_is_releasable(const struct cgroup *cgrp)
{
	const int bits =
		(1 << CGRP_RELEASABLE) |
		(1 << CGRP_NOTIFY_ON_RELEASE);
	return (cgrp->flags & bits) == bits;
}

static int notify_on_release(const struct cgroup *cgrp)
{
	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}

/*
 * for_each_subsys() allows you to iterate on each subsystem attached to
 * an active hierarchy
 */
#define for_each_subsys(_root, _ss) \
list_for_each_entry(_ss, &_root->subsys_list, sibling)

/* for_each_active_root() allows you to iterate across the active hierarchies */
#define for_each_active_root(_root) \
list_for_each_entry(_root, &roots, root_list)

/* the list of cgroups eligible for automatic release. Protected by
 * release_list_lock */
static LIST_HEAD(release_list);
static DEFINE_SPINLOCK(release_list_lock);
static void cgroup_release_agent(struct work_struct *work);
static DECLARE_WORK(release_agent_work, cgroup_release_agent);
static void check_for_release(struct cgroup *cgrp);

/* Link structure for associating css_set objects with cgroups */
struct cg_cgroup_link {
	/*
	 * List running through cg_cgroup_links associated with a
	 * cgroup, anchored on cgroup->css_sets
	 */
	struct list_head cgrp_link_list;
	struct cgroup *cgrp;
	/*
	 * List running through cg_cgroup_links pointing at a
	 * single css_set object, anchored on css_set->cg_links
	 */
	struct list_head cg_link_list;
	struct css_set *cg;
};

/* The default css_set - used by init and its children prior to any
 * hierarchies being mounted. It contains a pointer to the root state
 * for each subsystem. Also used to anchor the list of css_sets. Not
 * reference-counted, to improve performance when child cgroups
 * haven't been created.
 */

static struct css_set init_css_set;
static struct cg_cgroup_link init_css_set_link;

static int cgroup_init_idr(struct cgroup_subsys *ss,
			   struct cgroup_subsys_state *css);

/* css_set_lock protects the list of css_set objects, and the
 * chain of tasks off each css_set.  Nests outside task->alloc_lock
 * due to cgroup_iter_start() */
static DEFINE_RWLOCK(css_set_lock);
static int css_set_count;

/*
 * hash table for cgroup groups. This improves the performance to find
 * an existing css_set. This hash doesn't (currently) take into
 * account cgroups in empty hierarchies.
 */
#define CSS_SET_HASH_BITS	7
#define CSS_SET_TABLE_SIZE	(1 << CSS_SET_HASH_BITS)
static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];

static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
{
	int i;
	int index;
	unsigned long tmp = 0UL;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
		tmp += (unsigned long)css[i];
	tmp = (tmp >> 16) ^ tmp;

	index = hash_long(tmp, CSS_SET_HASH_BITS);

	return &css_set_table[index];
}

static void free_css_set_rcu(struct rcu_head *obj)
{
	struct css_set *cg = container_of(obj, struct css_set, rcu_head);
	kfree(cg);
}

/* We don't maintain the lists running through each css_set to its
 * task until after the first call to cgroup_iter_start(). This
 * reduces the fork()/exit() overhead for people who have cgroups
 * compiled into their kernel but not actually in use */
static int use_task_css_set_links __read_mostly;

static void __put_css_set(struct css_set *cg, int taskexit)
{
	struct cg_cgroup_link *link;
	struct cg_cgroup_link *saved_link;
	/*
	 * Ensure that the refcount doesn't hit zero while any readers
	 * can see it. Similar to atomic_dec_and_lock(), but for an
	 * rwlock
	 */
	if (atomic_add_unless(&cg->refcount, -1, 1))
		return;
	write_lock(&css_set_lock);
	if (!atomic_dec_and_test(&cg->refcount)) {
		write_unlock(&css_set_lock);
		return;
	}

	/* This css_set is dead. unlink it and release cgroup refcounts */
	hlist_del(&cg->hlist);
	css_set_count--;

	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
				 cg_link_list) {
		struct cgroup *cgrp = link->cgrp;
		list_del(&link->cg_link_list);
		list_del(&link->cgrp_link_list);
		if (atomic_dec_and_test(&cgrp->count) &&
		    notify_on_release(cgrp)) {
			if (taskexit)
				set_bit(CGRP_RELEASABLE, &cgrp->flags);
			check_for_release(cgrp);
		}

		kfree(link);
	}

	write_unlock(&css_set_lock);
	call_rcu(&cg->rcu_head, free_css_set_rcu);
}

/*
 * refcounted get/put for css_set objects
 */
static inline void get_css_set(struct css_set *cg)
{
	atomic_inc(&cg->refcount);
}

static inline void put_css_set(struct css_set *cg)
{
	__put_css_set(cg, 0);
}

static inline void put_css_set_taskexit(struct css_set *cg)
{
	__put_css_set(cg, 1);
}

/*
 * compare_css_sets - helper function for find_existing_css_set().
 * @cg: candidate css_set being tested
 * @old_cg: existing css_set for a task
 * @new_cgrp: cgroup that's being entered by the task
 * @template: desired set of css pointers in css_set (pre-calculated)
 *
 * Returns true if "cg" matches "old_cg" except for the hierarchy
 * which "new_cgrp" belongs to, for which it should match "new_cgrp".
 */
static bool compare_css_sets(struct css_set *cg,
			     struct css_set *old_cg,
			     struct cgroup *new_cgrp,
			     struct cgroup_subsys_state *template[])
{
	struct list_head *l1, *l2;

	if (memcmp(template, cg->subsys, sizeof(cg->subsys))) {
		/* Not all subsystems matched */
		return false;
	}

	/*
	 * Compare cgroup pointers in order to distinguish between
	 * different cgroups in heirarchies with no subsystems. We
	 * could get by with just this check alone (and skip the
	 * memcmp above) but on most setups the memcmp check will
	 * avoid the need for this more expensive check on almost all
	 * candidates.
	 */

	l1 = &cg->cg_links;
	l2 = &old_cg->cg_links;
	while (1) {
		struct cg_cgroup_link *cgl1, *cgl2;
		struct cgroup *cg1, *cg2;

		l1 = l1->next;
		l2 = l2->next;
		/* See if we reached the end - both lists are equal length. */
		if (l1 == &cg->cg_links) {
			BUG_ON(l2 != &old_cg->cg_links);
			break;
		} else {
			BUG_ON(l2 == &old_cg->cg_links);
		}
		/* Locate the cgroups associated with these links. */
		cgl1 = list_entry(l1, struct cg_cgroup_link, cg_link_list);
		cgl2 = list_entry(l2, struct cg_cgroup_link, cg_link_list);
		cg1 = cgl1->cgrp;
		cg2 = cgl2->cgrp;
		/* Hierarchies should be linked in the same order. */
		BUG_ON(cg1->root != cg2->root);

		/*
		 * If this hierarchy is the hierarchy of the cgroup
		 * that's changing, then we need to check that this
		 * css_set points to the new cgroup; if it's any other
		 * hierarchy, then this css_set should point to the
		 * same cgroup as the old css_set.
		 */
		if (cg1->root == new_cgrp->root) {
			if (cg1 != new_cgrp)
				return false;
		} else {
			if (cg1 != cg2)
				return false;
		}
	}
	return true;
}

/*
 * find_existing_css_set() is a helper for
 * find_css_set(), and checks to see whether an existing
 * css_set is suitable.
 *
 * oldcg: the cgroup group that we're using before the cgroup
 * transition
 *
 * cgrp: the cgroup that we're moving into
 *
 * template: location in which to build the desired set of subsystem
 * state objects for the new cgroup group
 */
static struct css_set *find_existing_css_set(
	struct css_set *oldcg,
	struct cgroup *cgrp,
	struct cgroup_subsys_state *template[])
{
	int i;
	struct cgroupfs_root *root = cgrp->root;
	struct hlist_head *hhead;
	struct hlist_node *node;
	struct css_set *cg;

	/*
	 * Build the set of subsystem state objects that we want to see in the
	 * new css_set. while subsystems can change globally, the entries here
	 * won't change, so no need for locking.
	 */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		if (root->subsys_bits & (1UL << i)) {
			/* Subsystem is in this hierarchy. So we want
			 * the subsystem state from the new
			 * cgroup */
			template[i] = cgrp->subsys[i];
		} else {
			/* Subsystem is not in this hierarchy, so we
			 * don't want to change the subsystem state */
			template[i] = oldcg->subsys[i];
		}
	}

	hhead = css_set_hash(template);
	hlist_for_each_entry(cg, node, hhead, hlist) {
		if (!compare_css_sets(cg, oldcg, cgrp, template))
			continue;

		/* This css_set matches what we need */
		return cg;
	}

	/* No existing cgroup group matched */
	return NULL;
}

static void free_cg_links(struct list_head *tmp)
{
	struct cg_cgroup_link *link;
	struct cg_cgroup_link *saved_link;

	list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) {
		list_del(&link->cgrp_link_list);
		kfree(link);
	}
}

/*
 * allocate_cg_links() allocates "count" cg_cgroup_link structures
 * and chains them on tmp through their cgrp_link_list fields. Returns 0 on
 * success or a negative error
 */
static int allocate_cg_links(int count, struct list_head *tmp)
{
	struct cg_cgroup_link *link;
	int i;
	INIT_LIST_HEAD(tmp);
	for (i = 0; i < count; i++) {
		link = kmalloc(sizeof(*link), GFP_KERNEL);
		if (!link) {
			free_cg_links(tmp);
			return -ENOMEM;
		}
		list_add(&link->cgrp_link_list, tmp);
	}
	return 0;
}

/**
 * link_css_set - a helper function to link a css_set to a cgroup
 * @tmp_cg_links: cg_cgroup_link objects allocated by allocate_cg_links()
 * @cg: the css_set to be linked
 * @cgrp: the destination cgroup
 */
static void link_css_set(struct list_head *tmp_cg_links,
			 struct css_set *cg, struct cgroup *cgrp)
{
	struct cg_cgroup_link *link;

	BUG_ON(list_empty(tmp_cg_links));
	link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
				cgrp_link_list);
	link->cg = cg;
	link->cgrp = cgrp;
	atomic_inc(&cgrp->count);
	list_move(&link->cgrp_link_list, &cgrp->css_sets);
	/*
	 * Always add links to the tail of the list so that the list
	 * is sorted by order of hierarchy creation
	 */
	list_add_tail(&link->cg_link_list, &cg->cg_links);
}

/*
 * find_css_set() takes an existing cgroup group and a
 * cgroup object, and returns a css_set object that's
 * equivalent to the old group, but with the given cgroup
 * substituted into the appropriate hierarchy. Must be called with
 * cgroup_mutex held
 */
static struct css_set *find_css_set(
	struct css_set *oldcg, struct cgroup *cgrp)
{
	struct css_set *res;
	struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];

	struct list_head tmp_cg_links;

	struct hlist_head *hhead;
	struct cg_cgroup_link *link;

	/* First see if we already have a cgroup group that matches
	 * the desired set */
	read_lock(&css_set_lock);
	res = find_existing_css_set(oldcg, cgrp, template);
	if (res)
		get_css_set(res);
	read_unlock(&css_set_lock);

	if (res)
		return res;

	res = kmalloc(sizeof(*res), GFP_KERNEL);
	if (!res)
		return NULL;

	/* Allocate all the cg_cgroup_link objects that we'll need */
	if (allocate_cg_links(root_count, &tmp_cg_links) < 0) {
		kfree(res);
		return NULL;
	}

	atomic_set(&res->refcount, 1);
	INIT_LIST_HEAD(&res->cg_links);
	INIT_LIST_HEAD(&res->tasks);
	INIT_HLIST_NODE(&res->hlist);

	/* Copy the set of subsystem state objects generated in
	 * find_existing_css_set() */
	memcpy(res->subsys, template, sizeof(res->subsys));

	write_lock(&css_set_lock);
	/* Add reference counts and links from the new css_set. */
	list_for_each_entry(link, &oldcg->cg_links, cg_link_list) {
		struct cgroup *c = link->cgrp;
		if (c->root == cgrp->root)
			c = cgrp;
		link_css_set(&tmp_cg_links, res, c);
	}

	BUG_ON(!list_empty(&tmp_cg_links));

	css_set_count++;

	/* Add this cgroup group to the hash table */
	hhead = css_set_hash(res->subsys);
	hlist_add_head(&res->hlist, hhead);

	write_unlock(&css_set_lock);

	return res;
}

/*
 * Return the cgroup for "task" from the given hierarchy. Must be
 * called with cgroup_mutex held.
 */
static struct cgroup *task_cgroup_from_root(struct task_struct *task,
					    struct cgroupfs_root *root)
{
	struct css_set *css;
	struct cgroup *res = NULL;

	BUG_ON(!mutex_is_locked(&cgroup_mutex));
	read_lock(&css_set_lock);
	/*
	 * No need to lock the task - since we hold cgroup_mutex the
	 * task can't change groups, so the only thing that can happen
	 * is that it exits and its css is set back to init_css_set.
	 */
	css = task->cgroups;
	if (css == &init_css_set) {
		res = &root->top_cgroup;
	} else {
		struct cg_cgroup_link *link;
		list_for_each_entry(link, &css->cg_links, cg_link_list) {
			struct cgroup *c = link->cgrp;
			if (c->root == root) {
				res = c;
				break;
			}
		}
	}
	read_unlock(&css_set_lock);
	BUG_ON(!res);
	return res;
}

/*
 * There is one global cgroup mutex. We also require taking
 * task_lock() when dereferencing a task's cgroup subsys pointers.
 * See "The task_lock() exception", at the end of this comment.
 *
 * A task must hold cgroup_mutex to modify cgroups.
 *
 * Any task can increment and decrement the count field without lock.
 * So in general, code holding cgroup_mutex can't rely on the count
 * field not changing.  However, if the count goes to zero, then only
 * cgroup_attach_task() can increment it again.  Because a count of zero
 * means that no tasks are currently attached, therefore there is no
 * way a task attached to that cgroup can fork (the other way to
 * increment the count).  So code holding cgroup_mutex can safely
 * assume that if the count is zero, it will stay zero. Similarly, if
 * a task holds cgroup_mutex on a cgroup with zero count, it
 * knows that the cgroup won't be removed, as cgroup_rmdir()
 * needs that mutex.
 *
 * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
 * (usually) take cgroup_mutex.  These are the two most performance
 * critical pieces of code here.  The exception occurs on cgroup_exit(),
 * when a task in a notify_on_release cgroup exits.  Then cgroup_mutex
 * is taken, and if the cgroup count is zero, a usermode call made
 * to the release agent with the name of the cgroup (path relative to
 * the root of cgroup file system) as the argument.
 *
 * A cgroup can only be deleted if both its 'count' of using tasks
 * is zero, and its list of 'children' cgroups is empty.  Since all
 * tasks in the system use _some_ cgroup, and since there is always at
 * least one task in the system (init, pid == 1), therefore, top_cgroup
 * always has either children cgroups and/or using tasks.  So we don't
 * need a special hack to ensure that top_cgroup cannot be deleted.
 *
 *	The task_lock() exception
 *
 * The need for this exception arises from the action of
 * cgroup_attach_task(), which overwrites one tasks cgroup pointer with
 * another.  It does so using cgroup_mutex, however there are
 * several performance critical places that need to reference
 * task->cgroup without the expense of grabbing a system global
 * mutex.  Therefore except as noted below, when dereferencing or, as
 * in cgroup_attach_task(), modifying a task'ss cgroup pointer we use
 * task_lock(), which acts on a spinlock (task->alloc_lock) already in
 * the task_struct routinely used for such matters.
 *
 * P.S.  One more locking exception.  RCU is used to guard the
 * update of a tasks cgroup pointer by cgroup_attach_task()
 */

/**
 * cgroup_lock - lock out any changes to cgroup structures
 *
 */
void cgroup_lock(void)
{
	mutex_lock(&cgroup_mutex);
}
EXPORT_SYMBOL_GPL(cgroup_lock);

/**
 * cgroup_unlock - release lock on cgroup changes
 *
 * Undo the lock taken in a previous cgroup_lock() call.
 */
void cgroup_unlock(void)
{
	mutex_unlock(&cgroup_mutex);
}
EXPORT_SYMBOL_GPL(cgroup_unlock);

