Eric Lee / smarc-fsl-linux-kernel

workqueue.c 104 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 
/*
 * kernel/workqueue.c - generic async execution with shared worker pool
 *
 * Copyright (C) 2002		Ingo Molnar
 *
 *   Derived from the taskqueue/keventd code by:
 *     David Woodhouse <dwmw2@infradead.org>
 *     Andrew Morton
 *     Kai Petzke <wpp@marie.physik.tu-berlin.de>
 *     Theodore Ts'o <tytso@mit.edu>
 *
 * Made to use alloc_percpu by Christoph Lameter.
 *
 * Copyright (C) 2010		SUSE Linux Products GmbH
 * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
 *
 * This is the generic async execution mechanism.  Work items as are
 * executed in process context.  The worker pool is shared and
 * automatically managed.  There is one worker pool for each CPU and
 * one extra for works which are better served by workers which are
 * not bound to any specific CPU.
 *
 * Please read Documentation/workqueue.txt for details.
 */

#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/completion.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/kthread.h>
#include <linux/hardirq.h>
#include <linux/mempolicy.h>
#include <linux/freezer.h>
#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
#include <linux/idr.h>
#include <linux/hashtable.h>

#include "workqueue_internal.h"

enum {
	/*
	 * worker_pool flags
	 *
	 * A bound pool is either associated or disassociated with its CPU.
	 * While associated (!DISASSOCIATED), all workers are bound to the
	 * CPU and none has %WORKER_UNBOUND set and concurrency management
	 * is in effect.
	 *
	 * While DISASSOCIATED, the cpu may be offline and all workers have
	 * %WORKER_UNBOUND set and concurrency management disabled, and may
	 * be executing on any CPU.  The pool behaves as an unbound one.
	 *
	 * Note that DISASSOCIATED can be flipped only while holding
	 * assoc_mutex to avoid changing binding state while
	 * create_worker() is in progress.
	 */
	POOL_MANAGE_WORKERS	= 1 << 0,	/* need to manage workers */
	POOL_MANAGING_WORKERS   = 1 << 1,       /* managing workers */
	POOL_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
	POOL_FREEZING		= 1 << 3,	/* freeze in progress */

	/* worker flags */
	WORKER_STARTED		= 1 << 0,	/* started */
	WORKER_DIE		= 1 << 1,	/* die die die */
	WORKER_IDLE		= 1 << 2,	/* is idle */
	WORKER_PREP		= 1 << 3,	/* preparing to run works */
	WORKER_CPU_INTENSIVE	= 1 << 6,	/* cpu intensive */
	WORKER_UNBOUND		= 1 << 7,	/* worker is unbound */

	WORKER_NOT_RUNNING	= WORKER_PREP | WORKER_UNBOUND |
				  WORKER_CPU_INTENSIVE,

	NR_STD_WORKER_POOLS	= 2,		/* # standard pools per cpu */

	BUSY_WORKER_HASH_ORDER	= 6,		/* 64 pointers */

	MAX_IDLE_WORKERS_RATIO	= 4,		/* 1/4 of busy can be idle */
	IDLE_WORKER_TIMEOUT	= 300 * HZ,	/* keep idle ones for 5 mins */

	MAYDAY_INITIAL_TIMEOUT  = HZ / 100 >= 2 ? HZ / 100 : 2,
						/* call for help after 10ms
						   (min two ticks) */
	MAYDAY_INTERVAL		= HZ / 10,	/* and then every 100ms */
	CREATE_COOLDOWN		= HZ,		/* time to breath after fail */

	/*
	 * Rescue workers are used only on emergencies and shared by
	 * all cpus.  Give -20.
	 */
	RESCUER_NICE_LEVEL	= -20,
	HIGHPRI_NICE_LEVEL	= -20,
};

/*
 * Structure fields follow one of the following exclusion rules.
 *
 * I: Modifiable by initialization/destruction paths and read-only for
 *    everyone else.
 *
 * P: Preemption protected.  Disabling preemption is enough and should
 *    only be modified and accessed from the local cpu.
 *
 * L: pool->lock protected.  Access with pool->lock held.
 *
 * X: During normal operation, modification requires pool->lock and should
 *    be done only from local cpu.  Either disabling preemption on local
 *    cpu or grabbing pool->lock is enough for read access.  If
 *    POOL_DISASSOCIATED is set, it's identical to L.
 *
 * F: wq->flush_mutex protected.
 *
 * W: workqueue_lock protected.
 */

/* struct worker is defined in workqueue_internal.h */

struct worker_pool {
	spinlock_t		lock;		/* the pool lock */
	unsigned int		cpu;		/* I: the associated cpu */
	int			id;		/* I: pool ID */
	unsigned int		flags;		/* X: flags */

	struct list_head	worklist;	/* L: list of pending works */
	int			nr_workers;	/* L: total number of workers */

	/* nr_idle includes the ones off idle_list for rebinding */
	int			nr_idle;	/* L: currently idle ones */

	struct list_head	idle_list;	/* X: list of idle workers */
	struct timer_list	idle_timer;	/* L: worker idle timeout */
	struct timer_list	mayday_timer;	/* L: SOS timer for workers */

	/* workers are chained either in busy_hash or idle_list */
	DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER);
						/* L: hash of busy workers */

	struct mutex		assoc_mutex;	/* protect POOL_DISASSOCIATED */
	struct ida		worker_ida;	/* L: for worker IDs */

	/*
	 * The current concurrency level.  As it's likely to be accessed
	 * from other CPUs during try_to_wake_up(), put it in a separate
	 * cacheline.
	 */
	atomic_t		nr_running ____cacheline_aligned_in_smp;
} ____cacheline_aligned_in_smp;

/*
 * The per-pool workqueue.  While queued, the lower WORK_STRUCT_FLAG_BITS
 * of work_struct->data are used for flags and the remaining high bits
 * point to the pwq; thus, pwqs need to be aligned at two's power of the
 * number of flag bits.
 */
struct pool_workqueue {
	struct worker_pool	*pool;		/* I: the associated pool */
	struct workqueue_struct *wq;		/* I: the owning workqueue */
	int			work_color;	/* L: current color */
	int			flush_color;	/* L: flushing color */
	int			nr_in_flight[WORK_NR_COLORS];
						/* L: nr of in_flight works */
	int			nr_active;	/* L: nr of active works */
	int			max_active;	/* L: max active works */
	struct list_head	delayed_works;	/* L: delayed works */
};

/*
 * Structure used to wait for workqueue flush.
 */
struct wq_flusher {
	struct list_head	list;		/* F: list of flushers */
	int			flush_color;	/* F: flush color waiting for */
	struct completion	done;		/* flush completion */
};

/*
 * All cpumasks are assumed to be always set on UP and thus can't be
 * used to determine whether there's something to be done.
 */
#ifdef CONFIG_SMP
typedef cpumask_var_t mayday_mask_t;
#define mayday_test_and_set_cpu(cpu, mask)	\
	cpumask_test_and_set_cpu((cpu), (mask))
#define mayday_clear_cpu(cpu, mask)		cpumask_clear_cpu((cpu), (mask))
#define for_each_mayday_cpu(cpu, mask)		for_each_cpu((cpu), (mask))
#define alloc_mayday_mask(maskp, gfp)		zalloc_cpumask_var((maskp), (gfp))
#define free_mayday_mask(mask)			free_cpumask_var((mask))
#else
typedef unsigned long mayday_mask_t;
#define mayday_test_and_set_cpu(cpu, mask)	test_and_set_bit(0, &(mask))
#define mayday_clear_cpu(cpu, mask)		clear_bit(0, &(mask))
#define for_each_mayday_cpu(cpu, mask)		if ((cpu) = 0, (mask))
#define alloc_mayday_mask(maskp, gfp)		true
#define free_mayday_mask(mask)			do { } while (0)
#endif

/*
 * The externally visible workqueue abstraction is an array of
 * per-CPU workqueues:
 */
struct workqueue_struct {
	unsigned int		flags;		/* W: WQ_* flags */
	union {
		struct pool_workqueue __percpu		*pcpu;
		struct pool_workqueue			*single;
		unsigned long				v;
	} pool_wq;				/* I: pwq's */
	struct list_head	list;		/* W: list of all workqueues */

	struct mutex		flush_mutex;	/* protects wq flushing */
	int			work_color;	/* F: current work color */
	int			flush_color;	/* F: current flush color */
	atomic_t		nr_pwqs_to_flush; /* flush in progress */
	struct wq_flusher	*first_flusher;	/* F: first flusher */
	struct list_head	flusher_queue;	/* F: flush waiters */
	struct list_head	flusher_overflow; /* F: flush overflow list */

	mayday_mask_t		mayday_mask;	/* cpus requesting rescue */
	struct worker		*rescuer;	/* I: rescue worker */

	int			nr_drainers;	/* W: drain in progress */
	int			saved_max_active; /* W: saved pwq max_active */
#ifdef CONFIG_LOCKDEP
	struct lockdep_map	lockdep_map;
#endif
	char			name[];		/* I: workqueue name */
};

struct workqueue_struct *system_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_wq);
struct workqueue_struct *system_highpri_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_highpri_wq);
struct workqueue_struct *system_long_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_long_wq);
struct workqueue_struct *system_unbound_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_unbound_wq);
struct workqueue_struct *system_freezable_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_freezable_wq);

#define CREATE_TRACE_POINTS
#include <trace/events/workqueue.h>

#define for_each_std_worker_pool(pool, cpu)				\
	for ((pool) = &std_worker_pools(cpu)[0];			\
	     (pool) < &std_worker_pools(cpu)[NR_STD_WORKER_POOLS]; (pool)++)

