aboutsummaryrefslogtreecommitdiffstats
path: root/target/linux/generic-2.6/patches-2.6.30/270-sched_bfs.patch
blob: f521b3239cf3422bc2e5e81601870885126a7344 (plain) 
1
2
3
4
5
6
7
8
9
10
11

--- a/include/linux/atm.h
+++ b/include/linux/atm.h
@@ -139,6 +139,9 @@ struct atm_trafprm {
 	int		min_pcr;	/* minimum PCR in cells per second */
 	int		max_cdv;	/* maximum CDV in microseconds */
 	int		max_sdu;	/* maximum SDU in bytes */
+	int		scr;		/* sustained rate in cells per second */
+	int		mbs;		/* maximum burst size (MBS) in cells */
+	int		cdv;		/* Cell delay varition */
         /* extra params for ABR */
         unsigned int 	icr;         	/* Initial Cell Rate (24-bit) */
         unsigned int	tbe;		/* Transient Buffer Exposure (24-bit) */
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-15 04:55:06 +0000
'#n203'>203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 
This patch adds support for bfs v230, modified for diff size reduction

--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -27,6 +27,7 @@ show up in /proc/sys/kernel:
 - domainname
 - hostname
 - hotplug
+- iso_cpu
 - java-appletviewer           [ binfmt_java, obsolete ]
 - java-interpreter            [ binfmt_java, obsolete ]
 - kstack_depth_to_print       [ X86 only ]
@@ -48,6 +49,7 @@ show up in /proc/sys/kernel:
 - randomize_va_space
 - real-root-dev               ==> Documentation/initrd.txt
 - reboot-cmd                  [ SPARC only ]
+- rr_interval
 - rtsig-max
 - rtsig-nr
 - sem
@@ -170,6 +172,16 @@ Default value is "/sbin/hotplug".
 
 ==============================================================
 
+iso_cpu: (BFS only)
+
+This sets the percentage cpu that the unprivileged SCHED_ISO tasks can
+run effectively at realtime priority, averaged over a rolling five
+seconds over the -whole- system, meaning all cpus.
+
+Set to 70 (percent) by default.
+
+==============================================================
+
 l2cr: (PPC only)
 
 This flag controls the L2 cache of G3 processor boards. If
@@ -322,6 +334,19 @@ rebooting. ???
 
 ==============================================================
 
+rr_interval: (BFS only)
+
+This is the smallest duration that any cpu process scheduling unit
+will run for. Increasing this value can increase throughput of cpu
+bound tasks substantially but at the expense of increased latencies
+overall. This value is in milliseconds and the default value chosen
+depends on the number of cpus available at scheduler initialisation
+with a minimum of 6.
+
+Valid values are from 1-5000.
+
+==============================================================
+
 rtsig-max & rtsig-nr:
 
 The file rtsig-max can be used to tune the maximum number
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -119,9 +119,10 @@ extern struct cred init_cred;
 	.usage		= ATOMIC_INIT(2),				\
 	.flags		= PF_KTHREAD,					\
 	.lock_depth	= -1,						\
-	.prio		= MAX_PRIO-20,					\
+	.prio		= NORMAL_PRIO,					\
 	.static_prio	= MAX_PRIO-20,					\
-	.normal_prio	= MAX_PRIO-20,					\
+	.normal_prio	= NORMAL_PRIO,					\
+	.deadline	= 0,						\
 	.policy		= SCHED_NORMAL,					\
 	.cpus_allowed	= CPU_MASK_ALL,					\
 	.mm		= NULL,						\
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -36,9 +36,12 @@
 #define SCHED_FIFO		1
 #define SCHED_RR		2
 #define SCHED_BATCH		3
-/* SCHED_ISO: reserved but not implemented yet */
+#define SCHED_ISO		4
 #define SCHED_IDLE		5
 
+#define SCHED_MAX		(SCHED_IDLE)
+#define SCHED_RANGE(policy)	((policy) <= SCHED_MAX)
+
 #ifdef __KERNEL__
 
 struct sched_param {
@@ -1042,10 +1045,13 @@ struct sched_entity {
 	struct load_weight	load;		/* for load-balancing */
 	struct rb_node		run_node;
 	struct list_head	group_node;
+#ifdef CONFIG_SCHED_CFS
 	unsigned int		on_rq;
 
 	u64			exec_start;
+#endif
 	u64			sum_exec_runtime;
+#ifdef CONFIG_SCHED_CFS
 	u64			vruntime;
 	u64			prev_sum_exec_runtime;
 
@@ -1096,6 +1102,7 @@ struct sched_entity {
 	/* rq "owned" by this entity/group: */
 	struct cfs_rq		*my_q;
 #endif
+#endif
 };
 
 struct sched_rt_entity {
@@ -1123,17 +1130,19 @@ struct task_struct {
 
 	int lock_depth;		/* BKL lock depth */
 
-#ifdef CONFIG_SMP
-#ifdef __ARCH_WANT_UNLOCKED_CTXSW
 	int oncpu;
-#endif
-#endif
-
 	int prio, static_prio, normal_prio;
 	unsigned int rt_priority;
 	const struct sched_class *sched_class;
 	struct sched_entity se;
 	struct sched_rt_entity rt;
+	unsigned long deadline;
+#ifdef CONFIG_SCHED_BFS
+	int load_weight;	/* for niceness load balancing purposes */
+	int first_time_slice;
+	unsigned long long timestamp, last_ran;
+	unsigned long utime_pc, stime_pc;
+#endif
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	/* list of struct preempt_notifier: */
@@ -1156,6 +1165,9 @@ struct task_struct {
 
 	unsigned int policy;
 	cpumask_t cpus_allowed;
+#ifdef CONFIG_HOTPLUG_CPU
+	cpumask_t unplugged_mask;
+#endif
 
 #ifdef CONFIG_PREEMPT_RCU
 	int rcu_read_lock_nesting;
@@ -1446,11 +1458,19 @@ struct task_struct {
  * priority to a value higher than any user task. Note:
  * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
  */
-
+#define PRIO_RANGE		(40)
 #define MAX_USER_RT_PRIO	100
 #define MAX_RT_PRIO		MAX_USER_RT_PRIO
-
+#ifdef CONFIG_SCHED_BFS
+#define MAX_PRIO		(MAX_RT_PRIO + PRIO_RANGE)
+#define ISO_PRIO		(MAX_RT_PRIO)
+#define NORMAL_PRIO		(MAX_RT_PRIO + 1)
+#define IDLE_PRIO		(MAX_RT_PRIO + 2)
+#define PRIO_LIMIT		((IDLE_PRIO) + 1)
+#else
 #define MAX_PRIO		(MAX_RT_PRIO + 40)
+#define NORMAL_PRIO	(MAX_RT_PRIO - 20)
+#endif
 #define DEFAULT_PRIO		(MAX_RT_PRIO + 20)
 
 static inline int rt_prio(int prio)
@@ -1734,7 +1754,7 @@ task_sched_runtime(struct task_struct *t
 extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
 
 /* sched_exec is called by processes performing an exec */
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_CFS)
 extern void sched_exec(void);
 #else
 #define sched_exec()   {}
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -435,9 +435,22 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
+choice
+	prompt "Scheduler"
+	default SCHED_CFS
+
+	config SCHED_CFS
+		bool "CFS"
+
+	config SCHED_BFS
+		bool "BFS"
+
+endchoice
+
 config GROUP_SCHED
 	bool "Group CPU scheduler"
 	depends on EXPERIMENTAL
+	depends on SCHED_CFS
 	default n
 	help
 	  This feature lets CPU scheduler recognize task groups and control CPU
@@ -488,6 +501,7 @@ endchoice
 
 menuconfig CGROUPS
 	boolean "Control Group support"
+	depends on SCHED_CFS
 	help
 	  This option adds support for grouping sets of processes together, for
 	  use with process control subsystems such as Cpusets, CFS, memory
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the linux kernel.
 #
 
-obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
+obj-y     = $(if $(CONFIG_SCHED_CFS),sched.o,sched_bfs.o) fork.o exec_domain.o panic.o printk.o \
 	    cpu.o exit.o itimer.o time.o softirq.o resource.o \
 	    sysctl.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
@@ -103,6 +103,7 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER
 # I turn this off for IA-64 only.  Andreas Schwab says it's also needed on m68k
 # to get a correct value for the wait-channel (WCHAN in ps). --davidm
 CFLAGS_sched.o := $(PROFILING) -fno-omit-frame-pointer
+CFLAGS_sched_bfs.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
 $(obj)/configs.o: $(obj)/config_data.h
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -15,7 +15,11 @@
 #include <linux/mutex.h>
 #include <trace/sched.h>
 
+#ifdef CONFIG_SCHED_BFS
+#define KTHREAD_NICE_LEVEL (0)
+#else
 #define KTHREAD_NICE_LEVEL (-5)
+#endif
 