/*
 * A couple of forward declarations required, due to cyclic reference loop:
 * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
 * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
 * -> cgroup_mkdir.
 */

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static const struct inode_operations cgroup_dir_inode_operations;
static const struct file_operations proc_cgroupstats_operations;

static struct backing_dev_info cgroup_backing_dev_info = {
	.name		= "cgroup",
	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
};

static int alloc_css_id(struct cgroup_subsys *ss,
			struct cgroup *parent, struct cgroup *child);

static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
{
	struct inode *inode = new_inode(sb);

	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current_fsuid();
		inode->i_gid = current_fsgid();
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
	}
	return inode;
}

/*
 * Call subsys's pre_destroy handler.
 * This is called before css refcnt check.
 */
static int cgroup_call_pre_destroy(struct cgroup *cgrp)
{
	struct cgroup_subsys *ss;
	int ret = 0;

	for_each_subsys(cgrp->root, ss)
		if (ss->pre_destroy) {
			ret = ss->pre_destroy(ss, cgrp);
			if (ret)
				break;
		}

	return ret;
}

static void free_cgroup_rcu(struct rcu_head *obj)
{
	struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head);

	kfree(cgrp);
}

static void cgroup_diput(struct dentry *dentry, struct inode *inode)
{
	/* is dentry a directory ? if so, kfree() associated cgroup */
	if (S_ISDIR(inode->i_mode)) {
		struct cgroup *cgrp = dentry->d_fsdata;
		struct cgroup_subsys *ss;
		BUG_ON(!(cgroup_is_removed(cgrp)));
		/* It's possible for external users to be holding css
		 * reference counts on a cgroup; css_put() needs to
		 * be able to access the cgroup after decrementing
		 * the reference count in order to know if it needs to
		 * queue the cgroup to be handled by the release
		 * agent */
		synchronize_rcu();

		mutex_lock(&cgroup_mutex);
		/*
		 * Release the subsystem state objects.
		 */
		for_each_subsys(cgrp->root, ss)
			ss->destroy(ss, cgrp);

		cgrp->root->number_of_cgroups--;
		mutex_unlock(&cgroup_mutex);

		/*
		 * Drop the active superblock reference that we took when we
		 * created the cgroup
		 */
		deactivate_super(cgrp->root->sb);

		/*
		 * if we're getting rid of the cgroup, refcount should ensure
		 * that there are no pidlists left.
		 */
		BUG_ON(!list_empty(&cgrp->pidlists));

		call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
	}
	iput(inode);
}

static void remove_dir(struct dentry *d)
{
	struct dentry *parent = dget(d->d_parent);

	d_delete(d);
	simple_rmdir(parent->d_inode, d);
	dput(parent);
}

static void cgroup_clear_directory(struct dentry *dentry)
{
	struct list_head *node;

	BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
	spin_lock(&dcache_lock);
	node = dentry->d_subdirs.next;
	while (node != &dentry->d_subdirs) {
		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
		list_del_init(node);
		if (d->d_inode) {
			/* This should never be called on a cgroup
			 * directory with child cgroups */
			BUG_ON(d->d_inode->i_mode & S_IFDIR);
			d = dget_locked(d);
			spin_unlock(&dcache_lock);
			d_delete(d);
			simple_unlink(dentry->d_inode, d);
			dput(d);
			spin_lock(&dcache_lock);
		}
		node = dentry->d_subdirs.next;
	}
	spin_unlock(&dcache_lock);
}

/*
 * NOTE : the dentry must have been dget()'ed
 */
static void cgroup_d_remove_dir(struct dentry *dentry)
{
	cgroup_clear_directory(dentry);

	spin_lock(&dcache_lock);
	list_del_init(&dentry->d_u.d_child);
	spin_unlock(&dcache_lock);
	remove_dir(dentry);
}

/*
 * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
 * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
 * reference to css->refcnt. In general, this refcnt is expected to goes down
 * to zero, soon.
 *
 * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
 */
DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);

static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
{
	if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
		wake_up_all(&cgroup_rmdir_waitq);
}

void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
{
	css_get(css);
}

void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
{
	cgroup_wakeup_rmdir_waiter(css->cgroup);
	css_put(css);
}

/*
 * Call with cgroup_mutex held. Drops reference counts on modules, including
 * any duplicate ones that parse_cgroupfs_options took. If this function
 * returns an error, no reference counts are touched.
 */
static int rebind_subsystems(struct cgroupfs_root *root,
			      unsigned long final_bits)
{
	unsigned long added_bits, removed_bits;
	struct cgroup *cgrp = &root->top_cgroup;
	int i;

	BUG_ON(!mutex_is_locked(&cgroup_mutex));

	removed_bits = root->actual_subsys_bits & ~final_bits;
	added_bits = final_bits & ~root->actual_subsys_bits;
	/* Check that any added subsystems are currently free */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		unsigned long bit = 1UL << i;
		struct cgroup_subsys *ss = subsys[i];
		if (!(bit & added_bits))
			continue;
		/*
		 * Nobody should tell us to do a subsys that doesn't exist:
		 * parse_cgroupfs_options should catch that case and refcounts
		 * ensure that subsystems won't disappear once selected.
		 */
		BUG_ON(ss == NULL);
		if (ss->root != &rootnode) {
			/* Subsystem isn't free */
			return -EBUSY;
		}
	}

	/* Currently we don't handle adding/removing subsystems when
	 * any child cgroups exist. This is theoretically supportable
	 * but involves complex error handling, so it's being left until
	 * later */
	if (root->number_of_cgroups > 1)
		return -EBUSY;

	/* Process each subsystem */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		unsigned long bit = 1UL << i;
		if (bit & added_bits) {
			/* We're binding this subsystem to this hierarchy */
			BUG_ON(ss == NULL);
			BUG_ON(cgrp->subsys[i]);
			BUG_ON(!dummytop->subsys[i]);
			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
			mutex_lock(&ss->hierarchy_mutex);
			cgrp->subsys[i] = dummytop->subsys[i];
			cgrp->subsys[i]->cgroup = cgrp;
			list_move(&ss->sibling, &root->subsys_list);
			ss->root = root;
			if (ss->bind)
				ss->bind(ss, cgrp);
			mutex_unlock(&ss->hierarchy_mutex);
			/* refcount was already taken, and we're keeping it */
		} else if (bit & removed_bits) {
			/* We're removing this subsystem */
			BUG_ON(ss == NULL);
			BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
			BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
			mutex_lock(&ss->hierarchy_mutex);
			if (ss->bind)
				ss->bind(ss, dummytop);
			dummytop->subsys[i]->cgroup = dummytop;
			cgrp->subsys[i] = NULL;
			subsys[i]->root = &rootnode;
			list_move(&ss->sibling, &rootnode.subsys_list);
			mutex_unlock(&ss->hierarchy_mutex);
			/* subsystem is now free - drop reference on module */
			module_put(ss->module);
		} else if (bit & final_bits) {
			/* Subsystem state should already exist */
			BUG_ON(ss == NULL);
			BUG_ON(!cgrp->subsys[i]);
			/*
			 * a refcount was taken, but we already had one, so
			 * drop the extra reference.
			 */
			module_put(ss->module);
#ifdef CONFIG_MODULE_UNLOAD
			BUG_ON(ss->module && !module_refcount(ss->module));
#endif
		} else {
			/* Subsystem state shouldn't exist */
			BUG_ON(cgrp->subsys[i]);
		}
	}
	root->subsys_bits = root->actual_subsys_bits = final_bits;
	synchronize_rcu();

	return 0;
}

static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
	struct cgroupfs_root *root = vfs->mnt_sb->s_fs_info;
	struct cgroup_subsys *ss;

	mutex_lock(&cgroup_mutex);
	for_each_subsys(root, ss)
		seq_printf(seq, ",%s", ss->name);
	if (test_bit(ROOT_NOPREFIX, &root->flags))
		seq_puts(seq, ",noprefix");
	if (strlen(root->release_agent_path))
		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
	if (strlen(root->name))
		seq_printf(seq, ",name=%s", root->name);
	mutex_unlock(&cgroup_mutex);
	return 0;
}

struct cgroup_sb_opts {
	unsigned long subsys_bits;
	unsigned long flags;
	char *release_agent;
	char *name;
	/* User explicitly requested empty subsystem */
	bool none;

	struct cgroupfs_root *new_root;

};

/*
 * Convert a hierarchy specifier into a bitmask of subsystems and flags. Call
 * with cgroup_mutex held to protect the subsys[] array. This function takes
 * refcounts on subsystems to be used, unless it returns error, in which case
 * no refcounts are taken.
 */
static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
{
	char *token, *o = data ?: "all";
	unsigned long mask = (unsigned long)-1;
	int i;
	bool module_pin_failed = false;

	BUG_ON(!mutex_is_locked(&cgroup_mutex));

#ifdef CONFIG_CPUSETS
	mask = ~(1UL << cpuset_subsys_id);
#endif

	memset(opts, 0, sizeof(*opts));

	while ((token = strsep(&o, ",")) != NULL) {
		if (!*token)
			return -EINVAL;
		if (!strcmp(token, "all")) {
			/* Add all non-disabled subsystems */
			opts->subsys_bits = 0;
			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
				struct cgroup_subsys *ss = subsys[i];
				if (ss == NULL)
					continue;
				if (!ss->disabled)
					opts->subsys_bits |= 1ul << i;
			}
		} else if (!strcmp(token, "none")) {
			/* Explicitly have no subsystems */
			opts->none = true;
		} else if (!strcmp(token, "noprefix")) {
			set_bit(ROOT_NOPREFIX, &opts->flags);
		} else if (!strncmp(token, "release_agent=", 14)) {
			/* Specifying two release agents is forbidden */
			if (opts->release_agent)
				return -EINVAL;
			opts->release_agent =
				kstrndup(token + 14, PATH_MAX, GFP_KERNEL);
			if (!opts->release_agent)
				return -ENOMEM;
		} else if (!strncmp(token, "name=", 5)) {
			const char *name = token + 5;
			/* Can't specify an empty name */
			if (!strlen(name))
				return -EINVAL;
			/* Must match [\w.-]+ */
			for (i = 0; i < strlen(name); i++) {
				char c = name[i];
				if (isalnum(c))
					continue;
				if ((c == '.') || (c == '-') || (c == '_'))
					continue;
				return -EINVAL;
			}
			/* Specifying two names is forbidden */
			if (opts->name)
				return -EINVAL;
			opts->name = kstrndup(name,
					      MAX_CGROUP_ROOT_NAMELEN,
					      GFP_KERNEL);
			if (!opts->name)
				return -ENOMEM;
		} else {
			struct cgroup_subsys *ss;
			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
				ss = subsys[i];
				if (ss == NULL)
					continue;
				if (!strcmp(token, ss->name)) {
					if (!ss->disabled)
						set_bit(i, &opts->subsys_bits);
					break;
				}
			}
			if (i == CGROUP_SUBSYS_COUNT)
				return -ENOENT;
		}
	}

	/* Consistency checks */

	/*
	 * Option noprefix was introduced just for backward compatibility
	 * with the old cpuset, so we allow noprefix only if mounting just
	 * the cpuset subsystem.
	 */
	if (test_bit(ROOT_NOPREFIX, &opts->flags) &&
	    (opts->subsys_bits & mask))
		return -EINVAL;


	/* Can't specify "none" and some subsystems */
	if (opts->subsys_bits && opts->none)
		return -EINVAL;

	/*
	 * We either have to specify by name or by subsystems. (So all
	 * empty hierarchies must have a name).
	 */
	if (!opts->subsys_bits && !opts->name)
		return -EINVAL;

	/*
	 * Grab references on all the modules we'll need, so the subsystems
	 * don't dance around before rebind_subsystems attaches them. This may
	 * take duplicate reference counts on a subsystem that's already used,
	 * but rebind_subsystems handles this case.
	 */
	for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
		unsigned long bit = 1UL << i;

		if (!(bit & opts->subsys_bits))
			continue;
		if (!try_module_get(subsys[i]->module)) {
			module_pin_failed = true;
			break;
		}
	}
	if (module_pin_failed) {
		/*
		 * oops, one of the modules was going away. this means that we
		 * raced with a module_delete call, and to the user this is
		 * essentially a "subsystem doesn't exist" case.
		 */
		for (i--; i >= CGROUP_BUILTIN_SUBSYS_COUNT; i--) {
			/* drop refcounts only on the ones we took */
			unsigned long bit = 1UL << i;

			if (!(bit & opts->subsys_bits))
				continue;
			module_put(subsys[i]->module);
		}
		return -ENOENT;
	}

	return 0;
}

static void drop_parsed_module_refcounts(unsigned long subsys_bits)
{
	int i;
	for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
		unsigned long bit = 1UL << i;

		if (!(bit & subsys_bits))
			continue;
		module_put(subsys[i]->module);
	}
}

static int cgroup_remount(struct super_block *sb, int *flags, char *data)
{
	int ret = 0;
	struct cgroupfs_root *root = sb->s_fs_info;
	struct cgroup *cgrp = &root->top_cgroup;
	struct cgroup_sb_opts opts;

	lock_kernel();
	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
	mutex_lock(&cgroup_mutex);

	/* See what subsystems are wanted */
	ret = parse_cgroupfs_options(data, &opts);
	if (ret)
		goto out_unlock;

	/* Don't allow flags or name to change at remount */
	if (opts.flags != root->flags ||
	    (opts.name && strcmp(opts.name, root->name))) {
		ret = -EINVAL;
		drop_parsed_module_refcounts(opts.subsys_bits);
		goto out_unlock;
	}

	ret = rebind_subsystems(root, opts.subsys_bits);
	if (ret) {
		drop_parsed_module_refcounts(opts.subsys_bits);
		goto out_unlock;
	}

	/* (re)populate subsystem files */
	cgroup_populate_dir(cgrp);

	if (opts.release_agent)
		strcpy(root->release_agent_path, opts.release_agent);
 out_unlock:
	kfree(opts.release_agent);
	kfree(opts.name);
	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
	unlock_kernel();
	return ret;
}

static const struct super_operations cgroup_ops = {
	.statfs = simple_statfs,
	.drop_inode = generic_delete_inode,
	.show_options = cgroup_show_options,
	.remount_fs = cgroup_remount,
};

static void init_cgroup_housekeeping(struct cgroup *cgrp)
{
	INIT_LIST_HEAD(&cgrp->sibling);
	INIT_LIST_HEAD(&cgrp->children);
	INIT_LIST_HEAD(&cgrp->css_sets);
	INIT_LIST_HEAD(&cgrp->release_list);
	INIT_LIST_HEAD(&cgrp->pidlists);
	mutex_init(&cgrp->pidlist_mutex);
	INIT_LIST_HEAD(&cgrp->event_list);
	spin_lock_init(&cgrp->event_list_lock);
}

static void init_cgroup_root(struct cgroupfs_root *root)
{
	struct cgroup *cgrp = &root->top_cgroup;
	INIT_LIST_HEAD(&root->subsys_list);
	INIT_LIST_HEAD(&root->root_list);
	root->number_of_cgroups = 1;
	cgrp->root = root;
	cgrp->top_cgroup = cgrp;
	init_cgroup_housekeeping(cgrp);
}

static bool init_root_id(struct cgroupfs_root *root)
{
	int ret = 0;

	do {
		if (!ida_pre_get(&hierarchy_ida, GFP_KERNEL))
			return false;
		spin_lock(&hierarchy_id_lock);
		/* Try to allocate the next unused ID */
		ret = ida_get_new_above(&hierarchy_ida, next_hierarchy_id,
					&root->hierarchy_id);
		if (ret == -ENOSPC)
			/* Try again starting from 0 */
			ret = ida_get_new(&hierarchy_ida, &root->hierarchy_id);
		if (!ret) {
			next_hierarchy_id = root->hierarchy_id + 1;
		} else if (ret != -EAGAIN) {
			/* Can only get here if the 31-bit IDR is full ... */
			BUG_ON(ret);
		}
		spin_unlock(&hierarchy_id_lock);
	} while (ret);
	return true;
}

static int cgroup_test_super(struct super_block *sb, void *data)
{
	struct cgroup_sb_opts *opts = data;
	struct cgroupfs_root *root = sb->s_fs_info;