#define for_each_busy_worker(worker, i, pool)				\
	hash_for_each(pool->busy_hash, i, worker, hentry)

static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
				unsigned int sw)
{
	if (cpu < nr_cpu_ids) {
		if (sw & 1) {
			cpu = cpumask_next(cpu, mask);
			if (cpu < nr_cpu_ids)
				return cpu;
		}
		if (sw & 2)
			return WORK_CPU_UNBOUND;
	}
	return WORK_CPU_END;
}

static inline int __next_pwq_cpu(int cpu, const struct cpumask *mask,
				 struct workqueue_struct *wq)
{
	return __next_wq_cpu(cpu, mask, !(wq->flags & WQ_UNBOUND) ? 1 : 2);
}

/*
 * CPU iterators
 *
 * An extra cpu number is defined using an invalid cpu number
 * (WORK_CPU_UNBOUND) to host workqueues which are not bound to any
 * specific CPU.  The following iterators are similar to for_each_*_cpu()
 * iterators but also considers the unbound CPU.
 *
 * for_each_wq_cpu()		: possible CPUs + WORK_CPU_UNBOUND
 * for_each_online_wq_cpu()	: online CPUs + WORK_CPU_UNBOUND
 * for_each_pwq_cpu()		: possible CPUs for bound workqueues,
 *				  WORK_CPU_UNBOUND for unbound workqueues
 */
#define for_each_wq_cpu(cpu)						\
	for ((cpu) = __next_wq_cpu(-1, cpu_possible_mask, 3);		\
	     (cpu) < WORK_CPU_END;					\
	     (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, 3))

#define for_each_online_wq_cpu(cpu)					\
	for ((cpu) = __next_wq_cpu(-1, cpu_online_mask, 3);		\
	     (cpu) < WORK_CPU_END;					\
	     (cpu) = __next_wq_cpu((cpu), cpu_online_mask, 3))

#define for_each_pwq_cpu(cpu, wq)					\
	for ((cpu) = __next_pwq_cpu(-1, cpu_possible_mask, (wq));	\
	     (cpu) < WORK_CPU_END;					\
	     (cpu) = __next_pwq_cpu((cpu), cpu_possible_mask, (wq)))

#ifdef CONFIG_DEBUG_OBJECTS_WORK

static struct debug_obj_descr work_debug_descr;

static void *work_debug_hint(void *addr)
{
	return ((struct work_struct *) addr)->func;
}

/*
 * fixup_init is called when:
 * - an active object is initialized
 */
static int work_fixup_init(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		cancel_work_sync(work);
		debug_object_init(work, &work_debug_descr);
		return 1;
	default:
		return 0;
	}
}

/*
 * fixup_activate is called when:
 * - an active object is activated
 * - an unknown object is activated (might be a statically initialized object)
 */
static int work_fixup_activate(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {

	case ODEBUG_STATE_NOTAVAILABLE:
		/*
		 * This is not really a fixup. The work struct was
		 * statically initialized. We just make sure that it
		 * is tracked in the object tracker.
		 */
		if (test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work))) {
			debug_object_init(work, &work_debug_descr);
			debug_object_activate(work, &work_debug_descr);
			return 0;
		}
		WARN_ON_ONCE(1);
		return 0;

	case ODEBUG_STATE_ACTIVE:
		WARN_ON(1);

	default:
		return 0;
	}
}

/*
 * fixup_free is called when:
 * - an active object is freed
 */
static int work_fixup_free(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		cancel_work_sync(work);
		debug_object_free(work, &work_debug_descr);
		return 1;
	default:
		return 0;
	}
}

static struct debug_obj_descr work_debug_descr = {
	.name		= "work_struct",
	.debug_hint	= work_debug_hint,
	.fixup_init	= work_fixup_init,
	.fixup_activate	= work_fixup_activate,
	.fixup_free	= work_fixup_free,
};

static inline void debug_work_activate(struct work_struct *work)
{
	debug_object_activate(work, &work_debug_descr);
}

static inline void debug_work_deactivate(struct work_struct *work)
{
	debug_object_deactivate(work, &work_debug_descr);
}

void __init_work(struct work_struct *work, int onstack)
{
	if (onstack)
		debug_object_init_on_stack(work, &work_debug_descr);
	else
		debug_object_init(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(__init_work);

void destroy_work_on_stack(struct work_struct *work)
{
	debug_object_free(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_work_on_stack);

#else
static inline void debug_work_activate(struct work_struct *work) { }
static inline void debug_work_deactivate(struct work_struct *work) { }
#endif

/* Serializes the accesses to the list of workqueues. */
static DEFINE_SPINLOCK(workqueue_lock);
static LIST_HEAD(workqueues);
static bool workqueue_freezing;		/* W: have wqs started freezing? */

/*
 * The CPU and unbound standard worker pools.  The unbound ones have
 * POOL_DISASSOCIATED set, and their workers have WORKER_UNBOUND set.
 */
static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
				     cpu_std_worker_pools);
static struct worker_pool unbound_std_worker_pools[NR_STD_WORKER_POOLS];

/* idr of all pools */
static DEFINE_MUTEX(worker_pool_idr_mutex);
static DEFINE_IDR(worker_pool_idr);

static int worker_thread(void *__worker);

static struct worker_pool *std_worker_pools(int cpu)
{
	if (cpu != WORK_CPU_UNBOUND)
		return per_cpu(cpu_std_worker_pools, cpu);
	else
		return unbound_std_worker_pools;
}

static int std_worker_pool_pri(struct worker_pool *pool)
{
	return pool - std_worker_pools(pool->cpu);
}

/* allocate ID and assign it to @pool */
static int worker_pool_assign_id(struct worker_pool *pool)
{
	int ret;

	mutex_lock(&worker_pool_idr_mutex);
	ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	if (ret >= 0)
		pool->id = ret;
	mutex_unlock(&worker_pool_idr_mutex);

	return ret < 0 ? ret : 0;
}

/*
 * Lookup worker_pool by id.  The idr currently is built during boot and
 * never modified.  Don't worry about locking for now.
 */
static struct worker_pool *worker_pool_by_id(int pool_id)
{
	return idr_find(&worker_pool_idr, pool_id);
}

static struct worker_pool *get_std_worker_pool(int cpu, bool highpri)
{
	struct worker_pool *pools = std_worker_pools(cpu);

	return &pools[highpri];
}

static struct pool_workqueue *get_pwq(unsigned int cpu,
				      struct workqueue_struct *wq)
{
	if (!(wq->flags & WQ_UNBOUND)) {
		if (likely(cpu < nr_cpu_ids))
			return per_cpu_ptr(wq->pool_wq.pcpu, cpu);
	} else if (likely(cpu == WORK_CPU_UNBOUND))
		return wq->pool_wq.single;
	return NULL;
}

static unsigned int work_color_to_flags(int color)
{
	return color << WORK_STRUCT_COLOR_SHIFT;
}

static int get_work_color(struct work_struct *work)
{
	return (*work_data_bits(work) >> WORK_STRUCT_COLOR_SHIFT) &
		((1 << WORK_STRUCT_COLOR_BITS) - 1);
}

static int work_next_color(int color)
{
	return (color + 1) % WORK_NR_COLORS;
}

/*
 * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data
 * contain the pointer to the queued pwq.  Once execution starts, the flag
 * is cleared and the high bits contain OFFQ flags and pool ID.
 *
 * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling()
 * and clear_work_data() can be used to set the pwq, pool or clear
 * work->data.  These functions should only be called while the work is
 * owned - ie. while the PENDING bit is set.
 *
 * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq
 * corresponding to a work.  Pool is available once the work has been
 * queued anywhere after initialization until it is sync canceled.  pwq is
 * available only while the work item is queued.
 *
 * %WORK_OFFQ_CANCELING is used to mark a work item which is being
 * canceled.  While being canceled, a work item may have its PENDING set
 * but stay off timer and worklist for arbitrarily long and nobody should
 * try to steal the PENDING bit.
 */
static inline void set_work_data(struct work_struct *work, unsigned long data,
				 unsigned long flags)
{
	BUG_ON(!work_pending(work));
	atomic_long_set(&work->data, data | flags | work_static(work));
}

static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq,
			 unsigned long extra_flags)
{
	set_work_data(work, (unsigned long)pwq,
		      WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags);
}

static void set_work_pool_and_keep_pending(struct work_struct *work,
					   int pool_id)
{
	set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT,
		      WORK_STRUCT_PENDING);
}

static void set_work_pool_and_clear_pending(struct work_struct *work,
					    int pool_id)
{
	/*
	 * The following wmb is paired with the implied mb in
	 * test_and_set_bit(PENDING) and ensures all updates to @work made
	 * here are visible to and precede any updates by the next PENDING
	 * owner.
	 */
	smp_wmb();
	set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0);
}

static void clear_work_data(struct work_struct *work)
{
	smp_wmb();	/* see set_work_pool_and_clear_pending() */
	set_work_data(work, WORK_STRUCT_NO_POOL, 0);
}

static struct pool_workqueue *get_work_pwq(struct work_struct *work)
{
	unsigned long data = atomic_long_read(&work->data);

	if (data & WORK_STRUCT_PWQ)
		return (void *)(data & WORK_STRUCT_WQ_DATA_MASK);
	else
		return NULL;
}