 static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
--- /dev/null
+++ b/kernel/sched_bfs.c
@@ -0,0 +1,6059 @@
+/*
+ *  kernel/sched_bfs.c, was sched.c
+ *
+ *  Kernel scheduler and related syscalls
+ *
+ *  Copyright (C) 1991-2002  Linus Torvalds
+ *
+ *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
+ *		make semaphores SMP safe
+ *  1998-11-19	Implemented schedule_timeout() and related stuff
+ *		by Andrea Arcangeli
+ *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
+ *		hybrid priority-list and round-robin design with
+ *		an array-switch method of distributing timeslices
+ *		and per-CPU runqueues.  Cleanups and useful suggestions
+ *		by Davide Libenzi, preemptible kernel bits by Robert Love.
+ *  2003-09-03	Interactivity tuning by Con Kolivas.
+ *  2004-04-02	Scheduler domains code by Nick Piggin
+ *  2007-04-15  Work begun on replacing all interactivity tuning with a
+ *              fair scheduling design by Con Kolivas.
+ *  2007-05-05  Load balancing (smp-nice) and other improvements
+ *              by Peter Williams
+ *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
+ *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
+ *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
+ *              Thomas Gleixner, Mike Kravetz
+ *  now		Brainfuck deadline scheduling policy by Con Kolivas deletes
+ *              a whole lot of those previous things.
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
+#include <linux/init.h>
+#include <asm/uaccess.h>
+#include <linux/highmem.h>
+#include <linux/smp_lock.h>
+#include <asm/mmu_context.h>
+#include <linux/interrupt.h>
+#include <linux/capability.h>
+#include <linux/completion.h>
+#include <linux/kernel_stat.h>
+#include <linux/debug_locks.h>
+#include <linux/perf_counter.h>
+#include <linux/security.h>
+#include <linux/notifier.h>
+#include <linux/profile.h>
+#include <linux/freezer.h>
+#include <linux/vmalloc.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/threads.h>
+#include <linux/timer.h>
+#include <linux/rcupdate.h>
+#include <linux/cpu.h>
+#include <linux/cpuset.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/kthread.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/syscalls.h>
+#include <linux/times.h>
+#include <linux/tsacct_kern.h>
+#include <linux/kprobes.h>
+#include <linux/delayacct.h>
+#include <linux/reciprocal_div.h>
+#include <linux/log2.h>
+#include <linux/bootmem.h>
+#include <linux/ftrace.h>
+
+#include <asm/tlb.h>
+#include <asm/unistd.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+
+#define rt_prio(prio)		unlikely((prio) < MAX_RT_PRIO)
+#define rt_task(p)		rt_prio((p)->prio)
+#define rt_queue(rq)		rt_prio((rq)->rq_prio)
+#define batch_task(p)		(unlikely((p)->policy == SCHED_BATCH))
+#define is_rt_policy(policy)	((policy) == SCHED_FIFO || \
+					(policy) == SCHED_RR)
+#define has_rt_policy(p)	unlikely(is_rt_policy((p)->policy))
+#define idleprio_task(p)	unlikely((p)->policy == SCHED_IDLE)
+#define iso_task(p)		unlikely((p)->policy == SCHED_ISO)
+#define iso_queue(rq)		unlikely((rq)->rq_policy == SCHED_ISO)
+#define ISO_PERIOD		((5 * HZ * num_online_cpus()) + 1)
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+ * and back.
+ */
+#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
+#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
+#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)
+
+/*
+ * 'User priority' is the nice value converted to something we
+ * can work with better when scaling various scheduler parameters,
+ * it's a [ 0 ... 39 ] range.
+ */
+#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
+#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
+#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
+#define SCHED_PRIO(p)		((p)+MAX_RT_PRIO)
+
+/* Some helpers for converting to/from various scales.*/
+#define JIFFIES_TO_NS(TIME)	((TIME) * (1000000000 / HZ))
+#define MS_TO_NS(TIME)		((TIME) * 1000000)
+#define MS_TO_US(TIME)		((TIME) * 1000)
+
+#ifdef CONFIG_SMP
+/*
+ * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
+ * Since cpu_power is a 'constant', we can use a reciprocal divide.
+ */
+static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
+{
+	return reciprocal_divide(load, sg->reciprocal_cpu_power);
+}
+
+/*
+ * Each time a sched group cpu_power is changed,
+ * we must compute its reciprocal value
+ */
+static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
+{
+	sg->__cpu_power += val;
+	sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
+}
+#endif
+
+/*
+ * This is the time all tasks within the same priority round robin.
+ * Value is in ms and set to a minimum of 6ms. Scales with number of cpus.
+ * Tunable via /proc interface.
+ */
+int rr_interval __read_mostly = 6;
+
+/*
+ * sched_iso_cpu - sysctl which determines the cpu percentage SCHED_ISO tasks
+ * are allowed to run five seconds as real time tasks. This is the total over
+ * all online cpus.
+ */
+int sched_iso_cpu __read_mostly = 70;
+
+int prio_ratios[PRIO_RANGE] __read_mostly;
+
+static inline unsigned long timeslice(void)
+{
+	return MS_TO_US(rr_interval);
+}
+
+struct global_rq {
+	spinlock_t lock;
+	unsigned long nr_running;
+	unsigned long nr_uninterruptible;
+	unsigned long long nr_switches;
+	struct list_head queue[PRIO_LIMIT];
+	DECLARE_BITMAP(prio_bitmap, PRIO_LIMIT + 1);
+	unsigned long iso_ticks;
+	unsigned short iso_refractory;
+#ifdef CONFIG_SMP
+	unsigned long qnr; /* queued not running */
+	cpumask_t cpu_idle_map;
+#endif
+};
+
+static struct global_rq grq;
+
+/*
+ * This is the main, per-CPU runqueue data structure.
+ * All this is protected by the global_rq lock.
+ */
+struct rq {
+#ifdef CONFIG_SMP
+#ifdef CONFIG_NO_HZ
+	unsigned char in_nohz_recently;
+#endif
+#endif
+
+	struct task_struct *curr, *idle;
+	struct mm_struct *prev_mm;
+	struct list_head queue; /* Place to store currently running task */
+
+	/* Stored data about rq->curr to work outside grq lock */
+	unsigned long rq_deadline;
+	unsigned int rq_policy;
+	int rq_time_slice;
+	int rq_prio;
+
+	/* Accurate timekeeping data */
+	u64 timekeep_clock;
+	unsigned long user_pc, nice_pc, irq_pc, softirq_pc, system_pc,
+			iowait_pc, idle_pc;
+	atomic_t nr_iowait;
+
+	int cpu;		/* cpu of this runqueue */
+	int online;
+
+#ifdef CONFIG_SMP
+	struct root_domain *rd;
+	struct sched_domain *sd;
+
+	struct list_head migration_queue;
+#endif
+
+	u64 clock;
+#ifdef CONFIG_SCHEDSTATS
+
+	/* latency stats */
+	struct sched_info rq_sched_info;
+	unsigned long long rq_cpu_time;
+	/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
+
+	/* sys_sched_yield() stats */
+	unsigned int yld_count;
+
+	/* schedule() stats */
+	unsigned int sched_switch;
+	unsigned int sched_count;
+	unsigned int sched_goidle;
+
+	/* try_to_wake_up() stats */
+	unsigned int ttwu_count;
+	unsigned int ttwu_local;
+
+	/* BKL stats */
+	unsigned int bkl_count;
+#endif
+};
+
+static DEFINE_PER_CPU(struct rq, runqueues) ____cacheline_aligned_in_smp;
+static DEFINE_MUTEX(sched_hotcpu_mutex);
+
+#ifdef CONFIG_SMP
+
+/*
+ * We add the notion of a root-domain which will be used to define per-domain
+ * variables. Each exclusive cpuset essentially defines an island domain by
+ * fully partitioning the member cpus from any other cpuset. Whenever a new
+ * exclusive cpuset is created, we also create and attach a new root-domain
+ * object.
+ *
+ */
+struct root_domain {
+	atomic_t refcount;
+	cpumask_var_t span;
+	cpumask_var_t online;
+
+	/*
+	 * The "RT overload" flag: it gets set if a CPU has more than
+	 * one runnable RT task.
+	 */
+	cpumask_var_t rto_mask;
+	atomic_t rto_count;
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+	/*
+	 * Preferred wake up cpu nominated by sched_mc balance that will be
+	 * used when most cpus are idle in the system indicating overall very
+	 * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2)
+	 */
+	unsigned int sched_mc_preferred_wakeup_cpu;
+#endif
+};
+
+/*
+ * By default the system creates a single root-domain with all cpus as
+ * members (mimicking the global state we have today).
+ */
+static struct root_domain def_root_domain;
+
+#endif
+
+static inline int cpu_of(struct rq *rq)
+{
+#ifdef CONFIG_SMP
+	return rq->cpu;
+#else
+	return 0;
+#endif
+}
+
+/*
+ * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
+ * See detach_destroy_domains: synchronize_sched for details.
+ *
+ * The domain tree of any CPU may only be accessed from within
+ * preempt-disabled sections.
+ */
+#define for_each_domain(cpu, __sd) \
+	for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
+
+#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
+#define this_rq()		(&__get_cpu_var(runqueues))
+#define task_rq(p)		cpu_rq(task_cpu(p))
+#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
+
+#include "sched_stats.h"
+
+#ifndef prepare_arch_switch
+# define prepare_arch_switch(next)	do { } while (0)
+#endif
+#ifndef finish_arch_switch
+# define finish_arch_switch(prev)	do { } while (0)
+#endif
+
+inline void update_rq_clock(struct rq *rq)
+{
+	rq->clock = sched_clock_cpu(cpu_of(rq));
+}
+
+static inline int task_running(struct task_struct *p)
+{
+	return (!!p->oncpu);
+}
+
+static inline void grq_lock(void)
+	__acquires(grq.lock)
+{
+	smp_mb();
+	spin_lock(&grq.lock);
+}
+
+static inline void grq_unlock(void)
+	__releases(grq.lock)
+{
+	spin_unlock(&grq.lock);
+}
+
+static inline void grq_lock_irq(void)
+	__acquires(grq.lock)
+{
+	smp_mb();
+	spin_lock_irq(&grq.lock);
+}
+
+static inline void time_lock_grq(struct rq *rq)
+	__acquires(grq.lock)
+{
+	grq_lock();
+	update_rq_clock(rq);
+}
+
+static inline void grq_unlock_irq(void)
+	__releases(grq.lock)
+{
+	spin_unlock_irq(&grq.lock);
+}
+
+static inline void grq_lock_irqsave(unsigned long *flags)
+	__acquires(grq.lock)
+{
+	smp_mb();
+	spin_lock_irqsave(&grq.lock, *flags);
+}
+
+static inline void grq_unlock_irqrestore(unsigned long *flags)
+	__releases(grq.lock)
+{
+	spin_unlock_irqrestore(&grq.lock, *flags);
+}
+
+static inline struct rq
+*task_grq_lock(struct task_struct *p, unsigned long *flags)
+	__acquires(grq.lock)
+{
+	grq_lock_irqsave(flags);
+	return task_rq(p);
+}
+
+static inline struct rq
+*time_task_grq_lock(struct task_struct *p, unsigned long *flags)
+	__acquires(grq.lock)
+{
+	struct rq *rq = task_grq_lock(p, flags);
+	update_rq_clock(rq);
+	return rq;
+}
+
+static inline void task_grq_unlock(unsigned long *flags)
+	__releases(grq.lock)
+{
+	grq_unlock_irqrestore(flags);
+}
+
+/**
+ * runqueue_is_locked
+ *
+ * Returns true if the global runqueue is locked.
+ * This interface allows printk to be called with the runqueue lock
+ * held and know whether or not it is OK to wake up the klogd.
+ */
+int runqueue_is_locked(void)
+{
+	return spin_is_locked(&grq.lock);
+}
+
+void task_rq_unlock_wait(struct task_struct *p)
+	__releases(grq.lock)
+{
+	smp_mb(); /* spin-unlock-wait is not a full memory barrier */
+	spin_unlock_wait(&grq.lock);
+}
+
+static inline void time_grq_lock(struct rq *rq, unsigned long *flags)
+	__acquires(grq.lock)
+{
+	spin_lock_irqsave(&grq.lock, *flags);
+	update_rq_clock(rq);
+}
+
+static inline struct rq *__task_grq_lock(struct task_struct *p)
+	__acquires(grq.lock)
+{
+	grq_lock();
+	return task_rq(p);
+}
+
+static inline void __task_grq_unlock(void)
+	__releases(grq.lock)
+{
+	grq_unlock();
+}
+
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
+{
+}
+
+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+	/* this is a valid case when another task releases the spinlock */
+	grq.lock.owner = current;
+#endif
+	/*
+	 * If we are tracking spinlock dependencies then we have to
+	 * fix up the runqueue lock - which gets 'carried over' from
+	 * prev into current:
+	 */
+	spin_acquire(&grq.lock.dep_map, 0, 0, _THIS_IP_);
+
+	grq_unlock_irq();
+}
+
+#else /* __ARCH_WANT_UNLOCKED_CTXSW */
+
+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
+{
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	grq_unlock_irq();
+#else
+	grq_unlock();
+#endif
+}
+
+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
+{
+	smp_wmb();
+#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	local_irq_enable();
+#endif
+}
+#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
+
+/*
+ * A task that is queued will be on the grq run list.
+ * A task that is not running or queued will not be on the grq run list.
+ * A task that is currently running will have ->oncpu set and be queued
+ * temporarily in its own rq queue.
+ * A task that is running and no longer queued will be seen only on
+ * context switch exit.
+ */
+
+static inline int task_queued(struct task_struct *p)
+{
+	return (!list_empty(&p->rt.run_list));
+}
+
+static inline int task_queued_only(struct task_struct *p)
+{
+	return (!list_empty(&p->rt.run_list) && !task_running(p));
+}
+
+/*
+ * Removing from the global runqueue. Enter with grq locked.
+ */
+static void dequeue_task(struct task_struct *p)
+{
+	list_del_init(&p->rt.run_list);
+	if (list_empty(grq.queue + p->prio))
+		__clear_bit(p->prio, grq.prio_bitmap);
+}
+
+static inline void reset_first_time_slice(struct task_struct *p)
+{
+	if (unlikely(p->first_time_slice))
+		p->first_time_slice = 0;
+}
+
+static int idleprio_suitable(struct task_struct *p)
+{
+	return (!freezing(p) && !signal_pending(p) &&
+		!(task_contributes_to_load(p)) && !(p->flags & (PF_EXITING)));
+}
+
+static int isoprio_suitable(void)
+{
+	return !grq.iso_refractory;
+}
+
+/*
+ * Adding to the global runqueue. Enter with grq locked.
+ */
+static void enqueue_task(struct task_struct *p)
+{
+	if (!rt_task(p)) {
+		/* Check it hasn't gotten rt from PI */
+		if ((idleprio_task(p) && idleprio_suitable(p)) ||
+		   (iso_task(p) && isoprio_suitable()))
+			p->prio = p->normal_prio;
+		else
+			p->prio = NORMAL_PRIO;
+	}
+	__set_bit(p->prio, grq.prio_bitmap);
+	list_add_tail(&p->rt.run_list, grq.queue + p->prio);
+	sched_info_queued(p);
+}
+
+/* Only idle task does this as a real time task*/
+static inline void enqueue_task_head(struct task_struct *p)
+{
+	__set_bit(p->prio, grq.prio_bitmap);
+	list_add(&p->rt.run_list, grq.queue + p->prio);
+	sched_info_queued(p);
+}
+
+static inline void requeue_task(struct task_struct *p)
+{
+	sched_info_queued(p);
+}
+
+static inline int pratio(struct task_struct *p)
+{
+	return prio_ratios[TASK_USER_PRIO(p)];
+}
+
+/*
+ * task_timeslice - all tasks of all priorities get the exact same timeslice
+ * length. CPU distribution is handled by giving different deadlines to
+ * tasks of different priorities.
+ */
+static inline int task_timeslice(struct task_struct *p)
+{
+	return (rr_interval * pratio(p) / 100);
+}
+
+#ifdef CONFIG_SMP
+static inline void inc_qnr(void)
+{
+	grq.qnr++;
+}
+
+static inline void dec_qnr(void)
+{
+	grq.qnr--;
+}
+
+static inline int queued_notrunning(void)
+{
+	return grq.qnr;
+}
+#else
+static inline void inc_qnr(void)
+{
+}
+
+static inline void dec_qnr(void)
+{
+}
+
+static inline int queued_notrunning(void)
+{
+	return grq.nr_running;
+}
+#endif
+
+/*
+ * activate_idle_task - move idle task to the _front_ of runqueue.
+ */
+static inline void activate_idle_task(struct task_struct *p)
+{
+	enqueue_task_head(p);
+	grq.nr_running++;
+	inc_qnr();
+}
+
+static inline int normal_prio(struct task_struct *p)
+{
+	if (has_rt_policy(p))
+		return MAX_RT_PRIO - 1 - p->rt_priority;
+	if (idleprio_task(p))
+		return IDLE_PRIO;
+	if (iso_task(p))
+		return ISO_PRIO;
+	return NORMAL_PRIO;
+}
+
+/*
+ * Calculate the current priority, i.e. the priority
+ * taken into account by the scheduler. This value might
+ * be boosted by RT tasks as it will be RT if the task got
+ * RT-boosted. If not then it returns p->normal_prio.
+ */
+static int effective_prio(struct task_struct *p)
+{
+	p->normal_prio = normal_prio(p);
+	/*
+	 * If we are RT tasks or we were boosted to RT priority,
+	 * keep the priority unchanged. Otherwise, update priority
+	 * to the normal priority:
+	 */
+	if (!rt_prio(p->prio))
+		return p->normal_prio;
+	return p->prio;
+}
+
+/*
+ * activate_task - move a task to the runqueue. Enter with grq locked. The rq
+ * doesn't really matter but gives us the local clock.
+ */
+static void activate_task(struct task_struct *p, struct rq *rq)
+{
+	u64 now = rq->clock;
+
+	/*
+	 * Sleep time is in units of nanosecs, so shift by 20 to get a
+	 * milliseconds-range estimation of the amount of time that the task
+	 * spent sleeping:
+	 */
+	if (unlikely(prof_on == SLEEP_PROFILING)) {
+		if (p->state == TASK_UNINTERRUPTIBLE)
+			profile_hits(SLEEP_PROFILING, (void *)get_wchan(p),
+				     (now - p->timestamp) >> 20);
+	}
+
+	p->prio = effective_prio(p);
+	p->timestamp = now;
+	if (task_contributes_to_load(p))
+		grq.nr_uninterruptible--;
+	enqueue_task(p);
+	grq.nr_running++;
+	inc_qnr();
+}
+
+/*
+ * deactivate_task - If it's running, it's not on the grq and we can just
+ * decrement the nr_running.
+ */
+static inline void deactivate_task(struct task_struct *p)
+{
+	if (task_contributes_to_load(p))
+		grq.nr_uninterruptible++;
+	grq.nr_running--;
+}
+
+#ifdef CONFIG_SMP
+void set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+	trace_sched_migrate_task(p, cpu);
+	/*
+	 * After ->cpu is set up to a new value, task_grq_lock(p, ...) can be
+	 * successfuly executed on another CPU. We must ensure that updates of
+	 * per-task data have been completed by this moment.
+	 */
+	smp_wmb();
+	task_thread_info(p)->cpu = cpu;
+}
+#endif
+
+/*
+ * Move a task off the global queue and take it to a cpu for it will
+ * become the running task.
+ */
+static inline void take_task(struct rq *rq, struct task_struct *p)
+{
+	set_task_cpu(p, rq->cpu);
+	dequeue_task(p);
+	list_add(&p->rt.run_list, &rq->queue);
+	dec_qnr();
+}
+
+/*
+ * Returns a descheduling task to the grq runqueue unless it is being
+ * deactivated.
+ */
+static inline void return_task(struct task_struct *p, int deactivate)
+{
+	list_del_init(&p->rt.run_list);
+	if (deactivate)
+		deactivate_task(p);
+	else {
+		inc_qnr();
+		enqueue_task(p);
+	}
+}
+
+/*
+ * resched_task - mark a task 'to be rescheduled now'.
+ *
+ * On UP this means the setting of the need_resched flag, on SMP it
+ * might also involve a cross-CPU call to trigger the scheduler on
+ * the target CPU.
+ */
+#ifdef CONFIG_SMP
+
+#ifndef tsk_is_polling
+#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
+#endif
+
+static void resched_task(struct task_struct *p)
+{
+	int cpu;
+
+	assert_spin_locked(&grq.lock);
+
+	if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+		return;
+
+	set_tsk_thread_flag(p, TIF_NEED_RESCHED);
+
+	cpu = task_cpu(p);
+	if (cpu == smp_processor_id())
+		return;
+
+	/* NEED_RESCHED must be visible before we test polling */
+	smp_mb();
+	if (!tsk_is_polling(p))
+		smp_send_reschedule(cpu);
+}
+
+#else
+static inline void resched_task(struct task_struct *p)
+{
+	assert_spin_locked(&grq.lock);
+	set_tsk_need_resched(p);
+}
+#endif
+
+/**
+ * task_curr - is this task currently executing on a CPU?
+ * @p: the task in question.
+ */
+inline int task_curr(const struct task_struct *p)
+{
+	return cpu_curr(task_cpu(p)) == p;
+}
+
+#ifdef CONFIG_SMP
+struct migration_req {
+	struct list_head list;
+
+	struct task_struct *task;
+	int dest_cpu;
+
+	struct completion done;
+};
+
+/*
+ * wait_task_context_switch -	wait for a thread to complete at least one
+ *				context switch.
+ *
+ * @p must not be current.
+ */
+void wait_task_context_switch(struct task_struct *p)
+{
+	unsigned long nvcsw, nivcsw, flags;
+	int running;
+	struct rq *rq;
+
+	nvcsw	= p->nvcsw;
+	nivcsw	= p->nivcsw;
+	for (;;) {
+		/*
+		 * The runqueue is assigned before the actual context
+		 * switch. We need to take the runqueue lock.
+		 *
+		 * We could check initially without the lock but it is
+		 * very likely that we need to take the lock in every
+		 * iteration.
+		 */
+		rq = task_grq_lock(p, &flags);
+		running = task_running(p);
+		task_grq_unlock(&flags);
+
+		if (likely(!running))
+			break;
+		/*
+		 * The switch count is incremented before the actual
+		 * context switch. We thus wait for two switches to be
+		 * sure at least one completed.
+		 */
+		if ((p->nvcsw - nvcsw) > 1)
+			break;
+		if ((p->nivcsw - nivcsw) > 1)
+			break;
+
+		cpu_relax();
+	}
+}
+
+/*
+ * wait_task_inactive - wait for a thread to unschedule.
+ *
+ * If @match_state is nonzero, it's the @p->state value just checked and
+ * not expected to change.  If it changes, i.e. @p might have woken up,
+ * then return zero.  When we succeed in waiting for @p to be off its CPU,
+ * we return a positive number (its total switch count).  If a second call
+ * a short while later returns the same number, the caller can be sure that
+ * @p has remained unscheduled the whole time.
+ *
+ * The caller must ensure that the task *will* unschedule sometime soon,
+ * else this function might spin for a *long* time. This function can't
+ * be called with interrupts off, or it may introduce deadlock with
+ * smp_call_function() if an IPI is sent by the same process we are
+ * waiting to become inactive.
+ */
+unsigned long wait_task_inactive(struct task_struct *p, long match_state)
+{
+	unsigned long flags;
+	int running, on_rq;
+	unsigned long ncsw;
+	struct rq *rq;
+
+	for (;;) {
+		/*
+		 * We do the initial early heuristics without holding
+		 * any task-queue locks at all. We'll only try to get
+		 * the runqueue lock when things look like they will
+		 * work out!
+		 */
+		rq = task_rq(p);
+
+		/*
+		 * If the task is actively running on another CPU
+		 * still, just relax and busy-wait without holding
+		 * any locks.
+		 *
+		 * NOTE! Since we don't hold any locks, it's not
+		 * even sure that "rq" stays as the right runqueue!
+		 * But we don't care, since this will
+		 * return false if the runqueue has changed and p
+		 * is actually now running somewhere else!
+		 */
+		while (task_running(p) && p == rq->curr) {
+			if (match_state && unlikely(p->state != match_state))
+				return 0;
+			cpu_relax();
+		}
+
+		/*
+		 * Ok, time to look more closely! We need the grq
+		 * lock now, to be *sure*. If we're wrong, we'll
+		 * just go back and repeat.
+		 */
+		rq = task_grq_lock(p, &flags);
+		trace_sched_wait_task(rq, p);
+		running = task_running(p);
+		on_rq = task_queued(p);
+		ncsw = 0;
+		if (!match_state || p->state == match_state)
+			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
+		task_grq_unlock(&flags);
+
+		/*
+		 * If it changed from the expected state, bail out now.
+		 */
+		if (unlikely(!ncsw))
+			break;
+
+		/*
+		 * Was it really running after all now that we
+		 * checked with the proper locks actually held?
+		 *
+		 * Oops. Go back and try again..
+		 */
+		if (unlikely(running)) {
+			cpu_relax();
+			continue;
+		}
+
+		/*
+		 * It's not enough that it's not actively running,
+		 * it must be off the runqueue _entirely_, and not
+		 * preempted!
+		 *
+		 * So if it was still runnable (but just not actively
+		 * running right now), it's preempted, and we should
+		 * yield - it could be a while.
+		 */
+		if (unlikely(on_rq)) {
+			schedule_timeout_uninterruptible(1);
+			continue;
+		}
+
+		/*
+		 * Ahh, all good. It wasn't running, and it wasn't
+		 * runnable, which means that it will never become
+		 * running in the future either. We're all done!
+		 */
+		break;
+	}
+
+	return ncsw;
+}
+
+/***
+ * kick_process - kick a running thread to enter/exit the kernel
+ * @p: the to-be-kicked thread
+ *
+ * Cause a process which is running on another CPU to enter
+ * kernel-mode, without any delay. (to get signals handled.)
+ *
+ * NOTE: this function doesnt have to take the runqueue lock,
+ * because all it wants to ensure is that the remote task enters
+ * the kernel. If the IPI races and the task has been migrated
+ * to another CPU then no harm is done and the purpose has been
+ * achieved as well.
+ */
+void kick_process(struct task_struct *p)
+{
+	int cpu;
+
+	preempt_disable();
+	cpu = task_cpu(p);
+	if ((cpu != smp_processor_id()) && task_curr(p))
+		smp_send_reschedule(cpu);
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kick_process);
+#endif
+
+#define rq_idle(rq)	((rq)->rq_prio == PRIO_LIMIT)
+
+/*
+ * RT tasks preempt purely on priority. SCHED_NORMAL tasks preempt on the
+ * basis of earlier deadlines. SCHED_BATCH and SCHED_IDLE don't preempt,
+ * they cooperatively multitask.
+ */
+static inline int task_preempts_curr(struct task_struct *p, struct rq *rq)
+{
+	int preempts = 0;
+
+	if (p->prio < rq->rq_prio)
+		preempts = 1;
+	else if (p->policy == SCHED_NORMAL && (p->prio == rq->rq_prio &&
+		 time_before(p->deadline, rq->rq_deadline)))
+			preempts = 1;
+	return preempts;
+}
+
+/*
+ * Wake up *any* suitable cpu to schedule this task.
+ */
+static void try_preempt(struct task_struct *p)
+{
+	struct rq *highest_prio_rq, *this_rq;
+	unsigned long latest_deadline, cpu;
+	int highest_prio;
+	cpumask_t tmp;
+
+	/* Try the task's previous rq first and as a fallback */