	/* If we asked for a name then it must match */
	if (opts->name && strcmp(opts->name, root->name))
		return 0;

	/*
	 * If we asked for subsystems (or explicitly for no
	 * subsystems) then they must match
	 */
	if ((opts->subsys_bits || opts->none)
	    && (opts->subsys_bits != root->subsys_bits))
		return 0;

	return 1;
}

static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
{
	struct cgroupfs_root *root;

	if (!opts->subsys_bits && !opts->none)
		return NULL;

	root = kzalloc(sizeof(*root), GFP_KERNEL);
	if (!root)
		return ERR_PTR(-ENOMEM);

	if (!init_root_id(root)) {
		kfree(root);
		return ERR_PTR(-ENOMEM);
	}
	init_cgroup_root(root);

	root->subsys_bits = opts->subsys_bits;
	root->flags = opts->flags;
	if (opts->release_agent)
		strcpy(root->release_agent_path, opts->release_agent);
	if (opts->name)
		strcpy(root->name, opts->name);
	return root;
}

static void cgroup_drop_root(struct cgroupfs_root *root)
{
	if (!root)
		return;

	BUG_ON(!root->hierarchy_id);
	spin_lock(&hierarchy_id_lock);
	ida_remove(&hierarchy_ida, root->hierarchy_id);
	spin_unlock(&hierarchy_id_lock);
	kfree(root);
}

static int cgroup_set_super(struct super_block *sb, void *data)
{
	int ret;
	struct cgroup_sb_opts *opts = data;

	/* If we don't have a new root, we can't set up a new sb */
	if (!opts->new_root)
		return -EINVAL;

	BUG_ON(!opts->subsys_bits && !opts->none);

	ret = set_anon_super(sb, NULL);
	if (ret)
		return ret;

	sb->s_fs_info = opts->new_root;
	opts->new_root->sb = sb;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = CGROUP_SUPER_MAGIC;
	sb->s_op = &cgroup_ops;

	return 0;
}

static int cgroup_get_rootdir(struct super_block *sb)
{
	struct inode *inode =
		cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
	struct dentry *dentry;

	if (!inode)
		return -ENOMEM;

	inode->i_fop = &simple_dir_operations;
	inode->i_op = &cgroup_dir_inode_operations;
	/* directories start off with i_nlink == 2 (for "." entry) */
	inc_nlink(inode);
	dentry = d_alloc_root(inode);
	if (!dentry) {
		iput(inode);
		return -ENOMEM;
	}
	sb->s_root = dentry;
	return 0;
}

static int cgroup_get_sb(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data, struct vfsmount *mnt)
{
	struct cgroup_sb_opts opts;
	struct cgroupfs_root *root;
	int ret = 0;
	struct super_block *sb;
	struct cgroupfs_root *new_root;

	/* First find the desired set of subsystems */
	mutex_lock(&cgroup_mutex);
	ret = parse_cgroupfs_options(data, &opts);
	mutex_unlock(&cgroup_mutex);
	if (ret)
		goto out_err;

	/*
	 * Allocate a new cgroup root. We may not need it if we're
	 * reusing an existing hierarchy.
	 */
	new_root = cgroup_root_from_opts(&opts);
	if (IS_ERR(new_root)) {
		ret = PTR_ERR(new_root);
		goto drop_modules;
	}
	opts.new_root = new_root;

	/* Locate an existing or new sb for this hierarchy */
	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts);
	if (IS_ERR(sb)) {
		ret = PTR_ERR(sb);
		cgroup_drop_root(opts.new_root);
		goto drop_modules;
	}

	root = sb->s_fs_info;
	BUG_ON(!root);
	if (root == opts.new_root) {
		/* We used the new root structure, so this is a new hierarchy */
		struct list_head tmp_cg_links;
		struct cgroup *root_cgrp = &root->top_cgroup;
		struct inode *inode;
		struct cgroupfs_root *existing_root;
		int i;

		BUG_ON(sb->s_root != NULL);

		ret = cgroup_get_rootdir(sb);
		if (ret)
			goto drop_new_super;
		inode = sb->s_root->d_inode;

		mutex_lock(&inode->i_mutex);
		mutex_lock(&cgroup_mutex);

		if (strlen(root->name)) {
			/* Check for name clashes with existing mounts */
			for_each_active_root(existing_root) {
				if (!strcmp(existing_root->name, root->name)) {
					ret = -EBUSY;
					mutex_unlock(&cgroup_mutex);
					mutex_unlock(&inode->i_mutex);
					goto drop_new_super;
				}
			}
		}

		/*
		 * We're accessing css_set_count without locking
		 * css_set_lock here, but that's OK - it can only be
		 * increased by someone holding cgroup_lock, and
		 * that's us. The worst that can happen is that we
		 * have some link structures left over
		 */
		ret = allocate_cg_links(css_set_count, &tmp_cg_links);
		if (ret) {
			mutex_unlock(&cgroup_mutex);
			mutex_unlock(&inode->i_mutex);
			goto drop_new_super;
		}

		ret = rebind_subsystems(root, root->subsys_bits);
		if (ret == -EBUSY) {
			mutex_unlock(&cgroup_mutex);
			mutex_unlock(&inode->i_mutex);
			free_cg_links(&tmp_cg_links);
			goto drop_new_super;
		}
		/*
		 * There must be no failure case after here, since rebinding
		 * takes care of subsystems' refcounts, which are explicitly
		 * dropped in the failure exit path.
		 */

		/* EBUSY should be the only error here */
		BUG_ON(ret);

		list_add(&root->root_list, &roots);
		root_count++;

		sb->s_root->d_fsdata = root_cgrp;
		root->top_cgroup.dentry = sb->s_root;

		/* Link the top cgroup in this hierarchy into all
		 * the css_set objects */
		write_lock(&css_set_lock);
		for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
			struct hlist_head *hhead = &css_set_table[i];
			struct hlist_node *node;
			struct css_set *cg;

			hlist_for_each_entry(cg, node, hhead, hlist)
				link_css_set(&tmp_cg_links, cg, root_cgrp);
		}
		write_unlock(&css_set_lock);

		free_cg_links(&tmp_cg_links);

		BUG_ON(!list_empty(&root_cgrp->sibling));
		BUG_ON(!list_empty(&root_cgrp->children));
		BUG_ON(root->number_of_cgroups != 1);

		cgroup_populate_dir(root_cgrp);
		mutex_unlock(&cgroup_mutex);
		mutex_unlock(&inode->i_mutex);
	} else {
		/*
		 * We re-used an existing hierarchy - the new root (if
		 * any) is not needed
		 */
		cgroup_drop_root(opts.new_root);
		/* no subsys rebinding, so refcounts don't change */
		drop_parsed_module_refcounts(opts.subsys_bits);
	}

	simple_set_mnt(mnt, sb);
	kfree(opts.release_agent);
	kfree(opts.name);
	return 0;

 drop_new_super:
	deactivate_locked_super(sb);
 drop_modules:
	drop_parsed_module_refcounts(opts.subsys_bits);
 out_err:
	kfree(opts.release_agent);
	kfree(opts.name);

	return ret;
}

static void cgroup_kill_sb(struct super_block *sb) {
	struct cgroupfs_root *root = sb->s_fs_info;
	struct cgroup *cgrp = &root->top_cgroup;
	int ret;
	struct cg_cgroup_link *link;
	struct cg_cgroup_link *saved_link;

	BUG_ON(!root);

	BUG_ON(root->number_of_cgroups != 1);
	BUG_ON(!list_empty(&cgrp->children));
	BUG_ON(!list_empty(&cgrp->sibling));

	mutex_lock(&cgroup_mutex);

	/* Rebind all subsystems back to the default hierarchy */
	ret = rebind_subsystems(root, 0);
	/* Shouldn't be able to fail ... */
	BUG_ON(ret);

	/*
	 * Release all the links from css_sets to this hierarchy's
	 * root cgroup
	 */
	write_lock(&css_set_lock);

	list_for_each_entry_safe(link, saved_link, &cgrp->css_sets,
				 cgrp_link_list) {
		list_del(&link->cg_link_list);
		list_del(&link->cgrp_link_list);
		kfree(link);
	}
	write_unlock(&css_set_lock);

	if (!list_empty(&root->root_list)) {
		list_del(&root->root_list);
		root_count--;
	}

	mutex_unlock(&cgroup_mutex);

	kill_litter_super(sb);
	cgroup_drop_root(root);
}

static struct file_system_type cgroup_fs_type = {
	.name = "cgroup",
	.get_sb = cgroup_get_sb,
	.kill_sb = cgroup_kill_sb,
};

static inline struct cgroup *__d_cgrp(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

static inline struct cftype *__d_cft(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

/**
 * cgroup_path - generate the path of a cgroup
 * @cgrp: the cgroup in question
 * @buf: the buffer to write the path into
 * @buflen: the length of the buffer
 *
 * Called with cgroup_mutex held or else with an RCU-protected cgroup
 * reference.  Writes path of cgroup into buf.  Returns 0 on success,
 * -errno on error.
 */
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
	char *start;
	struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
						      rcu_read_lock_held() ||
						      cgroup_lock_is_held());

	if (!dentry || cgrp == dummytop) {
		/*
		 * Inactive subsystems have no dentry for their root
		 * cgroup
		 */
		strcpy(buf, "/");
		return 0;
	}

	start = buf + buflen;

	*--start = '\0';
	for (;;) {
		int len = dentry->d_name.len;

		if ((start -= len) < buf)
			return -ENAMETOOLONG;
		memcpy(start, dentry->d_name.name, len);
		cgrp = cgrp->parent;
		if (!cgrp)
			break;

		dentry = rcu_dereference_check(cgrp->dentry,
					       rcu_read_lock_held() ||
					       cgroup_lock_is_held());
		if (!cgrp->parent)
			continue;
		if (--start < buf)
			return -ENAMETOOLONG;
		*start = '/';
	}
	memmove(buf, start, buf + buflen - start);
	return 0;
}
EXPORT_SYMBOL_GPL(cgroup_path);

/**
 * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
 * @cgrp: the cgroup the task is attaching to
 * @tsk: the task to be attached
 *
 * Call holding cgroup_mutex. May take task_lock of
 * the task 'tsk' during call.
 */
int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
	int retval = 0;
	struct cgroup_subsys *ss, *failed_ss = NULL;
	struct cgroup *oldcgrp;
	struct css_set *cg;
	struct css_set *newcg;
	struct cgroupfs_root *root = cgrp->root;

	/* Nothing to do if the task is already in that cgroup */
	oldcgrp = task_cgroup_from_root(tsk, root);
	if (cgrp == oldcgrp)
		return 0;

	for_each_subsys(root, ss) {
		if (ss->can_attach) {
			retval = ss->can_attach(ss, cgrp, tsk, false);
			if (retval) {
				/*
				 * Remember on which subsystem the can_attach()
				 * failed, so that we only call cancel_attach()
				 * against the subsystems whose can_attach()
				 * succeeded. (See below)
				 */
				failed_ss = ss;
				goto out;
			}
		}
	}

	task_lock(tsk);
	cg = tsk->cgroups;
	get_css_set(cg);
	task_unlock(tsk);
	/*
	 * Locate or allocate a new css_set for this task,
	 * based on its final set of cgroups
	 */
	newcg = find_css_set(cg, cgrp);
	put_css_set(cg);
	if (!newcg) {
		retval = -ENOMEM;
		goto out;
	}

	task_lock(tsk);
	if (tsk->flags & PF_EXITING) {
		task_unlock(tsk);
		put_css_set(newcg);
		retval = -ESRCH;
		goto out;
	}
	rcu_assign_pointer(tsk->cgroups, newcg);
	task_unlock(tsk);

	/* Update the css_set linked lists if we're using them */
	write_lock(&css_set_lock);
	if (!list_empty(&tsk->cg_list)) {
		list_del(&tsk->cg_list);
		list_add(&tsk->cg_list, &newcg->tasks);
	}
	write_unlock(&css_set_lock);

	for_each_subsys(root, ss) {
		if (ss->attach)
			ss->attach(ss, cgrp, oldcgrp, tsk, false);
	}
	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
	synchronize_rcu();
	put_css_set(cg);

	/*
	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
	 * is no longer empty.
	 */
	cgroup_wakeup_rmdir_waiter(cgrp);
out:
	if (retval) {
		for_each_subsys(root, ss) {
			if (ss == failed_ss)
				/*
				 * This subsystem was the one that failed the
				 * can_attach() check earlier, so we don't need
				 * to call cancel_attach() against it or any
				 * remaining subsystems.
				 */
				break;
			if (ss->cancel_attach)
				ss->cancel_attach(ss, cgrp, tsk, false);
		}
	}
	return retval;
}

/*
 * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
 * held. May take task_lock of task
 */
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
{
	struct task_struct *tsk;
	const struct cred *cred = current_cred(), *tcred;
	int ret;

	if (pid) {
		rcu_read_lock();
		tsk = find_task_by_vpid(pid);
		if (!tsk || tsk->flags & PF_EXITING) {
			rcu_read_unlock();
			return -ESRCH;
		}

		tcred = __task_cred(tsk);
		if (cred->euid &&
		    cred->euid != tcred->uid &&
		    cred->euid != tcred->suid) {
			rcu_read_unlock();
			return -EACCES;
		}
		get_task_struct(tsk);
		rcu_read_unlock();
	} else {
		tsk = current;
		get_task_struct(tsk);
	}

	ret = cgroup_attach_task(cgrp, tsk);
	put_task_struct(tsk);
	return ret;
}

static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
{
	int ret;
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	ret = attach_task_by_pid(cgrp, pid);
	cgroup_unlock();
	return ret;
}

/**
 * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
 * @cgrp: the cgroup to be checked for liveness
 *
 * On success, returns true; the lock should be later released with
 * cgroup_unlock(). On failure returns false with no lock held.
 */
bool cgroup_lock_live_group(struct cgroup *cgrp)
{
	mutex_lock(&cgroup_mutex);
	if (cgroup_is_removed(cgrp)) {
		mutex_unlock(&cgroup_mutex);
		return false;
	}
	return true;
}
EXPORT_SYMBOL_GPL(cgroup_lock_live_group);

static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
				      const char *buffer)
{
	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	strcpy(cgrp->root->release_agent_path, buffer);
	cgroup_unlock();
	return 0;
}

static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
				     struct seq_file *seq)
{
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	seq_puts(seq, cgrp->root->release_agent_path);
	seq_putc(seq, '\n');
	cgroup_unlock();
	return 0;
}

/* A buffer size big enough for numbers or short strings */
#define CGROUP_LOCAL_BUFFER_SIZE 64

static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
				struct file *file,
				const char __user *userbuf,
				size_t nbytes, loff_t *unused_ppos)
{
	char buffer[CGROUP_LOCAL_BUFFER_SIZE];
	int retval = 0;
	char *end;

	if (!nbytes)
		return -EINVAL;
	if (nbytes >= sizeof(buffer))
		return -E2BIG;
	if (copy_from_user(buffer, userbuf, nbytes))
		return -EFAULT;

	buffer[nbytes] = 0;     /* nul-terminate */
	if (cft->write_u64) {
		u64 val = simple_strtoull(strstrip(buffer), &end, 0);
		if (*end)
			return -EINVAL;
		retval = cft->write_u64(cgrp, cft, val);
	} else {
		s64 val = simple_strtoll(strstrip(buffer), &end, 0);
		if (*end)
			return -EINVAL;
		retval = cft->write_s64(cgrp, cft, val);
	}
	if (!retval)
		retval = nbytes;
	return retval;
}

static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
				   struct file *file,
				   const char __user *userbuf,
				   size_t nbytes, loff_t *unused_ppos)
{
	char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
	int retval = 0;
	size_t max_bytes = cft->max_write_len;
	char *buffer = local_buffer;

	if (!max_bytes)
		max_bytes = sizeof(local_buffer) - 1;
	if (nbytes >= max_bytes)
		return -E2BIG;
	/* Allocate a dynamic buffer if we need one */
	if (nbytes >= sizeof(local_buffer)) {
		buffer = kmalloc(nbytes + 1, GFP_KERNEL);
		if (buffer == NULL)
			return -ENOMEM;
	}
	if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
		retval = -EFAULT;
		goto out;
	}

	buffer[nbytes] = 0;     /* nul-terminate */
	retval = cft->write_string(cgrp, cft, strstrip(buffer));
	if (!retval)
		retval = nbytes;
out:
	if (buffer != local_buffer)
		kfree(buffer);
	return retval;
}

static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
						size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

	if (cgroup_is_removed(cgrp))
		return -ENODEV;
	if (cft->write)
		return cft->write(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->write_u64 || cft->write_s64)
		return cgroup_write_X64(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->write_string)
		return cgroup_write_string(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->trigger) {
		int ret = cft->trigger(cgrp, (unsigned int)cft->private);
		return ret ? ret : nbytes;
	}
	return -EINVAL;
}

static ssize_t cgroup_read_u64(struct cgroup *cgrp, struct cftype *cft,
			       struct file *file,
			       char __user *buf, size_t nbytes,
			       loff_t *ppos)
{
	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
	u64 val = cft->read_u64(cgrp, cft);
	int len = sprintf(tmp, "%llu\n", (unsigned long long) val);