/**
 * get_work_pool - return the worker_pool a given work was associated with
 * @work: the work item of interest
 *
 * Return the worker_pool @work was last associated with.  %NULL if none.
 */
static struct worker_pool *get_work_pool(struct work_struct *work)
{
	unsigned long data = atomic_long_read(&work->data);
	struct worker_pool *pool;
	int pool_id;

	if (data & WORK_STRUCT_PWQ)
		return ((struct pool_workqueue *)
			(data & WORK_STRUCT_WQ_DATA_MASK))->pool;

	pool_id = data >> WORK_OFFQ_POOL_SHIFT;
	if (pool_id == WORK_OFFQ_POOL_NONE)
		return NULL;

	pool = worker_pool_by_id(pool_id);
	WARN_ON_ONCE(!pool);
	return pool;
}

/**
 * get_work_pool_id - return the worker pool ID a given work is associated with
 * @work: the work item of interest
 *
 * Return the worker_pool ID @work was last associated with.
 * %WORK_OFFQ_POOL_NONE if none.
 */
static int get_work_pool_id(struct work_struct *work)
{
	unsigned long data = atomic_long_read(&work->data);

	if (data & WORK_STRUCT_PWQ)
		return ((struct pool_workqueue *)
			(data & WORK_STRUCT_WQ_DATA_MASK))->pool->id;

	return data >> WORK_OFFQ_POOL_SHIFT;
}

static void mark_work_canceling(struct work_struct *work)
{
	unsigned long pool_id = get_work_pool_id(work);

	pool_id <<= WORK_OFFQ_POOL_SHIFT;
	set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING);
}

static bool work_is_canceling(struct work_struct *work)
{
	unsigned long data = atomic_long_read(&work->data);

	return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING);
}

/*
 * Policy functions.  These define the policies on how the global worker
 * pools are managed.  Unless noted otherwise, these functions assume that
 * they're being called with pool->lock held.
 */

static bool __need_more_worker(struct worker_pool *pool)
{
	return !atomic_read(&pool->nr_running);
}

/*
 * Need to wake up a worker?  Called from anything but currently
 * running workers.
 *
 * Note that, because unbound workers never contribute to nr_running, this
 * function will always return %true for unbound pools as long as the
 * worklist isn't empty.
 */
static bool need_more_worker(struct worker_pool *pool)
{
	return !list_empty(&pool->worklist) && __need_more_worker(pool);
}

/* Can I start working?  Called from busy but !running workers. */
static bool may_start_working(struct worker_pool *pool)
{
	return pool->nr_idle;
}

/* Do I need to keep working?  Called from currently running workers. */
static bool keep_working(struct worker_pool *pool)
{
	return !list_empty(&pool->worklist) &&
		atomic_read(&pool->nr_running) <= 1;
}

/* Do we need a new worker?  Called from manager. */
static bool need_to_create_worker(struct worker_pool *pool)
{
	return need_more_worker(pool) && !may_start_working(pool);
}

/* Do I need to be the manager? */
static bool need_to_manage_workers(struct worker_pool *pool)
{
	return need_to_create_worker(pool) ||
		(pool->flags & POOL_MANAGE_WORKERS);
}

/* Do we have too many workers and should some go away? */
static bool too_many_workers(struct worker_pool *pool)
{
	bool managing = pool->flags & POOL_MANAGING_WORKERS;
	int nr_idle = pool->nr_idle + managing; /* manager is considered idle */
	int nr_busy = pool->nr_workers - nr_idle;

	/*
	 * nr_idle and idle_list may disagree if idle rebinding is in
	 * progress.  Never return %true if idle_list is empty.
	 */
	if (list_empty(&pool->idle_list))
		return false;

	return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy;
}

/*
 * Wake up functions.
 */

/* Return the first worker.  Safe with preemption disabled */
static struct worker *first_worker(struct worker_pool *pool)
{
	if (unlikely(list_empty(&pool->idle_list)))
		return NULL;

	return list_first_entry(&pool->idle_list, struct worker, entry);
}

/**
 * wake_up_worker - wake up an idle worker
 * @pool: worker pool to wake worker from
 *
 * Wake up the first idle worker of @pool.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock).
 */
static void wake_up_worker(struct worker_pool *pool)
{
	struct worker *worker = first_worker(pool);

	if (likely(worker))
		wake_up_process(worker->task);
}

/**
 * wq_worker_waking_up - a worker is waking up
 * @task: task waking up
 * @cpu: CPU @task is waking up to
 *
 * This function is called during try_to_wake_up() when a worker is
 * being awoken.
 *
 * CONTEXT:
 * spin_lock_irq(rq->lock)
 */
void wq_worker_waking_up(struct task_struct *task, unsigned int cpu)
{
	struct worker *worker = kthread_data(task);

	if (!(worker->flags & WORKER_NOT_RUNNING)) {
		WARN_ON_ONCE(worker->pool->cpu != cpu);
		atomic_inc(&worker->pool->nr_running);
	}
}

/**
 * wq_worker_sleeping - a worker is going to sleep
 * @task: task going to sleep
 * @cpu: CPU in question, must be the current CPU number
 *
 * This function is called during schedule() when a busy worker is
 * going to sleep.  Worker on the same cpu can be woken up by
 * returning pointer to its task.
 *
 * CONTEXT:
 * spin_lock_irq(rq->lock)
 *
 * RETURNS:
 * Worker task on @cpu to wake up, %NULL if none.
 */
struct task_struct *wq_worker_sleeping(struct task_struct *task,
				       unsigned int cpu)
{
	struct worker *worker = kthread_data(task), *to_wakeup = NULL;
	struct worker_pool *pool;

	/*
	 * Rescuers, which may not have all the fields set up like normal
	 * workers, also reach here, let's not access anything before
	 * checking NOT_RUNNING.
	 */
	if (worker->flags & WORKER_NOT_RUNNING)
		return NULL;

	pool = worker->pool;

	/* this can only happen on the local cpu */
	BUG_ON(cpu != raw_smp_processor_id());

	/*
	 * The counterpart of the following dec_and_test, implied mb,
	 * worklist not empty test sequence is in insert_work().
	 * Please read comment there.
	 *
	 * NOT_RUNNING is clear.  This means that we're bound to and
	 * running on the local cpu w/ rq lock held and preemption
	 * disabled, which in turn means that none else could be
	 * manipulating idle_list, so dereferencing idle_list without pool
	 * lock is safe.
	 */
	if (atomic_dec_and_test(&pool->nr_running) &&
	    !list_empty(&pool->worklist))
		to_wakeup = first_worker(pool);
	return to_wakeup ? to_wakeup->task : NULL;
}

/**
 * worker_set_flags - set worker flags and adjust nr_running accordingly
 * @worker: self
 * @flags: flags to set
 * @wakeup: wakeup an idle worker if necessary
 *
 * Set @flags in @worker->flags and adjust nr_running accordingly.  If
 * nr_running becomes zero and @wakeup is %true, an idle worker is
 * woken up.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock)
 */
static inline void worker_set_flags(struct worker *worker, unsigned int flags,
				    bool wakeup)
{
	struct worker_pool *pool = worker->pool;

	WARN_ON_ONCE(worker->task != current);

	/*
	 * If transitioning into NOT_RUNNING, adjust nr_running and
	 * wake up an idle worker as necessary if requested by
	 * @wakeup.
	 */
	if ((flags & WORKER_NOT_RUNNING) &&
	    !(worker->flags & WORKER_NOT_RUNNING)) {
		if (wakeup) {
			if (atomic_dec_and_test(&pool->nr_running) &&
			    !list_empty(&pool->worklist))
				wake_up_worker(pool);
		} else
			atomic_dec(&pool->nr_running);
	}

	worker->flags |= flags;
}

/**
 * worker_clr_flags - clear worker flags and adjust nr_running accordingly
 * @worker: self
 * @flags: flags to clear
 *
 * Clear @flags in @worker->flags and adjust nr_running accordingly.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock)
 */
static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
{
	struct worker_pool *pool = worker->pool;
	unsigned int oflags = worker->flags;

	WARN_ON_ONCE(worker->task != current);

	worker->flags &= ~flags;

	/*
	 * If transitioning out of NOT_RUNNING, increment nr_running.  Note
	 * that the nested NOT_RUNNING is not a noop.  NOT_RUNNING is mask
	 * of multiple flags, not a single flag.
	 */
	if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING))
		if (!(worker->flags & WORKER_NOT_RUNNING))
			atomic_inc(&pool->nr_running);
}