+	this_rq = task_rq(p);
+
+	if (cpu_isset(this_rq->cpu, p->cpus_allowed)) {
+		highest_prio_rq = this_rq;
+		/* If this_rq is idle, use that. */
+		if (rq_idle(this_rq))
+			goto found_rq;
+	} else
+		highest_prio_rq = cpu_rq(any_online_cpu(p->cpus_allowed));
+	latest_deadline = this_rq->rq_deadline;
+	highest_prio = this_rq->rq_prio;
+
+	cpus_and(tmp, cpu_online_map, p->cpus_allowed);
+
+	for_each_cpu_mask(cpu, tmp) {
+		struct rq *rq;
+		int rq_prio;
+
+		rq = cpu_rq(cpu);
+
+		if (rq_idle(rq)) {
+			/* found an idle rq, use that one */
+			highest_prio_rq = rq;
+			goto found_rq;
+		}
+
+		rq_prio = rq->rq_prio;
+		if (rq_prio > highest_prio ||
+			(rq_prio == highest_prio &&
+			time_after(rq->rq_deadline, latest_deadline))) {
+				highest_prio = rq_prio;
+				latest_deadline = rq->rq_deadline;
+				highest_prio_rq = rq;
+		}
+	}
+
+	if (!task_preempts_curr(p, highest_prio_rq))
+		return;
+found_rq:
+	resched_task(highest_prio_rq->curr);
+	return;
+}
+
+/**
+ * task_oncpu_function_call - call a function on the cpu on which a task runs
+ * @p:		the task to evaluate
+ * @func:	the function to be called
+ * @info:	the function call argument
+ *
+ * Calls the function @func when the task is currently running. This might
+ * be on the current CPU, which just calls the function directly
+ */
+void task_oncpu_function_call(struct task_struct *p,
+			      void (*func) (void *info), void *info)
+{
+	int cpu;
+
+	preempt_disable();
+	cpu = task_cpu(p);
+	if (task_curr(p))
+		smp_call_function_single(cpu, func, info, 1);
+	preempt_enable();
+}
+
+#ifdef CONFIG_SMP
+static int suitable_idle_cpus(struct task_struct *p)
+{
+	return (cpus_intersects(p->cpus_allowed, grq.cpu_idle_map));
+}
+#else
+static int suitable_idle_cpus(struct task_struct *p)
+{
+	return 0;
+}
+#endif
+
+/***
+ * try_to_wake_up - wake up a thread
+ * @p: the to-be-woken-up thread
+ * @state: the mask of task states that can be woken
+ * @sync: do a synchronous wakeup?
+ *
+ * Put it on the run-queue if it's not already there. The "current"
+ * thread is always on the run-queue (except when the actual
+ * re-schedule is in progress), and as such you're allowed to do
+ * the simpler "current->state = TASK_RUNNING" to mark yourself
+ * runnable without the overhead of this.
+ *
+ * returns failure only if the task is already active.
+ */
+static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
+{
+	unsigned long flags;
+	int success = 0;
+	long old_state;
+	struct rq *rq;
+
+	rq = time_task_grq_lock(p, &flags);
+	old_state = p->state;
+	if (!(old_state & state))
+		goto out_unlock;
+
+	/*
+	 * Note this catches tasks that are running and queued, but returns
+	 * false during the context switch when they're running and no
+	 * longer queued.
+	 */
+	if (task_queued(p))
+		goto out_running;
+
+	activate_task(p, rq);
+	/*
+	 * Sync wakeups (i.e. those types of wakeups where the waker
+	 * has indicated that it will leave the CPU in short order)
+	 * don't trigger a preemption if there are no idle cpus,
+	 * instead waiting for current to deschedule.
+	 */
+	if (!sync || (sync && suitable_idle_cpus(p)))
+		try_preempt(p);
+	success = 1;
+
+out_running:
+	trace_sched_wakeup(rq, p, success);
+	p->state = TASK_RUNNING;
+out_unlock:
+	task_grq_unlock(&flags);
+	return success;
+}
+
+/**
+ * wake_up_process - Wake up a specific process
+ * @p: The process to be woken up.
+ *
+ * Attempt to wake up the nominated process and move it to the set of runnable
+ * processes.  Returns 1 if the process was woken up, 0 if it was already
+ * running.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+int wake_up_process(struct task_struct *p)
+{
+	return try_to_wake_up(p, TASK_ALL, 0);
+}
+EXPORT_SYMBOL(wake_up_process);
+
+int wake_up_state(struct task_struct *p, unsigned int state)
+{
+	return try_to_wake_up(p, state, 0);
+}
+
+/*
+ * Perform scheduler related setup for a newly forked process p.
+ * p is forked by current.
+ */
+void sched_fork(struct task_struct *p, int clone_flags)
+{
+	int cpu = get_cpu();
+	struct rq *rq;
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+	INIT_HLIST_HEAD(&p->preempt_notifiers);
+#endif
+	/*
+	 * We mark the process as running here, but have not actually
+	 * inserted it onto the runqueue yet. This guarantees that
+	 * nobody will actually run it, and a signal or other external
+	 * event cannot wake it up and insert it on the runqueue either.
+	 */
+	p->state = TASK_RUNNING;
+	set_task_cpu(p, cpu);
+
+	/* Should be reset in fork.c but done here for ease of bfs patching */
+	p->se.sum_exec_runtime = p->stime_pc = p->utime_pc = 0;
+
+	/*
+	 * Make sure we do not leak PI boosting priority to the child:
+	 */
+	p->prio = current->normal_prio;
+
+	INIT_LIST_HEAD(&p->rt.run_list);
+#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+	if (unlikely(sched_info_on()))
+		memset(&p->sched_info, 0, sizeof(p->sched_info));
+#endif
+
+	p->oncpu = 0;
+
+#ifdef CONFIG_PREEMPT
+	/* Want to start with kernel preemption disabled. */
+	task_thread_info(p)->preempt_count = 1;
+#endif
+	if (unlikely(p->policy == SCHED_FIFO))
+		goto out;
+	/*
+	 * Share the timeslice between parent and child, thus the
+	 * total amount of pending timeslices in the system doesn't change,
+	 * resulting in more scheduling fairness. If it's negative, it won't
+	 * matter since that's the same as being 0. current's time_slice is
+	 * actually in rq_time_slice when it's running.
+	 */
+	local_irq_disable();
+	rq = task_rq(current);
+	if (likely(rq->rq_time_slice > 0)) {
+		rq->rq_time_slice /= 2;
+		/*
+		 * The remainder of the first timeslice might be recovered by
+		 * the parent if the child exits early enough.
+		 */
+		p->first_time_slice = 1;
+	}
+	p->rt.time_slice = rq->rq_time_slice;
+	local_irq_enable();
+out:
+	put_cpu();
+}
+
+/*
+ * wake_up_new_task - wake up a newly created task for the first time.
+ *
+ * This function will do some initial scheduler statistics housekeeping
+ * that must be done for every newly created context, then puts the task
+ * on the runqueue and wakes it.
+ */
+void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
+{
+	struct task_struct *parent;
+	unsigned long flags;
+	struct rq *rq;
+
+	rq = time_task_grq_lock(p, &flags); ;
+	parent = p->parent;
+	BUG_ON(p->state != TASK_RUNNING);
+	set_task_cpu(p, task_cpu(parent));
+
+	activate_task(p, rq);
+	trace_sched_wakeup_new(rq, p, 1);
+	if (!(clone_flags & CLONE_VM) && rq->curr == parent &&
+		!suitable_idle_cpus(p)) {
+		/*
+		 * The VM isn't cloned, so we're in a good position to
+		 * do child-runs-first in anticipation of an exec. This
+		 * usually avoids a lot of COW overhead.
+		 */
+			resched_task(parent);
+	} else
+		try_preempt(p);
+	task_grq_unlock(&flags);
+}
+
+/*
+ * Potentially available exiting-child timeslices are
+ * retrieved here - this way the parent does not get
+ * penalized for creating too many threads.
+ *
+ * (this cannot be used to 'generate' timeslices
+ * artificially, because any timeslice recovered here
+ * was given away by the parent in the first place.)
+ */
+void sched_exit(struct task_struct *p)
+{
+	struct task_struct *parent;
+	unsigned long flags;
+	struct rq *rq;
+
+	if (p->first_time_slice) {
+		parent = p->parent;
+		rq = task_grq_lock(parent, &flags);
+		parent->rt.time_slice += p->rt.time_slice;
+		if (unlikely(parent->rt.time_slice > timeslice()))
+			parent->rt.time_slice = timeslice();
+		task_grq_unlock(&flags);
+	}
+}
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+
+/**
+ * preempt_notifier_register - tell me when current is being preempted & rescheduled
+ * @notifier: notifier struct to register
+ */
+void preempt_notifier_register(struct preempt_notifier *notifier)
+{
+	hlist_add_head(&notifier->link, &current->preempt_notifiers);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_register);
+
+/**
+ * preempt_notifier_unregister - no longer interested in preemption notifications
+ * @notifier: notifier struct to unregister
+ *
+ * This is safe to call from within a preemption notifier.
+ */
+void preempt_notifier_unregister(struct preempt_notifier *notifier)
+{
+	hlist_del(&notifier->link);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
+
+static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+	struct preempt_notifier *notifier;
+	struct hlist_node *node;
+
+	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+		notifier->ops->sched_in(notifier, raw_smp_processor_id());
+}
+
+static void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				 struct task_struct *next)
+{
+	struct preempt_notifier *notifier;
+	struct hlist_node *node;
+
+	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+		notifier->ops->sched_out(notifier, next);
+}
+
+#else /* !CONFIG_PREEMPT_NOTIFIERS */
+
+static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+}
+
+static void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				 struct task_struct *next)
+{
+}
+
+#endif /* CONFIG_PREEMPT_NOTIFIERS */
+
+/**
+ * prepare_task_switch - prepare to switch tasks
+ * @rq: the runqueue preparing to switch
+ * @next: the task we are going to switch to.
+ *
+ * This is called with the rq lock held and interrupts off. It must
+ * be paired with a subsequent finish_task_switch after the context
+ * switch.
+ *
+ * prepare_task_switch sets up locking and calls architecture specific
+ * hooks.
+ */
+static inline void
+prepare_task_switch(struct rq *rq, struct task_struct *prev,
+		    struct task_struct *next)
+{
+	fire_sched_out_preempt_notifiers(prev, next);
+	prepare_lock_switch(rq, next);
+	prepare_arch_switch(next);
+}
+
+/**
+ * finish_task_switch - clean up after a task-switch
+ * @rq: runqueue associated with task-switch
+ * @prev: the thread we just switched away from.
+ *
+ * finish_task_switch must be called after the context switch, paired
+ * with a prepare_task_switch call before the context switch.
+ * finish_task_switch will reconcile locking set up by prepare_task_switch,
+ * and do any other architecture-specific cleanup actions.
+ *
+ * Note that we may have delayed dropping an mm in context_switch(). If
+ * so, we finish that here outside of the runqueue lock.  (Doing it
+ * with the lock held can cause deadlocks; see schedule() for
+ * details.)
+ */
+static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
+	__releases(grq.lock)
+{
+	struct mm_struct *mm = rq->prev_mm;
+	long prev_state;
+
+	rq->prev_mm = NULL;
+
+	/*
+	 * A task struct has one reference for the use as "current".
+	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
+	 * schedule one last time. The schedule call will never return, and
+	 * the scheduled task must drop that reference.
+	 * The test for TASK_DEAD must occur while the runqueue locks are
+	 * still held, otherwise prev could be scheduled on another cpu, die
+	 * there before we look at prev->state, and then the reference would
+	 * be dropped twice.
+	 *		Manfred Spraul <manfred@colorfullife.com>
+	 */
+	prev_state = prev->state;
+	finish_arch_switch(prev);
+	perf_counter_task_sched_in(current, cpu_of(rq));
+	finish_lock_switch(rq, prev);
+
+	fire_sched_in_preempt_notifiers(current);
+	if (mm)
+		mmdrop(mm);
+	if (unlikely(prev_state == TASK_DEAD)) {
+		/*
+		 * Remove function-return probe instances associated with this
+		 * task and put them back on the free list.
+	 	 */
+		kprobe_flush_task(prev);
+		put_task_struct(prev);
+	}
+}
+
+/**
+ * schedule_tail - first thing a freshly forked thread must call.
+ * @prev: the thread we just switched away from.
+ */
+asmlinkage void schedule_tail(struct task_struct *prev)
+	__releases(grq.lock)
+{
+	struct rq *rq = this_rq();
+
+	finish_task_switch(rq, prev);
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+	/* In this case, finish_task_switch does not reenable preemption */
+	preempt_enable();
+#endif
+	if (current->set_child_tid)
+		put_user(current->pid, current->set_child_tid);
+}
+
+/*
+ * context_switch - switch to the new MM and the new
+ * thread's register state.
+ */
+static inline void
+context_switch(struct rq *rq, struct task_struct *prev,
+	       struct task_struct *next)
+{
+	struct mm_struct *mm, *oldmm;
+
+	prepare_task_switch(rq, prev, next);
+	trace_sched_switch(rq, prev, next);
+	mm = next->mm;
+	oldmm = prev->active_mm;
+	/*
+	 * For paravirt, this is coupled with an exit in switch_to to
+	 * combine the page table reload and the switch backend into
+	 * one hypercall.
+	 */
+	arch_enter_lazy_cpu_mode();
+
+	if (unlikely(!mm)) {
+		next->active_mm = oldmm;
+		atomic_inc(&oldmm->mm_count);
+		enter_lazy_tlb(oldmm, next);
+	} else
+		switch_mm(oldmm, mm, next);
+
+	if (unlikely(!prev->mm)) {
+		prev->active_mm = NULL;
+		rq->prev_mm = oldmm;
+	}
+	/*
+	 * Since the runqueue lock will be released by the next
+	 * task (which is an invalid locking op but in the case
+	 * of the scheduler it's an obvious special-case), so we
+	 * do an early lockdep release here:
+	 */
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
+	spin_release(&grq.lock.dep_map, 1, _THIS_IP_);
+#endif
+
+	/* Here we just switch the register state and the stack. */
+	switch_to(prev, next, prev);
+
+	barrier();
+	/*
+	 * this_rq must be evaluated again because prev may have moved
+	 * CPUs since it called schedule(), thus the 'rq' on its stack
+	 * frame will be invalid.
+	 */
+	finish_task_switch(this_rq(), prev);
+}
+
+/*
+ * nr_running, nr_uninterruptible and nr_context_switches:
+ *
+ * externally visible scheduler statistics: current number of runnable
+ * threads, current number of uninterruptible-sleeping threads, total
+ * number of context switches performed since bootup. All are measured
+ * without grabbing the grq lock but the occasional inaccurate result
+ * doesn't matter so long as it's positive.
+ */
+unsigned long nr_running(void)
+{
+	long nr = grq.nr_running;
+
+	if (unlikely(nr < 0))
+		nr = 0;
+	return (unsigned long)nr;
+}
+
+unsigned long nr_uninterruptible(void)
+{
+	unsigned long nu = grq.nr_uninterruptible;
+
+	if (unlikely(nu < 0))
+		nu = 0;
+	return nu;
+}
+
+unsigned long long nr_context_switches(void)
+{
+	long long ns = grq.nr_switches;
+
+	/* This is of course impossible */
+	if (unlikely(ns < 0))
+		ns = 1;
+	return (long long)ns;
+}
+
+unsigned long nr_iowait(void)
+{
+	unsigned long i, sum = 0;
+
+	for_each_possible_cpu(i)
+		sum += atomic_read(&cpu_rq(i)->nr_iowait);
+
+	return sum;
+}
+
+unsigned long nr_active(void)
+{
+	return nr_running() + nr_uninterruptible();
+}
+
+DEFINE_PER_CPU(struct kernel_stat, kstat);
+
+EXPORT_PER_CPU_SYMBOL(kstat);
+
+/*
+ * On each tick, see what percentage of that tick was attributed to each
+ * component and add the percentage to the _pc values. Once a _pc value has
+ * accumulated one tick's worth, account for that. This means the total
+ * percentage of load components will always be 100 per tick.
+ */
+static void pc_idle_time(struct rq *rq, unsigned long pc)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t tmp = cputime_to_cputime64(jiffies_to_cputime(1));
+
+	if (atomic_read(&rq->nr_iowait) > 0) {
+		rq->iowait_pc += pc;
+		if (rq->iowait_pc >= 100) {
+			rq->iowait_pc %= 100;
+			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
+		}
+	} else {
+		rq->idle_pc += pc;
+		if (rq->idle_pc >= 100) {
+			rq->idle_pc %= 100;
+			cpustat->idle = cputime64_add(cpustat->idle, tmp);
+		}
+	}
+}
+
+static void
+pc_system_time(struct rq *rq, struct task_struct *p, int hardirq_offset,
+	       unsigned long pc, unsigned long ns)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime_t one_jiffy = jiffies_to_cputime(1);
+	cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+	cputime64_t tmp = cputime_to_cputime64(one_jiffy);
+
+	p->stime_pc += pc;
+	if (p->stime_pc >= 100) {
+		p->stime_pc -= 100;
+		p->stime = cputime_add(p->stime, one_jiffy);
+		p->stimescaled = cputime_add(p->stimescaled, one_jiffy_scaled);
+		account_group_system_time(p, one_jiffy);
+		acct_update_integrals(p);
+	}
+	p->se.sum_exec_runtime += ns;
+
+	if (hardirq_count() - hardirq_offset)
+		rq->irq_pc += pc;
+	else if (softirq_count()) {
+		rq->softirq_pc += pc;
+		if (rq->softirq_pc >= 100) {
+			rq->softirq_pc %= 100;
+			cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+		}
+	} else {
+		rq->system_pc += pc;
+		if (rq->system_pc >= 100) {
+			rq->system_pc %= 100;
+			cpustat->system = cputime64_add(cpustat->system, tmp);
+		}
+	}
+}
+
+static void pc_user_time(struct rq *rq, struct task_struct *p,
+			 unsigned long pc, unsigned long ns)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime_t one_jiffy = jiffies_to_cputime(1);
+	cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+	cputime64_t tmp = cputime_to_cputime64(one_jiffy);
+
+	p->utime_pc += pc;
+	if (p->utime_pc >= 100) {
+		p->utime_pc -= 100;
+		p->utime = cputime_add(p->utime, one_jiffy);
+		p->utimescaled = cputime_add(p->utimescaled, one_jiffy_scaled);
+		account_group_user_time(p, one_jiffy);
+		acct_update_integrals(p);
+	}
+	p->se.sum_exec_runtime += ns;
+
+	if (TASK_NICE(p) > 0 || idleprio_task(p)) {
+		rq->nice_pc += pc;
+		if (rq->nice_pc >= 100) {
+			rq->nice_pc %= 100;
+			cpustat->nice = cputime64_add(cpustat->nice, tmp);
+		}
+	} else {
+		rq->user_pc += pc;
+		if (rq->user_pc >= 100) {
+			rq->user_pc %= 100;
+			cpustat->user = cputime64_add(cpustat->user, tmp);
+		}
+	}
+}
+
+/* Convert nanoseconds to percentage of one tick. */
+#define NS_TO_PC(NS)	(NS * 100 / JIFFIES_TO_NS(1))
+
+/*
+ * This is called on clock ticks and on context switches.
+ * Bank in p->se.sum_exec_runtime the ns elapsed since the last tick or switch.
+ * CPU scheduler quota accounting is also performed here in microseconds.
+ * The value returned from sched_clock() occasionally gives bogus values so
+ * some sanity checking is required. Time is supposed to be banked all the
+ * time so default to half a tick to make up for when sched_clock reverts
+ * to just returning jiffies, and for hardware that can't do tsc.
+ */
+static void
+update_cpu_clock(struct rq *rq, struct task_struct *p, int tick)
+{
+	long time_diff = rq->clock - p->last_ran;
+	long account_ns = rq->clock - rq->timekeep_clock;
+	struct task_struct *idle = rq->idle;
+	unsigned long account_pc;
+
+	/*
+	 * There should be less than or equal to one jiffy worth, and not
+	 * negative/overflow. time_diff is only used for internal scheduler
+	 * time_slice accounting.
+	 */
+	if (time_diff <= 0)
+		time_diff = JIFFIES_TO_NS(1) / 2;
+	else if (time_diff > JIFFIES_TO_NS(1))
+		time_diff = JIFFIES_TO_NS(1);
+
+	if (unlikely(account_ns < 0))
+		account_ns = 0;
+
+	account_pc = NS_TO_PC(account_ns);
+
+	if (tick) {
+		int user_tick = user_mode(get_irq_regs());
+
+		/* Accurate tick timekeeping */
+		if (user_tick)
+			pc_user_time(rq, p, account_pc, account_ns);
+		else if (p != idle || (irq_count() != HARDIRQ_OFFSET))
+			pc_system_time(rq, p, HARDIRQ_OFFSET,
+				       account_pc, account_ns);
+		else
+			pc_idle_time(rq, account_pc);
+	} else {
+		/* Accurate subtick timekeeping */
+		if (p == idle)
+			pc_idle_time(rq, account_pc);
+		else
+			pc_user_time(rq, p, account_pc, account_ns);
+	}
+
+	/* time_slice accounting is done in usecs to avoid overflow on 32bit */
+	if (rq->rq_policy != SCHED_FIFO && p != idle)
+		rq->rq_time_slice -= time_diff / 1000;
+	p->last_ran = rq->timekeep_clock = rq->clock;
+}
+
+/*
+ * Return any ns on the sched_clock that have not yet been accounted in
+ * @p in case that task is currently running.
+ *
+ * Called with task_grq_lock() held on @rq.
+ */
+static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
+{
+	u64 ns = 0;
+
+	if (p == rq->curr) {
+		update_rq_clock(rq);
+		ns = rq->clock - p->last_ran;
+		if ((s64)ns < 0)
+			ns = 0;
+	}
+
+	return ns;
+}
+
+unsigned long long task_delta_exec(struct task_struct *p)
+{
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns = 0;
+
+	rq = task_grq_lock(p, &flags);
+	ns = do_task_delta_exec(p, rq);
+	task_grq_unlock(&flags);
+
+	return ns;
+}
+
+/*
+ * Return accounted runtime for the task.
+ * In case the task is currently running, return the runtime plus current's
+ * pending runtime that have not been accounted yet.
+ */
+unsigned long long task_sched_runtime(struct task_struct *p)
+{
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns = 0;
+
+	rq = task_grq_lock(p, &flags);
+	ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
+	task_grq_unlock(&flags);
+
+	return ns;
+}
+
+/*
+ * Return sum_exec_runtime for the thread group.
+ * In case the task is currently running, return the sum plus current's
+ * pending runtime that have not been accounted yet.
+ *
+ * Note that the thread group might have other running tasks as well,
+ * so the return value not includes other pending runtime that other
+ * running tasks might have.
+ */
+unsigned long long thread_group_sched_runtime(struct task_struct *p)
+{
+	struct task_cputime totals;
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns;
+
+	rq = task_grq_lock(p, &flags);
+	thread_group_cputime(p, &totals);
+	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
+	task_grq_unlock(&flags);
+
+	return ns;
+}
+
+/* Compatibility crap for removal */
+void account_user_time(struct task_struct *p, cputime_t cputime,
+		       cputime_t cputime_scaled)
+{
+}
+
+void account_idle_time(cputime_t cputime)
+{
+}
+
+/*
+ * Account guest cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+			       cputime_t cputime_scaled)
+{
+	cputime64_t tmp;
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+	tmp = cputime_to_cputime64(cputime);
+
+	/* Add guest time to process. */
+	p->utime = cputime_add(p->utime, cputime);
+	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
+	account_group_user_time(p, cputime);
+	p->gtime = cputime_add(p->gtime, cputime);
+
+	/* Add guest time to cpustat. */
+	cpustat->user = cputime64_add(cpustat->user, tmp);
+	cpustat->guest = cputime64_add(cpustat->guest, tmp);
+}
+
+/*
+ * Account system cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * This is for guest only now.
+ */
+void account_system_time(struct task_struct *p, int hardirq_offset,
+			 cputime_t cputime, cputime_t cputime_scaled)
+{
+
+	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0))
+		account_guest_time(p, cputime, cputime_scaled);
+}
+
+/*
+ * Account for involuntary wait time.
+ * @steal: the cpu time spent in involuntary wait
+ */
+void account_steal_time(cputime_t cputime)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t cputime64 = cputime_to_cputime64(cputime);
+
+	cpustat->steal = cputime64_add(cpustat->steal, cputime64);
+}
+
+/*
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
+ */
+static void account_idle_times(cputime_t cputime)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t cputime64 = cputime_to_cputime64(cputime);
+	struct rq *rq = this_rq();
+
+	if (atomic_read(&rq->nr_iowait) > 0)
+		cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
+	else
+		cpustat->idle = cputime64_add(cpustat->idle, cputime64);
+}
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+	account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+	account_idle_times(jiffies_to_cputime(ticks));
+}
+#endif
+
+/*
+ * Functions to test for when SCHED_ISO tasks have used their allocated
+ * quota as real time scheduling and convert them back to SCHED_NORMAL.
+ * Where possible, the data is tested lockless, to avoid grabbing grq_lock
+ * because the occasional inaccurate result won't matter. However the
+ * data is only ever modified under lock.
+ */
+static void set_iso_refractory(void)
+{
+	grq_lock();
+	grq.iso_refractory = 1;
+	grq_unlock();
+}
+
+static void clear_iso_refractory(void)
+{
+	grq_lock();
+	grq.iso_refractory = 0;
+	grq_unlock();
+}
+
+/*
+ * Test if SCHED_ISO tasks have run longer than their alloted period as RT
+ * tasks and set the refractory flag if necessary. There is 10% hysteresis
+ * for unsetting the flag.
+ */
+static unsigned int test_ret_isorefractory(struct rq *rq)
+{
+	if (likely(!grq.iso_refractory)) {
+		if (grq.iso_ticks / ISO_PERIOD > sched_iso_cpu)
+			set_iso_refractory();
+	} else {
+		if (grq.iso_ticks / ISO_PERIOD < (sched_iso_cpu * 90 / 100))
+			clear_iso_refractory();
+	}
+	return grq.iso_refractory;
+}
+
+static void iso_tick(void)
+{
+	grq_lock();
+	grq.iso_ticks += 100;
+	grq_unlock();
+}
+
+/* No SCHED_ISO task was running so decrease rq->iso_ticks */
+static inline void no_iso_tick(void)
+{
+	if (grq.iso_ticks) {
+		grq_lock();
+		grq.iso_ticks = grq.iso_ticks * (ISO_PERIOD - 1) / ISO_PERIOD;
+		grq_unlock();
+	}
+}
+
+static int rq_running_iso(struct rq *rq)
+{
+	return rq->rq_prio == ISO_PRIO;
+}
+
+/* This manages tasks that have run out of timeslice during a scheduler_tick */
+static void task_running_tick(struct rq *rq)
+{
+	struct task_struct *p;
+
+	/*
+	 * If a SCHED_ISO task is running we increment the iso_ticks. In