	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_read_s64(struct cgroup *cgrp, struct cftype *cft,
			       struct file *file,
			       char __user *buf, size_t nbytes,
			       loff_t *ppos)
{
	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
	s64 val = cft->read_s64(cgrp, cft);
	int len = sprintf(tmp, "%lld\n", (long long) val);

	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_file_read(struct file *file, char __user *buf,
				   size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

	if (cgroup_is_removed(cgrp))
		return -ENODEV;

	if (cft->read)
		return cft->read(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->read_u64)
		return cgroup_read_u64(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->read_s64)
		return cgroup_read_s64(cgrp, cft, file, buf, nbytes, ppos);
	return -EINVAL;
}

/*
 * seqfile ops/methods for returning structured data. Currently just
 * supports string->u64 maps, but can be extended in future.
 */

struct cgroup_seqfile_state {
	struct cftype *cft;
	struct cgroup *cgroup;
};

static int cgroup_map_add(struct cgroup_map_cb *cb, const char *key, u64 value)
{
	struct seq_file *sf = cb->state;
	return seq_printf(sf, "%s %llu\n", key, (unsigned long long)value);
}

static int cgroup_seqfile_show(struct seq_file *m, void *arg)
{
	struct cgroup_seqfile_state *state = m->private;
	struct cftype *cft = state->cft;
	if (cft->read_map) {
		struct cgroup_map_cb cb = {
			.fill = cgroup_map_add,
			.state = m,
		};
		return cft->read_map(state->cgroup, cft, &cb);
	}
	return cft->read_seq_string(state->cgroup, cft, m);
}

static int cgroup_seqfile_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	kfree(seq->private);
	return single_release(inode, file);
}

static const struct file_operations cgroup_seqfile_operations = {
	.read = seq_read,
	.write = cgroup_file_write,
	.llseek = seq_lseek,
	.release = cgroup_seqfile_release,
};

static int cgroup_file_open(struct inode *inode, struct file *file)
{
	int err;
	struct cftype *cft;

	err = generic_file_open(inode, file);
	if (err)
		return err;
	cft = __d_cft(file->f_dentry);

	if (cft->read_map || cft->read_seq_string) {
		struct cgroup_seqfile_state *state =
			kzalloc(sizeof(*state), GFP_USER);
		if (!state)
			return -ENOMEM;
		state->cft = cft;
		state->cgroup = __d_cgrp(file->f_dentry->d_parent);
		file->f_op = &cgroup_seqfile_operations;
		err = single_open(file, cgroup_seqfile_show, state);
		if (err < 0)
			kfree(state);
	} else if (cft->open)
		err = cft->open(inode, file);
	else
		err = 0;

	return err;
}

static int cgroup_file_release(struct inode *inode, struct file *file)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	if (cft->release)
		return cft->release(inode, file);
	return 0;
}

/*
 * cgroup_rename - Only allow simple rename of directories in place.
 */
static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
			    struct inode *new_dir, struct dentry *new_dentry)
{
	if (!S_ISDIR(old_dentry->d_inode->i_mode))
		return -ENOTDIR;
	if (new_dentry->d_inode)
		return -EEXIST;
	if (old_dir != new_dir)
		return -EIO;
	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}

static const struct file_operations cgroup_file_operations = {
	.read = cgroup_file_read,
	.write = cgroup_file_write,
	.llseek = generic_file_llseek,
	.open = cgroup_file_open,
	.release = cgroup_file_release,
};

static const struct inode_operations cgroup_dir_inode_operations = {
	.lookup = simple_lookup,
	.mkdir = cgroup_mkdir,
	.rmdir = cgroup_rmdir,
	.rename = cgroup_rename,
};

/*
 * Check if a file is a control file
 */
static inline struct cftype *__file_cft(struct file *file)
{
	if (file->f_dentry->d_inode->i_fop != &cgroup_file_operations)
		return ERR_PTR(-EINVAL);
	return __d_cft(file->f_dentry);
}

static int cgroup_create_file(struct dentry *dentry, mode_t mode,
				struct super_block *sb)
{
	static const struct dentry_operations cgroup_dops = {
		.d_iput = cgroup_diput,
	};

	struct inode *inode;

	if (!dentry)
		return -ENOENT;
	if (dentry->d_inode)
		return -EEXIST;

	inode = cgroup_new_inode(mode, sb);
	if (!inode)
		return -ENOMEM;

	if (S_ISDIR(mode)) {
		inode->i_op = &cgroup_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;

		/* start off with i_nlink == 2 (for "." entry) */
		inc_nlink(inode);

		/* start with the directory inode held, so that we can
		 * populate it without racing with another mkdir */
		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
	} else if (S_ISREG(mode)) {
		inode->i_size = 0;
		inode->i_fop = &cgroup_file_operations;
	}
	dentry->d_op = &cgroup_dops;
	d_instantiate(dentry, inode);
	dget(dentry);	/* Extra count - pin the dentry in core */
	return 0;
}

/*
 * cgroup_create_dir - create a directory for an object.
 * @cgrp: the cgroup we create the directory for. It must have a valid
 *        ->parent field. And we are going to fill its ->dentry field.
 * @dentry: dentry of the new cgroup
 * @mode: mode to set on new directory.
 */
static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
				mode_t mode)
{
	struct dentry *parent;
	int error = 0;

	parent = cgrp->parent->dentry;
	error = cgroup_create_file(dentry, S_IFDIR | mode, cgrp->root->sb);
	if (!error) {
		dentry->d_fsdata = cgrp;
		inc_nlink(parent->d_inode);
		rcu_assign_pointer(cgrp->dentry, dentry);
		dget(dentry);
	}
	dput(dentry);

	return error;
}

/**
 * cgroup_file_mode - deduce file mode of a control file
 * @cft: the control file in question
 *
 * returns cft->mode if ->mode is not 0
 * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
 * returns S_IRUGO if it has only a read handler
 * returns S_IWUSR if it has only a write hander
 */
static mode_t cgroup_file_mode(const struct cftype *cft)
{
	mode_t mode = 0;

	if (cft->mode)
		return cft->mode;

	if (cft->read || cft->read_u64 || cft->read_s64 ||
	    cft->read_map || cft->read_seq_string)
		mode |= S_IRUGO;

	if (cft->write || cft->write_u64 || cft->write_s64 ||
	    cft->write_string || cft->trigger)
		mode |= S_IWUSR;

	return mode;
}

int cgroup_add_file(struct cgroup *cgrp,
		       struct cgroup_subsys *subsys,
		       const struct cftype *cft)
{
	struct dentry *dir = cgrp->dentry;
	struct dentry *dentry;
	int error;
	mode_t mode;

	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
	if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
		strcpy(name, subsys->name);
		strcat(name, ".");
	}
	strcat(name, cft->name);
	BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
	dentry = lookup_one_len(name, dir, strlen(name));
	if (!IS_ERR(dentry)) {
		mode = cgroup_file_mode(cft);
		error = cgroup_create_file(dentry, mode | S_IFREG,
						cgrp->root->sb);
		if (!error)
			dentry->d_fsdata = (void *)cft;
		dput(dentry);
	} else
		error = PTR_ERR(dentry);
	return error;
}
EXPORT_SYMBOL_GPL(cgroup_add_file);

int cgroup_add_files(struct cgroup *cgrp,
			struct cgroup_subsys *subsys,
			const struct cftype cft[],
			int count)
{
	int i, err;
	for (i = 0; i < count; i++) {
		err = cgroup_add_file(cgrp, subsys, &cft[i]);
		if (err)
			return err;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(cgroup_add_files);

/**
 * cgroup_task_count - count the number of tasks in a cgroup.
 * @cgrp: the cgroup in question
 *
 * Return the number of tasks in the cgroup.
 */
int cgroup_task_count(const struct cgroup *cgrp)
{
	int count = 0;
	struct cg_cgroup_link *link;

	read_lock(&css_set_lock);
	list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
		count += atomic_read(&link->cg->refcount);
	}
	read_unlock(&css_set_lock);
	return count;
}

/*
 * Advance a list_head iterator.  The iterator should be positioned at
 * the start of a css_set
 */
static void cgroup_advance_iter(struct cgroup *cgrp,
				struct cgroup_iter *it)
{
	struct list_head *l = it->cg_link;
	struct cg_cgroup_link *link;
	struct css_set *cg;

	/* Advance to the next non-empty css_set */
	do {
		l = l->next;
		if (l == &cgrp->css_sets) {
			it->cg_link = NULL;
			return;
		}
		link = list_entry(l, struct cg_cgroup_link, cgrp_link_list);
		cg = link->cg;
	} while (list_empty(&cg->tasks));
	it->cg_link = l;
	it->task = cg->tasks.next;
}

/*
 * To reduce the fork() overhead for systems that are not actually
 * using their cgroups capability, we don't maintain the lists running
 * through each css_set to its tasks until we see the list actually
 * used - in other words after the first call to cgroup_iter_start().
 *
 * The tasklist_lock is not held here, as do_each_thread() and
 * while_each_thread() are protected by RCU.
 */
static void cgroup_enable_task_cg_lists(void)
{
	struct task_struct *p, *g;
	write_lock(&css_set_lock);
	use_task_css_set_links = 1;
	do_each_thread(g, p) {
		task_lock(p);
		/*
		 * We should check if the process is exiting, otherwise
		 * it will race with cgroup_exit() in that the list
		 * entry won't be deleted though the process has exited.
		 */
		if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
			list_add(&p->cg_list, &p->cgroups->tasks);
		task_unlock(p);
	} while_each_thread(g, p);
	write_unlock(&css_set_lock);
}

void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
{
	/*
	 * The first time anyone tries to iterate across a cgroup,
	 * we need to enable the list linking each css_set to its
	 * tasks, and fix up all existing tasks.
	 */
	if (!use_task_css_set_links)
		cgroup_enable_task_cg_lists();

	read_lock(&css_set_lock);
	it->cg_link = &cgrp->css_sets;
	cgroup_advance_iter(cgrp, it);
}

struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
					struct cgroup_iter *it)
{
	struct task_struct *res;
	struct list_head *l = it->task;
	struct cg_cgroup_link *link;

	/* If the iterator cg is NULL, we have no tasks */
	if (!it->cg_link)
		return NULL;
	res = list_entry(l, struct task_struct, cg_list);
	/* Advance iterator to find next entry */
	l = l->next;
	link = list_entry(it->cg_link, struct cg_cgroup_link, cgrp_link_list);
	if (l == &link->cg->tasks) {
		/* We reached the end of this task list - move on to
		 * the next cg_cgroup_link */
		cgroup_advance_iter(cgrp, it);
	} else {
		it->task = l;
	}
	return res;
}

void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it)
{
	read_unlock(&css_set_lock);
}

static inline int started_after_time(struct task_struct *t1,
				     struct timespec *time,
				     struct task_struct *t2)
{
	int start_diff = timespec_compare(&t1->start_time, time);
	if (start_diff > 0) {
		return 1;
	} else if (start_diff < 0) {
		return 0;
	} else {
		/*
		 * Arbitrarily, if two processes started at the same
		 * time, we'll say that the lower pointer value
		 * started first. Note that t2 may have exited by now
		 * so this may not be a valid pointer any longer, but
		 * that's fine - it still serves to distinguish
		 * between two tasks started (effectively) simultaneously.
		 */
		return t1 > t2;
	}
}

/*
 * This function is a callback from heap_insert() and is used to order
 * the heap.
 * In this case we order the heap in descending task start time.
 */
static inline int started_after(void *p1, void *p2)
{
	struct task_struct *t1 = p1;
	struct task_struct *t2 = p2;
	return started_after_time(t1, &t2->start_time, t2);
}

/**
 * cgroup_scan_tasks - iterate though all the tasks in a cgroup
 * @scan: struct cgroup_scanner containing arguments for the scan
 *
 * Arguments include pointers to callback functions test_task() and
 * process_task().
 * Iterate through all the tasks in a cgroup, calling test_task() for each,
 * and if it returns true, call process_task() for it also.
 * The test_task pointer may be NULL, meaning always true (select all tasks).
 * Effectively duplicates cgroup_iter_{start,next,end}()
 * but does not lock css_set_lock for the call to process_task().
 * The struct cgroup_scanner may be embedded in any structure of the caller's
 * creation.
 * It is guaranteed that process_task() will act on every task that
 * is a member of the cgroup for the duration of this call. This
 * function may or may not call process_task() for tasks that exit
 * or move to a different cgroup during the call, or are forked or
 * move into the cgroup during the call.
 *
 * Note that test_task() may be called with locks held, and may in some
 * situations be called multiple times for the same task, so it should
 * be cheap.
 * If the heap pointer in the struct cgroup_scanner is non-NULL, a heap has been
 * pre-allocated and will be used for heap operations (and its "gt" member will
 * be overwritten), else a temporary heap will be used (allocation of which
 * may cause this function to fail).
 */
int cgroup_scan_tasks(struct cgroup_scanner *scan)
{
	int retval, i;
	struct cgroup_iter it;
	struct task_struct *p, *dropped;
	/* Never dereference latest_task, since it's not refcounted */
	struct task_struct *latest_task = NULL;
	struct ptr_heap tmp_heap;
	struct ptr_heap *heap;
	struct timespec latest_time = { 0, 0 };

	if (scan->heap) {
		/* The caller supplied our heap and pre-allocated its memory */
		heap = scan->heap;
		heap->gt = &started_after;
	} else {
		/* We need to allocate our own heap memory */
		heap = &tmp_heap;
		retval = heap_init(heap, PAGE_SIZE, GFP_KERNEL, &started_after);
		if (retval)
			/* cannot allocate the heap */
			return retval;
	}

 again:
	/*
	 * Scan tasks in the cgroup, using the scanner's "test_task" callback
	 * to determine which are of interest, and using the scanner's
	 * "process_task" callback to process any of them that need an update.
	 * Since we don't want to hold any locks during the task updates,
	 * gather tasks to be processed in a heap structure.
	 * The heap is sorted by descending task start time.
	 * If the statically-sized heap fills up, we overflow tasks that
	 * started later, and in future iterations only consider tasks that
	 * started after the latest task in the previous pass. This
	 * guarantees forward progress and that we don't miss any tasks.
	 */
	heap->size = 0;
	cgroup_iter_start(scan->cg, &it);
	while ((p = cgroup_iter_next(scan->cg, &it))) {
		/*
		 * Only affect tasks that qualify per the caller's callback,
		 * if he provided one
		 */
		if (scan->test_task && !scan->test_task(p, scan))
			continue;
		/*
		 * Only process tasks that started after the last task
		 * we processed
		 */
		if (!started_after_time(p, &latest_time, latest_task))
			continue;
		dropped = heap_insert(heap, p);
		if (dropped == NULL) {
			/*
			 * The new task was inserted; the heap wasn't
			 * previously full
			 */
			get_task_struct(p);
		} else if (dropped != p) {
			/*
			 * The new task was inserted, and pushed out a
			 * different task
			 */
			get_task_struct(p);
			put_task_struct(dropped);
		}
		/*
		 * Else the new task was newer than anything already in
		 * the heap and wasn't inserted
		 */
	}
	cgroup_iter_end(scan->cg, &it);

	if (heap->size) {
		for (i = 0; i < heap->size; i++) {
			struct task_struct *q = heap->ptrs[i];
			if (i == 0) {
				latest_time = q->start_time;
				latest_task = q;
			}
			/* Process the task per the caller's callback */
			scan->process_task(q, scan);
			put_task_struct(q);
		}
		/*
		 * If we had to process any tasks at all, scan again
		 * in case some of them were in the middle of forking
		 * children that didn't get processed.
		 * Not the most efficient way to do it, but it avoids
		 * having to take callback_mutex in the fork path
		 */
		goto again;
	}
	if (heap == &tmp_heap)
		heap_free(&tmp_heap);
	return 0;
}