/**
 * find_worker_executing_work - find worker which is executing a work
 * @pool: pool of interest
 * @work: work to find worker for
 *
 * Find a worker which is executing @work on @pool by searching
 * @pool->busy_hash which is keyed by the address of @work.  For a worker
 * to match, its current execution should match the address of @work and
 * its work function.  This is to avoid unwanted dependency between
 * unrelated work executions through a work item being recycled while still
 * being executed.
 *
 * This is a bit tricky.  A work item may be freed once its execution
 * starts and nothing prevents the freed area from being recycled for
 * another work item.  If the same work item address ends up being reused
 * before the original execution finishes, workqueue will identify the
 * recycled work item as currently executing and make it wait until the
 * current execution finishes, introducing an unwanted dependency.
 *
 * This function checks the work item address, work function and workqueue
 * to avoid false positives.  Note that this isn't complete as one may
 * construct a work function which can introduce dependency onto itself
 * through a recycled work item.  Well, if somebody wants to shoot oneself
 * in the foot that badly, there's only so much we can do, and if such
 * deadlock actually occurs, it should be easy to locate the culprit work
 * function.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock).
 *
 * RETURNS:
 * Pointer to worker which is executing @work if found, NULL
 * otherwise.
 */
static struct worker *find_worker_executing_work(struct worker_pool *pool,
						 struct work_struct *work)
{
	struct worker *worker;

	hash_for_each_possible(pool->busy_hash, worker, hentry,
			       (unsigned long)work)
		if (worker->current_work == work &&
		    worker->current_func == work->func)
			return worker;

	return NULL;
}

/**
 * move_linked_works - move linked works to a list
 * @work: start of series of works to be scheduled
 * @head: target list to append @work to
 * @nextp: out paramter for nested worklist walking
 *
 * Schedule linked works starting from @work to @head.  Work series to
 * be scheduled starts at @work and includes any consecutive work with
 * WORK_STRUCT_LINKED set in its predecessor.
 *
 * If @nextp is not NULL, it's updated to point to the next work of
 * the last scheduled work.  This allows move_linked_works() to be
 * nested inside outer list_for_each_entry_safe().
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock).
 */
static void move_linked_works(struct work_struct *work, struct list_head *head,
			      struct work_struct **nextp)
{
	struct work_struct *n;

	/*
	 * Linked worklist will always end before the end of the list,
	 * use NULL for list head.
	 */
	list_for_each_entry_safe_from(work, n, NULL, entry) {
		list_move_tail(&work->entry, head);
		if (!(*work_data_bits(work) & WORK_STRUCT_LINKED))
			break;
	}

	/*
	 * If we're already inside safe list traversal and have moved
	 * multiple works to the scheduled queue, the next position
	 * needs to be updated.
	 */
	if (nextp)
		*nextp = n;
}

static void pwq_activate_delayed_work(struct work_struct *work)
{
	struct pool_workqueue *pwq = get_work_pwq(work);

	trace_workqueue_activate_work(work);
	move_linked_works(work, &pwq->pool->worklist, NULL);
	__clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
	pwq->nr_active++;
}

static void pwq_activate_first_delayed(struct pool_workqueue *pwq)
{
	struct work_struct *work = list_first_entry(&pwq->delayed_works,
						    struct work_struct, entry);

	pwq_activate_delayed_work(work);
}

/**
 * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight
 * @pwq: pwq of interest
 * @color: color of work which left the queue
 *
 * A work either has completed or is removed from pending queue,
 * decrement nr_in_flight of its pwq and handle workqueue flushing.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock).
 */
static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color)
{
	/* ignore uncolored works */
	if (color == WORK_NO_COLOR)
		return;

	pwq->nr_in_flight[color]--;

	pwq->nr_active--;
	if (!list_empty(&pwq->delayed_works)) {
		/* one down, submit a delayed one */
		if (pwq->nr_active < pwq->max_active)
			pwq_activate_first_delayed(pwq);
	}

	/* is flush in progress and are we at the flushing tip? */
	if (likely(pwq->flush_color != color))
		return;

	/* are there still in-flight works? */
	if (pwq->nr_in_flight[color])
		return;

	/* this pwq is done, clear flush_color */
	pwq->flush_color = -1;

	/*
	 * If this was the last pwq, wake up the first flusher.  It
	 * will handle the rest.
	 */
	if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush))
		complete(&pwq->wq->first_flusher->done);
}

/**
 * try_to_grab_pending - steal work item from worklist and disable irq
 * @work: work item to steal
 * @is_dwork: @work is a delayed_work
 * @flags: place to store irq state
 *
 * Try to grab PENDING bit of @work.  This function can handle @work in any
 * stable state - idle, on timer or on worklist.  Return values are
 *
 *  1		if @work was pending and we successfully stole PENDING
 *  0		if @work was idle and we claimed PENDING
 *  -EAGAIN	if PENDING couldn't be grabbed at the moment, safe to busy-retry
 *  -ENOENT	if someone else is canceling @work, this state may persist
 *		for arbitrarily long
 *
 * On >= 0 return, the caller owns @work's PENDING bit.  To avoid getting
 * interrupted while holding PENDING and @work off queue, irq must be
 * disabled on entry.  This, combined with delayed_work->timer being
 * irqsafe, ensures that we return -EAGAIN for finite short period of time.
 *
 * On successful return, >= 0, irq is disabled and the caller is
 * responsible for releasing it using local_irq_restore(*@flags).
 *
 * This function is safe to call from any context including IRQ handler.
 */
static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
			       unsigned long *flags)
{
	struct worker_pool *pool;
	struct pool_workqueue *pwq;

	local_irq_save(*flags);

	/* try to steal the timer if it exists */
	if (is_dwork) {
		struct delayed_work *dwork = to_delayed_work(work);

		/*
		 * dwork->timer is irqsafe.  If del_timer() fails, it's
		 * guaranteed that the timer is not queued anywhere and not
		 * running on the local CPU.
		 */
		if (likely(del_timer(&dwork->timer)))
			return 1;
	}

	/* try to claim PENDING the normal way */
	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)))
		return 0;

	/*
	 * The queueing is in progress, or it is already queued. Try to
	 * steal it from ->worklist without clearing WORK_STRUCT_PENDING.
	 */
	pool = get_work_pool(work);
	if (!pool)
		goto fail;

	spin_lock(&pool->lock);
	/*
	 * work->data is guaranteed to point to pwq only while the work
	 * item is queued on pwq->wq, and both updating work->data to point
	 * to pwq on queueing and to pool on dequeueing are done under
	 * pwq->pool->lock.  This in turn guarantees that, if work->data
	 * points to pwq which is associated with a locked pool, the work
	 * item is currently queued on that pool.
	 */
	pwq = get_work_pwq(work);
	if (pwq && pwq->pool == pool) {
		debug_work_deactivate(work);

		/*
		 * A delayed work item cannot be grabbed directly because
		 * it might have linked NO_COLOR work items which, if left
		 * on the delayed_list, will confuse pwq->nr_active
		 * management later on and cause stall.  Make sure the work
		 * item is activated before grabbing.
		 */
		if (*work_data_bits(work) & WORK_STRUCT_DELAYED)
			pwq_activate_delayed_work(work);

		list_del_init(&work->entry);
		pwq_dec_nr_in_flight(get_work_pwq(work), get_work_color(work));

		/* work->data points to pwq iff queued, point to pool */
		set_work_pool_and_keep_pending(work, pool->id);

		spin_unlock(&pool->lock);
		return 1;
	}
	spin_unlock(&pool->lock);
fail:
	local_irq_restore(*flags);
	if (work_is_canceling(work))
		return -ENOENT;
	cpu_relax();
	return -EAGAIN;
}

/**
 * insert_work - insert a work into a pool
 * @pwq: pwq @work belongs to
 * @work: work to insert
 * @head: insertion point
 * @extra_flags: extra WORK_STRUCT_* flags to set
 *
 * Insert @work which belongs to @pwq after @head.  @extra_flags is or'd to
 * work_struct flags.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock).
 */
static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
			struct list_head *head, unsigned int extra_flags)
{
	struct worker_pool *pool = pwq->pool;

	/* we own @work, set data and link */
	set_work_pwq(work, pwq, extra_flags);
	list_add_tail(&work->entry, head);

	/*
	 * Ensure either worker_sched_deactivated() sees the above
	 * list_add_tail() or we see zero nr_running to avoid workers
	 * lying around lazily while there are works to be processed.
	 */
	smp_mb();

	if (__need_more_worker(pool))
		wake_up_worker(pool);
}

/*
 * Test whether @work is being queued from another work executing on the
 * same workqueue.
 */
static bool is_chained_work(struct workqueue_struct *wq)
{
	struct worker *worker;

	worker = current_wq_worker();
	/*
	 * Return %true iff I'm a worker execuing a work item on @wq.  If
	 * I'm @worker, it's safe to dereference it without locking.
	 */
	return worker && worker->current_pwq->wq == wq;
}

static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
			 struct work_struct *work)
{
	struct pool_workqueue *pwq;
	struct list_head *worklist;
	unsigned int work_flags;
	unsigned int req_cpu = cpu;

	/*
	 * While a work item is PENDING && off queue, a task trying to
	 * steal the PENDING will busy-loop waiting for it to either get
	 * queued or lose PENDING.  Grabbing PENDING and queueing should
	 * happen with IRQ disabled.
	 */
	WARN_ON_ONCE(!irqs_disabled());

	debug_work_activate(work);

	/* if dying, only works from the same workqueue are allowed */
	if (unlikely(wq->flags & WQ_DRAINING) &&
	    WARN_ON_ONCE(!is_chained_work(wq)))
		return;

	/* determine the pwq to use */
	if (!(wq->flags & WQ_UNBOUND)) {
		struct worker_pool *last_pool;

		if (cpu == WORK_CPU_UNBOUND)
			cpu = raw_smp_processor_id();

		/*
		 * It's multi cpu.  If @work was previously on a different
		 * cpu, it might still be running there, in which case the
		 * work needs to be queued on that cpu to guarantee
		 * non-reentrancy.
		 */
		pwq = get_pwq(cpu, wq);
		last_pool = get_work_pool(work);

		if (last_pool && last_pool != pwq->pool) {
			struct worker *worker;

			spin_lock(&last_pool->lock);

			worker = find_worker_executing_work(last_pool, work);

			if (worker && worker->current_pwq->wq == wq) {
				pwq = get_pwq(last_pool->cpu, wq);
			} else {
				/* meh... not running there, queue here */
				spin_unlock(&last_pool->lock);
				spin_lock(&pwq->pool->lock);
			}
		} else {
			spin_lock(&pwq->pool->lock);
		}
	} else {
		pwq = get_pwq(WORK_CPU_UNBOUND, wq);
		spin_lock(&pwq->pool->lock);
	}