+	 * order to prevent SCHED_ISO tasks from causing starvation in the
+	 * presence of true RT tasks we account those as iso_ticks as well.
+	 */
+	if ((rt_queue(rq) || (iso_queue(rq) && !grq.iso_refractory))) {
+		if (grq.iso_ticks <= (ISO_PERIOD * 100) - 100)
+			iso_tick();
+	} else
+		no_iso_tick();
+
+	if (iso_queue(rq)) {
+		if (unlikely(test_ret_isorefractory(rq))) {
+			if (rq_running_iso(rq)) {
+				/*
+				 * SCHED_ISO task is running as RT and limit
+				 * has been hit. Force it to reschedule as
+				 * SCHED_NORMAL by zeroing its time_slice
+				 */
+				rq->rq_time_slice = 0;
+			}
+		}
+	}
+
+	/* SCHED_FIFO tasks never run out of timeslice. */
+	if (rq_idle(rq) || rq->rq_time_slice > 0 || rq->rq_policy == SCHED_FIFO)
+		return;
+
+	/* p->rt.time_slice <= 0. We only modify task_struct under grq lock */
+	grq_lock();
+	p = rq->curr;
+	if (likely(task_running(p))) {
+		requeue_task(p);
+		set_tsk_need_resched(p);
+	}
+	grq_unlock();
+}
+
+void wake_up_idle_cpu(int cpu);
+
+/*
+ * This function gets called by the timer code, with HZ frequency.
+ * We call it with interrupts disabled. The data modified is all
+ * local to struct rq so we don't need to grab grq lock.
+ */
+void scheduler_tick(void)
+{
+	int cpu = smp_processor_id();
+	struct rq *rq = cpu_rq(cpu);
+
+	sched_clock_tick();
+	update_rq_clock(rq);
+	update_cpu_clock(rq, rq->curr, 1);
+	if (!rq_idle(rq))
+		task_running_tick(rq);
+	else {
+		no_iso_tick();
+		if (unlikely(queued_notrunning()))
+			set_tsk_need_resched(rq->idle);
+	}
+}
+
+notrace unsigned long get_parent_ip(unsigned long addr)
+{
+	if (in_lock_functions(addr)) {
+		addr = CALLER_ADDR2;
+		if (in_lock_functions(addr))
+			addr = CALLER_ADDR3;
+	}
+	return addr;
+}
+
+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+				defined(CONFIG_PREEMPT_TRACER))
+void __kprobes add_preempt_count(int val)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Underflow?
+	 */
+	if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
+		return;
+#endif
+	preempt_count() += val;
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Spinlock count overflowing soon?
+	 */
+	DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
+				PREEMPT_MASK - 10);
+#endif
+	if (preempt_count() == val)
+		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+}
+EXPORT_SYMBOL(add_preempt_count);
+
+void __kprobes sub_preempt_count(int val)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Underflow?
+	 */
+	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+		return;
+	/*
+	 * Is the spinlock portion underflowing?
+	 */
+	if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
+			!(preempt_count() & PREEMPT_MASK)))
+		return;
+#endif
+
+	if (preempt_count() == val)
+		trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+	preempt_count() -= val;
+}
+EXPORT_SYMBOL(sub_preempt_count);
+#endif
+
+/*
+ * Deadline is "now" in jiffies + (offset by priority). Setting the deadline
+ * is the key to everything. It distributes cpu fairly amongst tasks of the
+ * same nice value, it proportions cpu according to nice level, it means the
+ * task that last woke up the longest ago has the earliest deadline, thus
+ * ensuring that interactive tasks get low latency on wake up.
+ */
+static inline int prio_deadline_diff(struct task_struct *p)
+{
+	return (pratio(p) * rr_interval * HZ / 1000 / 100) ? : 1;
+}
+
+static inline int longest_deadline(void)
+{
+	return (prio_ratios[39] * rr_interval * HZ / 1000 / 100);
+}
+
+/*
+ * SCHED_IDLE tasks still have a deadline set, but offset by to nice +19.
+ * This allows nice levels to work between IDLEPRIO tasks and gives a
+ * deadline longer than nice +19 for when they're scheduled as SCHED_NORMAL
+ * tasks.
+ */
+static inline void time_slice_expired(struct task_struct *p)
+{
+	reset_first_time_slice(p);
+	p->rt.time_slice = timeslice();
+	p->deadline = jiffies + prio_deadline_diff(p);
+	if (idleprio_task(p))
+		p->deadline += longest_deadline();
+}
+
+static inline void check_deadline(struct task_struct *p)
+{
+	if (p->rt.time_slice <= 0)
+		time_slice_expired(p);
+}
+
+/*
+ * O(n) lookup of all tasks in the global runqueue. The real brainfuck
+ * of lock contention and O(n). It's not really O(n) as only the queued,
+ * but not running tasks are scanned, and is O(n) queued in the worst case
+ * scenario only because the right task can be found before scanning all of
+ * them.
+ * Tasks are selected in this order:
+ * Real time tasks are selected purely by their static priority and in the
+ * order they were queued, so the lowest value idx, and the first queued task
+ * of that priority value is chosen.
+ * If no real time tasks are found, the SCHED_ISO priority is checked, and
+ * all SCHED_ISO tasks have the same priority value, so they're selected by
+ * the earliest deadline value.
+ * If no SCHED_ISO tasks are found, SCHED_NORMAL tasks are selected by the
+ * earliest deadline.
+ * Finally if no SCHED_NORMAL tasks are found, SCHED_IDLEPRIO tasks are
+ * selected by the earliest deadline.
+ */
+static inline struct
+task_struct *earliest_deadline_task(struct rq *rq, struct task_struct *idle)
+{
+	unsigned long dl, earliest_deadline = 0; /* Initialise to silence compiler */
+	struct task_struct *p, *edt;
+	unsigned int cpu = rq->cpu;
+	struct list_head *queue;
+	int idx = 0;
+
+	edt = idle;
+retry:
+	idx = find_next_bit(grq.prio_bitmap, PRIO_LIMIT, idx);
+	if (idx >= PRIO_LIMIT)
+		goto out;
+	queue = &grq.queue[idx];
+	list_for_each_entry(p, queue, rt.run_list) {
+		/* Make sure cpu affinity is ok */
+		if (!cpu_isset(cpu, p->cpus_allowed))
+			continue;
+		if (idx < MAX_RT_PRIO) {
+			/* We found an rt task */
+			edt = p;
+			goto out_take;
+		}
+
+		/*
+		 * No rt task, select the earliest deadline task now.
+		 * On the 1st run the 2nd condition is never used, so
+		 * there is no need to initialise earliest_deadline
+		 * before. Normalise all old deadlines to now.
+		 */
+		if (time_before(p->deadline, jiffies))
+			dl = jiffies;
+		else
+			dl = p->deadline;
+
+		if (edt == idle ||
+		    time_before(dl, earliest_deadline)) {
+			earliest_deadline = dl;
+			edt = p;
+		}
+	}
+	if (edt == idle) {
+		if (++idx < PRIO_LIMIT)
+			goto retry;
+		goto out;
+	}
+out_take:
+	take_task(rq, edt);
+out:
+	return edt;
+}
+
+#ifdef CONFIG_SMP
+static inline void set_cpuidle_map(unsigned long cpu)
+{
+	cpu_set(cpu, grq.cpu_idle_map);
+}
+
+static inline void clear_cpuidle_map(unsigned long cpu)
+{
+	cpu_clear(cpu, grq.cpu_idle_map);
+}
+
+#else /* CONFIG_SMP */
+static inline void set_cpuidle_map(unsigned long cpu)
+{
+}
+
+static inline void clear_cpuidle_map(unsigned long cpu)
+{
+}
+#endif /* !CONFIG_SMP */
+
+/*
+ * Print scheduling while atomic bug:
+ */
+static noinline void __schedule_bug(struct task_struct *prev)
+{
+	struct pt_regs *regs = get_irq_regs();
+
+	printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
+		prev->comm, prev->pid, preempt_count());
+
+	debug_show_held_locks(prev);
+	print_modules();
+	if (irqs_disabled())
+		print_irqtrace_events(prev);
+
+	if (regs)
+		show_regs(regs);
+	else
+		dump_stack();
+}
+
+/*
+ * Various schedule()-time debugging checks and statistics:
+ */
+static inline void schedule_debug(struct task_struct *prev)
+{
+	/*
+	 * Test if we are atomic. Since do_exit() needs to call into
+	 * schedule() atomically, we ignore that path for now.
+	 * Otherwise, whine if we are scheduling when we should not be.
+	 */
+	if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
+		__schedule_bug(prev);
+
+	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
+
+	schedstat_inc(this_rq(), sched_count);
+#ifdef CONFIG_SCHEDSTATS
+	if (unlikely(prev->lock_depth >= 0)) {
+		schedstat_inc(this_rq(), bkl_count);
+		schedstat_inc(prev, sched_info.bkl_count);
+	}
+#endif
+}
+
+/*
+ * schedule() is the main scheduler function.
+ */
+asmlinkage void __sched __schedule(void)
+{
+	struct task_struct *prev, *next, *idle;
+	int deactivate = 0, cpu;
+	long *switch_count;
+	struct rq *rq;
+	u64 now;
+
+	cpu = smp_processor_id();
+	rq = this_rq();
+	rcu_qsctr_inc(cpu);
+	prev = rq->curr;
+	switch_count = &prev->nivcsw;
+
+	release_kernel_lock(prev);
+need_resched_nonpreemptible:
+
+	schedule_debug(prev);
+	idle = rq->idle;
+	/*
+	 * The idle thread is not allowed to schedule!
+	 * Remove this check after it has been exercised a bit.
+	 */
+	if (unlikely(prev == idle) && prev->state != TASK_RUNNING) {
+		printk(KERN_ERR "bad: scheduling from the idle thread!\n");
+		dump_stack();
+	}
+
+	grq_lock_irq();
+	update_rq_clock(rq);
+	now = rq->clock;
+	update_cpu_clock(rq, prev, 0);
+
+	clear_tsk_need_resched(prev);
+
+	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
+		if (unlikely(signal_pending_state(prev->state, prev)))
+			prev->state = TASK_RUNNING;
+		else
+			deactivate = 1;
+		switch_count = &prev->nvcsw;
+	}
+
+	if (prev != idle) {
+		/* Update all the information stored on struct rq */
+		prev->rt.time_slice = rq->rq_time_slice;
+		prev->deadline = rq->rq_deadline;
+		check_deadline(prev);
+		return_task(prev, deactivate);
+	}
+
+	if (likely(queued_notrunning())) {
+		next = earliest_deadline_task(rq, idle);
+	} else {
+		next = idle;
+		schedstat_inc(rq, sched_goidle);
+	}
+
+	if (next == rq->idle)
+		set_cpuidle_map(cpu);
+	else
+		clear_cpuidle_map(cpu);
+
+	prefetch(next);
+	prefetch_stack(next);
+
+	prev->timestamp = prev->last_ran = now;
+
+	if (likely(prev != next)) {
+		rq->rq_time_slice = next->rt.time_slice;
+		rq->rq_deadline = next->deadline;
+		rq->rq_prio = next->prio;
+
+		sched_info_switch(prev, next);
+		grq.nr_switches++;
+		next->oncpu = 1;
+		prev->oncpu = 0;
+		rq->curr = next;
+		++*switch_count;
+
+		context_switch(rq, prev, next); /* unlocks the rq */
+		/*
+		 * the context switch might have flipped the stack from under
+		 * us, hence refresh the local variables.
+		 */
+		cpu = smp_processor_id();
+		rq = cpu_rq(cpu);
+	} else
+		grq_unlock_irq();
+
+	if (unlikely(reacquire_kernel_lock(current) < 0))
+		goto need_resched_nonpreemptible;
+}
+
+asmlinkage void __sched schedule(void)
+{
+need_resched:
+	preempt_disable();
+	__schedule();
+	preempt_enable_no_resched();
+	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+		goto need_resched;
+}
+EXPORT_SYMBOL(schedule);
+
+#ifdef CONFIG_SMP
+int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_PREEMPT
+/*
+ * this is the entry point to schedule() from in-kernel preemption
+ * off of preempt_enable. Kernel preemptions off return from interrupt
+ * occur there and call schedule directly.
+ */
+asmlinkage void __sched preempt_schedule(void)
+{
+	struct thread_info *ti = current_thread_info();
+
+	/*
+	 * If there is a non-zero preempt_count or interrupts are disabled,
+	 * we do not want to preempt the current task. Just return..
+	 */
+	if (likely(ti->preempt_count || irqs_disabled()))
+		return;
+
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+		schedule();
+		sub_preempt_count(PREEMPT_ACTIVE);
+
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (need_resched());
+}
+EXPORT_SYMBOL(preempt_schedule);
+
+/*
+ * this is the entry point to schedule() from kernel preemption
+ * off of irq context.
+ * Note, that this is called and return with irqs disabled. This will
+ * protect us against recursive calling from irq.
+ */
+asmlinkage void __sched preempt_schedule_irq(void)
+{
+	struct thread_info *ti = current_thread_info();
+
+	/* Catch callers which need to be fixed */
+	BUG_ON(ti->preempt_count || !irqs_disabled());
+
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+		local_irq_enable();
+		schedule();
+		local_irq_disable();
+		sub_preempt_count(PREEMPT_ACTIVE);
+
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (need_resched());
+}
+
+#endif /* CONFIG_PREEMPT */
+
+int default_wake_function(wait_queue_t *curr, unsigned mode, int sync,
+			  void *key)
+{
+	return try_to_wake_up(curr->private, mode, sync);
+}
+EXPORT_SYMBOL(default_wake_function);
+
+/*
+ * The core wakeup function.  Non-exclusive wakeups (nr_exclusive == 0) just
+ * wake everything up.  If it's an exclusive wakeup (nr_exclusive == small +ve
+ * number) then we wake all the non-exclusive tasks and one exclusive task.
+ *
+ * There are circumstances in which we can try to wake a task which has already
+ * started to run but is not in state TASK_RUNNING.  try_to_wake_up() returns
+ * zero in this (rare) case, and we handle it by continuing to scan the queue.
+ */
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+		      int nr_exclusive, int sync, void *key)
+{
+	struct list_head *tmp, *next;
+
+	list_for_each_safe(tmp, next, &q->task_list) {
+		wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list);
+		unsigned flags = curr->flags;
+
+		if (curr->func(curr, mode, sync, key) &&
+				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
+			break;
+	}
+}
+
+/**
+ * __wake_up - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: is directly passed to the wakeup function
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void __wake_up(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, 0, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(__wake_up);
+
+/*
+ * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
+ */
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
+{
+	__wake_up_common(q, mode, 1, 0, NULL);
+}
+
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+{
+	__wake_up_common(q, mode, 1, 0, key);
+}
+
+/**
+ * __wake_up_sync_key - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: opaque value to be passed to wakeup targets
+ *
+ * The sync wakeup differs that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
+{
+	unsigned long flags;
+	int sync = 1;
+
+	if (unlikely(!q))
+		return;
+
+	if (unlikely(!nr_exclusive))
+		sync = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, sync, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync_key);
+
+/**
+ * __wake_up_sync - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ *
+ * The sync wakeup differs that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ */
+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+	unsigned long flags;
+	int sync = 1;
+
+	if (unlikely(!q))
+		return;
+
+	if (unlikely(!nr_exclusive))
+		sync = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, sync, NULL);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
+
+/**
+ * complete: - signals a single thread waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up a single thread waiting on this completion. Threads will be
+ * awakened in the same order in which they were queued.
+ *
+ * See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done++;
+	__wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete);
+
+/**
+ * complete_all: - signals all threads waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete_all(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done += UINT_MAX/2;
+	__wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete_all);
+
+static inline long __sched
+do_wait_for_common(struct completion *x, long timeout, int state)
+{
+	if (!x->done) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		wait.flags |= WQ_FLAG_EXCLUSIVE;
+		__add_wait_queue_tail(&x->wait, &wait);
+		do {
+			if (signal_pending_state(state, current)) {
+				timeout = -ERESTARTSYS;
+				break;
+			}
+			__set_current_state(state);
+			spin_unlock_irq(&x->wait.lock);
+			timeout = schedule_timeout(timeout);
+			spin_lock_irq(&x->wait.lock);
+		} while (!x->done && timeout);
+		__remove_wait_queue(&x->wait, &wait);
+		if (!x->done)
+			return timeout;
+	}
+	x->done--;
+	return timeout ?: 1;
+}
+
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+	might_sleep();
+
+	spin_lock_irq(&x->wait.lock);
+	timeout = do_wait_for_common(x, timeout, state);
+	spin_unlock_irq(&x->wait.lock);
+	return timeout;
+}
+
+/**
+ * wait_for_completion: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout.
+ *
+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
+ * and interrupt capability. Also see complete().
+ */
+void __sched wait_for_completion(struct completion *x)
+{
+	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion);
+
+/**
+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible.
+ */
+unsigned long __sched
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_timeout);
+
+/**
+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits for completion of a specific task to be signaled. It is
+ * interruptible.
+ */
+int __sched wait_for_completion_interruptible(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible);
+
+/**
+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ */
+unsigned long __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+					  unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+
+/**
+ * wait_for_completion_killable: - waits for completion of a task (killable)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It can be
+ * interrupted by a kill signal.
+ */
+int __sched wait_for_completion_killable(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_killable);
+
+/**
+ *	try_wait_for_completion - try to decrement a completion without blocking
+ *	@x:	completion structure
+ *
+ *	Returns: 0 if a decrement cannot be done without blocking
+ *		 1 if a decrement succeeded.
+ *
+ *	If a completion is being used as a counting completion,
+ *	attempt to decrement the counter without blocking. This
+ *	enables us to avoid waiting if the resource the completion
+ *	is protecting is not available.
+ */
+bool try_wait_for_completion(struct completion *x)
+{
+	int ret = 1;
+
+	spin_lock_irq(&x->wait.lock);
+	if (!x->done)
+		ret = 0;
+	else
+		x->done--;
+	spin_unlock_irq(&x->wait.lock);
+	return ret;
+}
+EXPORT_SYMBOL(try_wait_for_completion);
+
+/**
+ *	completion_done - Test to see if a completion has any waiters
+ *	@x:	completion structure
+ *
+ *	Returns: 0 if there are waiters (wait_for_completion() in progress)
+ *		 1 if there are no waiters.
+ *
+ */
+bool completion_done(struct completion *x)
+{
+	int ret = 1;
+
+	spin_lock_irq(&x->wait.lock);
+	if (!x->done)
+		ret = 0;
+	spin_unlock_irq(&x->wait.lock);
+	return ret;
+}
+EXPORT_SYMBOL(completion_done);
+
+static long __sched
+sleep_on_common(wait_queue_head_t *q, int state, long timeout)
+{
+	unsigned long flags;
+	wait_queue_t wait;
+
+	init_waitqueue_entry(&wait, current);
+
+	__set_current_state(state);
+
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, &wait);
+	spin_unlock(&q->lock);
+	timeout = schedule_timeout(timeout);
+	spin_lock_irq(&q->lock);
+	__remove_wait_queue(q, &wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return timeout;
+}
+
+void __sched interruptible_sleep_on(wait_queue_head_t *q)
+{
+	sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+EXPORT_SYMBOL(interruptible_sleep_on);
+
+long __sched
+interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+	return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
+}
+EXPORT_SYMBOL(interruptible_sleep_on_timeout);
+
+void __sched sleep_on(wait_queue_head_t *q)
+{
+	sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+EXPORT_SYMBOL(sleep_on);
+
+long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+	return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
+}
+EXPORT_SYMBOL(sleep_on_timeout);
+
+#ifdef CONFIG_RT_MUTEXES
+
+/*
+ * rt_mutex_setprio - set the current priority of a task
+ * @p: task
+ * @prio: prio value (kernel-internal form)
+ *
+ * This function changes the 'effective' priority of a task. It does
+ * not touch ->normal_prio like __setscheduler().
+ *
+ * Used by the rt_mutex code to implement priority inheritance logic.
+ */
+void rt_mutex_setprio(struct task_struct *p, int prio)
+{
+	unsigned long flags;
+	int queued, oldprio;
+	struct rq *rq;
+
+	BUG_ON(prio < 0 || prio > MAX_PRIO);
+
+	rq = time_task_grq_lock(p, &flags);
+
+	oldprio = p->prio;
+	queued = task_queued_only(p);
+	if (queued)
+		dequeue_task(p);
+	p->prio = prio;
+	if (task_running(p) && prio > oldprio)
+		resched_task(p);
+	if (queued) {
+		enqueue_task(p);
+		try_preempt(p);
+	}
+
+	task_grq_unlock(&flags);
+}
+
+#endif
+
+/*
+ * Adjust the deadline for when the priority is to change, before it's
+ * changed.
+ */
+static void adjust_deadline(struct task_struct *p, int new_prio)
+{
+	p->deadline += (prio_ratios[USER_PRIO(new_prio)] - pratio(p)) *
+			rr_interval * HZ / 1000 / 100;
+}
+
+void set_user_nice(struct task_struct *p, long nice)
+{
+	int queued, new_static;
+	unsigned long flags;
+	struct rq *rq;
+
+	if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+		return;
+	new_static = NICE_TO_PRIO(nice);
+	/*
+	 * We have to be careful, if called from sys_setpriority(),
+	 * the task might be in the middle of scheduling on another CPU.
+	 */
+	rq = time_task_grq_lock(p, &flags);
+	/*
+	 * The RT priorities are set via sched_setscheduler(), but we still
+	 * allow the 'normal' nice value to be set - but as expected
+	 * it wont have any effect on scheduling until the task is
+	 * not SCHED_NORMAL/SCHED_BATCH:
+	 */
+	if (has_rt_policy(p)) {
+		p->static_prio = new_static;
+		goto out_unlock;
+	}
+	queued = task_queued_only(p);
+	/*
+	 * If p is actually running, we don't need to do anything when
+	 * changing the priority because the grq is unaffected.
+	 */
+	if (queued)
+		dequeue_task(p);
+
+	adjust_deadline(p, new_static);
+	p->static_prio = new_static;
+	p->prio = effective_prio(p);
+
+	if (queued) {
+		enqueue_task(p);
+		try_preempt(p);
+	}
+
+	/* Just resched the task, schedule() will know what to do. */
+	if (task_running(p))
+		resched_task(p);
+out_unlock:
+	task_grq_unlock(&flags);
+}
+EXPORT_SYMBOL(set_user_nice);
+
+/*
+ * can_nice - check if a task can reduce its nice value
+ * @p: task
+ * @nice: nice value
+ */
+int can_nice(const struct task_struct *p, const int nice)
+{
+	/* convert nice value [19,-20] to rlimit style value [1,40] */
+	int nice_rlim = 20 - nice;
+
+	return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
+		capable(CAP_SYS_NICE));
+}
+
+#ifdef __ARCH_WANT_SYS_NICE
+
+/*
+ * sys_nice - change the priority of the current process.
+ * @increment: priority increment
+ *
+ * sys_setpriority is a more generic, but much slower function that
+ * does similar things.
+ */
+SYSCALL_DEFINE1(nice, int, increment)
+{
+	long nice, retval;
+
+	/*
+	 * Setpriority might change our priority at the same moment.
+	 * We don't have to worry. Conceptually one call occurs first
+	 * and we have a single winner.
+	 */
+	if (increment < -40)
+		increment = -40;
+	if (increment > 40)
+		increment = 40;
+
+	nice = TASK_NICE(current) + increment;
+	if (nice < -20)
+		nice = -20;
+	if (nice > 19)
+		nice = 19;
+
+	if (increment < 0 && !can_nice(current, nice))
+		return -EPERM;
+
+	retval = security_task_setnice(current, nice);
+	if (retval)
+		return retval;
+
+	set_user_nice(current, nice);
+	return 0;
+}
+
+#endif
+
+/**
+ * task_prio - return the priority value of a given task.
+ * @p: the task in question.
+ *
+ * This is the priority value as seen by users in /proc.
+ * RT tasks are offset by -100. Normal tasks are centered
+ * around 1, value goes from 0 (SCHED_ISO) up to 82 (nice +19
+ * SCHED_IDLE).
+ */
+int task_prio(const struct task_struct *p)
+{
+	int delta, prio = p->prio - MAX_RT_PRIO;
+
+	/* rt tasks and iso tasks */
+	if (prio <= 0)
+		goto out;
+
+	delta = (p->deadline - jiffies) * 40 / longest_deadline();
+	if (delta > 0 && delta <= 80)
+		prio += delta;
+out:
+	return prio;
+}
+
+/**
+ * task_nice - return the nice value of a given task.
+ * @p: the task in question.
+ */
+int task_nice(const struct task_struct *p)
+{
+	return TASK_NICE(p);
+}
+EXPORT_SYMBOL_GPL(task_nice);
+
+/**
+ * idle_cpu - is a given cpu idle currently?
+ * @cpu: the processor in question.
+ */
+int idle_cpu(int cpu)
+{
+	return cpu_curr(cpu) == cpu_rq(cpu)->idle;
+}
+
+/**
+ * idle_task - return the idle task for a given cpu.
+ * @cpu: the processor in question.
+ */
+struct task_struct *idle_task(int cpu)
+{
+	return cpu_rq(cpu)->idle;
+}
+
+/**
+ * find_process_by_pid - find a process with a matching PID value.
+ * @pid: the pid in question.
+ */
+static inline struct task_struct *find_process_by_pid(pid_t pid)
+{
+	return pid ? find_task_by_vpid(pid) : current;
+}
+
+/* Actually do priority change: must hold grq lock. */
+static void __setscheduler(struct task_struct *p, int policy, int prio)
+{
+	BUG_ON(task_queued_only(p));
+
+	p->policy = policy;
+	p->rt_priority = prio;
+	p->normal_prio = normal_prio(p);
+	/* we are holding p->pi_lock already */
+	p->prio = rt_mutex_getprio(p);
+	/*
+	 * Reschedule if running. schedule() will know if it can continue
+	 * running or not.
+	 */
+	if (task_running(p))
+		resched_task(p);
+}
+
+/*
+ * check the target process has a UID that matches the current process's
+ */
+static bool check_same_owner(struct task_struct *p)
+{
+	const struct cred *cred = current_cred(), *pcred;