/*
 * Stuff for reading the 'tasks'/'procs' files.
 *
 * Reading this file can return large amounts of data if a cgroup has
 * *lots* of attached tasks. So it may need several calls to read(),
 * but we cannot guarantee that the information we produce is correct
 * unless we produce it entirely atomically.
 *
 */

/*
 * The following two functions "fix" the issue where there are more pids
 * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
 * TODO: replace with a kernel-wide solution to this problem
 */
#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
static void *pidlist_allocate(int count)
{
	if (PIDLIST_TOO_LARGE(count))
		return vmalloc(count * sizeof(pid_t));
	else
		return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
}
static void pidlist_free(void *p)
{
	if (is_vmalloc_addr(p))
		vfree(p);
	else
		kfree(p);
}
static void *pidlist_resize(void *p, int newcount)
{
	void *newlist;
	/* note: if new alloc fails, old p will still be valid either way */
	if (is_vmalloc_addr(p)) {
		newlist = vmalloc(newcount * sizeof(pid_t));
		if (!newlist)
			return NULL;
		memcpy(newlist, p, newcount * sizeof(pid_t));
		vfree(p);
	} else {
		newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
	}
	return newlist;
}

/*
 * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
 * If the new stripped list is sufficiently smaller and there's enough memory
 * to allocate a new buffer, will let go of the unneeded memory. Returns the
 * number of unique elements.
 */
/* is the size difference enough that we should re-allocate the array? */
#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
static int pidlist_uniq(pid_t **p, int length)
{
	int src, dest = 1;
	pid_t *list = *p;
	pid_t *newlist;

	/*
	 * we presume the 0th element is unique, so i starts at 1. trivial
	 * edge cases first; no work needs to be done for either
	 */
	if (length == 0 || length == 1)
		return length;
	/* src and dest walk down the list; dest counts unique elements */
	for (src = 1; src < length; src++) {
		/* find next unique element */
		while (list[src] == list[src-1]) {
			src++;
			if (src == length)
				goto after;
		}
		/* dest always points to where the next unique element goes */
		list[dest] = list[src];
		dest++;
	}
after:
	/*
	 * if the length difference is large enough, we want to allocate a
	 * smaller buffer to save memory. if this fails due to out of memory,
	 * we'll just stay with what we've got.
	 */
	if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
		newlist = pidlist_resize(list, dest);
		if (newlist)
			*p = newlist;
	}
	return dest;
}

static int cmppid(const void *a, const void *b)
{
	return *(pid_t *)a - *(pid_t *)b;
}

/*
 * find the appropriate pidlist for our purpose (given procs vs tasks)
 * returns with the lock on that pidlist already held, and takes care
 * of the use count, or returns NULL with no locks held if we're out of
 * memory.
 */
static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
						  enum cgroup_filetype type)
{
	struct cgroup_pidlist *l;
	/* don't need task_nsproxy() if we're looking at ourself */
	struct pid_namespace *ns = current->nsproxy->pid_ns;

	/*
	 * We can't drop the pidlist_mutex before taking the l->mutex in case
	 * the last ref-holder is trying to remove l from the list at the same
	 * time. Holding the pidlist_mutex precludes somebody taking whichever
	 * list we find out from under us - compare release_pid_array().
	 */
	mutex_lock(&cgrp->pidlist_mutex);
	list_for_each_entry(l, &cgrp->pidlists, links) {
		if (l->key.type == type && l->key.ns == ns) {
			/* make sure l doesn't vanish out from under us */
			down_write(&l->mutex);
			mutex_unlock(&cgrp->pidlist_mutex);
			return l;
		}
	}
	/* entry not found; create a new one */
	l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
	if (!l) {
		mutex_unlock(&cgrp->pidlist_mutex);
		return l;
	}
	init_rwsem(&l->mutex);
	down_write(&l->mutex);
	l->key.type = type;
	l->key.ns = get_pid_ns(ns);
	l->use_count = 0; /* don't increment here */
	l->list = NULL;
	l->owner = cgrp;
	list_add(&l->links, &cgrp->pidlists);
	mutex_unlock(&cgrp->pidlist_mutex);
	return l;
}

/*
 * Load a cgroup's pidarray with either procs' tgids or tasks' pids
 */
static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
			      struct cgroup_pidlist **lp)
{
	pid_t *array;
	int length;
	int pid, n = 0; /* used for populating the array */
	struct cgroup_iter it;
	struct task_struct *tsk;
	struct cgroup_pidlist *l;

	/*
	 * If cgroup gets more users after we read count, we won't have
	 * enough space - tough.  This race is indistinguishable to the
	 * caller from the case that the additional cgroup users didn't
	 * show up until sometime later on.
	 */
	length = cgroup_task_count(cgrp);
	array = pidlist_allocate(length);
	if (!array)
		return -ENOMEM;
	/* now, populate the array */
	cgroup_iter_start(cgrp, &it);
	while ((tsk = cgroup_iter_next(cgrp, &it))) {
		if (unlikely(n == length))
			break;
		/* get tgid or pid for procs or tasks file respectively */
		if (type == CGROUP_FILE_PROCS)
			pid = task_tgid_vnr(tsk);
		else
			pid = task_pid_vnr(tsk);
		if (pid > 0) /* make sure to only use valid results */
			array[n++] = pid;
	}
	cgroup_iter_end(cgrp, &it);
	length = n;
	/* now sort & (if procs) strip out duplicates */
	sort(array, length, sizeof(pid_t), cmppid, NULL);
	if (type == CGROUP_FILE_PROCS)
		length = pidlist_uniq(&array, length);
	l = cgroup_pidlist_find(cgrp, type);
	if (!l) {
		pidlist_free(array);
		return -ENOMEM;
	}
	/* store array, freeing old if necessary - lock already held */
	pidlist_free(l->list);
	l->list = array;
	l->length = length;
	l->use_count++;
	up_write(&l->mutex);
	*lp = l;
	return 0;
}

/**
 * cgroupstats_build - build and fill cgroupstats
 * @stats: cgroupstats to fill information into
 * @dentry: A dentry entry belonging to the cgroup for which stats have
 * been requested.
 *
 * Build and fill cgroupstats so that taskstats can export it to user
 * space.
 */
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
	int ret = -EINVAL;
	struct cgroup *cgrp;
	struct cgroup_iter it;
	struct task_struct *tsk;

	/*
	 * Validate dentry by checking the superblock operations,
	 * and make sure it's a directory.
	 */
	if (dentry->d_sb->s_op != &cgroup_ops ||
	    !S_ISDIR(dentry->d_inode->i_mode))
		 goto err;

	ret = 0;
	cgrp = dentry->d_fsdata;

	cgroup_iter_start(cgrp, &it);
	while ((tsk = cgroup_iter_next(cgrp, &it))) {
		switch (tsk->state) {
		case TASK_RUNNING:
			stats->nr_running++;
			break;
		case TASK_INTERRUPTIBLE:
			stats->nr_sleeping++;
			break;
		case TASK_UNINTERRUPTIBLE:
			stats->nr_uninterruptible++;
			break;
		case TASK_STOPPED:
			stats->nr_stopped++;
			break;
		default:
			if (delayacct_is_task_waiting_on_io(tsk))
				stats->nr_io_wait++;
			break;
		}
	}
	cgroup_iter_end(cgrp, &it);

err:
	return ret;
}


/*
 * seq_file methods for the tasks/procs files. The seq_file position is the
 * next pid to display; the seq_file iterator is a pointer to the pid
 * in the cgroup->l->list array.
 */

static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
{
	/*
	 * Initially we receive a position value that corresponds to
	 * one more than the last pid shown (or 0 on the first call or
	 * after a seek to the start). Use a binary-search to find the
	 * next pid to display, if any
	 */
	struct cgroup_pidlist *l = s->private;
	int index = 0, pid = *pos;
	int *iter;

	down_read(&l->mutex);
	if (pid) {
		int end = l->length;

		while (index < end) {
			int mid = (index + end) / 2;
			if (l->list[mid] == pid) {
				index = mid;
				break;
			} else if (l->list[mid] <= pid)
				index = mid + 1;
			else
				end = mid;
		}
	}
	/* If we're off the end of the array, we're done */
	if (index >= l->length)
		return NULL;
	/* Update the abstract position to be the actual pid that we found */
	iter = l->list + index;
	*pos = *iter;
	return iter;
}

static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
	struct cgroup_pidlist *l = s->private;
	up_read(&l->mutex);
}

static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
	struct cgroup_pidlist *l = s->private;
	pid_t *p = v;
	pid_t *end = l->list + l->length;
	/*
	 * Advance to the next pid in the array. If this goes off the
	 * end, we're done
	 */
	p++;
	if (p >= end) {
		return NULL;
	} else {
		*pos = *p;
		return p;
	}
}

static int cgroup_pidlist_show(struct seq_file *s, void *v)
{
	return seq_printf(s, "%d\n", *(int *)v);
}

/*
 * seq_operations functions for iterating on pidlists through seq_file -
 * independent of whether it's tasks or procs
 */
static const struct seq_operations cgroup_pidlist_seq_operations = {
	.start = cgroup_pidlist_start,
	.stop = cgroup_pidlist_stop,
	.next = cgroup_pidlist_next,
	.show = cgroup_pidlist_show,
};

static void cgroup_release_pid_array(struct cgroup_pidlist *l)
{
	/*
	 * the case where we're the last user of this particular pidlist will
	 * have us remove it from the cgroup's list, which entails taking the
	 * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
	 * pidlist_mutex, we have to take pidlist_mutex first.
	 */
	mutex_lock(&l->owner->pidlist_mutex);
	down_write(&l->mutex);
	BUG_ON(!l->use_count);
	if (!--l->use_count) {
		/* we're the last user if refcount is 0; remove and free */
		list_del(&l->links);
		mutex_unlock(&l->owner->pidlist_mutex);
		pidlist_free(l->list);
		put_pid_ns(l->key.ns);
		up_write(&l->mutex);
		kfree(l);
		return;
	}
	mutex_unlock(&l->owner->pidlist_mutex);
	up_write(&l->mutex);
}

static int cgroup_pidlist_release(struct inode *inode, struct file *file)
{
	struct cgroup_pidlist *l;
	if (!(file->f_mode & FMODE_READ))
		return 0;
	/*
	 * the seq_file will only be initialized if the file was opened for
	 * reading; hence we check if it's not null only in that case.
	 */
	l = ((struct seq_file *)file->private_data)->private;
	cgroup_release_pid_array(l);
	return seq_release(inode, file);
}

static const struct file_operations cgroup_pidlist_operations = {
	.read = seq_read,
	.llseek = seq_lseek,
	.write = cgroup_file_write,
	.release = cgroup_pidlist_release,
};

/*
 * The following functions handle opens on a file that displays a pidlist
 * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
 * in the cgroup.
 */
/* helper function for the two below it */
static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
{
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
	struct cgroup_pidlist *l;
	int retval;

	/* Nothing to do for write-only files */
	if (!(file->f_mode & FMODE_READ))
		return 0;

	/* have the array populated */
	retval = pidlist_array_load(cgrp, type, &l);
	if (retval)
		return retval;
	/* configure file information */
	file->f_op = &cgroup_pidlist_operations;

	retval = seq_open(file, &cgroup_pidlist_seq_operations);
	if (retval) {
		cgroup_release_pid_array(l);
		return retval;
	}
	((struct seq_file *)file->private_data)->private = l;
	return 0;
}
static int cgroup_tasks_open(struct inode *unused, struct file *file)
{
	return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
}
static int cgroup_procs_open(struct inode *unused, struct file *file)
{
	return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
}

static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
					    struct cftype *cft)
{
	return notify_on_release(cgrp);
}

static int cgroup_write_notify_on_release(struct cgroup *cgrp,
					  struct cftype *cft,
					  u64 val)
{
	clear_bit(CGRP_RELEASABLE, &cgrp->flags);
	if (val)
		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
	else
		clear_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
	return 0;
}

/*
 * Unregister event and free resources.
 *
 * Gets called from workqueue.
 */
static void cgroup_event_remove(struct work_struct *work)
{
	struct cgroup_event *event = container_of(work, struct cgroup_event,
			remove);
	struct cgroup *cgrp = event->cgrp;

	event->cft->unregister_event(cgrp, event->cft, event->eventfd);

	eventfd_ctx_put(event->eventfd);
	kfree(event);
	dput(cgrp->dentry);
}

/*
 * Gets called on POLLHUP on eventfd when user closes it.
 *
 * Called with wqh->lock held and interrupts disabled.
 */
static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
		int sync, void *key)
{
	struct cgroup_event *event = container_of(wait,
			struct cgroup_event, wait);
	struct cgroup *cgrp = event->cgrp;
	unsigned long flags = (unsigned long)key;

	if (flags & POLLHUP) {
		__remove_wait_queue(event->wqh, &event->wait);
		spin_lock(&cgrp->event_list_lock);
		list_del(&event->list);
		spin_unlock(&cgrp->event_list_lock);
		/*
		 * We are in atomic context, but cgroup_event_remove() may
		 * sleep, so we have to call it in workqueue.
		 */
		schedule_work(&event->remove);
	}

	return 0;
}

static void cgroup_event_ptable_queue_proc(struct file *file,
		wait_queue_head_t *wqh, poll_table *pt)
{
	struct cgroup_event *event = container_of(pt,
			struct cgroup_event, pt);

	event->wqh = wqh;
	add_wait_queue(wqh, &event->wait);
}

/*
 * Parse input and register new cgroup event handler.
 *
 * Input must be in format '<event_fd> <control_fd> <args>'.
 * Interpretation of args is defined by control file implementation.
 */
static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft,
				      const char *buffer)
{
	struct cgroup_event *event = NULL;
	unsigned int efd, cfd;
	struct file *efile = NULL;
	struct file *cfile = NULL;
	char *endp;
	int ret;

	efd = simple_strtoul(buffer, &endp, 10);
	if (*endp != ' ')
		return -EINVAL;
	buffer = endp + 1;

	cfd = simple_strtoul(buffer, &endp, 10);
	if ((*endp != ' ') && (*endp != '\0'))
		return -EINVAL;
	buffer = endp + 1;

	event = kzalloc(sizeof(*event), GFP_KERNEL);
	if (!event)
		return -ENOMEM;
	event->cgrp = cgrp;
	INIT_LIST_HEAD(&event->list);
	init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc);
	init_waitqueue_func_entry(&event->wait, cgroup_event_wake);
	INIT_WORK(&event->remove, cgroup_event_remove);

	efile = eventfd_fget(efd);
	if (IS_ERR(efile)) {
		ret = PTR_ERR(efile);
		goto fail;
	}

	event->eventfd = eventfd_ctx_fileget(efile);
	if (IS_ERR(event->eventfd)) {
		ret = PTR_ERR(event->eventfd);
		goto fail;
	}

	cfile = fget(cfd);
	if (!cfile) {
		ret = -EBADF;
		goto fail;
	}

	/* the process need read permission on control file */
	ret = file_permission(cfile, MAY_READ);
	if (ret < 0)
		goto fail;

	event->cft = __file_cft(cfile);
	if (IS_ERR(event->cft)) {
		ret = PTR_ERR(event->cft);
		goto fail;
	}

	if (!event->cft->register_event || !event->cft->unregister_event) {
		ret = -EINVAL;
		goto fail;
	}

	ret = event->cft->register_event(cgrp, event->cft,
			event->eventfd, buffer);
	if (ret)
		goto fail;

	if (efile->f_op->poll(efile, &event->pt) & POLLHUP) {
		event->cft->unregister_event(cgrp, event->cft, event->eventfd);
		ret = 0;
		goto fail;
	}