	/* pwq determined, queue */
	trace_workqueue_queue_work(req_cpu, pwq, work);

	if (WARN_ON(!list_empty(&work->entry))) {
		spin_unlock(&pwq->pool->lock);
		return;
	}

	pwq->nr_in_flight[pwq->work_color]++;
	work_flags = work_color_to_flags(pwq->work_color);

	if (likely(pwq->nr_active < pwq->max_active)) {
		trace_workqueue_activate_work(work);
		pwq->nr_active++;
		worklist = &pwq->pool->worklist;
	} else {
		work_flags |= WORK_STRUCT_DELAYED;
		worklist = &pwq->delayed_works;
	}

	insert_work(pwq, work, worklist, work_flags);

	spin_unlock(&pwq->pool->lock);
}

/**
 * queue_work_on - queue work on specific cpu
 * @cpu: CPU number to execute work on
 * @wq: workqueue to use
 * @work: work to queue
 *
 * Returns %false if @work was already on a queue, %true otherwise.
 *
 * We queue the work to a specific CPU, the caller must ensure it
 * can't go away.
 */
bool queue_work_on(int cpu, struct workqueue_struct *wq,
		   struct work_struct *work)
{
	bool ret = false;
	unsigned long flags;

	local_irq_save(flags);

	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
		__queue_work(cpu, wq, work);
		ret = true;
	}

	local_irq_restore(flags);
	return ret;
}
EXPORT_SYMBOL_GPL(queue_work_on);

/**
 * queue_work - queue work on a workqueue
 * @wq: workqueue to use
 * @work: work to queue
 *
 * Returns %false if @work was already on a queue, %true otherwise.
 *
 * We queue the work to the CPU on which it was submitted, but if the CPU dies
 * it can be processed by another CPU.
 */
bool queue_work(struct workqueue_struct *wq, struct work_struct *work)
{
	return queue_work_on(WORK_CPU_UNBOUND, wq, work);
}
EXPORT_SYMBOL_GPL(queue_work);

void delayed_work_timer_fn(unsigned long __data)
{
	struct delayed_work *dwork = (struct delayed_work *)__data;

	/* should have been called from irqsafe timer with irq already off */
	__queue_work(dwork->cpu, dwork->wq, &dwork->work);
}
EXPORT_SYMBOL(delayed_work_timer_fn);

static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
				struct delayed_work *dwork, unsigned long delay)
{
	struct timer_list *timer = &dwork->timer;
	struct work_struct *work = &dwork->work;

	WARN_ON_ONCE(timer->function != delayed_work_timer_fn ||
		     timer->data != (unsigned long)dwork);
	WARN_ON_ONCE(timer_pending(timer));
	WARN_ON_ONCE(!list_empty(&work->entry));

	/*
	 * If @delay is 0, queue @dwork->work immediately.  This is for
	 * both optimization and correctness.  The earliest @timer can
	 * expire is on the closest next tick and delayed_work users depend
	 * on that there's no such delay when @delay is 0.
	 */
	if (!delay) {
		__queue_work(cpu, wq, &dwork->work);
		return;
	}

	timer_stats_timer_set_start_info(&dwork->timer);

	dwork->wq = wq;
	dwork->cpu = cpu;
	timer->expires = jiffies + delay;

	if (unlikely(cpu != WORK_CPU_UNBOUND))
		add_timer_on(timer, cpu);
	else
		add_timer(timer);
}

/**
 * queue_delayed_work_on - queue work on specific CPU after delay
 * @cpu: CPU number to execute work on
 * @wq: workqueue to use
 * @dwork: work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * Returns %false if @work was already on a queue, %true otherwise.  If
 * @delay is zero and @dwork is idle, it will be scheduled for immediate
 * execution.
 */
bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
			   struct delayed_work *dwork, unsigned long delay)
{
	struct work_struct *work = &dwork->work;
	bool ret = false;
	unsigned long flags;

	/* read the comment in __queue_work() */
	local_irq_save(flags);

	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
		__queue_delayed_work(cpu, wq, dwork, delay);
		ret = true;
	}

	local_irq_restore(flags);
	return ret;
}
EXPORT_SYMBOL_GPL(queue_delayed_work_on);

/**
 * queue_delayed_work - queue work on a workqueue after delay
 * @wq: workqueue to use
 * @dwork: delayable work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * Equivalent to queue_delayed_work_on() but tries to use the local CPU.
 */
bool queue_delayed_work(struct workqueue_struct *wq,
			struct delayed_work *dwork, unsigned long delay)
{
	return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
}
EXPORT_SYMBOL_GPL(queue_delayed_work);

/**
 * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU
 * @cpu: CPU number to execute work on
 * @wq: workqueue to use
 * @dwork: work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise,
 * modify @dwork's timer so that it expires after @delay.  If @delay is
 * zero, @work is guaranteed to be scheduled immediately regardless of its
 * current state.
 *
 * Returns %false if @dwork was idle and queued, %true if @dwork was
 * pending and its timer was modified.
 *
 * This function is safe to call from any context including IRQ handler.
 * See try_to_grab_pending() for details.
 */
bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
			 struct delayed_work *dwork, unsigned long delay)
{
	unsigned long flags;
	int ret;

	do {
		ret = try_to_grab_pending(&dwork->work, true, &flags);
	} while (unlikely(ret == -EAGAIN));

	if (likely(ret >= 0)) {
		__queue_delayed_work(cpu, wq, dwork, delay);
		local_irq_restore(flags);
	}

	/* -ENOENT from try_to_grab_pending() becomes %true */
	return ret;
}
EXPORT_SYMBOL_GPL(mod_delayed_work_on);

/**
 * mod_delayed_work - modify delay of or queue a delayed work
 * @wq: workqueue to use
 * @dwork: work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * mod_delayed_work_on() on local CPU.
 */
bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork,
		      unsigned long delay)
{
	return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
}
EXPORT_SYMBOL_GPL(mod_delayed_work);

/**
 * worker_enter_idle - enter idle state
 * @worker: worker which is entering idle state
 *
 * @worker is entering idle state.  Update stats and idle timer if
 * necessary.
 *
 * LOCKING:
 * spin_lock_irq(pool->lock).
 */
static void worker_enter_idle(struct worker *worker)
{
	struct worker_pool *pool = worker->pool;

	BUG_ON(worker->flags & WORKER_IDLE);
	BUG_ON(!list_empty(&worker->entry) &&
	       (worker->hentry.next || worker->hentry.pprev));

	/* can't use worker_set_flags(), also called from start_worker() */
	worker->flags |= WORKER_IDLE;
	pool->nr_idle++;
	worker->last_active = jiffies;

	/* idle_list is LIFO */
	list_add(&worker->entry, &pool->idle_list);

	if (too_many_workers(pool) && !timer_pending(&pool->idle_timer))
		mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT);

	/*
	 * Sanity check nr_running.  Because wq_unbind_fn() releases
	 * pool->lock between setting %WORKER_UNBOUND and zapping
	 * nr_running, the warning may trigger spuriously.  Check iff
	 * unbind is not in progress.
	 */
	WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) &&
		     pool->nr_workers == pool->nr_idle &&
		     atomic_read(&pool->nr_running));
}

/**
 * worker_leave_idle - leave idle state
 * @worker: worker which is leaving idle state
 *
 * @worker is leaving idle state.  Update stats.
 *
 * LOCKING:
 * spin_lock_irq(pool->lock).
 */
static void worker_leave_idle(struct worker *worker)
{
	struct worker_pool *pool = worker->pool;

	BUG_ON(!(worker->flags & WORKER_IDLE));
	worker_clr_flags(worker, WORKER_IDLE);
	pool->nr_idle--;
	list_del_init(&worker->entry);
}

/**
 * worker_maybe_bind_and_lock - bind worker to its cpu if possible and lock pool
 * @worker: self
 *
 * Works which are scheduled while the cpu is online must at least be
 * scheduled to a worker which is bound to the cpu so that if they are
 * flushed from cpu callbacks while cpu is going down, they are
 * guaranteed to execute on the cpu.
 *
 * This function is to be used by rogue workers and rescuers to bind
 * themselves to the target cpu and may race with cpu going down or
 * coming online.  kthread_bind() can't be used because it may put the
 * worker to already dead cpu and set_cpus_allowed_ptr() can't be used
 * verbatim as it's best effort and blocking and pool may be
 * [dis]associated in the meantime.
 *
 * This function tries set_cpus_allowed() and locks pool and verifies the
 * binding against %POOL_DISASSOCIATED which is set during
 * %CPU_DOWN_PREPARE and cleared during %CPU_ONLINE, so if the worker
 * enters idle state or fetches works without dropping lock, it can
 * guarantee the scheduling requirement described in the first paragraph.
 *
 * CONTEXT:
 * Might sleep.  Called without any lock but returns with pool->lock
 * held.
 *
 * RETURNS:
 * %true if the associated pool is online (@worker is successfully
 * bound), %false if offline.
 */
static bool worker_maybe_bind_and_lock(struct worker *worker)
__acquires(&pool->lock)
{
	struct worker_pool *pool = worker->pool;
	struct task_struct *task = worker->task;

	while (true) {
		/*
		 * The following call may fail, succeed or succeed
		 * without actually migrating the task to the cpu if
		 * it races with cpu hotunplug operation.  Verify
		 * against POOL_DISASSOCIATED.
		 */
		if (!(pool->flags & POOL_DISASSOCIATED))
			set_cpus_allowed_ptr(task, get_cpu_mask(pool->cpu));

		spin_lock_irq(&pool->lock);
		if (pool->flags & POOL_DISASSOCIATED)
			return false;
		if (task_cpu(task) == pool->cpu &&
		    cpumask_equal(&current->cpus_allowed,
				  get_cpu_mask(pool->cpu)))
			return true;
		spin_unlock_irq(&pool->lock);