+	bool match;
+
+	rcu_read_lock();
+	pcred = __task_cred(p);
+	match = (cred->euid == pcred->euid ||
+		 cred->euid == pcred->uid);
+	rcu_read_unlock();
+	return match;
+}
+
+static int __sched_setscheduler(struct task_struct *p, int policy,
+		       struct sched_param *param, bool user)
+{
+	struct sched_param zero_param = { .sched_priority = 0 };
+	int queued, retval, oldprio, oldpolicy = -1;
+	unsigned long flags, rlim_rtprio = 0;
+	struct rq *rq;
+
+	/* may grab non-irq protected spin_locks */
+	BUG_ON(in_interrupt());
+
+	if (is_rt_policy(policy) && !capable(CAP_SYS_NICE)) {
+		unsigned long lflags;
+
+		if (!lock_task_sighand(p, &lflags))
+			return -ESRCH;
+		rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
+		unlock_task_sighand(p, &lflags);
+		if (rlim_rtprio)
+			goto recheck;
+		/*
+		 * If the caller requested an RT policy without having the
+		 * necessary rights, we downgrade the policy to SCHED_ISO.
+		 * We also set the parameter to zero to pass the checks.
+		 */
+		policy = SCHED_ISO;
+		param = &zero_param;
+	}
+recheck:
+	/* double check policy once rq lock held */
+	if (policy < 0)
+		policy = oldpolicy = p->policy;
+	else if (!SCHED_RANGE(policy))
+		return -EINVAL;
+	/*
+	 * Valid priorities for SCHED_FIFO and SCHED_RR are
+	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and
+	 * SCHED_BATCH is 0.
+	 */
+	if (param->sched_priority < 0 ||
+	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
+	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+		return -EINVAL;
+	if (is_rt_policy(policy) != (param->sched_priority != 0))
+		return -EINVAL;
+
+	/*
+	 * Allow unprivileged RT tasks to decrease priority:
+	 */
+	if (user && !capable(CAP_SYS_NICE)) {
+		if (is_rt_policy(policy)) {
+			/* can't set/change the rt policy */
+			if (policy != p->policy && !rlim_rtprio)
+				return -EPERM;
+
+			/* can't increase priority */
+			if (param->sched_priority > p->rt_priority &&
+			    param->sched_priority > rlim_rtprio)
+				return -EPERM;
+		} else {
+			switch (p->policy) {
+				/*
+				 * Can only downgrade policies but not back to
+				 * SCHED_NORMAL
+				 */
+				case SCHED_ISO:
+					if (policy == SCHED_ISO)
+						goto out;
+					if (policy == SCHED_NORMAL)
+						return -EPERM;
+					break;
+				case SCHED_BATCH:
+					if (policy == SCHED_BATCH)
+						goto out;
+					if (policy != SCHED_IDLE)
+					    	return -EPERM;
+					break;
+				case SCHED_IDLE:
+					if (policy == SCHED_IDLE)
+						goto out;
+					return -EPERM;
+				default:
+					break;
+			}
+		}
+
+		/* can't change other user's priorities */
+		if (!check_same_owner(p))
+			return -EPERM;
+	}
+
+	retval = security_task_setscheduler(p, policy, param);
+	if (retval)
+		return retval;
+	/*
+	 * make sure no PI-waiters arrive (or leave) while we are
+	 * changing the priority of the task:
+	 */
+	spin_lock_irqsave(&p->pi_lock, flags);
+	/*
+	 * To be able to change p->policy safely, the apropriate
+	 * runqueue lock must be held.
+	 */
+	rq = __task_grq_lock(p);
+	/* recheck policy now with rq lock held */
+	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
+		__task_grq_unlock();
+		spin_unlock_irqrestore(&p->pi_lock, flags);
+		policy = oldpolicy = -1;
+		goto recheck;
+	}
+	update_rq_clock(rq);
+	queued = task_queued_only(p);
+	if (queued)
+		dequeue_task(p);
+	oldprio = p->prio;
+	__setscheduler(p, policy, param->sched_priority);
+	if (queued) {
+		enqueue_task(p);
+		try_preempt(p);
+	}
+	__task_grq_unlock();
+	spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	rt_mutex_adjust_pi(p);
+out:
+	return 0;
+}
+
+/**
+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * NOTE that the task may be already dead.
+ */
+int sched_setscheduler(struct task_struct *p, int policy,
+		       struct sched_param *param)
+{
+	return __sched_setscheduler(p, policy, param, true);
+}
+
+EXPORT_SYMBOL_GPL(sched_setscheduler);
+
+/**
+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * Just like sched_setscheduler, only don't bother checking if the
+ * current context has permission.  For example, this is needed in
+ * stop_machine(): we create temporary high priority worker threads,
+ * but our caller might not have that capability.
+ */
+int sched_setscheduler_nocheck(struct task_struct *p, int policy,
+			       struct sched_param *param)
+{
+	return __sched_setscheduler(p, policy, param, false);
+}
+
+static int
+do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+{
+	struct sched_param lparam;
+	struct task_struct *p;
+	int retval;
+
+	if (!param || pid < 0)
+		return -EINVAL;
+	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
+		return -EFAULT;
+
+	rcu_read_lock();
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (p != NULL)
+		retval = sched_setscheduler(p, policy, &lparam);
+	rcu_read_unlock();
+
+	return retval;
+}
+
+/**
+ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
+ * @pid: the pid in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ */
+asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
+				       struct sched_param __user *param)
+{
+	/* negative values for policy are not valid */
+	if (policy < 0)
+		return -EINVAL;
+
+	return do_sched_setscheduler(pid, policy, param);
+}
+
+/**
+ * sys_sched_setparam - set/change the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the new RT priority.
+ */
+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
+{
+	return do_sched_setscheduler(pid, -1, param);
+}
+
+/**
+ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
+ * @pid: the pid in question.
+ */
+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
+{
+	struct task_struct *p;
+	int retval = -EINVAL;
+
+	if (pid < 0)
+		goto out_nounlock;
+
+	retval = -ESRCH;
+	read_lock(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	if (p) {
+		retval = security_task_getscheduler(p);
+		if (!retval)
+			retval = p->policy;
+	}
+	read_unlock(&tasklist_lock);
+
+out_nounlock:
+	return retval;
+}
+
+/**
+ * sys_sched_getscheduler - get the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the RT priority.
+ */
+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
+{
+	struct sched_param lp;
+	struct task_struct *p;
+	int retval = -EINVAL;
+
+	if (!param || pid < 0)
+		goto out_nounlock;
+
+	read_lock(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	retval = -ESRCH;
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	lp.sched_priority = p->rt_priority;
+	read_unlock(&tasklist_lock);
+
+	/*
+	 * This one might sleep, we cannot do it with a spinlock held ...
+	 */
+	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
+
+out_nounlock:
+	return retval;
+
+out_unlock:
+	read_unlock(&tasklist_lock);
+	return retval;
+}
+
+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+{
+	cpumask_var_t cpus_allowed, new_mask;
+	struct task_struct *p;
+	int retval;
+
+	get_online_cpus();
+	read_lock(&tasklist_lock);
+
+	p = find_process_by_pid(pid);
+	if (!p) {
+		read_unlock(&tasklist_lock);
+		put_online_cpus();
+		return -ESRCH;
+	}
+
+	/*
+	 * It is not safe to call set_cpus_allowed with the
+	 * tasklist_lock held. We will bump the task_struct's
+	 * usage count and then drop tasklist_lock.
+	 */
+	get_task_struct(p);
+	read_unlock(&tasklist_lock);
+
+	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_put_task;
+	}
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_free_cpus_allowed;
+	}
+	retval = -EPERM;
+	if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
+		goto out_unlock;
+
+	retval = security_task_setscheduler(p, 0, NULL);
+	if (retval)
+		goto out_unlock;
+
+	cpuset_cpus_allowed(p, cpus_allowed);
+	cpumask_and(new_mask, in_mask, cpus_allowed);
+again:
+	retval = set_cpus_allowed_ptr(p, new_mask);
+
+	if (!retval) {
+		cpuset_cpus_allowed(p, cpus_allowed);
+		if (!cpumask_subset(new_mask, cpus_allowed)) {
+			/*
+			 * We must have raced with a concurrent cpuset
+			 * update. Just reset the cpus_allowed to the
+			 * cpuset's cpus_allowed
+			 */
+			cpumask_copy(new_mask, cpus_allowed);
+			goto again;
+		}
+	}
+out_unlock:
+	free_cpumask_var(new_mask);
+out_free_cpus_allowed:
+	free_cpumask_var(cpus_allowed);
+out_put_task:
+	put_task_struct(p);
+	put_online_cpus();
+	return retval;
+}
+
+static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
+			     cpumask_t *new_mask)
+{
+	if (len < sizeof(cpumask_t)) {
+		memset(new_mask, 0, sizeof(cpumask_t));
+	} else if (len > sizeof(cpumask_t)) {
+		len = sizeof(cpumask_t);
+	}
+	return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
+}
+
+
+/**
+ * sys_sched_setaffinity - set the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to the new cpu mask
+ */
+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
+{
+	cpumask_var_t new_mask;
+	int retval;
+
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
+	if (retval == 0)
+		retval = sched_setaffinity(pid, new_mask);
+	free_cpumask_var(new_mask);
+	return retval;
+}
+
+long sched_getaffinity(pid_t pid, cpumask_t *mask)
+{
+	struct task_struct *p;
+	int retval;
+
+	mutex_lock(&sched_hotcpu_mutex);
+	read_lock(&tasklist_lock);
+
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	cpus_and(*mask, p->cpus_allowed, cpu_online_map);
+
+out_unlock:
+	read_unlock(&tasklist_lock);
+	mutex_unlock(&sched_hotcpu_mutex);
+	if (retval)
+		return retval;
+
+	return 0;
+}
+
+/**
+ * sys_sched_getaffinity - get the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ */
+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
+{
+	int ret;
+	cpumask_var_t mask;
+
+	if (len < cpumask_size())
+		return -EINVAL;
+
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	ret = sched_getaffinity(pid, mask);
+	if (ret == 0) {
+		if (copy_to_user(user_mask_ptr, mask, cpumask_size()))
+			ret = -EFAULT;
+		else
+			ret = cpumask_size();
+	}
+	free_cpumask_var(mask);
+
+	return ret;
+}
+
+/**
+ * sys_sched_yield - yield the current processor to other threads.
+ *
+ * This function yields the current CPU to other tasks. It does this by
+ * refilling the timeslice, resetting the deadline and scheduling away.
+ */
+SYSCALL_DEFINE0(sched_yield)
+{
+	struct task_struct *p;
+
+	grq_lock_irq();
+	p = current;
+	schedstat_inc(this_rq(), yld_count);
+	update_rq_clock(task_rq(p));
+	time_slice_expired(p);
+	requeue_task(p);
+
+	/*
+	 * Since we are going to call schedule() anyway, there's
+	 * no need to preempt or enable interrupts:
+	 */
+	__release(grq.lock);
+	spin_release(&grq.lock.dep_map, 1, _THIS_IP_);
+	_raw_spin_unlock(&grq.lock);
+	preempt_enable_no_resched();
+
+	schedule();
+
+	return 0;
+}
+
+static inline int should_resched(void)
+{
+	return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
+}
+
+static void __cond_resched(void)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
+	__might_sleep(__FILE__, __LINE__);
+#endif
+	/*
+	 * The BKS might be reacquired before we have dropped
+	 * PREEMPT_ACTIVE, which could trigger a second
+	 * cond_resched() call.
+	 */
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+		schedule();
+		sub_preempt_count(PREEMPT_ACTIVE);
+	} while (need_resched());
+}
+
+int __sched _cond_resched(void)
+{
+	if (should_resched()) {
+		__cond_resched();
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(_cond_resched);
+
+/*
+ * cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * call schedule, and on return reacquire the lock.
+ *
+ * This works OK both with and without CONFIG_PREEMPT.  We do strange low-level
+ * operations here to prevent schedule() from being called twice (once via
+ * spin_unlock(), once by hand).
+ */
+int cond_resched_lock(spinlock_t *lock)
+{
+	int resched = should_resched();
+	int ret = 0;
+
+	if (spin_needbreak(lock) || resched) {
+		spin_unlock(lock);
+		if (resched)
+			__cond_resched();
+		else
+			cpu_relax();
+		ret = 1;
+		spin_lock(lock);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(cond_resched_lock);
+
+int __sched cond_resched_softirq(void)
+{
+	BUG_ON(!in_softirq());
+
+	if (should_resched()) {
+		local_bh_enable();
+		__cond_resched();
+		local_bh_disable();
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(cond_resched_softirq);
+
+/**
+ * yield - yield the current processor to other threads.
+ *
+ * This is a shortcut for kernel-space yielding - it marks the
+ * thread runnable and calls sys_sched_yield().
+ */
+void __sched yield(void)
+{
+	set_current_state(TASK_RUNNING);
+	sys_sched_yield();
+}
+EXPORT_SYMBOL(yield);
+
+/*
+ * This task is about to go to sleep on IO.  Increment rq->nr_iowait so
+ * that process accounting knows that this is a task in IO wait state.
+ *
+ * But don't do that if it is a deliberate, throttling IO wait (this task
+ * has set its backing_dev_info: the queue against which it should throttle)
+ */
+void __sched io_schedule(void)
+{
+	struct rq *rq = &__raw_get_cpu_var(runqueues);
+
+	delayacct_blkio_start();
+	atomic_inc(&rq->nr_iowait);
+	schedule();
+	atomic_dec(&rq->nr_iowait);
+	delayacct_blkio_end();
+}
+EXPORT_SYMBOL(io_schedule);
+
+long __sched io_schedule_timeout(long timeout)
+{
+	struct rq *rq = &__raw_get_cpu_var(runqueues);
+	long ret;
+
+	delayacct_blkio_start();
+	atomic_inc(&rq->nr_iowait);
+	ret = schedule_timeout(timeout);
+	atomic_dec(&rq->nr_iowait);
+	delayacct_blkio_end();
+	return ret;
+}
+
+/**
+ * sys_sched_get_priority_max - return maximum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the maximum rt_priority that can be used
+ * by a given scheduling class.
+ */
+SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
+{
+	int ret = -EINVAL;
+
+	switch (policy) {
+	case SCHED_FIFO:
+	case SCHED_RR:
+		ret = MAX_USER_RT_PRIO-1;
+		break;
+	case SCHED_NORMAL:
+	case SCHED_BATCH:
+	case SCHED_ISO:
+	case SCHED_IDLE:
+		ret = 0;
+		break;
+	}
+	return ret;
+}
+
+/**
+ * sys_sched_get_priority_min - return minimum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the minimum rt_priority that can be used
+ * by a given scheduling class.
+ */
+SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
+{
+	int ret = -EINVAL;
+
+	switch (policy) {
+	case SCHED_FIFO:
+	case SCHED_RR:
+		ret = 1;
+		break;
+	case SCHED_NORMAL:
+	case SCHED_BATCH:
+	case SCHED_ISO:
+	case SCHED_IDLE:
+		ret = 0;
+		break;
+	}
+	return ret;
+}
+
+/**
+ * sys_sched_rr_get_interval - return the default timeslice of a process.
+ * @pid: pid of the process.
+ * @interval: userspace pointer to the timeslice value.
+ *
+ * this syscall writes the default timeslice value of a given process
+ * into the user-space timespec buffer. A value of '0' means infinity.
+ */
+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
+		struct timespec __user *, interval)
+{
+	struct task_struct *p;
+	int retval = -EINVAL;
+	struct timespec t;
+
+	if (pid < 0)
+		goto out_nounlock;
+
+	retval = -ESRCH;
+	read_lock(&tasklist_lock);
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	t = ns_to_timespec(p->policy == SCHED_FIFO ? 0 :
+			   MS_TO_NS(task_timeslice(p)));
+	read_unlock(&tasklist_lock);
+	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
+out_nounlock:
+	return retval;
+out_unlock:
+	read_unlock(&tasklist_lock);
+	return retval;
+}
+
+static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
+
+void sched_show_task(struct task_struct *p)
+{
+	unsigned long free = 0;
+	unsigned state;
+
+	state = p->state ? __ffs(p->state) + 1 : 0;
+	printk(KERN_INFO "%-13.13s %c", p->comm,
+		state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
+#if BITS_PER_LONG == 32
+	if (state == TASK_RUNNING)
+		printk(KERN_CONT " running  ");
+	else
+		printk(KERN_CONT " %08lx ", thread_saved_pc(p));
+#else
+	if (state == TASK_RUNNING)
+		printk(KERN_CONT "  running task    ");
+	else
+		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
+#endif
+#ifdef CONFIG_DEBUG_STACK_USAGE
+	free = stack_not_used(p);
+#endif
+	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
+		task_pid_nr(p), task_pid_nr(p->real_parent),
+		(unsigned long)task_thread_info(p)->flags);
+
+	show_stack(p, NULL);
+}
+
+void show_state_filter(unsigned long state_filter)
+{
+	struct task_struct *g, *p;
+
+#if BITS_PER_LONG == 32
+	printk(KERN_INFO
+		"  task                PC stack   pid father\n");
+#else
+	printk(KERN_INFO
+		"  task                        PC stack   pid father\n");
+#endif
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		/*
+		 * reset the NMI-timeout, listing all files on a slow
+		 * console might take alot of time:
+		 */
+		touch_nmi_watchdog();
+		if (!state_filter || (p->state & state_filter))
+			sched_show_task(p);
+	} while_each_thread(g, p);
+
+	touch_all_softlockup_watchdogs();
+
+	read_unlock(&tasklist_lock);
+	/*
+	 * Only show locks if all tasks are dumped:
+	 */
+	if (state_filter == -1)
+		debug_show_all_locks();
+}
+
+/**
+ * init_idle - set up an idle thread for a given CPU
+ * @idle: task in question
+ * @cpu: cpu the idle task belongs to
+ *
+ * NOTE: this function does not set the idle thread's NEED_RESCHED
+ * flag, to make booting more robust.
+ */
+void __cpuinit init_idle(struct task_struct *idle, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	time_grq_lock(rq, &flags);
+	idle->timestamp = idle->last_ran = rq->clock;
+	idle->state = TASK_RUNNING;
+	/* Setting prio to illegal value shouldn't matter when never queued */
+	idle->prio = rq->rq_prio = PRIO_LIMIT;
+	rq->rq_deadline = idle->deadline;
+	rq->rq_policy = idle->policy;
+	rq->rq_time_slice = idle->rt.time_slice;
+	idle->cpus_allowed = cpumask_of_cpu(cpu);
+	set_task_cpu(idle, cpu);
+	rq->curr = rq->idle = idle;
+	idle->oncpu = 1;
+	set_cpuidle_map(cpu);
+#ifdef CONFIG_HOTPLUG_CPU
+	idle->unplugged_mask = CPU_MASK_NONE;
+#endif
+	grq_unlock_irqrestore(&flags);
+
+	/* Set the preempt count _outside_ the spinlocks! */
+#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL)
+	task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
+#else
+	task_thread_info(idle)->preempt_count = 0;
+#endif
+	ftrace_graph_init_task(idle);
+}
+
+/*
+ * In a system that switches off the HZ timer nohz_cpu_mask
+ * indicates which cpus entered this state. This is used
+ * in the rcu update to wait only for active cpus. For system
+ * which do not switch off the HZ timer nohz_cpu_mask should
+ * always be CPU_BITS_NONE.
+ */
+cpumask_var_t nohz_cpu_mask;
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_NO_HZ
+static struct {
+	atomic_t load_balancer;
+	cpumask_var_t cpu_mask;
+	cpumask_var_t ilb_grp_nohz_mask;
+} nohz ____cacheline_aligned = {
+	.load_balancer = ATOMIC_INIT(-1),
+};
+
+int get_nohz_load_balancer(void)
+{
+	return atomic_read(&nohz.load_balancer);
+}
+
+/*
+ * This routine will try to nominate the ilb (idle load balancing)
+ * owner among the cpus whose ticks are stopped. ilb owner will do the idle
+ * load balancing on behalf of all those cpus. If all the cpus in the system
+ * go into this tickless mode, then there will be no ilb owner (as there is
+ * no need for one) and all the cpus will sleep till the next wakeup event
+ * arrives...
+ *
+ * For the ilb owner, tick is not stopped. And this tick will be used
+ * for idle load balancing. ilb owner will still be part of
+ * nohz.cpu_mask..
+ *
+ * While stopping the tick, this cpu will become the ilb owner if there
+ * is no other owner. And will be the owner till that cpu becomes busy
+ * or if all cpus in the system stop their ticks at which point
+ * there is no need for ilb owner.
+ *
+ * When the ilb owner becomes busy, it nominates another owner, during the
+ * next busy scheduler_tick()
+ */
+int select_nohz_load_balancer(int stop_tick)
+{
+	int cpu = smp_processor_id();
+
+	if (stop_tick) {
+		cpu_rq(cpu)->in_nohz_recently = 1;
+
+		if (!cpu_active(cpu)) {
+			if (atomic_read(&nohz.load_balancer) != cpu)
+				return 0;
+
+			/*
+			 * If we are going offline and still the leader,
+			 * give up!
+			 */
+			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
+				BUG();
+
+			return 0;
+		}
+
+		cpumask_set_cpu(cpu, nohz.cpu_mask);
+
+		/* time for ilb owner also to sleep */
+		if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
+			if (atomic_read(&nohz.load_balancer) == cpu)
+				atomic_set(&nohz.load_balancer, -1);
+			return 0;
+		}
+
+		if (atomic_read(&nohz.load_balancer) == -1) {
+			/* make me the ilb owner */
+			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
+				return 1;
+		} else if (atomic_read(&nohz.load_balancer) == cpu)
+			return 1;
+	} else {
+		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
+			return 0;
+
+		cpumask_clear_cpu(cpu, nohz.cpu_mask);
+
+		if (atomic_read(&nohz.load_balancer) == cpu)
+			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
+				BUG();
+	}
+	return 0;
+}
+
+/*
+ * When add_timer_on() enqueues a timer into the timer wheel of an
+ * idle CPU then this timer might expire before the next timer event
+ * which is scheduled to wake up that CPU. In case of a completely
+ * idle system the next event might even be infinite time into the
+ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
+ * leaves the inner idle loop so the newly added timer is taken into
+ * account when the CPU goes back to idle and evaluates the timer
+ * wheel for the next timer event.
+ */
+void wake_up_idle_cpu(int cpu)
+{
+	struct task_struct *idle;
+	struct rq *rq;
+
+	if (cpu == smp_processor_id())
+		return;
+
+	rq = cpu_rq(cpu);
+	idle = rq->idle;
+
+	/*
+	 * This is safe, as this function is called with the timer
+	 * wheel base lock of (cpu) held. When the CPU is on the way
+	 * to idle and has not yet set rq->curr to idle then it will
+	 * be serialized on the timer wheel base lock and take the new
+	 * timer into account automatically.
+	 */
+	if (unlikely(rq->curr != idle))
+		return;
+
+	/*
+	 * We can set TIF_RESCHED on the idle task of the other CPU
+	 * lockless. The worst case is that the other CPU runs the
+	 * idle task through an additional NOOP schedule()
+	 */
+	set_tsk_need_resched(idle);
+
+	/* NEED_RESCHED must be visible before we test polling */
+	smp_mb();
+	if (!tsk_is_polling(idle))
+		smp_send_reschedule(cpu);
+}
+
+#endif /* CONFIG_NO_HZ */
+
+/*
+ * Change a given task's CPU affinity. Migrate the thread to a
+ * proper CPU and schedule it away if the CPU it's executing on
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely. The
+ * call is not atomic; no spinlocks may be held.
+ */
+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
+{
+	unsigned long flags;
+	int running = 0;
+	int queued = 0;
+	struct rq *rq;
+	int ret = 0;
+
+	rq = task_grq_lock(p, &flags);
+	if (!cpumask_intersects(new_mask, cpu_online_mask)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
+		     !cpumask_equal(&p->cpus_allowed, new_mask))) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	queued = task_queued_only(p);
+
+	cpumask_copy(&p->cpus_allowed, new_mask);
+	p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+
+	/* Can the task run on the task's current CPU? If so, we're done */
+	if (cpumask_test_cpu(task_cpu(p), new_mask))
+		goto out;
+
+	/* Reschedule the task, schedule() will know if it can keep running */
+	if (task_running(p))
+		running = 1;
+	else
+		set_task_cpu(p, cpumask_any_and(cpu_online_mask, new_mask));
+
+out:
+	if (queued)
+		try_preempt(p);
+	task_grq_unlock(&flags);
+
+	/* This might be a flaky way of changing cpus! */
+	if (running)
+		schedule();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
+
+#ifdef CONFIG_HOTPLUG_CPU
+/* Schedules idle task to be the next runnable task on current CPU.
+ * It does so by boosting its priority to highest possible.
+ * Used by CPU offline code.
+ */
+void sched_idle_next(void)
+{
+	int this_cpu = smp_processor_id();
+	struct rq *rq = cpu_rq(this_cpu);
+	struct task_struct *idle = rq->idle;
+	unsigned long flags;
+
+	/* cpu has to be offline */
+	BUG_ON(cpu_online(this_cpu));
+
+	/*
+	 * Strictly not necessary since rest of the CPUs are stopped by now
+	 * and interrupts disabled on the current cpu.
+	 */
+	time_grq_lock(rq, &flags);
+
+	__setscheduler(idle, SCHED_FIFO, MAX_RT_PRIO - 1);
+
+	activate_idle_task(idle);
+	set_tsk_need_resched(rq->curr);
+
+	grq_unlock_irqrestore(&flags);
+}
+
+/*
+ * Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
+ */
+void idle_task_exit(void)
+{
+	struct mm_struct *mm = current->active_mm;
+
+	BUG_ON(cpu_online(smp_processor_id()));
+
+	if (mm != &init_mm)
+		switch_mm(mm, &init_mm, current);
+	mmdrop(mm);
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
+
+static struct ctl_table sd_ctl_dir[] = {
+	{
+		.procname	= "sched_domain",
+		.mode		= 0555,
+	},
+	{0, },
+};
+
+static struct ctl_table sd_ctl_root[] = {
+	{
+		.ctl_name	= CTL_KERN,
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= sd_ctl_dir,
+	},
+	{0, },
+};
+
+static struct ctl_table *sd_alloc_ctl_entry(int n)
+{
+	struct ctl_table *entry =
+		kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
+
+	return entry;
+}
+
+static void sd_free_ctl_entry(struct ctl_table **tablep)
+{