	/*
	 * Events should be removed after rmdir of cgroup directory, but before
	 * destroying subsystem state objects. Let's take reference to cgroup
	 * directory dentry to do that.
	 */
	dget(cgrp->dentry);

	spin_lock(&cgrp->event_list_lock);
	list_add(&event->list, &cgrp->event_list);
	spin_unlock(&cgrp->event_list_lock);

	fput(cfile);
	fput(efile);

	return 0;

fail:
	if (cfile)
		fput(cfile);

	if (event && event->eventfd && !IS_ERR(event->eventfd))
		eventfd_ctx_put(event->eventfd);

	if (!IS_ERR_OR_NULL(efile))
		fput(efile);

	kfree(event);

	return ret;
}

/*
 * for the common functions, 'private' gives the type of file
 */
/* for hysterical raisins, we can't put this on the older files */
#define CGROUP_FILE_GENERIC_PREFIX "cgroup."
static struct cftype files[] = {
	{
		.name = "tasks",
		.open = cgroup_tasks_open,
		.write_u64 = cgroup_tasks_write,
		.release = cgroup_pidlist_release,
		.mode = S_IRUGO | S_IWUSR,
	},
	{
		.name = CGROUP_FILE_GENERIC_PREFIX "procs",
		.open = cgroup_procs_open,
		/* .write_u64 = cgroup_procs_write, TODO */
		.release = cgroup_pidlist_release,
		.mode = S_IRUGO,
	},
	{
		.name = "notify_on_release",
		.read_u64 = cgroup_read_notify_on_release,
		.write_u64 = cgroup_write_notify_on_release,
	},
	{
		.name = CGROUP_FILE_GENERIC_PREFIX "event_control",
		.write_string = cgroup_write_event_control,
		.mode = S_IWUGO,
	},
};

static struct cftype cft_release_agent = {
	.name = "release_agent",
	.read_seq_string = cgroup_release_agent_show,
	.write_string = cgroup_release_agent_write,
	.max_write_len = PATH_MAX,
};

static int cgroup_populate_dir(struct cgroup *cgrp)
{
	int err;
	struct cgroup_subsys *ss;

	/* First clear out any existing files */
	cgroup_clear_directory(cgrp->dentry);

	err = cgroup_add_files(cgrp, NULL, files, ARRAY_SIZE(files));
	if (err < 0)
		return err;

	if (cgrp == cgrp->top_cgroup) {
		if ((err = cgroup_add_file(cgrp, NULL, &cft_release_agent)) < 0)
			return err;
	}

	for_each_subsys(cgrp->root, ss) {
		if (ss->populate && (err = ss->populate(ss, cgrp)) < 0)
			return err;
	}
	/* This cgroup is ready now */
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
		/*
		 * Update id->css pointer and make this css visible from
		 * CSS ID functions. This pointer will be dereferened
		 * from RCU-read-side without locks.
		 */
		if (css->id)
			rcu_assign_pointer(css->id->css, css);
	}

	return 0;
}

static void init_cgroup_css(struct cgroup_subsys_state *css,
			       struct cgroup_subsys *ss,
			       struct cgroup *cgrp)
{
	css->cgroup = cgrp;
	atomic_set(&css->refcnt, 1);
	css->flags = 0;
	css->id = NULL;
	if (cgrp == dummytop)
		set_bit(CSS_ROOT, &css->flags);
	BUG_ON(cgrp->subsys[ss->subsys_id]);
	cgrp->subsys[ss->subsys_id] = css;
}

static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
{
	/* We need to take each hierarchy_mutex in a consistent order */
	int i;

	/*
	 * No worry about a race with rebind_subsystems that might mess up the
	 * locking order, since both parties are under cgroup_mutex.
	 */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (ss == NULL)
			continue;
		if (ss->root == root)
			mutex_lock(&ss->hierarchy_mutex);
	}
}

static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
{
	int i;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (ss == NULL)
			continue;
		if (ss->root == root)
			mutex_unlock(&ss->hierarchy_mutex);
	}
}

/*
 * cgroup_create - create a cgroup
 * @parent: cgroup that will be parent of the new cgroup
 * @dentry: dentry of the new cgroup
 * @mode: mode to set on new inode
 *
 * Must be called with the mutex on the parent inode held
 */
static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
			     mode_t mode)
{
	struct cgroup *cgrp;
	struct cgroupfs_root *root = parent->root;
	int err = 0;
	struct cgroup_subsys *ss;
	struct super_block *sb = root->sb;

	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
	if (!cgrp)
		return -ENOMEM;

	/* Grab a reference on the superblock so the hierarchy doesn't
	 * get deleted on unmount if there are child cgroups.  This
	 * can be done outside cgroup_mutex, since the sb can't
	 * disappear while someone has an open control file on the
	 * fs */
	atomic_inc(&sb->s_active);

	mutex_lock(&cgroup_mutex);

	init_cgroup_housekeeping(cgrp);

	cgrp->parent = parent;
	cgrp->root = parent->root;
	cgrp->top_cgroup = parent->top_cgroup;

	if (notify_on_release(parent))
		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);

	for_each_subsys(root, ss) {
		struct cgroup_subsys_state *css = ss->create(ss, cgrp);

		if (IS_ERR(css)) {
			err = PTR_ERR(css);
			goto err_destroy;
		}
		init_cgroup_css(css, ss, cgrp);
		if (ss->use_id) {
			err = alloc_css_id(ss, parent, cgrp);
			if (err)
				goto err_destroy;
		}
		/* At error, ->destroy() callback has to free assigned ID. */
	}

	cgroup_lock_hierarchy(root);
	list_add(&cgrp->sibling, &cgrp->parent->children);
	cgroup_unlock_hierarchy(root);
	root->number_of_cgroups++;

	err = cgroup_create_dir(cgrp, dentry, mode);
	if (err < 0)
		goto err_remove;

	/* The cgroup directory was pre-locked for us */
	BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));

	err = cgroup_populate_dir(cgrp);
	/* If err < 0, we have a half-filled directory - oh well ;) */

	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);

	return 0;

 err_remove:

	cgroup_lock_hierarchy(root);
	list_del(&cgrp->sibling);
	cgroup_unlock_hierarchy(root);
	root->number_of_cgroups--;

 err_destroy:

	for_each_subsys(root, ss) {
		if (cgrp->subsys[ss->subsys_id])
			ss->destroy(ss, cgrp);
	}

	mutex_unlock(&cgroup_mutex);

	/* Release the reference count that we took on the superblock */
	deactivate_super(sb);

	kfree(cgrp);
	return err;
}

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	struct cgroup *c_parent = dentry->d_parent->d_fsdata;

	/* the vfs holds inode->i_mutex already */
	return cgroup_create(c_parent, dentry, mode | S_IFDIR);
}

static int cgroup_has_css_refs(struct cgroup *cgrp)
{
	/* Check the reference count on each subsystem. Since we
	 * already established that there are no tasks in the
	 * cgroup, if the css refcount is also 1, then there should
	 * be no outstanding references, so the subsystem is safe to
	 * destroy. We scan across all subsystems rather than using
	 * the per-hierarchy linked list of mounted subsystems since
	 * we can be called via check_for_release() with no
	 * synchronization other than RCU, and the subsystem linked
	 * list isn't RCU-safe */
	int i;
	/*
	 * We won't need to lock the subsys array, because the subsystems
	 * we're concerned about aren't going anywhere since our cgroup root
	 * has a reference on them.
	 */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		struct cgroup_subsys_state *css;
		/* Skip subsystems not present or not in this hierarchy */
		if (ss == NULL || ss->root != cgrp->root)
			continue;
		css = cgrp->subsys[ss->subsys_id];
		/* When called from check_for_release() it's possible
		 * that by this point the cgroup has been removed
		 * and the css deleted. But a false-positive doesn't
		 * matter, since it can only happen if the cgroup
		 * has been deleted and hence no longer needs the
		 * release agent to be called anyway. */
		if (css && (atomic_read(&css->refcnt) > 1))
			return 1;
	}
	return 0;
}

/*
 * Atomically mark all (or else none) of the cgroup's CSS objects as
 * CSS_REMOVED. Return true on success, or false if the cgroup has
 * busy subsystems. Call with cgroup_mutex held
 */

static int cgroup_clear_css_refs(struct cgroup *cgrp)
{
	struct cgroup_subsys *ss;
	unsigned long flags;
	bool failed = false;
	local_irq_save(flags);
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
		int refcnt;
		while (1) {
			/* We can only remove a CSS with a refcnt==1 */
			refcnt = atomic_read(&css->refcnt);
			if (refcnt > 1) {
				failed = true;
				goto done;
			}
			BUG_ON(!refcnt);
			/*
			 * Drop the refcnt to 0 while we check other
			 * subsystems. This will cause any racing
			 * css_tryget() to spin until we set the
			 * CSS_REMOVED bits or abort
			 */
			if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt)
				break;
			cpu_relax();
		}
	}
 done:
	for_each_subsys(cgrp->root, ss) {
		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
		if (failed) {
			/*
			 * Restore old refcnt if we previously managed
			 * to clear it from 1 to 0
			 */
			if (!atomic_read(&css->refcnt))
				atomic_set(&css->refcnt, 1);
		} else {
			/* Commit the fact that the CSS is removed */
			set_bit(CSS_REMOVED, &css->flags);
		}
	}
	local_irq_restore(flags);
	return !failed;
}

static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
	struct cgroup *cgrp = dentry->d_fsdata;
	struct dentry *d;
	struct cgroup *parent;
	DEFINE_WAIT(wait);
	struct cgroup_event *event, *tmp;
	int ret;

	/* the vfs holds both inode->i_mutex already */
again:
	mutex_lock(&cgroup_mutex);
	if (atomic_read(&cgrp->count) != 0) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	if (!list_empty(&cgrp->children)) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	mutex_unlock(&cgroup_mutex);

	/*
	 * In general, subsystem has no css->refcnt after pre_destroy(). But
	 * in racy cases, subsystem may have to get css->refcnt after
	 * pre_destroy() and it makes rmdir return with -EBUSY. This sometimes
	 * make rmdir return -EBUSY too often. To avoid that, we use waitqueue
	 * for cgroup's rmdir. CGRP_WAIT_ON_RMDIR is for synchronizing rmdir
	 * and subsystem's reference count handling. Please see css_get/put
	 * and css_tryget() and cgroup_wakeup_rmdir_waiter() implementation.
	 */
	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);

	/*
	 * Call pre_destroy handlers of subsys. Notify subsystems
	 * that rmdir() request comes.
	 */
	ret = cgroup_call_pre_destroy(cgrp);
	if (ret) {
		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
		return ret;
	}

	mutex_lock(&cgroup_mutex);
	parent = cgrp->parent;
	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
	if (!cgroup_clear_css_refs(cgrp)) {
		mutex_unlock(&cgroup_mutex);
		/*
		 * Because someone may call cgroup_wakeup_rmdir_waiter() before
		 * prepare_to_wait(), we need to check this flag.
		 */
		if (test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags))
			schedule();
		finish_wait(&cgroup_rmdir_waitq, &wait);
		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
		if (signal_pending(current))
			return -EINTR;
		goto again;
	}
	/* NO css_tryget() can success after here. */
	finish_wait(&cgroup_rmdir_waitq, &wait);
	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);

	spin_lock(&release_list_lock);
	set_bit(CGRP_REMOVED, &cgrp->flags);
	if (!list_empty(&cgrp->release_list))
		list_del(&cgrp->release_list);
	spin_unlock(&release_list_lock);

	cgroup_lock_hierarchy(cgrp->root);
	/* delete this cgroup from parent->children */
	list_del(&cgrp->sibling);
	cgroup_unlock_hierarchy(cgrp->root);

	spin_lock(&cgrp->dentry->d_lock);
	d = dget(cgrp->dentry);
	spin_unlock(&d->d_lock);

	cgroup_d_remove_dir(d);
	dput(d);

	set_bit(CGRP_RELEASABLE, &parent->flags);
	check_for_release(parent);

	/*
	 * Unregister events and notify userspace.
	 * Notify userspace about cgroup removing only after rmdir of cgroup
	 * directory to avoid race between userspace and kernelspace
	 */
	spin_lock(&cgrp->event_list_lock);
	list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
		list_del(&event->list);
		remove_wait_queue(event->wqh, &event->wait);
		eventfd_signal(event->eventfd, 1);
		schedule_work(&event->remove);
	}
	spin_unlock(&cgrp->event_list_lock);

	mutex_unlock(&cgroup_mutex);
	return 0;
}

static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
{
	struct cgroup_subsys_state *css;

	printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);

	/* Create the top cgroup state for this subsystem */
	list_add(&ss->sibling, &rootnode.subsys_list);
	ss->root = &rootnode;
	css = ss->create(ss, dummytop);
	/* We don't handle early failures gracefully */
	BUG_ON(IS_ERR(css));
	init_cgroup_css(css, ss, dummytop);

	/* Update the init_css_set to contain a subsys
	 * pointer to this state - since the subsystem is
	 * newly registered, all tasks and hence the
	 * init_css_set is in the subsystem's top cgroup. */
	init_css_set.subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id];

	need_forkexit_callback |= ss->fork || ss->exit;

	/* At system boot, before all subsystems have been
	 * registered, no tasks have been forked, so we don't
	 * need to invoke fork callbacks here. */
	BUG_ON(!list_empty(&init_task.tasks));

	mutex_init(&ss->hierarchy_mutex);
	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
	ss->active = 1;

	/* this function shouldn't be used with modular subsystems, since they
	 * need to register a subsys_id, among other things */
	BUG_ON(ss->module);
}

/**
 * cgroup_load_subsys: load and register a modular subsystem at runtime
 * @ss: the subsystem to load
 *
 * This function should be called in a modular subsystem's initcall. If the
 * subsystem is built as a module, it will be assigned a new subsys_id and set
 * up for use. If the subsystem is built-in anyway, work is delegated to the
 * simpler cgroup_init_subsys.
 */
int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
{
	int i;
	struct cgroup_subsys_state *css;

	/* check name and function validity */
	if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
	    ss->create == NULL || ss->destroy == NULL)
		return -EINVAL;

	/*
	 * we don't support callbacks in modular subsystems. this check is
	 * before the ss->module check for consistency; a subsystem that could
	 * be a module should still have no callbacks even if the user isn't
	 * compiling it as one.
	 */
	if (ss->fork || ss->exit)
		return -EINVAL;

	/*
	 * an optionally modular subsystem is built-in: we want to do nothing,
	 * since cgroup_init_subsys will have already taken care of it.
	 */
	if (ss->module == NULL) {
		/* a few sanity checks */
		BUG_ON(ss->subsys_id >= CGROUP_BUILTIN_SUBSYS_COUNT);
		BUG_ON(subsys[ss->subsys_id] != ss);
		return 0;
	}

	/*
	 * need to register a subsys id before anything else - for example,
	 * init_cgroup_css needs it.
	 */
	mutex_lock(&cgroup_mutex);
	/* find the first empty slot in the array */
	for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
		if (subsys[i] == NULL)
			break;
	}
	if (i == CGROUP_SUBSYS_COUNT) {
		/* maximum number of subsystems already registered! */
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	/* assign ourselves the subsys_id */
	ss->subsys_id = i;
	subsys[i] = ss;

	/*
	 * no ss->create seems to need anything important in the ss struct, so
	 * this can happen first (i.e. before the rootnode attachment).
	 */
	css = ss->create(ss, dummytop);
	if (IS_ERR(css)) {
		/* failure case - need to deassign the subsys[] slot. */
		subsys[i] = NULL;
		mutex_unlock(&cgroup_mutex);
		return PTR_ERR(css);
	}

	list_add(&ss->sibling, &rootnode.subsys_list);
	ss->root = &rootnode;

	/* our new subsystem will be attached to the dummy hierarchy. */
	init_cgroup_css(css, ss, dummytop);
	/* init_idr must be after init_cgroup_css because it sets css->id. */
	if (ss->use_id) {
		int ret = cgroup_init_idr(ss, css);
		if (ret) {
			dummytop->subsys[ss->subsys_id] = NULL;
			ss->destroy(ss, dummytop);
			subsys[i] = NULL;
			mutex_unlock(&cgroup_mutex);
			return ret;
		}
	}