		/*
		 * We've raced with CPU hot[un]plug.  Give it a breather
		 * and retry migration.  cond_resched() is required here;
		 * otherwise, we might deadlock against cpu_stop trying to
		 * bring down the CPU on non-preemptive kernel.
		 */
		cpu_relax();
		cond_resched();
	}
}

/*
 * Rebind an idle @worker to its CPU.  worker_thread() will test
 * list_empty(@worker->entry) before leaving idle and call this function.
 */
static void idle_worker_rebind(struct worker *worker)
{
	/* CPU may go down again inbetween, clear UNBOUND only on success */
	if (worker_maybe_bind_and_lock(worker))
		worker_clr_flags(worker, WORKER_UNBOUND);

	/* rebind complete, become available again */
	list_add(&worker->entry, &worker->pool->idle_list);
	spin_unlock_irq(&worker->pool->lock);
}

/*
 * Function for @worker->rebind.work used to rebind unbound busy workers to
 * the associated cpu which is coming back online.  This is scheduled by
 * cpu up but can race with other cpu hotplug operations and may be
 * executed twice without intervening cpu down.
 */
static void busy_worker_rebind_fn(struct work_struct *work)
{
	struct worker *worker = container_of(work, struct worker, rebind_work);

	if (worker_maybe_bind_and_lock(worker))
		worker_clr_flags(worker, WORKER_UNBOUND);

	spin_unlock_irq(&worker->pool->lock);
}

/**
 * rebind_workers - rebind all workers of a pool to the associated CPU
 * @pool: pool of interest
 *
 * @pool->cpu is coming online.  Rebind all workers to the CPU.  Rebinding
 * is different for idle and busy ones.
 *
 * Idle ones will be removed from the idle_list and woken up.  They will
 * add themselves back after completing rebind.  This ensures that the
 * idle_list doesn't contain any unbound workers when re-bound busy workers
 * try to perform local wake-ups for concurrency management.
 *
 * Busy workers can rebind after they finish their current work items.
 * Queueing the rebind work item at the head of the scheduled list is
 * enough.  Note that nr_running will be properly bumped as busy workers
 * rebind.
 *
 * On return, all non-manager workers are scheduled for rebind - see
 * manage_workers() for the manager special case.  Any idle worker
 * including the manager will not appear on @idle_list until rebind is
 * complete, making local wake-ups safe.
 */
static void rebind_workers(struct worker_pool *pool)
{
	struct worker *worker, *n;
	int i;

	lockdep_assert_held(&pool->assoc_mutex);
	lockdep_assert_held(&pool->lock);

	/* dequeue and kick idle ones */
	list_for_each_entry_safe(worker, n, &pool->idle_list, entry) {
		/*
		 * idle workers should be off @pool->idle_list until rebind
		 * is complete to avoid receiving premature local wake-ups.
		 */
		list_del_init(&worker->entry);

		/*
		 * worker_thread() will see the above dequeuing and call
		 * idle_worker_rebind().
		 */
		wake_up_process(worker->task);
	}

	/* rebind busy workers */
	for_each_busy_worker(worker, i, pool) {
		struct work_struct *rebind_work = &worker->rebind_work;
		struct workqueue_struct *wq;

		if (test_and_set_bit(WORK_STRUCT_PENDING_BIT,
				     work_data_bits(rebind_work)))
			continue;

		debug_work_activate(rebind_work);

		/*
		 * wq doesn't really matter but let's keep @worker->pool
		 * and @pwq->pool consistent for sanity.
		 */
		if (std_worker_pool_pri(worker->pool))
			wq = system_highpri_wq;
		else
			wq = system_wq;

		insert_work(get_pwq(pool->cpu, wq), rebind_work,
			    worker->scheduled.next,
			    work_color_to_flags(WORK_NO_COLOR));
	}
}

static struct worker *alloc_worker(void)
{
	struct worker *worker;

	worker = kzalloc(sizeof(*worker), GFP_KERNEL);
	if (worker) {
		INIT_LIST_HEAD(&worker->entry);
		INIT_LIST_HEAD(&worker->scheduled);
		INIT_WORK(&worker->rebind_work, busy_worker_rebind_fn);
		/* on creation a worker is in !idle && prep state */
		worker->flags = WORKER_PREP;
	}
	return worker;
}

/**
 * create_worker - create a new workqueue worker
 * @pool: pool the new worker will belong to
 *
 * Create a new worker which is bound to @pool.  The returned worker
 * can be started by calling start_worker() or destroyed using
 * destroy_worker().
 *
 * CONTEXT:
 * Might sleep.  Does GFP_KERNEL allocations.
 *
 * RETURNS:
 * Pointer to the newly created worker.
 */
static struct worker *create_worker(struct worker_pool *pool)
{
	const char *pri = std_worker_pool_pri(pool) ? "H" : "";
	struct worker *worker = NULL;
	int id = -1;

	spin_lock_irq(&pool->lock);
	while (ida_get_new(&pool->worker_ida, &id)) {
		spin_unlock_irq(&pool->lock);
		if (!ida_pre_get(&pool->worker_ida, GFP_KERNEL))
			goto fail;
		spin_lock_irq(&pool->lock);
	}
	spin_unlock_irq(&pool->lock);

	worker = alloc_worker();
	if (!worker)
		goto fail;

	worker->pool = pool;
	worker->id = id;

	if (pool->cpu != WORK_CPU_UNBOUND)
		worker->task = kthread_create_on_node(worker_thread,
					worker, cpu_to_node(pool->cpu),
					"kworker/%u:%d%s", pool->cpu, id, pri);
	else
		worker->task = kthread_create(worker_thread, worker,
					      "kworker/u:%d%s", id, pri);
	if (IS_ERR(worker->task))
		goto fail;

	if (std_worker_pool_pri(pool))
		set_user_nice(worker->task, HIGHPRI_NICE_LEVEL);

	/*
	 * Determine CPU binding of the new worker depending on
	 * %POOL_DISASSOCIATED.  The caller is responsible for ensuring the
	 * flag remains stable across this function.  See the comments
	 * above the flag definition for details.
	 *
	 * As an unbound worker may later become a regular one if CPU comes
	 * online, make sure every worker has %PF_THREAD_BOUND set.
	 */
	if (!(pool->flags & POOL_DISASSOCIATED)) {
		kthread_bind(worker->task, pool->cpu);
	} else {
		worker->task->flags |= PF_THREAD_BOUND;
		worker->flags |= WORKER_UNBOUND;
	}

	return worker;
fail:
	if (id >= 0) {
		spin_lock_irq(&pool->lock);
		ida_remove(&pool->worker_ida, id);
		spin_unlock_irq(&pool->lock);
	}
	kfree(worker);
	return NULL;
}

/**
 * start_worker - start a newly created worker
 * @worker: worker to start
 *
 * Make the pool aware of @worker and start it.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock).
 */
static void start_worker(struct worker *worker)
{
	worker->flags |= WORKER_STARTED;
	worker->pool->nr_workers++;
	worker_enter_idle(worker);
	wake_up_process(worker->task);
}

/**
 * destroy_worker - destroy a workqueue worker
 * @worker: worker to be destroyed
 *
 * Destroy @worker and adjust @pool stats accordingly.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock) which is released and regrabbed.
 */
static void destroy_worker(struct worker *worker)
{
	struct worker_pool *pool = worker->pool;
	int id = worker->id;

	/* sanity check frenzy */
	BUG_ON(worker->current_work);
	BUG_ON(!list_empty(&worker->scheduled));

	if (worker->flags & WORKER_STARTED)
		pool->nr_workers--;
	if (worker->flags & WORKER_IDLE)
		pool->nr_idle--;

	list_del_init(&worker->entry);
	worker->flags |= WORKER_DIE;

	spin_unlock_irq(&pool->lock);

	kthread_stop(worker->task);
	kfree(worker);

	spin_lock_irq(&pool->lock);
	ida_remove(&pool->worker_ida, id);
}

static void idle_worker_timeout(unsigned long __pool)
{
	struct worker_pool *pool = (void *)__pool;

	spin_lock_irq(&pool->lock);

	if (too_many_workers(pool)) {
		struct worker *worker;
		unsigned long expires;

		/* idle_list is kept in LIFO order, check the last one */
		worker = list_entry(pool->idle_list.prev, struct worker, entry);
		expires = worker->last_active + IDLE_WORKER_TIMEOUT;

		if (time_before(jiffies, expires))
			mod_timer(&pool->idle_timer, expires);
		else {
			/* it's been idle for too long, wake up manager */
			pool->flags |= POOL_MANAGE_WORKERS;
			wake_up_worker(pool);
		}
	}

	spin_unlock_irq(&pool->lock);
}

static bool send_mayday(struct work_struct *work)
{
	struct pool_workqueue *pwq = get_work_pwq(work);
	struct workqueue_struct *wq = pwq->wq;
	unsigned int cpu;

	if (!(wq->flags & WQ_RESCUER))
		return false;