+	struct ctl_table *entry;
+
+	/*
+	 * In the intermediate directories, both the child directory and
+	 * procname are dynamically allocated and could fail but the mode
+	 * will always be set. In the lowest directory the names are
+	 * static strings and all have proc handlers.
+	 */
+	for (entry = *tablep; entry->mode; entry++) {
+		if (entry->child)
+			sd_free_ctl_entry(&entry->child);
+		if (entry->proc_handler == NULL)
+			kfree(entry->procname);
+	}
+
+	kfree(*tablep);
+	*tablep = NULL;
+}
+
+static void
+set_table_entry(struct ctl_table *entry,
+		const char *procname, void *data, int maxlen,
+		mode_t mode, proc_handler *proc_handler)
+{
+	entry->procname = procname;
+	entry->data = data;
+	entry->maxlen = maxlen;
+	entry->mode = mode;
+	entry->proc_handler = proc_handler;
+}
+
+static struct ctl_table *
+sd_alloc_ctl_domain_table(struct sched_domain *sd)
+{
+	struct ctl_table *table = sd_alloc_ctl_entry(13);
+
+	if (table == NULL)
+		return NULL;
+
+	set_table_entry(&table[0], "min_interval", &sd->min_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax);
+	set_table_entry(&table[1], "max_interval", &sd->max_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax);
+	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[9], "cache_nice_tries",
+		&sd->cache_nice_tries,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[10], "flags", &sd->flags,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[11], "name", sd->name,
+		CORENAME_MAX_SIZE, 0444, proc_dostring);
+	/* &table[12] is terminator */
+
+	return table;
+}
+
+static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
+{
+	struct ctl_table *entry, *table;
+	struct sched_domain *sd;
+	int domain_num = 0, i;
+	char buf[32];
+
+	for_each_domain(cpu, sd)
+		domain_num++;
+	entry = table = sd_alloc_ctl_entry(domain_num + 1);
+	if (table == NULL)
+		return NULL;
+
+	i = 0;
+	for_each_domain(cpu, sd) {
+		snprintf(buf, 32, "domain%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_domain_table(sd);
+		entry++;
+		i++;
+	}
+	return table;
+}
+
+static struct ctl_table_header *sd_sysctl_header;
+static void register_sched_domain_sysctl(void)
+{
+	int i, cpu_num = num_online_cpus();
+	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
+	char buf[32];
+
+	WARN_ON(sd_ctl_dir[0].child);
+	sd_ctl_dir[0].child = entry;
+
+	if (entry == NULL)
+		return;
+
+	for_each_online_cpu(i) {
+		snprintf(buf, 32, "cpu%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_cpu_table(i);
+		entry++;
+	}
+
+	WARN_ON(sd_sysctl_header);
+	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
+}
+
+/* may be called multiple times per register */
+static void unregister_sched_domain_sysctl(void)
+{
+	if (sd_sysctl_header)
+		unregister_sysctl_table(sd_sysctl_header);
+	sd_sysctl_header = NULL;
+	if (sd_ctl_dir[0].child)
+		sd_free_ctl_entry(&sd_ctl_dir[0].child);
+}
+#else
+static void register_sched_domain_sysctl(void)
+{
+}
+static void unregister_sched_domain_sysctl(void)
+{
+}
+#endif
+
+static void set_rq_online(struct rq *rq)
+{
+	if (!rq->online) {
+		cpumask_set_cpu(rq->cpu, rq->rd->online);
+		rq->online = 1;
+	}
+}
+
+static void set_rq_offline(struct rq *rq)
+{
+	if (rq->online) {
+		cpumask_clear_cpu(rq->cpu, rq->rd->online);
+		rq->online = 0;
+	}
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * This cpu is going down, so walk over the tasklist and find tasks that can
+ * only run on this cpu and remove their affinity. Store their value in
+ * unplugged_mask so it can be restored once their correct cpu is online. No
+ * need to do anything special since they'll just move on next reschedule if
+ * they're running.
+ */
+static void remove_cpu(unsigned long cpu)
+{
+	struct task_struct *p, *t;
+
+	read_lock(&tasklist_lock);
+
+	do_each_thread(t, p) {
+		cpumask_t cpus_remaining;
+
+		cpus_and(cpus_remaining, p->cpus_allowed, cpu_online_map);
+		cpu_clear(cpu, cpus_remaining);
+		if (cpus_empty(cpus_remaining)) {
+			p->unplugged_mask = p->cpus_allowed;
+			p->cpus_allowed = cpu_possible_map;
+		}
+	} while_each_thread(t, p);
+
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ * This cpu is coming up so add it to the cpus_allowed.
+ */
+static void add_cpu(unsigned long cpu)
+{
+	struct task_struct *p, *t;
+
+	read_lock(&tasklist_lock);
+
+	do_each_thread(t, p) {
+		/* Have we taken all the cpus from the unplugged_mask back */
+		if (cpus_empty(p->unplugged_mask))
+			continue;
+
+		/* Was this cpu in the unplugged_mask mask */
+		if (cpu_isset(cpu, p->unplugged_mask)) {
+			cpu_set(cpu, p->cpus_allowed);
+			if (cpus_subset(p->unplugged_mask, p->cpus_allowed)) {
+				/*
+				 * Have we set more than the unplugged_mask?
+				 * If so, that means we have remnants set from
+				 * the unplug/plug cycle and need to remove
+				 * them. Then clear the unplugged_mask as we've
+				 * set all the cpus back.
+				 */
+				p->cpus_allowed = p->unplugged_mask;
+				cpus_clear(p->unplugged_mask);
+			}
+		}
+	} while_each_thread(t, p);
+
+	read_unlock(&tasklist_lock);
+}
+#else
+static void add_cpu(unsigned long cpu)
+{
+}
+#endif
+
+/*
+ * migration_call - callback that gets triggered when a CPU is added.
+ */
+static int __cpuinit
+migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+	unsigned long flags;
+	struct rq *rq;
+
+	switch (action) {
+
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		break;
+
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		/* Update our root-domain */
+		rq = cpu_rq(cpu);
+		grq_lock_irqsave(&flags);
+		if (rq->rd) {
+			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+
+			set_rq_online(rq);
+		}
+		add_cpu(cpu);
+		grq_unlock_irqrestore(&flags);
+		break;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+		break;
+
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */
+		rq = cpu_rq(cpu);
+		/* Idle task back to normal (off runqueue, low prio) */
+		grq_lock_irq();
+		remove_cpu(cpu);
+		deactivate_task(rq->idle);
+		rq->idle->static_prio = MAX_PRIO;
+		__setscheduler(rq->idle, SCHED_NORMAL, 0);
+		rq->idle->prio = PRIO_LIMIT;
+		update_rq_clock(rq);
+		grq_unlock_irq();
+		cpuset_unlock();
+		break;
+
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		rq = cpu_rq(cpu);
+		grq_lock_irqsave(&flags);
+		if (rq->rd) {
+			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+			set_rq_offline(rq);
+		}
+		grq_unlock_irqrestore(&flags);
+		break;
+#endif
+	}
+	return NOTIFY_OK;
+}
+
+/*
+ * Register at high priority so that task migration (migrate_all_tasks)
+ * happens before everything else.  This has to be lower priority than
+ * the notifier in the perf_counter subsystem, though.
+ */
+static struct notifier_block __cpuinitdata migration_notifier = {
+	.notifier_call = migration_call,
+	.priority = 10
+};
+
+int __init migration_init(void)
+{
+	void *cpu = (void *)(long)smp_processor_id();
+	int err;
+
+	/* Start one for the boot CPU: */
+	err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+	BUG_ON(err == NOTIFY_BAD);
+	migration_call(&migration_notifier, CPU_ONLINE, cpu);
+	register_cpu_notifier(&migration_notifier);
+
+	return 0;
+}
+early_initcall(migration_init);
+#endif
+
+/*
+ * sched_domains_mutex serializes calls to arch_init_sched_domains,
+ * detach_destroy_domains and partition_sched_domains.
+ */
+static DEFINE_MUTEX(sched_domains_mutex);
+
+#ifdef CONFIG_SMP
+
+#ifdef CONFIG_SCHED_DEBUG
+
+static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
+				  struct cpumask *groupmask)
+{
+	struct sched_group *group = sd->groups;
+	char str[256];
+
+	cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
+	cpumask_clear(groupmask);
+
+	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+
+	if (!(sd->flags & SD_LOAD_BALANCE)) {
+		printk("does not load-balance\n");
+		if (sd->parent)
+			printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
+					" has parent");
+		return -1;
+	}
+
+	printk(KERN_CONT "span %s level %s\n", str, sd->name);
+
+	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+		printk(KERN_ERR "ERROR: domain->span does not contain "
+				"CPU%d\n", cpu);
+	}
+	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
+		printk(KERN_ERR "ERROR: domain->groups does not contain"
+				" CPU%d\n", cpu);
+	}
+
+	printk(KERN_DEBUG "%*s groups:", level + 1, "");
+	do {
+		if (!group) {
+			printk("\n");
+			printk(KERN_ERR "ERROR: group is NULL\n");
+			break;
+		}
+
+		if (!group->__cpu_power) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: domain->cpu_power not "
+					"set\n");
+			break;
+		}
+
+		if (!cpumask_weight(sched_group_cpus(group))) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: empty group\n");
+			break;
+		}
+
+		if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: repeated CPUs\n");
+			break;
+		}
+
+		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
+
+		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
+
+		printk(KERN_CONT " %s", str);
+		if (group->__cpu_power != SCHED_LOAD_SCALE) {
+			printk(KERN_CONT " (__cpu_power = %d)",
+				group->__cpu_power);
+		}
+
+		group = group->next;
+	} while (group != sd->groups);
+	printk(KERN_CONT "\n");
+
+	if (!cpumask_equal(sched_domain_span(sd), groupmask))
+		printk(KERN_ERR "ERROR: groups don't span domain->span\n");
+
+	if (sd->parent &&
+	    !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
+		printk(KERN_ERR "ERROR: parent span is not a superset "
+			"of domain->span\n");
+	return 0;
+}
+
+static void sched_domain_debug(struct sched_domain *sd, int cpu)
+{
+	cpumask_var_t groupmask;
+	int level = 0;
+
+	if (!sd) {
+		printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+		return;
+	}
+
+	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+
+	if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) {
+		printk(KERN_DEBUG "Cannot load-balance (out of memory)\n");
+		return;
+	}
+
+	for (;;) {
+		if (sched_domain_debug_one(sd, cpu, level, groupmask))
+			break;
+		level++;
+		sd = sd->parent;
+		if (!sd)
+			break;
+	}
+	free_cpumask_var(groupmask);
+}
+#else /* !CONFIG_SCHED_DEBUG */
+# define sched_domain_debug(sd, cpu) do { } while (0)
+#endif /* CONFIG_SCHED_DEBUG */
+
+static int sd_degenerate(struct sched_domain *sd)
+{
+	if (cpumask_weight(sched_domain_span(sd)) == 1)
+		return 1;
+
+	/* Following flags need at least 2 groups */
+	if (sd->flags & (SD_LOAD_BALANCE |
+			 SD_BALANCE_NEWIDLE |
+			 SD_BALANCE_FORK |
+			 SD_BALANCE_EXEC |
+			 SD_SHARE_CPUPOWER |
+			 SD_SHARE_PKG_RESOURCES)) {
+		if (sd->groups != sd->groups->next)
+			return 0;
+	}
+
+	/* Following flags don't use groups */
+	if (sd->flags & (SD_WAKE_IDLE |
+			 SD_WAKE_AFFINE |
+			 SD_WAKE_BALANCE))
+		return 0;
+
+	return 1;
+}
+
+static int
+sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
+{
+	unsigned long cflags = sd->flags, pflags = parent->flags;
+
+	if (sd_degenerate(parent))
+		return 1;
+
+	if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
+		return 0;
+
+	/* Does parent contain flags not in child? */
+	/* WAKE_BALANCE is a subset of WAKE_AFFINE */
+	if (cflags & SD_WAKE_AFFINE)
+		pflags &= ~SD_WAKE_BALANCE;
+	/* Flags needing groups don't count if only 1 group in parent */
+	if (parent->groups == parent->groups->next) {
+		pflags &= ~(SD_LOAD_BALANCE |
+				SD_BALANCE_NEWIDLE |
+				SD_BALANCE_FORK |
+				SD_BALANCE_EXEC |
+				SD_SHARE_CPUPOWER |
+				SD_SHARE_PKG_RESOURCES);
+		if (nr_node_ids == 1)
+			pflags &= ~SD_SERIALIZE;
+	}
+	if (~cflags & pflags)
+		return 0;
+
+	return 1;
+}
+
+static void free_rootdomain(struct root_domain *rd)
+{
+	free_cpumask_var(rd->rto_mask);
+	free_cpumask_var(rd->online);
+	free_cpumask_var(rd->span);
+	kfree(rd);
+}
+
+static void rq_attach_root(struct rq *rq, struct root_domain *rd)
+{
+	struct root_domain *old_rd = NULL;
+	unsigned long flags;
+
+	grq_lock_irqsave(&flags);
+
+	if (rq->rd) {
+		old_rd = rq->rd;
+
+		if (cpumask_test_cpu(rq->cpu, old_rd->online))
+			set_rq_offline(rq);
+
+		cpumask_clear_cpu(rq->cpu, old_rd->span);
+
+		/*
+		 * If we dont want to free the old_rt yet then
+		 * set old_rd to NULL to skip the freeing later
+		 * in this function:
+		 */
+		if (!atomic_dec_and_test(&old_rd->refcount))
+			old_rd = NULL;
+	}
+
+	atomic_inc(&rd->refcount);
+	rq->rd = rd;
+
+	cpumask_set_cpu(rq->cpu, rd->span);
+	if (cpumask_test_cpu(rq->cpu, cpu_online_mask))
+		set_rq_online(rq);
+
+	grq_unlock_irqrestore(&flags);
+
+	if (old_rd)
+		free_rootdomain(old_rd);
+}
+
+static int init_rootdomain(struct root_domain *rd, bool bootmem)
+{
+	gfp_t gfp = GFP_KERNEL;
+
+	memset(rd, 0, sizeof(*rd));
+
+	if (bootmem)
+		gfp = GFP_NOWAIT;
+
+	if (!alloc_cpumask_var(&rd->span, gfp))
+		goto out;
+	if (!alloc_cpumask_var(&rd->online, gfp))
+		goto free_span;
+	if (!alloc_cpumask_var(&rd->rto_mask, gfp))
+		goto free_online;
+
+	return 0;
+
+free_online:
+	free_cpumask_var(rd->online);
+free_span:
+	free_cpumask_var(rd->span);
+out:
+	return -ENOMEM;
+}
+
+static void init_defrootdomain(void)
+{
+	init_rootdomain(&def_root_domain, true);
+
+	atomic_set(&def_root_domain.refcount, 1);
+}
+
+static struct root_domain *alloc_rootdomain(void)
+{
+	struct root_domain *rd;
+
+	rd = kmalloc(sizeof(*rd), GFP_KERNEL);
+	if (!rd)
+		return NULL;
+
+	if (init_rootdomain(rd, false) != 0) {
+		kfree(rd);
+		return NULL;
+	}
+
+	return rd;
+}
+
+/*
+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
+ * hold the hotplug lock.
+ */
+static void
+cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	struct sched_domain *tmp;
+
+	/* Remove the sched domains which do not contribute to scheduling. */
+	for (tmp = sd; tmp; ) {
+		struct sched_domain *parent = tmp->parent;
+		if (!parent)
+			break;
+
+		if (sd_parent_degenerate(tmp, parent)) {
+			tmp->parent = parent->parent;
+			if (parent->parent)
+				parent->parent->child = tmp;
+		} else
+			tmp = tmp->parent;
+	}
+
+	if (sd && sd_degenerate(sd)) {
+		sd = sd->parent;
+		if (sd)
+			sd->child = NULL;
+	}
+
+	sched_domain_debug(sd, cpu);
+
+	rq_attach_root(rq, rd);
+	rcu_assign_pointer(rq->sd, sd);
+}
+
+/* cpus with isolated domains */
+static cpumask_var_t cpu_isolated_map;
+
+/* Setup the mask of cpus configured for isolated domains */
+static int __init isolated_cpu_setup(char *str)
+{
+	cpulist_parse(str, cpu_isolated_map);
+	return 1;
+}
+
+__setup("isolcpus=", isolated_cpu_setup);
+
+/*
+ * init_sched_build_groups takes the cpumask we wish to span, and a pointer
+ * to a function which identifies what group(along with sched group) a CPU
+ * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
+ * (due to the fact that we keep track of groups covered with a struct cpumask).
+ *
+ * init_sched_build_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_power to 0.
+ */
+static void
+init_sched_build_groups(const struct cpumask *span,
+			const struct cpumask *cpu_map,
+			int (*group_fn)(int cpu, const struct cpumask *cpu_map,
+					struct sched_group **sg,
+					struct cpumask *tmpmask),
+			struct cpumask *covered, struct cpumask *tmpmask)
+{
+	struct sched_group *first = NULL, *last = NULL;
+	int i;
+
+	cpumask_clear(covered);
+
+	for_each_cpu(i, span) {
+		struct sched_group *sg;
+		int group = group_fn(i, cpu_map, &sg, tmpmask);
+		int j;
+
+		if (cpumask_test_cpu(i, covered))
+			continue;
+
+		cpumask_clear(sched_group_cpus(sg));
+		sg->__cpu_power = 0;
+
+		for_each_cpu(j, span) {
+			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
+				continue;
+
+			cpumask_set_cpu(j, covered);
+			cpumask_set_cpu(j, sched_group_cpus(sg));
+		}
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
+	}
+	last->next = first;
+}
+
+#define SD_NODES_PER_DOMAIN 16
+
+#ifdef CONFIG_NUMA
+
+/**
+ * find_next_best_node - find the next node to include in a sched_domain
+ * @node: node whose sched_domain we're building
+ * @used_nodes: nodes already in the sched_domain
+ *
+ * Find the next node to include in a given scheduling domain. Simply
+ * finds the closest node not already in the @used_nodes map.
+ *
+ * Should use nodemask_t.
+ */
+static int find_next_best_node(int node, nodemask_t *used_nodes)
+{
+	int i, n, val, min_val, best_node = 0;
+
+	min_val = INT_MAX;
+
+	for (i = 0; i < nr_node_ids; i++) {
+		/* Start at @node */
+		n = (node + i) % nr_node_ids;
+
+		if (!nr_cpus_node(n))
+			continue;
+
+		/* Skip already used nodes */
+		if (node_isset(n, *used_nodes))
+			continue;
+
+		/* Simple min distance search */
+		val = node_distance(node, n);
+
+		if (val < min_val) {
+			min_val = val;
+			best_node = n;
+		}
+	}
+
+	node_set(best_node, *used_nodes);
+	return best_node;
+}
+
+/**
+ * sched_domain_node_span - get a cpumask for a node's sched_domain
+ * @node: node whose cpumask we're constructing
+ * @span: resulting cpumask
+ *
+ * Given a node, construct a good cpumask for its sched_domain to span. It
+ * should be one that prevents unnecessary balancing, but also spreads tasks
+ * out optimally.
+ */
+static void sched_domain_node_span(int node, struct cpumask *span)
+{
+	nodemask_t used_nodes;
+	int i;
+
+	cpumask_clear(span);
+	nodes_clear(used_nodes);
+
+	cpumask_or(span, span, cpumask_of_node(node));
+	node_set(node, used_nodes);
+
+	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
+		int next_node = find_next_best_node(node, &used_nodes);
+
+		cpumask_or(span, span, cpumask_of_node(next_node));
+	}
+}
+#endif /* CONFIG_NUMA */
+
+int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
+
+/*
+ * The cpus mask in sched_group and sched_domain hangs off the end.
+ *
+ * ( See the the comments in include/linux/sched.h:struct sched_group
+ *   and struct sched_domain. )
+ */
+struct static_sched_group {
+	struct sched_group sg;
+	DECLARE_BITMAP(cpus, CONFIG_NR_CPUS);
+};
+
+struct static_sched_domain {
+	struct sched_domain sd;
+	DECLARE_BITMAP(span, CONFIG_NR_CPUS);
+};
+
+/*
+ * SMT sched-domains:
+ */
+#ifdef CONFIG_SCHED_SMT
+static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
+
+static int
+cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
+		 struct sched_group **sg, struct cpumask *unused)
+{
+	if (sg)
+		*sg = &per_cpu(sched_group_cpus, cpu).sg;
+	return cpu;
+}
+#endif /* CONFIG_SCHED_SMT */
+
+/*
+ * multi-core sched-domains:
+ */
+#ifdef CONFIG_SCHED_MC
+static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
+#endif /* CONFIG_SCHED_MC */
+
+#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
+static int
+cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *mask)
+{
+	int group;
+
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
+	group = cpumask_first(mask);
+	if (sg)
+		*sg = &per_cpu(sched_group_core, group).sg;
+	return group;
+}
+#elif defined(CONFIG_SCHED_MC)
+static int
+cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *unused)
+{
+	if (sg)
+		*sg = &per_cpu(sched_group_core, cpu).sg;
+	return cpu;
+}
+#endif
+
+static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
+
+static int
+cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *mask)
+{
+	int group;
+#ifdef CONFIG_SCHED_MC
+	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+	group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_SMT)
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
+	group = cpumask_first(mask);
+#else
+	group = cpu;
+#endif
+	if (sg)
+		*sg = &per_cpu(sched_group_phys, group).sg;
+	return group;
+}
+
+/**
+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
+ * @group: The group whose first cpu is to be returned.
+ */
+static inline unsigned int group_first_cpu(struct sched_group *group)
+{
+	return cpumask_first(sched_group_cpus(group));
+}
+
+#ifdef CONFIG_NUMA
+/*
+ * The init_sched_build_groups can't handle what we want to do with node
+ * groups, so roll our own. Now each node has its own list of groups which
+ * gets dynamically allocated.
+ */
+static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
+static struct sched_group ***sched_group_nodes_bycpu;
+
+static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
+
+static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
+				 struct sched_group **sg,
+				 struct cpumask *nodemask)
+{
+	int group;
+
+	cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map);
+	group = cpumask_first(nodemask);
+
+	if (sg)
+		*sg = &per_cpu(sched_group_allnodes, group).sg;
+	return group;
+}
+
+static void init_numa_sched_groups_power(struct sched_group *group_head)
+{
+	struct sched_group *sg = group_head;
+	int j;
+
+	if (!sg)
+		return;
+	do {
+		for_each_cpu(j, sched_group_cpus(sg)) {
+			struct sched_domain *sd;
+
+			sd = &per_cpu(phys_domains, j).sd;
+			if (j != group_first_cpu(sd->groups)) {
+				/*
+				 * Only add "power" once for each
+				 * physical package.
+				 */
+				continue;
+			}
+
+			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+		}
+		sg = sg->next;
+	} while (sg != group_head);
+}
+#endif /* CONFIG_NUMA */
+
+#ifdef CONFIG_NUMA
+/* Free memory allocated for various sched_group structures */
+static void free_sched_groups(const struct cpumask *cpu_map,
+			      struct cpumask *nodemask)
+{
+	int cpu, i;
+
+	for_each_cpu(cpu, cpu_map) {
+		struct sched_group **sched_group_nodes
+			= sched_group_nodes_bycpu[cpu];
+
+		if (!sched_group_nodes)
+			continue;
+
+		for (i = 0; i < nr_node_ids; i++) {
+			struct sched_group *oldsg, *sg = sched_group_nodes[i];
+
+			cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+			if (cpumask_empty(nodemask))
+				continue;
+
+			if (sg == NULL)
+				continue;
+			sg = sg->next;
+next_sg:
+			oldsg = sg;
+			sg = sg->next;
+			kfree(oldsg);
+			if (oldsg != sched_group_nodes[i])
+				goto next_sg;
+		}
+		kfree(sched_group_nodes);
+		sched_group_nodes_bycpu[cpu] = NULL;
+	}
+}
+#else /* !CONFIG_NUMA */
+static void free_sched_groups(const struct cpumask *cpu_map,
+			      struct cpumask *nodemask)
+{
+}
+#endif /* CONFIG_NUMA */
+
+/*
+ * Initialize sched groups cpu_power.
+ *
+ * cpu_power indicates the capacity of sched group, which is used while
+ * distributing the load between different sched groups in a sched domain.
+ * Typically cpu_power for all the groups in a sched domain will be same unless
+ * there are asymmetries in the topology. If there are asymmetries, group
+ * having more cpu_power will pickup more load compared to the group having
+ * less cpu_power.
+ *
+ * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents
+ * the maximum number of tasks a group can handle in the presence of other idle
+ * or lightly loaded groups in the same sched domain.
+ */
+static void init_sched_groups_power(int cpu, struct sched_domain *sd)
+{
+	struct sched_domain *child;
+	struct sched_group *group;
+
+	WARN_ON(!sd || !sd->groups);
+
+	if (cpu != group_first_cpu(sd->groups))
+		return;
+
+	child = sd->child;
+
+	sd->groups->__cpu_power = 0;
+
+	/*
+	 * For perf policy, if the groups in child domain share resources
+	 * (for example cores sharing some portions of the cache hierarchy
+	 * or SMT), then set this domain groups cpu_power such that each group
+	 * can handle only one task, when there are other idle groups in the
+	 * same sched domain.
+	 */
+	if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) &&
+		       (child->flags &
+			(SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) {
+		sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE);
+		return;
+	}
+
+	/*
+	 * add cpu_power of each child group to this groups cpu_power
+	 */
+	group = child->groups;
+	do {
+		sg_inc_cpu_power(sd->groups, group->__cpu_power);
+		group = group->next;
+	} while (group != child->groups);
+}
+
+/*
+ * Initializers for schedule domains
+ * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
+ */
+
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(sd, type)		sd->name = #type
+#else
+# define SD_INIT_NAME(sd, type)		do { } while (0)
+#endif
+
+#define	SD_INIT(sd, type)	sd_init_##type(sd)
+
+#define SD_INIT_FUNC(type)	\
+static noinline void sd_init_##type(struct sched_domain *sd)	\
+{								\
+	memset(sd, 0, sizeof(*sd));				\
+	*sd = SD_##type##_INIT;					\
+	sd->level = SD_LV_##type;				\
+	SD_INIT_NAME(sd, type);					\
+}
+
+SD_INIT_FUNC(CPU)
+#ifdef CONFIG_NUMA
+ SD_INIT_FUNC(ALLNODES)
+ SD_INIT_FUNC(NODE)
+#endif
+#ifdef CONFIG_SCHED_SMT
+ SD_INIT_FUNC(SIBLING)
+#endif
+#ifdef CONFIG_SCHED_MC
+ SD_INIT_FUNC(MC)
+#endif
+
+static int default_relax_domain_level = -1;
+
+static int __init setup_relax_domain_level(char *str)
+{
+	unsigned long val;
+
+	val = simple_strtoul(str, NULL, 0);
+	if (val < SD_LV_MAX)
+		default_relax_domain_level = val;
+
+	return 1;
+}
+__setup("relax_domain_level=", setup_relax_domain_level);
+
+static void set_domain_attribute(struct sched_domain *sd,
+				 struct sched_domain_attr *attr)
+{
+	int request;
+
+	if (!attr || attr->relax_domain_level < 0) {
+		if (default_relax_domain_level < 0)
+			return;
+		else
+			request = default_relax_domain_level;
+	} else
+		request = attr->relax_domain_level;
+	if (request < sd->level) {
+		/* turn off idle balance on this domain */