	/*
	 * Now we need to entangle the css into the existing css_sets. unlike
	 * in cgroup_init_subsys, there are now multiple css_sets, so each one
	 * will need a new pointer to it; done by iterating the css_set_table.
	 * furthermore, modifying the existing css_sets will corrupt the hash
	 * table state, so each changed css_set will need its hash recomputed.
	 * this is all done under the css_set_lock.
	 */
	write_lock(&css_set_lock);
	for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
		struct css_set *cg;
		struct hlist_node *node, *tmp;
		struct hlist_head *bucket = &css_set_table[i], *new_bucket;

		hlist_for_each_entry_safe(cg, node, tmp, bucket, hlist) {
			/* skip entries that we already rehashed */
			if (cg->subsys[ss->subsys_id])
				continue;
			/* remove existing entry */
			hlist_del(&cg->hlist);
			/* set new value */
			cg->subsys[ss->subsys_id] = css;
			/* recompute hash and restore entry */
			new_bucket = css_set_hash(cg->subsys);
			hlist_add_head(&cg->hlist, new_bucket);
		}
	}
	write_unlock(&css_set_lock);

	mutex_init(&ss->hierarchy_mutex);
	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
	ss->active = 1;

	/* success! */
	mutex_unlock(&cgroup_mutex);
	return 0;
}
EXPORT_SYMBOL_GPL(cgroup_load_subsys);

/**
 * cgroup_unload_subsys: unload a modular subsystem
 * @ss: the subsystem to unload
 *
 * This function should be called in a modular subsystem's exitcall. When this
 * function is invoked, the refcount on the subsystem's module will be 0, so
 * the subsystem will not be attached to any hierarchy.
 */
void cgroup_unload_subsys(struct cgroup_subsys *ss)
{
	struct cg_cgroup_link *link;
	struct hlist_head *hhead;

	BUG_ON(ss->module == NULL);

	/*
	 * we shouldn't be called if the subsystem is in use, and the use of
	 * try_module_get in parse_cgroupfs_options should ensure that it
	 * doesn't start being used while we're killing it off.
	 */
	BUG_ON(ss->root != &rootnode);

	mutex_lock(&cgroup_mutex);
	/* deassign the subsys_id */
	BUG_ON(ss->subsys_id < CGROUP_BUILTIN_SUBSYS_COUNT);
	subsys[ss->subsys_id] = NULL;

	/* remove subsystem from rootnode's list of subsystems */
	list_del(&ss->sibling);

	/*
	 * disentangle the css from all css_sets attached to the dummytop. as
	 * in loading, we need to pay our respects to the hashtable gods.
	 */
	write_lock(&css_set_lock);
	list_for_each_entry(link, &dummytop->css_sets, cgrp_link_list) {
		struct css_set *cg = link->cg;

		hlist_del(&cg->hlist);
		BUG_ON(!cg->subsys[ss->subsys_id]);
		cg->subsys[ss->subsys_id] = NULL;
		hhead = css_set_hash(cg->subsys);
		hlist_add_head(&cg->hlist, hhead);
	}
	write_unlock(&css_set_lock);

	/*
	 * remove subsystem's css from the dummytop and free it - need to free
	 * before marking as null because ss->destroy needs the cgrp->subsys
	 * pointer to find their state. note that this also takes care of
	 * freeing the css_id.
	 */
	ss->destroy(ss, dummytop);
	dummytop->subsys[ss->subsys_id] = NULL;

	mutex_unlock(&cgroup_mutex);
}
EXPORT_SYMBOL_GPL(cgroup_unload_subsys);

/**
 * cgroup_init_early - cgroup initialization at system boot
 *
 * Initialize cgroups at system boot, and initialize any
 * subsystems that request early init.
 */
int __init cgroup_init_early(void)
{
	int i;
	atomic_set(&init_css_set.refcount, 1);
	INIT_LIST_HEAD(&init_css_set.cg_links);
	INIT_LIST_HEAD(&init_css_set.tasks);
	INIT_HLIST_NODE(&init_css_set.hlist);
	css_set_count = 1;
	init_cgroup_root(&rootnode);
	root_count = 1;
	init_task.cgroups = &init_css_set;

	init_css_set_link.cg = &init_css_set;
	init_css_set_link.cgrp = dummytop;
	list_add(&init_css_set_link.cgrp_link_list,
		 &rootnode.top_cgroup.css_sets);
	list_add(&init_css_set_link.cg_link_list,
		 &init_css_set.cg_links);

	for (i = 0; i < CSS_SET_TABLE_SIZE; i++)
		INIT_HLIST_HEAD(&css_set_table[i]);

	/* at bootup time, we don't worry about modular subsystems */
	for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];

		BUG_ON(!ss->name);
		BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
		BUG_ON(!ss->create);
		BUG_ON(!ss->destroy);
		if (ss->subsys_id != i) {
			printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
			       ss->name, ss->subsys_id);
			BUG();
		}

		if (ss->early_init)
			cgroup_init_subsys(ss);
	}
	return 0;
}

/**
 * cgroup_init - cgroup initialization
 *
 * Register cgroup filesystem and /proc file, and initialize
 * any subsystems that didn't request early init.
 */
int __init cgroup_init(void)
{
	int err;
	int i;
	struct hlist_head *hhead;

	err = bdi_init(&cgroup_backing_dev_info);
	if (err)
		return err;

	/* at bootup time, we don't worry about modular subsystems */
	for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (!ss->early_init)
			cgroup_init_subsys(ss);
		if (ss->use_id)
			cgroup_init_idr(ss, init_css_set.subsys[ss->subsys_id]);
	}

	/* Add init_css_set to the hash table */
	hhead = css_set_hash(init_css_set.subsys);
	hlist_add_head(&init_css_set.hlist, hhead);
	BUG_ON(!init_root_id(&rootnode));
	err = register_filesystem(&cgroup_fs_type);
	if (err < 0)
		goto out;

	proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);

out:
	if (err)
		bdi_destroy(&cgroup_backing_dev_info);

	return err;
}

/*
 * proc_cgroup_show()
 *  - Print task's cgroup paths into seq_file, one line for each hierarchy
 *  - Used for /proc/<pid>/cgroup.
 *  - No need to task_lock(tsk) on this tsk->cgroup reference, as it
 *    doesn't really matter if tsk->cgroup changes after we read it,
 *    and we take cgroup_mutex, keeping cgroup_attach_task() from changing it
 *    anyway.  No need to check that tsk->cgroup != NULL, thanks to
 *    the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks
 *    cgroup to top_cgroup.
 */

/* TODO: Use a proper seq_file iterator */
static int proc_cgroup_show(struct seq_file *m, void *v)
{
	struct pid *pid;
	struct task_struct *tsk;
	char *buf;
	int retval;
	struct cgroupfs_root *root;

	retval = -ENOMEM;
	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!buf)
		goto out;

	retval = -ESRCH;
	pid = m->private;
	tsk = get_pid_task(pid, PIDTYPE_PID);
	if (!tsk)
		goto out_free;

	retval = 0;

	mutex_lock(&cgroup_mutex);

	for_each_active_root(root) {
		struct cgroup_subsys *ss;
		struct cgroup *cgrp;
		int count = 0;

		seq_printf(m, "%d:", root->hierarchy_id);
		for_each_subsys(root, ss)
			seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
		if (strlen(root->name))
			seq_printf(m, "%sname=%s", count ? "," : "",
				   root->name);
		seq_putc(m, ':');
		cgrp = task_cgroup_from_root(tsk, root);
		retval = cgroup_path(cgrp, buf, PAGE_SIZE);
		if (retval < 0)
			goto out_unlock;
		seq_puts(m, buf);
		seq_putc(m, '\n');
	}

out_unlock:
	mutex_unlock(&cgroup_mutex);
	put_task_struct(tsk);
out_free:
	kfree(buf);
out:
	return retval;
}

static int cgroup_open(struct inode *inode, struct file *file)
{
	struct pid *pid = PROC_I(inode)->pid;
	return single_open(file, proc_cgroup_show, pid);
}

const struct file_operations proc_cgroup_operations = {
	.open		= cgroup_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

/* Display information about each subsystem and each hierarchy */
static int proc_cgroupstats_show(struct seq_file *m, void *v)
{
	int i;

	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
	/*
	 * ideally we don't want subsystems moving around while we do this.
	 * cgroup_mutex is also necessary to guarantee an atomic snapshot of
	 * subsys/hierarchy state.
	 */
	mutex_lock(&cgroup_mutex);
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (ss == NULL)
			continue;
		seq_printf(m, "%s\t%d\t%d\t%d\n",
			   ss->name, ss->root->hierarchy_id,
			   ss->root->number_of_cgroups, !ss->disabled);
	}
	mutex_unlock(&cgroup_mutex);
	return 0;
}

static int cgroupstats_open(struct inode *inode, struct file *file)
{
	return single_open(file, proc_cgroupstats_show, NULL);
}

static const struct file_operations proc_cgroupstats_operations = {
	.open = cgroupstats_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

/**
 * cgroup_fork - attach newly forked task to its parents cgroup.
 * @child: pointer to task_struct of forking parent process.
 *
 * Description: A task inherits its parent's cgroup at fork().
 *
 * A pointer to the shared css_set was automatically copied in
 * fork.c by dup_task_struct().  However, we ignore that copy, since
 * it was not made under the protection of RCU or cgroup_mutex, so
 * might no longer be a valid cgroup pointer.  cgroup_attach_task() might
 * have already changed current->cgroups, allowing the previously
 * referenced cgroup group to be removed and freed.
 *
 * At the point that cgroup_fork() is called, 'current' is the parent
 * task, and the passed argument 'child' points to the child task.
 */
void cgroup_fork(struct task_struct *child)
{
	task_lock(current);
	child->cgroups = current->cgroups;
	get_css_set(child->cgroups);
	task_unlock(current);
	INIT_LIST_HEAD(&child->cg_list);
}

/**
 * cgroup_fork_callbacks - run fork callbacks
 * @child: the new task
 *
 * Called on a new task very soon before adding it to the
 * tasklist. No need to take any locks since no-one can
 * be operating on this task.
 */
void cgroup_fork_callbacks(struct task_struct *child)
{
	if (need_forkexit_callback) {
		int i;
		/*
		 * forkexit callbacks are only supported for builtin
		 * subsystems, and the builtin section of the subsys array is
		 * immutable, so we don't need to lock the subsys array here.
		 */
		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];
			if (ss->fork)
				ss->fork(ss, child);
		}
	}
}

/**
 * cgroup_post_fork - called on a new task after adding it to the task list
 * @child: the task in question
 *
 * Adds the task to the list running through its css_set if necessary.
 * Has to be after the task is visible on the task list in case we race
 * with the first call to cgroup_iter_start() - to guarantee that the
 * new task ends up on its list.
 */
void cgroup_post_fork(struct task_struct *child)
{
	if (use_task_css_set_links) {
		write_lock(&css_set_lock);
		task_lock(child);
		if (list_empty(&child->cg_list))
			list_add(&child->cg_list, &child->cgroups->tasks);
		task_unlock(child);
		write_unlock(&css_set_lock);
	}
}
/**
 * cgroup_exit - detach cgroup from exiting task
 * @tsk: pointer to task_struct of exiting process
 * @run_callback: run exit callbacks?
 *
 * Description: Detach cgroup from @tsk and release it.
 *
 * Note that cgroups marked notify_on_release force every task in
 * them to take the global cgroup_mutex mutex when exiting.
 * This could impact scaling on very large systems.  Be reluctant to
 * use notify_on_release cgroups where very high task exit scaling
 * is required on large systems.
 *
 * the_top_cgroup_hack:
 *
 *    Set the exiting tasks cgroup to the root cgroup (top_cgroup).
 *
 *    We call cgroup_exit() while the task is still competent to
 *    handle notify_on_release(), then leave the task attached to the
 *    root cgroup in each hierarchy for the remainder of its exit.
 *
 *    To do this properly, we would increment the reference count on
 *    top_cgroup, and near the very end of the kernel/exit.c do_exit()
 *    code we would add a second cgroup function call, to drop that
 *    reference.  This would just create an unnecessary hot spot on
 *    the top_cgroup reference count, to no avail.
 *
 *    Normally, holding a reference to a cgroup without bumping its
 *    count is unsafe.   The cgroup could go away, or someone could
 *    attach us to a different cgroup, decrementing the count on
 *    the first cgroup that we never incremented.  But in this case,
 *    top_cgroup isn't going away, and either task has PF_EXITING set,
 *    which wards off any cgroup_attach_task() attempts, or task is a failed
 *    fork, never visible to cgroup_attach_task.
 */
void cgroup_exit(struct task_struct *tsk, int run_callbacks)
{
	int i;
	struct css_set *cg;

	if (run_callbacks && need_forkexit_callback) {
		/*
		 * modular subsystems can't use callbacks, so no need to lock
		 * the subsys array
		 */
		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];
			if (ss->exit)
				ss->exit(ss, tsk);
		}
	}

	/*
	 * Unlink from the css_set task list if necessary.
	 * Optimistically check cg_list before taking
	 * css_set_lock
	 */
	if (!list_empty(&tsk->cg_list)) {
		write_lock(&css_set_lock);
		if (!list_empty(&tsk->cg_list))
			list_del(&tsk->cg_list);
		write_unlock(&css_set_lock);
	}

	/* Reassign the task to the init_css_set. */
	task_lock(tsk);
	cg = tsk->cgroups;
	tsk->cgroups = &init_css_set;
	task_unlock(tsk);
	if (cg)
		put_css_set_taskexit(cg);
}

/**
 * cgroup_clone - clone the cgroup the given subsystem is attached to
 * @tsk: the task to be moved
 * @subsys: the given subsystem
 * @nodename: the name for the new cgroup
 *
 * Duplicate the current cgroup in the hierarchy that the given
 * subsystem is attached to, and move this task into the new
 * child.
 */
int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
							char *nodename)
{
	struct dentry *dentry;
	int ret = 0;
	struct cgroup *parent, *child;
	struct inode *inode;
	struct css_set *cg;
	struct cgroupfs_root *root;
	struct cgroup_subsys *ss;

	/* We shouldn't be called by an unregistered subsystem */
	BUG_ON(!subsys->active);

	/* First figure out what hierarchy and cgroup we're dealing
	 * with, and pin them so we can drop cgroup_mutex */
	mutex_lock(&cgroup_mutex);
 again:
	root = subsys->root;
	if (root == &rootnode) {
		mutex_unlock(&cgroup_mutex);
		return 0;
	}

	/* Pin the hierarchy */
	if (!atomic_inc_not_zero(&root->sb->s_active)) {
		/* We race with the final deactivate_super() */
		mutex_unlock(&cgroup_mutex);
		return 0;
	}

	/* Keep the cgroup alive */
	task_lock(tsk);
	parent = task_cgroup(tsk, subsys->subsys_id);
	cg = tsk->cgroups;
	get_css_set(cg);
	task_unlock(tsk);

	mutex_unlock(&cgroup_mutex);

	/* Now do the VFS work to create a cgroup */
	inode = parent->dentry->d_inode;

	/* Hold the parent directory mutex across this operation to
	 * stop anyone else deleting the new cgroup */
	mutex_lock(&inode->i_mutex);
	dentry = lookup_one_len(nodename, parent->dentry, strlen(nodename));
	if (IS_ERR(dentry)) {
		printk(KERN_INFO
		       "cgroup: Couldn't allocate dentry for %s: %ld\n", nodename,
		       PTR_ERR(dentry));
		ret = PTR_ERR(dentry);
		goto out_release;
	}

	/* Create the cgroup directory, which also creates the cgroup */
	ret = vfs_mkdir(inode, dentry, 0755);
	child = __d_cgrp(dentry);
	dput(dentry);
	if (ret) {
		printk(KERN_INFO
		       "Failed to create cgroup %s: %d\n", nodename,
		       ret);
		goto out_release;
	}

	/* The cgroup now exists. Retake cgroup_mutex and check
	 * that we're still in the same state that we thought we
	 * were. */
	mutex_lock(&cgroup_mutex);
	if ((root != subsys->root) ||
	    (parent != task_cgroup(tsk, subsys->subsys_id))) {
		/* Aargh, we raced ... */
		mutex_unlock(&inode->i_mutex);
		put_css_set(cg);

		deactivate_super(root->sb);
		/* The cgroup is still accessible in the VFS, but
		 * we're not going to try to rmdir() it at this
		 * point. */
		printk(KERN_INFO
		       "Race in cgroup_clone() - leaking cgroup %s\n",
		       nodename);
		goto again;
	}