	/* mayday mayday mayday */
	cpu = pwq->pool->cpu;
	/* WORK_CPU_UNBOUND can't be set in cpumask, use cpu 0 instead */
	if (cpu == WORK_CPU_UNBOUND)
		cpu = 0;
	if (!mayday_test_and_set_cpu(cpu, wq->mayday_mask))
		wake_up_process(wq->rescuer->task);
	return true;
}

static void pool_mayday_timeout(unsigned long __pool)
{
	struct worker_pool *pool = (void *)__pool;
	struct work_struct *work;

	spin_lock_irq(&pool->lock);

	if (need_to_create_worker(pool)) {
		/*
		 * We've been trying to create a new worker but
		 * haven't been successful.  We might be hitting an
		 * allocation deadlock.  Send distress signals to
		 * rescuers.
		 */
		list_for_each_entry(work, &pool->worklist, entry)
			send_mayday(work);
	}

	spin_unlock_irq(&pool->lock);

	mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL);
}

/**
 * maybe_create_worker - create a new worker if necessary
 * @pool: pool to create a new worker for
 *
 * Create a new worker for @pool if necessary.  @pool is guaranteed to
 * have at least one idle worker on return from this function.  If
 * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is
 * sent to all rescuers with works scheduled on @pool to resolve
 * possible allocation deadlock.
 *
 * On return, need_to_create_worker() is guaranteed to be false and
 * may_start_working() true.
 *
 * LOCKING:
 * spin_lock_irq(pool->lock) which may be released and regrabbed
 * multiple times.  Does GFP_KERNEL allocations.  Called only from
 * manager.
 *
 * RETURNS:
 * false if no action was taken and pool->lock stayed locked, true
 * otherwise.
 */
static bool maybe_create_worker(struct worker_pool *pool)
__releases(&pool->lock)
__acquires(&pool->lock)
{
	if (!need_to_create_worker(pool))
		return false;
restart:
	spin_unlock_irq(&pool->lock);

	/* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */
	mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT);

	while (true) {
		struct worker *worker;

		worker = create_worker(pool);
		if (worker) {
			del_timer_sync(&pool->mayday_timer);
			spin_lock_irq(&pool->lock);
			start_worker(worker);
			BUG_ON(need_to_create_worker(pool));
			return true;
		}

		if (!need_to_create_worker(pool))
			break;

		__set_current_state(TASK_INTERRUPTIBLE);
		schedule_timeout(CREATE_COOLDOWN);

		if (!need_to_create_worker(pool))
			break;
	}

	del_timer_sync(&pool->mayday_timer);
	spin_lock_irq(&pool->lock);
	if (need_to_create_worker(pool))
		goto restart;
	return true;
}

/**
 * maybe_destroy_worker - destroy workers which have been idle for a while
 * @pool: pool to destroy workers for
 *
 * Destroy @pool workers which have been idle for longer than
 * IDLE_WORKER_TIMEOUT.
 *
 * LOCKING:
 * spin_lock_irq(pool->lock) which may be released and regrabbed
 * multiple times.  Called only from manager.
 *
 * RETURNS:
 * false if no action was taken and pool->lock stayed locked, true
 * otherwise.
 */
static bool maybe_destroy_workers(struct worker_pool *pool)
{
	bool ret = false;

	while (too_many_workers(pool)) {
		struct worker *worker;
		unsigned long expires;

		worker = list_entry(pool->idle_list.prev, struct worker, entry);
		expires = worker->last_active + IDLE_WORKER_TIMEOUT;

		if (time_before(jiffies, expires)) {
			mod_timer(&pool->idle_timer, expires);
			break;
		}

		destroy_worker(worker);
		ret = true;
	}

	return ret;
}

/**
 * manage_workers - manage worker pool
 * @worker: self
 *
 * Assume the manager role and manage the worker pool @worker belongs
 * to.  At any given time, there can be only zero or one manager per
 * pool.  The exclusion is handled automatically by this function.
 *
 * The caller can safely start processing works on false return.  On
 * true return, it's guaranteed that need_to_create_worker() is false
 * and may_start_working() is true.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock) which may be released and regrabbed
 * multiple times.  Does GFP_KERNEL allocations.
 *
 * RETURNS:
 * spin_lock_irq(pool->lock) which may be released and regrabbed
 * multiple times.  Does GFP_KERNEL allocations.
 */
static bool manage_workers(struct worker *worker)
{
	struct worker_pool *pool = worker->pool;
	bool ret = false;

	if (pool->flags & POOL_MANAGING_WORKERS)
		return ret;

	pool->flags |= POOL_MANAGING_WORKERS;

	/*
	 * To simplify both worker management and CPU hotplug, hold off
	 * management while hotplug is in progress.  CPU hotplug path can't
	 * grab %POOL_MANAGING_WORKERS to achieve this because that can
	 * lead to idle worker depletion (all become busy thinking someone
	 * else is managing) which in turn can result in deadlock under
	 * extreme circumstances.  Use @pool->assoc_mutex to synchronize
	 * manager against CPU hotplug.
	 *
	 * assoc_mutex would always be free unless CPU hotplug is in
	 * progress.  trylock first without dropping @pool->lock.
	 */
	if (unlikely(!mutex_trylock(&pool->assoc_mutex))) {
		spin_unlock_irq(&pool->lock);
		mutex_lock(&pool->assoc_mutex);
		/*
		 * CPU hotplug could have happened while we were waiting
		 * for assoc_mutex.  Hotplug itself can't handle us
		 * because manager isn't either on idle or busy list, and
		 * @pool's state and ours could have deviated.
		 *
		 * As hotplug is now excluded via assoc_mutex, we can
		 * simply try to bind.  It will succeed or fail depending
		 * on @pool's current state.  Try it and adjust
		 * %WORKER_UNBOUND accordingly.
		 */
		if (worker_maybe_bind_and_lock(worker))
			worker->flags &= ~WORKER_UNBOUND;
		else
			worker->flags |= WORKER_UNBOUND;

		ret = true;
	}

	pool->flags &= ~POOL_MANAGE_WORKERS;

	/*
	 * Destroy and then create so that may_start_working() is true
	 * on return.
	 */
	ret |= maybe_destroy_workers(pool);
	ret |= maybe_create_worker(pool);

	pool->flags &= ~POOL_MANAGING_WORKERS;
	mutex_unlock(&pool->assoc_mutex);
	return ret;
}

/**
 * process_one_work - process single work
 * @worker: self
 * @work: work to process
 *
 * Process @work.  This function contains all the logics necessary to
 * process a single work including synchronization against and
 * interaction with other workers on the same cpu, queueing and
 * flushing.  As long as context requirement is met, any worker can
 * call this function to process a work.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock) which is released and regrabbed.
 */
static void process_one_work(struct worker *worker, struct work_struct *work)
__releases(&pool->lock)
__acquires(&pool->lock)
{
	struct pool_workqueue *pwq = get_work_pwq(work);
	struct worker_pool *pool = worker->pool;
	bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE;
	int work_color;
	struct worker *collision;
#ifdef CONFIG_LOCKDEP
	/*
	 * It is permissible to free the struct work_struct from
	 * inside the function that is called from it, this we need to
	 * take into account for lockdep too.  To avoid bogus "held
	 * lock freed" warnings as well as problems when looking into
	 * work->lockdep_map, make a copy and use that here.
	 */
	struct lockdep_map lockdep_map;

	lockdep_copy_map(&lockdep_map, &work->lockdep_map);
#endif
	/*
	 * Ensure we're on the correct CPU.  DISASSOCIATED test is
	 * necessary to avoid spurious warnings from rescuers servicing the
	 * unbound or a disassociated pool.
	 */
	WARN_ON_ONCE(!(worker->flags & WORKER_UNBOUND) &&
		     !(pool->flags & POOL_DISASSOCIATED) &&
		     raw_smp_processor_id() != pool->cpu);

	/*
	 * A single work shouldn't be executed concurrently by
	 * multiple workers on a single cpu.  Check whether anyone is
	 * already processing the work.  If so, defer the work to the
	 * currently executing one.
	 */
	collision = find_worker_executing_work(pool, work);
	if (unlikely(collision)) {
		move_linked_works(work, &collision->scheduled, NULL);
		return;
	}

	/* claim and dequeue */
	debug_work_deactivate(work);
	hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work);
	worker->current_work = work;
	worker->current_func = work->func;
	worker->current_pwq = pwq;
	work_color = get_work_color(work);

	list_del_init(&work->entry);

	/*
	 * CPU intensive works don't participate in concurrency
	 * management.  They're the scheduler's responsibility.
	 */
	if (unlikely(cpu_intensive))
		worker_set_flags(worker, WORKER_CPU_INTENSIVE, true);

	/*
	 * Unbound pool isn't concurrency managed and work items should be
	 * executed ASAP.  Wake up another worker if necessary.
	 */
	if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool))
		wake_up_worker(pool);

	/*
	 * Record the last pool and clear PENDING which should be the last
	 * update to @work.  Also, do this inside @pool->lock so that
	 * PENDING and queued state changes happen together while IRQ is
	 * disabled.
	 */
	set_work_pool_and_clear_pending(work, pool->id);

	spin_unlock_irq(&pool->lock);

	lock_map_acquire_read(&pwq->wq->lockdep_map);
	lock_map_acquire(&lockdep_map);
	trace_workqueue_execute_start(work);
	worker->current_func(work);
	/*
	 * While we must be careful to not use "work" after this, the trace
	 * point will only record its address.
	 */
	trace_workqueue_execute_end(work);
	lock_map_release(&lockdep_map);
	lock_map_release(&pwq->wq->lockdep_map);

	if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
		pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n"
		       "     last function: %pf\n",
		       current->comm, preempt_count(), task_pid_nr(current),
		       worker->current_func);
		debug_show_held_locks(current);
		dump_stack();
	}

	spin_lock_irq(&pool->lock);