+		sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE);
+	} else {
+		/* turn on idle balance on this domain */
+		sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE);
+	}
+}
+
+/*
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
+ */
+static int __build_sched_domains(const struct cpumask *cpu_map,
+				 struct sched_domain_attr *attr)
+{
+	int i, err = -ENOMEM;
+	struct root_domain *rd;
+	cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered,
+		tmpmask;
+#ifdef CONFIG_NUMA
+	cpumask_var_t domainspan, covered, notcovered;
+	struct sched_group **sched_group_nodes = NULL;
+	int sd_allnodes = 0;
+
+	if (!alloc_cpumask_var(&domainspan, GFP_KERNEL))
+		goto out;
+	if (!alloc_cpumask_var(&covered, GFP_KERNEL))
+		goto free_domainspan;
+	if (!alloc_cpumask_var(&notcovered, GFP_KERNEL))
+		goto free_covered;
+#endif
+
+	if (!alloc_cpumask_var(&nodemask, GFP_KERNEL))
+		goto free_notcovered;
+	if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL))
+		goto free_nodemask;
+	if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL))
+		goto free_this_sibling_map;
+	if (!alloc_cpumask_var(&send_covered, GFP_KERNEL))
+		goto free_this_core_map;
+	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		goto free_send_covered;
+
+#ifdef CONFIG_NUMA
+	/*
+	 * Allocate the per-node list of sched groups
+	 */
+	sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *),
+				    GFP_KERNEL);
+	if (!sched_group_nodes) {
+		printk(KERN_WARNING "Can not alloc sched group node list\n");
+		goto free_tmpmask;
+	}
+#endif
+
+	rd = alloc_rootdomain();
+	if (!rd) {
+		printk(KERN_WARNING "Cannot alloc root domain\n");
+		goto free_sched_groups;
+	}
+
+#ifdef CONFIG_NUMA
+	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes;
+#endif
+
+	/*
+	 * Set up domains for cpus specified by the cpu_map.
+	 */
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = NULL, *p;
+
+		cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
+
+#ifdef CONFIG_NUMA
+		if (cpumask_weight(cpu_map) >
+				SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
+			sd = &per_cpu(allnodes_domains, i).sd;
+			SD_INIT(sd, ALLNODES);
+			set_domain_attribute(sd, attr);
+			cpumask_copy(sched_domain_span(sd), cpu_map);
+			cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
+			p = sd;
+			sd_allnodes = 1;
+		} else
+			p = NULL;
+
+		sd = &per_cpu(node_domains, i).sd;
+		SD_INIT(sd, NODE);
+		set_domain_attribute(sd, attr);
+		sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
+		sd->parent = p;
+		if (p)
+			p->child = sd;
+		cpumask_and(sched_domain_span(sd),
+			    sched_domain_span(sd), cpu_map);
+#endif
+
+		p = sd;
+		sd = &per_cpu(phys_domains, i).sd;
+		SD_INIT(sd, CPU);
+		set_domain_attribute(sd, attr);
+		cpumask_copy(sched_domain_span(sd), nodemask);
+		sd->parent = p;
+		if (p)
+			p->child = sd;
+		cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask);
+
+#ifdef CONFIG_SCHED_MC
+		p = sd;
+		sd = &per_cpu(core_domains, i).sd;
+		SD_INIT(sd, MC);
+		set_domain_attribute(sd, attr);
+		cpumask_and(sched_domain_span(sd), cpu_map,
+						   cpu_coregroup_mask(i));
+		sd->parent = p;
+		p->child = sd;
+		cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
+#endif
+
+#ifdef CONFIG_SCHED_SMT
+		p = sd;
+		sd = &per_cpu(cpu_domains, i).sd;
+		SD_INIT(sd, SIBLING);
+		set_domain_attribute(sd, attr);
+		cpumask_and(sched_domain_span(sd),
+			    topology_thread_cpumask(i), cpu_map);
+		sd->parent = p;
+		p->child = sd;
+		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
+#endif
+	}
+
+#ifdef CONFIG_SCHED_SMT
+	/* Set up CPU (sibling) groups */
+	for_each_cpu(i, cpu_map) {
+		cpumask_and(this_sibling_map,
+			    topology_thread_cpumask(i), cpu_map);
+		if (i != cpumask_first(this_sibling_map))
+			continue;
+
+		init_sched_build_groups(this_sibling_map, cpu_map,
+					&cpu_to_cpu_group,
+					send_covered, tmpmask);
+	}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+	/* Set up multi-core groups */
+	for_each_cpu(i, cpu_map) {
+		cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
+		if (i != cpumask_first(this_core_map))
+			continue;
+
+		init_sched_build_groups(this_core_map, cpu_map,
+					&cpu_to_core_group,
+					send_covered, tmpmask);
+	}
+#endif
+
+	/* Set up physical groups */
+	for (i = 0; i < nr_node_ids; i++) {
+		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+		if (cpumask_empty(nodemask))
+			continue;
+
+		init_sched_build_groups(nodemask, cpu_map,
+					&cpu_to_phys_group,
+					send_covered, tmpmask);
+	}
+
+#ifdef CONFIG_NUMA
+	/* Set up node groups */
+	if (sd_allnodes) {
+		init_sched_build_groups(cpu_map, cpu_map,
+					&cpu_to_allnodes_group,
+					send_covered, tmpmask);
+	}
+
+	for (i = 0; i < nr_node_ids; i++) {
+		/* Set up node groups */
+		struct sched_group *sg, *prev;
+		int j;
+
+		cpumask_clear(covered);
+		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+		if (cpumask_empty(nodemask)) {
+			sched_group_nodes[i] = NULL;
+			continue;
+		}
+
+		sched_domain_node_span(i, domainspan);
+		cpumask_and(domainspan, domainspan, cpu_map);
+
+		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+				  GFP_KERNEL, i);
+		if (!sg) {
+			printk(KERN_WARNING "Can not alloc domain group for "
+				"node %d\n", i);
+			goto error;
+		}
+		sched_group_nodes[i] = sg;
+		for_each_cpu(j, nodemask) {
+			struct sched_domain *sd;
+
+			sd = &per_cpu(node_domains, j).sd;
+			sd->groups = sg;
+		}
+		sg->__cpu_power = 0;
+		cpumask_copy(sched_group_cpus(sg), nodemask);
+		sg->next = sg;
+		cpumask_or(covered, covered, nodemask);
+		prev = sg;
+
+		for (j = 0; j < nr_node_ids; j++) {
+			int n = (i + j) % nr_node_ids;
+
+			cpumask_complement(notcovered, covered);
+			cpumask_and(tmpmask, notcovered, cpu_map);
+			cpumask_and(tmpmask, tmpmask, domainspan);
+			if (cpumask_empty(tmpmask))
+				break;
+
+			cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
+			if (cpumask_empty(tmpmask))
+				continue;
+
+			sg = kmalloc_node(sizeof(struct sched_group) +
+					  cpumask_size(),
+					  GFP_KERNEL, i);
+			if (!sg) {
+				printk(KERN_WARNING
+				"Can not alloc domain group for node %d\n", j);
+				goto error;
+			}
+			sg->__cpu_power = 0;
+			cpumask_copy(sched_group_cpus(sg), tmpmask);
+			sg->next = prev->next;
+			cpumask_or(covered, covered, tmpmask);
+			prev->next = sg;
+			prev = sg;
+		}
+	}
+#endif
+
+	/* Calculate CPU power for physical packages and nodes */
+#ifdef CONFIG_SCHED_SMT
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = &per_cpu(cpu_domains, i).sd;
+
+		init_sched_groups_power(i, sd);
+	}
+#endif
+#ifdef CONFIG_SCHED_MC
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = &per_cpu(core_domains, i).sd;
+
+		init_sched_groups_power(i, sd);
+	}
+#endif
+
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = &per_cpu(phys_domains, i).sd;
+
+		init_sched_groups_power(i, sd);
+	}
+
+#ifdef CONFIG_NUMA
+	for (i = 0; i < nr_node_ids; i++)
+		init_numa_sched_groups_power(sched_group_nodes[i]);
+
+	if (sd_allnodes) {
+		struct sched_group *sg;
+
+		cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
+								tmpmask);
+		init_numa_sched_groups_power(sg);
+	}
+#endif
+
+	/* Attach the domains */
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd;
+#ifdef CONFIG_SCHED_SMT
+		sd = &per_cpu(cpu_domains, i).sd;
+#elif defined(CONFIG_SCHED_MC)
+		sd = &per_cpu(core_domains, i).sd;
+#else
+		sd = &per_cpu(phys_domains, i).sd;
+#endif
+		cpu_attach_domain(sd, rd, i);
+	}
+
+	err = 0;
+
+free_tmpmask:
+	free_cpumask_var(tmpmask);
+free_send_covered:
+	free_cpumask_var(send_covered);
+free_this_core_map:
+	free_cpumask_var(this_core_map);
+free_this_sibling_map:
+	free_cpumask_var(this_sibling_map);
+free_nodemask:
+	free_cpumask_var(nodemask);
+free_notcovered:
+#ifdef CONFIG_NUMA
+	free_cpumask_var(notcovered);
+free_covered:
+	free_cpumask_var(covered);
+free_domainspan:
+	free_cpumask_var(domainspan);
+out:
+#endif
+	return err;
+
+free_sched_groups:
+#ifdef CONFIG_NUMA
+	kfree(sched_group_nodes);
+#endif
+	goto free_tmpmask;
+
+#ifdef CONFIG_NUMA
+error:
+	free_sched_groups(cpu_map, tmpmask);
+	free_rootdomain(rd);
+	goto free_tmpmask;
+#endif
+}
+
+static int build_sched_domains(const struct cpumask *cpu_map)
+{
+	return __build_sched_domains(cpu_map, NULL);
+}
+
+static struct cpumask *doms_cur;	/* current sched domains */
+static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
+static struct sched_domain_attr *dattr_cur;
+				/* attribues of custom domains in 'doms_cur' */
+
+/*
+ * Special case: If a kmalloc of a doms_cur partition (array of
+ * cpumask) fails, then fallback to a single sched domain,
+ * as determined by the single cpumask fallback_doms.
+ */
+static cpumask_var_t fallback_doms;
+
+/*
+ * arch_update_cpu_topology lets virtualized architectures update the
+ * cpu core maps. It is supposed to return 1 if the topology changed
+ * or 0 if it stayed the same.
+ */
+int __attribute__((weak)) arch_update_cpu_topology(void)
+{
+	return 0;
+}
+
+/*
+ * Set up scheduler domains and groups. Callers must hold the hotplug lock.
+ * For now this just excludes isolated cpus, but could be used to
+ * exclude other special cases in the future.
+ */
+static int arch_init_sched_domains(const struct cpumask *cpu_map)
+{
+	int err;
+
+	arch_update_cpu_topology();
+	ndoms_cur = 1;
+	doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
+	if (!doms_cur)
+		doms_cur = fallback_doms;
+	cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
+	dattr_cur = NULL;
+	err = build_sched_domains(doms_cur);
+	register_sched_domain_sysctl();
+
+	return err;
+}
+
+static void arch_destroy_sched_domains(const struct cpumask *cpu_map,
+				       struct cpumask *tmpmask)
+{
+	free_sched_groups(cpu_map, tmpmask);
+}
+
+/*
+ * Detach sched domains from a group of cpus specified in cpu_map
+ * These cpus will now be attached to the NULL domain
+ */
+static void detach_destroy_domains(const struct cpumask *cpu_map)
+{
+	/* Save because hotplug lock held. */
+	static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS);
+	int i;
+
+	for_each_cpu(i, cpu_map)
+		cpu_attach_domain(NULL, &def_root_domain, i);
+	synchronize_sched();
+	arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask));
+}
+
+/* handle null as "default" */
+static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
+			struct sched_domain_attr *new, int idx_new)
+{
+	struct sched_domain_attr tmp;
+
+	/* fast path */
+	if (!new && !cur)
+		return 1;
+
+	tmp = SD_ATTR_INIT;
+	return !memcmp(cur ? (cur + idx_cur) : &tmp,
+			new ? (new + idx_new) : &tmp,
+			sizeof(struct sched_domain_attr));
+}
+
+/*
+ * Partition sched domains as specified by the 'ndoms_new'
+ * cpumasks in the array doms_new[] of cpumasks. This compares
+ * doms_new[] to the current sched domain partitioning, doms_cur[].
+ * It destroys each deleted domain and builds each new domain.
+ *
+ * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
+ * The masks don't intersect (don't overlap.) We should setup one
+ * sched domain for each mask. CPUs not in any of the cpumasks will
+ * not be load balanced. If the same cpumask appears both in the
+ * current 'doms_cur' domains and in the new 'doms_new', we can leave
+ * it as it is.
+ *
+ * The passed in 'doms_new' should be kmalloc'd. This routine takes
+ * ownership of it and will kfree it when done with it. If the caller
+ * failed the kmalloc call, then it can pass in doms_new == NULL &&
+ * ndoms_new == 1, and partition_sched_domains() will fallback to
+ * the single partition 'fallback_doms', it also forces the domains
+ * to be rebuilt.
+ *
+ * If doms_new == NULL it will be replaced with cpu_online_mask.
+ * ndoms_new == 0 is a special case for destroying existing domains,
+ * and it will not create the default domain.
+ *
+ * Call with hotplug lock held
+ */
+/* FIXME: Change to struct cpumask *doms_new[] */
+void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+			     struct sched_domain_attr *dattr_new)
+{
+	int i, j, n;
+	int new_topology;
+
+	mutex_lock(&sched_domains_mutex);
+
+	/* always unregister in case we don't destroy any domains */
+	unregister_sched_domain_sysctl();
+
+	/* Let architecture update cpu core mappings. */
+	new_topology = arch_update_cpu_topology();
+
+	n = doms_new ? ndoms_new : 0;
+
+	/* Destroy deleted domains */
+	for (i = 0; i < ndoms_cur; i++) {
+		for (j = 0; j < n && !new_topology; j++) {
+			if (cpumask_equal(&doms_cur[i], &doms_new[j])
+			    && dattrs_equal(dattr_cur, i, dattr_new, j))
+				goto match1;
+		}
+		/* no match - a current sched domain not in new doms_new[] */
+		detach_destroy_domains(doms_cur + i);
+match1:
+		;
+	}
+
+	if (doms_new == NULL) {
+		ndoms_cur = 0;
+		doms_new = fallback_doms;
+		cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
+		WARN_ON_ONCE(dattr_new);
+	}
+
+	/* Build new domains */
+	for (i = 0; i < ndoms_new; i++) {
+		for (j = 0; j < ndoms_cur && !new_topology; j++) {
+			if (cpumask_equal(&doms_new[i], &doms_cur[j])
+			    && dattrs_equal(dattr_new, i, dattr_cur, j))
+				goto match2;
+		}
+		/* no match - add a new doms_new */
+		__build_sched_domains(doms_new + i,
+					dattr_new ? dattr_new + i : NULL);
+match2:
+		;
+	}
+
+	/* Remember the new sched domains */
+	if (doms_cur != fallback_doms)
+		kfree(doms_cur);
+	kfree(dattr_cur);	/* kfree(NULL) is safe */
+	doms_cur = doms_new;
+	dattr_cur = dattr_new;
+	ndoms_cur = ndoms_new;
+
+	register_sched_domain_sysctl();
+
+	mutex_unlock(&sched_domains_mutex);
+}
+
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+static void arch_reinit_sched_domains(void)
+{
+	get_online_cpus();
+
+	/* Destroy domains first to force the rebuild */
+	partition_sched_domains(0, NULL, NULL);
+
+	rebuild_sched_domains();
+	put_online_cpus();
+}
+
+static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
+{
+	unsigned int level = 0;
+
+	if (sscanf(buf, "%u", &level) != 1)
+		return -EINVAL;
+
+	/*
+	 * level is always be positive so don't check for
+	 * level < POWERSAVINGS_BALANCE_NONE which is 0
+	 * What happens on 0 or 1 byte write,
+	 * need to check for count as well?
+	 */
+
+	if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS)
+		return -EINVAL;
+
+	if (smt)
+		sched_smt_power_savings = level;
+	else
+		sched_mc_power_savings = level;
+
+	arch_reinit_sched_domains();
+
+	return count;
+}
+
+#ifdef CONFIG_SCHED_MC
+static ssize_t sched_mc_power_savings_show(struct sysdev_class *class,
+					   char *page)
+{
+	return sprintf(page, "%u\n", sched_mc_power_savings);
+}
+static ssize_t sched_mc_power_savings_store(struct sysdev_class *class,
+					    const char *buf, size_t count)
+{
+	return sched_power_savings_store(buf, count, 0);
+}
+static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644,
+			 sched_mc_power_savings_show,
+			 sched_mc_power_savings_store);
+#endif
+
+#ifdef CONFIG_SCHED_SMT
+static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev,
+					    char *page)
+{
+	return sprintf(page, "%u\n", sched_smt_power_savings);
+}
+static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev,
+					     const char *buf, size_t count)
+{
+	return sched_power_savings_store(buf, count, 1);
+}
+static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644,
+		   sched_smt_power_savings_show,
+		   sched_smt_power_savings_store);
+#endif
+
+int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
+{
+	int err = 0;
+
+#ifdef CONFIG_SCHED_SMT
+	if (smt_capable())
+		err = sysfs_create_file(&cls->kset.kobj,
+					&attr_sched_smt_power_savings.attr);
+#endif
+#ifdef CONFIG_SCHED_MC
+	if (!err && mc_capable())
+		err = sysfs_create_file(&cls->kset.kobj,
+					&attr_sched_mc_power_savings.attr);
+#endif
+	return err;
+}
+#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+
+#ifndef CONFIG_CPUSETS
+/*
+ * Add online and remove offline CPUs from the scheduler domains.
+ * When cpusets are enabled they take over this function.
+ */
+static int update_sched_domains(struct notifier_block *nfb,
+				unsigned long action, void *hcpu)
+{
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		partition_sched_domains(1, NULL, NULL);
+		return NOTIFY_OK;
+
+	default:
+		return NOTIFY_DONE;
+	}
+}
+#endif
+
+static int update_runtime(struct notifier_block *nfb,
+				unsigned long action, void *hcpu)
+{
+	switch (action) {
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		return NOTIFY_OK;
+
+	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		return NOTIFY_OK;
+
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+void __init sched_init_smp(void)
+{
+	cpumask_var_t non_isolated_cpus;
+
+	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
+
+#if defined(CONFIG_NUMA)
+	sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
+								GFP_KERNEL);
+	BUG_ON(sched_group_nodes_bycpu == NULL);
+#endif
+	get_online_cpus();
+	mutex_lock(&sched_domains_mutex);
+	arch_init_sched_domains(cpu_online_mask);
+	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+	if (cpumask_empty(non_isolated_cpus))
+		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
+	mutex_unlock(&sched_domains_mutex);
+	put_online_cpus();
+
+#ifndef CONFIG_CPUSETS
+	/* XXX: Theoretical race here - CPU may be hotplugged now */
+	hotcpu_notifier(update_sched_domains, 0);
+#endif
+
+	/* RT runtime code needs to handle some hotplug events */
+	hotcpu_notifier(update_runtime, 0);
+
+	/* Move init over to a non-isolated CPU */
+	if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
+		BUG();
+	free_cpumask_var(non_isolated_cpus);
+
+	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
+
+	/*
+	 * Assume that every added cpu gives us slightly less overall latency
+	 * allowing us to increase the base rr_interval, but in a non linear
+	 * fashion.
+	 */
+	rr_interval *= 1 + ilog2(num_online_cpus());
+}
+#else
+void __init sched_init_smp(void)
+{
+}
+#endif /* CONFIG_SMP */
+
+unsigned int sysctl_timer_migration = 1;
+
+int in_sched_functions(unsigned long addr)
+{
+	return in_lock_functions(addr) ||
+		(addr >= (unsigned long)__sched_text_start
+		&& addr < (unsigned long)__sched_text_end);
+}
+
+void __init sched_init(void)
+{
+	int i;
+	int highest_cpu = 0;
+
+	prio_ratios[0] = 100;
+	for (i = 1 ; i < PRIO_RANGE ; i++)
+		prio_ratios[i] = prio_ratios[i - 1] * 11 / 10;
+
+#ifdef CONFIG_SMP
+	init_defrootdomain();
+	cpus_clear(grq.cpu_idle_map);
+#endif
+	spin_lock_init(&grq.lock);
+	for_each_possible_cpu(i) {
+		struct rq *rq;
+
+		rq = cpu_rq(i);
+		INIT_LIST_HEAD(&rq->queue);
+		rq->rq_deadline = 0;
+		rq->rq_prio = 0;
+		rq->cpu = i;
+		rq->user_pc = rq->nice_pc = rq->softirq_pc = rq->system_pc =
+			      rq->iowait_pc = rq->idle_pc = 0;
+#ifdef CONFIG_SMP
+		rq->sd = NULL;
+		rq->rd = NULL;
+		rq->online = 0;
+		INIT_LIST_HEAD(&rq->migration_queue);
+		rq_attach_root(rq, &def_root_domain);
+#endif
+		atomic_set(&rq->nr_iowait, 0);
+		highest_cpu = i;
+	}
+	grq.iso_ticks = grq.nr_running = grq.nr_uninterruptible = 0;
+	for (i = 0; i < PRIO_LIMIT; i++)
+		INIT_LIST_HEAD(grq.queue + i);
+	bitmap_zero(grq.prio_bitmap, PRIO_LIMIT);
+	/* delimiter for bitsearch */
+	__set_bit(PRIO_LIMIT, grq.prio_bitmap);
+
+#ifdef CONFIG_SMP
+	nr_cpu_ids = highest_cpu + 1;
+#endif
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+	INIT_HLIST_HEAD(&init_task.preempt_notifiers);
+#endif
+
+#ifdef CONFIG_RT_MUTEXES
+	plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
+#endif
+
+	/*
+	 * The boot idle thread does lazy MMU switching as well:
+	 */
+	atomic_inc(&init_mm.mm_count);
+	enter_lazy_tlb(&init_mm, current);
+
+	/*
+	 * Make us the idle thread. Technically, schedule() should not be
+	 * called from this thread, however somewhere below it might be,
+	 * but because we are the idle thread, we just pick up running again
+	 * when this runqueue becomes "idle".
+	 */
+	init_idle(current, smp_processor_id());
+
+	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
+	alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+#ifdef CONFIG_SMP
+#ifdef CONFIG_NO_HZ
+	alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+	alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
+#endif
+	alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+#endif /* SMP */
+	perf_counter_init();
+}
+
+#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
+void __might_sleep(char *file, int line)
+{
+#ifdef in_atomic
+	static unsigned long prev_jiffy;	/* ratelimiting */
+
+	if ((in_atomic() || irqs_disabled()) &&
+	    system_state == SYSTEM_RUNNING && !oops_in_progress) {
+		if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+			return;
+		prev_jiffy = jiffies;
+		printk(KERN_ERR "BUG: sleeping function called from invalid"
+				" context at %s:%d\n", file, line);
+		printk("in_atomic():%d, irqs_disabled():%d\n",
+			in_atomic(), irqs_disabled());
+		debug_show_held_locks(current);
+		if (irqs_disabled())
+			print_irqtrace_events(current);
+		dump_stack();
+	}
+#endif
+}
+EXPORT_SYMBOL(__might_sleep);
+#endif
+
+#ifdef CONFIG_MAGIC_SYSRQ
+void normalize_rt_tasks(void)
+{
+	struct task_struct *g, *p;
+	unsigned long flags;
+	struct rq *rq;
+	int queued;
+
+	read_lock_irq(&tasklist_lock);
+
+	do_each_thread(g, p) {
+		if (!rt_task(p) && !iso_task(p))
+			continue;
+
+		spin_lock_irqsave(&p->pi_lock, flags);
+		rq = __task_grq_lock(p);
+		update_rq_clock(rq);
+
+		queued = task_queued_only(p);
+		if (queued)
+			dequeue_task(p);
+		__setscheduler(p, SCHED_NORMAL, 0);
+		if (task_running(p))
+			resched_task(p);
+		if (queued) {
+			enqueue_task(p);
+			try_preempt(p);
+		}
+
+		__task_grq_unlock();
+		spin_unlock_irqrestore(&p->pi_lock, flags);
+	} while_each_thread(g, p);
+
+	read_unlock_irq(&tasklist_lock);
+}
+#endif /* CONFIG_MAGIC_SYSRQ */
+
+#ifdef CONFIG_IA64
+/*
+ * These functions are only useful for the IA64 MCA handling.
+ *
+ * They can only be called when the whole system has been
+ * stopped - every CPU needs to be quiescent, and no scheduling
+ * activity can take place. Using them for anything else would
+ * be a serious bug, and as a result, they aren't even visible
+ * under any other configuration.
+ */
+
+/**
+ * curr_task - return the current task for a given cpu.
+ * @cpu: the processor in question.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+struct task_struct *curr_task(int cpu)
+{
+	return cpu_curr(cpu);
+}
+
+/**
+ * set_curr_task - set the current task for a given cpu.
+ * @cpu: the processor in question.
+ * @p: the task pointer to set.
+ *
+ * Description: This function must only be used when non-maskable interrupts
+ * are serviced on a separate stack.  It allows the architecture to switch the
+ * notion of the current task on a cpu in a non-blocking manner.  This function
+ * must be called with all CPU's synchronized, and interrupts disabled, the
+ * and caller must save the original value of the current task (see
+ * curr_task() above) and restore that value before reenabling interrupts and
+ * re-starting the system.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+void set_curr_task(int cpu, struct task_struct *p)
+{
+	cpu_curr(cpu) = p;
+}
+
+#endif
+
+/*
+ * Use precise platform statistics if available:
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+cputime_t task_utime(struct task_struct *p)
+{
+	return p->utime;
+}
+
+cputime_t task_stime(struct task_struct *p)
+{
+	return p->stime;
+}
+#else
+cputime_t task_utime(struct task_struct *p)
+{
+	clock_t utime = cputime_to_clock_t(p->utime),
+		total = utime + cputime_to_clock_t(p->stime);
+	u64 temp;
+
+	temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+
+	if (total) {
+		temp *= utime;
+		do_div(temp, total);
+	}
+	utime = (clock_t)temp;
+
+	p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
+	return p->prev_utime;
+}
+
+cputime_t task_stime(struct task_struct *p)
+{
+	clock_t stime;
+
+	stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
+			cputime_to_clock_t(task_utime(p));
+
+	if (stime >= 0)
+		p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+
+	return p->prev_stime;
+}
+#endif
+
+inline cputime_t task_gtime(struct task_struct *p)
+{
+	return p->gtime;
+}
+
+void __cpuinit init_idle_bootup_task(struct task_struct *idle)
+{}
+
+#ifdef CONFIG_SCHED_DEBUG
+void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
+{}
+
+void proc_sched_set_task(struct task_struct *p)
+{}
+#endif
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -83,6 +83,8 @@ extern int percpu_pagelist_fraction;
 extern int compat_log;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
+extern int rr_interval;
+extern int sched_iso_cpu;
 #ifndef CONFIG_MMU
 extern int sysctl_nr_trim_pages;
 #endif
@@ -100,7 +102,8 @@ static int zero;
 static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
 static unsigned long one_ul = 1;
-static int one_hundred = 100;
+static int __read_mostly one_hundred = 100;
+static int __maybe_unused __read_mostly five_thousand = 5000;
 