	/* do any required auto-setup */
	for_each_subsys(root, ss) {
		if (ss->post_clone)
			ss->post_clone(ss, child);
	}

	/* All seems fine. Finish by moving the task into the new cgroup */
	ret = cgroup_attach_task(child, tsk);
	mutex_unlock(&cgroup_mutex);

 out_release:
	mutex_unlock(&inode->i_mutex);

	mutex_lock(&cgroup_mutex);
	put_css_set(cg);
	mutex_unlock(&cgroup_mutex);
	deactivate_super(root->sb);
	return ret;
}

/**
 * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
 * @cgrp: the cgroup in question
 * @task: the task in question
 *
 * See if @cgrp is a descendant of @task's cgroup in the appropriate
 * hierarchy.
 *
 * If we are sending in dummytop, then presumably we are creating
 * the top cgroup in the subsystem.
 *
 * Called only by the ns (nsproxy) cgroup.
 */
int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
{
	int ret;
	struct cgroup *target;

	if (cgrp == dummytop)
		return 1;

	target = task_cgroup_from_root(task, cgrp->root);
	while (cgrp != target && cgrp!= cgrp->top_cgroup)
		cgrp = cgrp->parent;
	ret = (cgrp == target);
	return ret;
}

static void check_for_release(struct cgroup *cgrp)
{
	/* All of these checks rely on RCU to keep the cgroup
	 * structure alive */
	if (cgroup_is_releasable(cgrp) && !atomic_read(&cgrp->count)
	    && list_empty(&cgrp->children) && !cgroup_has_css_refs(cgrp)) {
		/* Control Group is currently removeable. If it's not
		 * already queued for a userspace notification, queue
		 * it now */
		int need_schedule_work = 0;
		spin_lock(&release_list_lock);
		if (!cgroup_is_removed(cgrp) &&
		    list_empty(&cgrp->release_list)) {
			list_add(&cgrp->release_list, &release_list);
			need_schedule_work = 1;
		}
		spin_unlock(&release_list_lock);
		if (need_schedule_work)
			schedule_work(&release_agent_work);
	}
}

/* Caller must verify that the css is not for root cgroup */
void __css_put(struct cgroup_subsys_state *css, int count)
{
	struct cgroup *cgrp = css->cgroup;
	int val;
	rcu_read_lock();
	val = atomic_sub_return(count, &css->refcnt);
	if (val == 1) {
		if (notify_on_release(cgrp)) {
			set_bit(CGRP_RELEASABLE, &cgrp->flags);
			check_for_release(cgrp);
		}
		cgroup_wakeup_rmdir_waiter(cgrp);
	}
	rcu_read_unlock();
	WARN_ON_ONCE(val < 1);
}
EXPORT_SYMBOL_GPL(__css_put);

/*
 * Notify userspace when a cgroup is released, by running the
 * configured release agent with the name of the cgroup (path
 * relative to the root of cgroup file system) as the argument.
 *
 * Most likely, this user command will try to rmdir this cgroup.
 *
 * This races with the possibility that some other task will be
 * attached to this cgroup before it is removed, or that some other
 * user task will 'mkdir' a child cgroup of this cgroup.  That's ok.
 * The presumed 'rmdir' will fail quietly if this cgroup is no longer
 * unused, and this cgroup will be reprieved from its death sentence,
 * to continue to serve a useful existence.  Next time it's released,
 * we will get notified again, if it still has 'notify_on_release' set.
 *
 * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which
 * means only wait until the task is successfully execve()'d.  The
 * separate release agent task is forked by call_usermodehelper(),
 * then control in this thread returns here, without waiting for the
 * release agent task.  We don't bother to wait because the caller of
 * this routine has no use for the exit status of the release agent
 * task, so no sense holding our caller up for that.
 */
static void cgroup_release_agent(struct work_struct *work)
{
	BUG_ON(work != &release_agent_work);
	mutex_lock(&cgroup_mutex);
	spin_lock(&release_list_lock);
	while (!list_empty(&release_list)) {
		char *argv[3], *envp[3];
		int i;
		char *pathbuf = NULL, *agentbuf = NULL;
		struct cgroup *cgrp = list_entry(release_list.next,
						    struct cgroup,
						    release_list);
		list_del_init(&cgrp->release_list);
		spin_unlock(&release_list_lock);
		pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
		if (!pathbuf)
			goto continue_free;
		if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0)
			goto continue_free;
		agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
		if (!agentbuf)
			goto continue_free;

		i = 0;
		argv[i++] = agentbuf;
		argv[i++] = pathbuf;
		argv[i] = NULL;

		i = 0;
		/* minimal command environment */
		envp[i++] = "HOME=/";
		envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
		envp[i] = NULL;

		/* Drop the lock while we invoke the usermode helper,
		 * since the exec could involve hitting disk and hence
		 * be a slow process */
		mutex_unlock(&cgroup_mutex);
		call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
		mutex_lock(&cgroup_mutex);
 continue_free:
		kfree(pathbuf);
		kfree(agentbuf);
		spin_lock(&release_list_lock);
	}
	spin_unlock(&release_list_lock);
	mutex_unlock(&cgroup_mutex);
}

static int __init cgroup_disable(char *str)
{
	int i;
	char *token;

	while ((token = strsep(&str, ",")) != NULL) {
		if (!*token)
			continue;
		/*
		 * cgroup_disable, being at boot time, can't know about module
		 * subsystems, so we don't worry about them.
		 */
		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];

			if (!strcmp(token, ss->name)) {
				ss->disabled = 1;
				printk(KERN_INFO "Disabling %s control group"
					" subsystem\n", ss->name);
				break;
			}
		}
	}
	return 1;
}
__setup("cgroup_disable=", cgroup_disable);

/*
 * Functons for CSS ID.
 */

/*
 *To get ID other than 0, this should be called when !cgroup_is_removed().
 */
unsigned short css_id(struct cgroup_subsys_state *css)
{
	struct css_id *cssid;

	/*
	 * This css_id() can return correct value when somone has refcnt
	 * on this or this is under rcu_read_lock(). Once css->id is allocated,
	 * it's unchanged until freed.
	 */
	cssid = rcu_dereference_check(css->id,
			rcu_read_lock_held() || atomic_read(&css->refcnt));

	if (cssid)
		return cssid->id;
	return 0;
}
EXPORT_SYMBOL_GPL(css_id);

unsigned short css_depth(struct cgroup_subsys_state *css)
{
	struct css_id *cssid;

	cssid = rcu_dereference_check(css->id,
			rcu_read_lock_held() || atomic_read(&css->refcnt));

	if (cssid)
		return cssid->depth;
	return 0;
}
EXPORT_SYMBOL_GPL(css_depth);

/**
 *  css_is_ancestor - test "root" css is an ancestor of "child"
 * @child: the css to be tested.
 * @root: the css supporsed to be an ancestor of the child.
 *
 * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
 * this function reads css->id, this use rcu_dereference() and rcu_read_lock().
 * But, considering usual usage, the csses should be valid objects after test.
 * Assuming that the caller will do some action to the child if this returns
 * returns true, the caller must take "child";s reference count.
 * If "child" is valid object and this returns true, "root" is valid, too.
 */

bool css_is_ancestor(struct cgroup_subsys_state *child,
		    const struct cgroup_subsys_state *root)
{
	struct css_id *child_id;
	struct css_id *root_id;
	bool ret = true;

	rcu_read_lock();
	child_id  = rcu_dereference(child->id);
	root_id = rcu_dereference(root->id);
	if (!child_id
	    || !root_id
	    || (child_id->depth < root_id->depth)
	    || (child_id->stack[root_id->depth] != root_id->id))
		ret = false;
	rcu_read_unlock();
	return ret;
}

static void __free_css_id_cb(struct rcu_head *head)
{
	struct css_id *id;

	id = container_of(head, struct css_id, rcu_head);
	kfree(id);
}

void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
{
	struct css_id *id = css->id;
	/* When this is called before css_id initialization, id can be NULL */
	if (!id)
		return;

	BUG_ON(!ss->use_id);

	rcu_assign_pointer(id->css, NULL);
	rcu_assign_pointer(css->id, NULL);
	spin_lock(&ss->id_lock);
	idr_remove(&ss->idr, id->id);
	spin_unlock(&ss->id_lock);
	call_rcu(&id->rcu_head, __free_css_id_cb);
}
EXPORT_SYMBOL_GPL(free_css_id);

/*
 * This is called by init or create(). Then, calls to this function are
 * always serialized (By cgroup_mutex() at create()).
 */

static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
{
	struct css_id *newid;
	int myid, error, size;

	BUG_ON(!ss->use_id);

	size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1);
	newid = kzalloc(size, GFP_KERNEL);
	if (!newid)
		return ERR_PTR(-ENOMEM);
	/* get id */
	if (unlikely(!idr_pre_get(&ss->idr, GFP_KERNEL))) {
		error = -ENOMEM;
		goto err_out;
	}
	spin_lock(&ss->id_lock);
	/* Don't use 0. allocates an ID of 1-65535 */
	error = idr_get_new_above(&ss->idr, newid, 1, &myid);
	spin_unlock(&ss->id_lock);

	/* Returns error when there are no free spaces for new ID.*/
	if (error) {
		error = -ENOSPC;
		goto err_out;
	}
	if (myid > CSS_ID_MAX)
		goto remove_idr;

	newid->id = myid;
	newid->depth = depth;
	return newid;
remove_idr:
	error = -ENOSPC;
	spin_lock(&ss->id_lock);
	idr_remove(&ss->idr, myid);
	spin_unlock(&ss->id_lock);
err_out:
	kfree(newid);
	return ERR_PTR(error);

}

static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
					    struct cgroup_subsys_state *rootcss)
{
	struct css_id *newid;

	spin_lock_init(&ss->id_lock);
	idr_init(&ss->idr);

	newid = get_new_cssid(ss, 0);
	if (IS_ERR(newid))
		return PTR_ERR(newid);

	newid->stack[0] = newid->id;
	newid->css = rootcss;
	rootcss->id = newid;
	return 0;
}

static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
			struct cgroup *child)
{
	int subsys_id, i, depth = 0;
	struct cgroup_subsys_state *parent_css, *child_css;
	struct css_id *child_id, *parent_id;

	subsys_id = ss->subsys_id;
	parent_css = parent->subsys[subsys_id];
	child_css = child->subsys[subsys_id];
	parent_id = parent_css->id;
	depth = parent_id->depth + 1;

	child_id = get_new_cssid(ss, depth);
	if (IS_ERR(child_id))
		return PTR_ERR(child_id);

	for (i = 0; i < depth; i++)
		child_id->stack[i] = parent_id->stack[i];
	child_id->stack[depth] = child_id->id;
	/*
	 * child_id->css pointer will be set after this cgroup is available
	 * see cgroup_populate_dir()
	 */
	rcu_assign_pointer(child_css->id, child_id);

	return 0;
}

/**
 * css_lookup - lookup css by id
 * @ss: cgroup subsys to be looked into.
 * @id: the id
 *
 * Returns pointer to cgroup_subsys_state if there is valid one with id.
 * NULL if not. Should be called under rcu_read_lock()
 */
struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
{
	struct css_id *cssid = NULL;

	BUG_ON(!ss->use_id);
	cssid = idr_find(&ss->idr, id);

	if (unlikely(!cssid))
		return NULL;

	return rcu_dereference(cssid->css);
}
EXPORT_SYMBOL_GPL(css_lookup);

/**
 * css_get_next - lookup next cgroup under specified hierarchy.
 * @ss: pointer to subsystem
 * @id: current position of iteration.
 * @root: pointer to css. search tree under this.
 * @foundid: position of found object.
 *
 * Search next css under the specified hierarchy of rootid. Calling under
 * rcu_read_lock() is necessary. Returns NULL if it reaches the end.
 */
struct cgroup_subsys_state *
css_get_next(struct cgroup_subsys *ss, int id,
	     struct cgroup_subsys_state *root, int *foundid)
{
	struct cgroup_subsys_state *ret = NULL;
	struct css_id *tmp;
	int tmpid;
	int rootid = css_id(root);
	int depth = css_depth(root);

	if (!rootid)
		return NULL;

	BUG_ON(!ss->use_id);
	/* fill start point for scan */
	tmpid = id;
	while (1) {
		/*
		 * scan next entry from bitmap(tree), tmpid is updated after
		 * idr_get_next().
		 */
		spin_lock(&ss->id_lock);
		tmp = idr_get_next(&ss->idr, &tmpid);
		spin_unlock(&ss->id_lock);

		if (!tmp)
			break;
		if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
			ret = rcu_dereference(tmp->css);
			if (ret) {
				*foundid = tmpid;
				break;
			}
		}
		/* continue to scan from next id */
		tmpid = tmpid + 1;
	}
	return ret;
}

#ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
						   struct cgroup *cont)
{
	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);

	if (!css)
		return ERR_PTR(-ENOMEM);

	return css;
}

static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
{
	kfree(cont->subsys[debug_subsys_id]);
}

static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
{
	return atomic_read(&cont->count);
}

static u64 debug_taskcount_read(struct cgroup *cont, struct cftype *cft)
{
	return cgroup_task_count(cont);
}

static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
{
	return (u64)(unsigned long)current->cgroups;
}

static u64 current_css_set_refcount_read(struct cgroup *cont,
					   struct cftype *cft)
{
	u64 count;

	rcu_read_lock();
	count = atomic_read(&current->cgroups->refcount);
	rcu_read_unlock();
	return count;
}

static int current_css_set_cg_links_read(struct cgroup *cont,
					 struct cftype *cft,
					 struct seq_file *seq)
{
	struct cg_cgroup_link *link;
	struct css_set *cg;

	read_lock(&css_set_lock);
	rcu_read_lock();
	cg = rcu_dereference(current->cgroups);
	list_for_each_entry(link, &cg->cg_links, cg_link_list) {
		struct cgroup *c = link->cgrp;
		const char *name;

		if (c->dentry)
			name = c->dentry->d_name.name;
		else
			name = "?";
		seq_printf(seq, "Root %d group %s\n",
			   c->root->hierarchy_id, name);
	}
	rcu_read_unlock();
	read_unlock(&css_set_lock);
	return 0;
}

#define MAX_TASKS_SHOWN_PER_CSS 25
static int cgroup_css_links_read(struct cgroup *cont,
				 struct cftype *cft,
				 struct seq_file *seq)
{
	struct cg_cgroup_link *link;

	read_lock(&css_set_lock);
	list_for_each_entry(link, &cont->css_sets, cgrp_link_list) {
		struct css_set *cg = link->cg;
		struct task_struct *task;
		int count = 0;
		seq_printf(seq, "css_set %p\n", cg);
		list_for_each_entry(task, &cg->tasks, cg_list) {
			if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
				seq_puts(seq, "  ...\n");
				break;
			} else {
				seq_printf(seq, "  task %d\n",
					   task_pid_vnr(task));
			}
		}
	}
	read_unlock(&css_set_lock);
	return 0;
}

static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
{
	return test_bit(CGRP_RELEASABLE, &cgrp->flags);
}

static struct cftype debug_files[] =  {
	{
		.name = "cgroup_refcount",
		.read_u64 = cgroup_refcount_read,
	},
	{
		.name = "taskcount",
		.read_u64 = debug_taskcount_read,
	},

	{
		.name = "current_css_set",
		.read_u64 = current_css_set_read,
	},

	{
		.name = "current_css_set_refcount",
		.read_u64 = current_css_set_refcount_read,
	},

	{
		.name = "current_css_set_cg_links",
		.read_seq_string = current_css_set_cg_links_read,
	},

	{
		.name = "cgroup_css_links",
		.read_seq_string = cgroup_css_links_read,
	},

	{
		.name = "releasable",
		.read_u64 = releasable_read,
	},
};

static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
{
	return cgroup_add_files(cont, ss, debug_files,
				ARRAY_SIZE(debug_files));
}

struct cgroup_subsys debug_subsys = {
	.name = "debug",
	.create = debug_create,
	.destroy = debug_destroy,
	.populate = debug_populate,
	.subsys_id = debug_subsys_id,
};
#endif /* CONFIG_CGROUP_DEBUG */