 /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
 static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
@@ -234,7 +237,7 @@ static struct ctl_table root_table[] = {
 	{ .ctl_name = 0 }
 };
 
-#ifdef CONFIG_SCHED_DEBUG
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SCHED_CFS)
 static int min_sched_granularity_ns = 100000;		/* 100 usecs */
 static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
 static int min_wakeup_granularity_ns;			/* 0 usecs */
@@ -242,7 +245,7 @@ static int max_wakeup_granularity_ns = N
 #endif
 
 static struct ctl_table kern_table[] = {
-#ifdef CONFIG_SCHED_DEBUG
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SCHED_CFS)
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "sched_min_granularity_ns",
@@ -327,6 +330,7 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_SCHED_CFS
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "sched_rt_period_us",
@@ -351,6 +355,7 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+#endif
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.ctl_name	= CTL_UNNUMBERED,
@@ -756,6 +761,30 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_SCHED_BFS
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "rr_interval",
+		.data		= &rr_interval,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &one,
+		.extra2		= &five_thousand,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "iso_cpu",
+		.data		= &sched_iso_cpu,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one_hundred,
+	},
+#endif
 #if defined(CONFIG_S390) && defined(CONFIG_SMP)
 	{
 		.ctl_name	= KERN_SPIN_RETRY,
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -320,7 +320,9 @@ static int worker_thread(void *__cwq)
 	if (cwq->wq->freezeable)
 		set_freezable();
 
+#ifdef CONFIG_SCHED_CFS
 	set_user_nice(current, -5);
+#endif
 
 	for (;;) {
 		prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE);
--- /dev/null
+++ b/include/linux/perf_counter.h
@@ -0,0 +1,2 @@
+#define perf_counter_init() do {} while(0)
+#define perf_counter_task_sched_in(...) do {} while(0)
--- /dev/null
+++ b/include/trace/events/sched.h
@@ -0,0 +1 @@
+#include <trace/sched.h>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-15 04:55:06 +0000