	/* clear cpu intensive status */
	if (unlikely(cpu_intensive))
		worker_clr_flags(worker, WORKER_CPU_INTENSIVE);

	/* we're done with it, release */
	hash_del(&worker->hentry);
	worker->current_work = NULL;
	worker->current_func = NULL;
	worker->current_pwq = NULL;
	pwq_dec_nr_in_flight(pwq, work_color);
}

/**
 * process_scheduled_works - process scheduled works
 * @worker: self
 *
 * Process all scheduled works.  Please note that the scheduled list
 * may change while processing a work, so this function repeatedly
 * fetches a work from the top and executes it.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock) which may be released and regrabbed
 * multiple times.
 */
static void process_scheduled_works(struct worker *worker)
{
	while (!list_empty(&worker->scheduled)) {
		struct work_struct *work = list_first_entry(&worker->scheduled,
						struct work_struct, entry);
		process_one_work(worker, work);
	}
}

/**
 * worker_thread - the worker thread function
 * @__worker: self
 *
 * The worker thread function.  There are NR_CPU_WORKER_POOLS dynamic pools
 * of these per each cpu.  These workers process all works regardless of
 * their specific target workqueue.  The only exception is works which
 * belong to workqueues with a rescuer which will be explained in
 * rescuer_thread().
 */
static int worker_thread(void *__worker)
{
	struct worker *worker = __worker;
	struct worker_pool *pool = worker->pool;

	/* tell the scheduler that this is a workqueue worker */
	worker->task->flags |= PF_WQ_WORKER;
woke_up:
	spin_lock_irq(&pool->lock);

	/* we are off idle list if destruction or rebind is requested */
	if (unlikely(list_empty(&worker->entry))) {
		spin_unlock_irq(&pool->lock);

		/* if DIE is set, destruction is requested */
		if (worker->flags & WORKER_DIE) {
			worker->task->flags &= ~PF_WQ_WORKER;
			return 0;
		}

		/* otherwise, rebind */
		idle_worker_rebind(worker);
		goto woke_up;
	}

	worker_leave_idle(worker);
recheck:
	/* no more worker necessary? */
	if (!need_more_worker(pool))
		goto sleep;

	/* do we need to manage? */
	if (unlikely(!may_start_working(pool)) && manage_workers(worker))
		goto recheck;

	/*
	 * ->scheduled list can only be filled while a worker is
	 * preparing to process a work or actually processing it.
	 * Make sure nobody diddled with it while I was sleeping.
	 */
	BUG_ON(!list_empty(&worker->scheduled));

	/*
	 * When control reaches this point, we're guaranteed to have
	 * at least one idle worker or that someone else has already
	 * assumed the manager role.
	 */
	worker_clr_flags(worker, WORKER_PREP);

	do {
		struct work_struct *work =
			list_first_entry(&pool->worklist,
					 struct work_struct, entry);

		if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) {
			/* optimization path, not strictly necessary */
			process_one_work(worker, work);
			if (unlikely(!list_empty(&worker->scheduled)))
				process_scheduled_works(worker);
		} else {
			move_linked_works(work, &worker->scheduled, NULL);
			process_scheduled_works(worker);
		}
	} while (keep_working(pool));

	worker_set_flags(worker, WORKER_PREP, false);
sleep:
	if (unlikely(need_to_manage_workers(pool)) && manage_workers(worker))
		goto recheck;

	/*
	 * pool->lock is held and there's no work to process and no need to
	 * manage, sleep.  Workers are woken up only while holding
	 * pool->lock or from local cpu, so setting the current state
	 * before releasing pool->lock is enough to prevent losing any
	 * event.
	 */
	worker_enter_idle(worker);
	__set_current_state(TASK_INTERRUPTIBLE);
	spin_unlock_irq(&pool->lock);
	schedule();
	goto woke_up;
}

/**
 * rescuer_thread - the rescuer thread function
 * @__rescuer: self
 *
 * Workqueue rescuer thread function.  There's one rescuer for each
 * workqueue which has WQ_RESCUER set.
 *
 * Regular work processing on a pool may block trying to create a new
 * worker which uses GFP_KERNEL allocation which has slight chance of
 * developing into deadlock if some works currently on the same queue
 * need to be processed to satisfy the GFP_KERNEL allocation.  This is
 * the problem rescuer solves.
 *
 * When such condition is possible, the pool summons rescuers of all
 * workqueues which have works queued on the pool and let them process
 * those works so that forward progress can be guaranteed.
 *
 * This should happen rarely.
 */
static int rescuer_thread(void *__rescuer)
{
	struct worker *rescuer = __rescuer;
	struct workqueue_struct *wq = rescuer->rescue_wq;
	struct list_head *scheduled = &rescuer->scheduled;
	bool is_unbound = wq->flags & WQ_UNBOUND;
	unsigned int cpu;

	set_user_nice(current, RESCUER_NICE_LEVEL);

	/*
	 * Mark rescuer as worker too.  As WORKER_PREP is never cleared, it
	 * doesn't participate in concurrency management.
	 */
	rescuer->task->flags |= PF_WQ_WORKER;
repeat:
	set_current_state(TASK_INTERRUPTIBLE);

	if (kthread_should_stop()) {
		__set_current_state(TASK_RUNNING);
		rescuer->task->flags &= ~PF_WQ_WORKER;
		return 0;
	}

	/*
	 * See whether any cpu is asking for help.  Unbounded
	 * workqueues use cpu 0 in mayday_mask for CPU_UNBOUND.
	 */
	for_each_mayday_cpu(cpu, wq->mayday_mask) {
		unsigned int tcpu = is_unbound ? WORK_CPU_UNBOUND : cpu;
		struct pool_workqueue *pwq = get_pwq(tcpu, wq);
		struct worker_pool *pool = pwq->pool;
		struct work_struct *work, *n;

		__set_current_state(TASK_RUNNING);
		mayday_clear_cpu(cpu, wq->mayday_mask);

		/* migrate to the target cpu if possible */
		rescuer->pool = pool;
		worker_maybe_bind_and_lock(rescuer);

		/*
		 * Slurp in all works issued via this workqueue and
		 * process'em.
		 */
		BUG_ON(!list_empty(&rescuer->scheduled));
		list_for_each_entry_safe(work, n, &pool->worklist, entry)
			if (get_work_pwq(work) == pwq)
				move_linked_works(work, scheduled, &n);

		process_scheduled_works(rescuer);

		/*
		 * Leave this pool.  If keep_working() is %true, notify a
		 * regular worker; otherwise, we end up with 0 concurrency
		 * and stalling the execution.
		 */
		if (keep_working(pool))
			wake_up_worker(pool);

		spin_unlock_irq(&pool->lock);
	}

	/* rescuers should never participate in concurrency management */
	WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
	schedule();
	goto repeat;
}

struct wq_barrier {
	struct work_struct	work;
	struct completion	done;
};

static void wq_barrier_func(struct work_struct *work)
{
	struct wq_barrier *barr = container_of(work, struct wq_barrier, work);
	complete(&barr->done);
}

/**
 * insert_wq_barrier - insert a barrier work
 * @pwq: pwq to insert barrier into
 * @barr: wq_barrier to insert
 * @target: target work to attach @barr to
 * @worker: worker currently executing @target, NULL if @target is not executing
 *
 * @barr is linked to @target such that @barr is completed only after
 * @target finishes execution.  Please note that the ordering
 * guarantee is observed only with respect to @target and on the local
 * cpu.
 *
 * Currently, a queued barrier can't be canceled.  This is because
 * try_to_grab_pending() can't determine whether the work to be
 * grabbed is at the head of the queue and thus can't clear LINKED
 * flag of the previous work while there must be a valid next work
 * after a work with LINKED flag set.
 *
 * Note that when @worker is non-NULL, @target may be modified
 * underneath us, so we can't reliably determine pwq from @target.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock).
 */
static void insert_wq_barrier(struct pool_workqueue *pwq,
			      struct wq_barrier *barr,
			      struct work_struct *target, struct worker *worker)
{
	struct list_head *head;
	unsigned int linked = 0;

	/*
	 * debugobject calls are safe here even with pool->lock locked
	 * as we know for sure that this will not trigger any of the
	 * checks and call back into the fixup functions where we
	 * might deadlock.
	 */
	INIT_WORK_ONSTACK(&barr->work, wq_barrier_func);
	__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
	init_completion(&barr->done);

	/*
	 * If @target is currently being executed, schedule the
	 * barrier to the worker; otherwise, put it after @target.
	 */
	if (worker)
		head = worker->scheduled.next;
	else {
		unsigned long *bits = work_data_bits(target);

		head = target->entry.next;
		/* there can already be other linked works, inherit and set */
		linked = *bits & WORK_STRUCT_LINKED;
		__set_bit(WORK_STRUCT_LINKED_BIT, bits);
	}

	debug_work_activate(&barr->work);
	insert_work(pwq, &barr->work, head,
		    work_color_to_flags(WORK_NO_COLOR) | linked);
}

/**
 * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing
 * @wq: workqueue being flushed
 * @flush_color: new flush color, < 0 for no-op
 * @work_color: new work color, < 0 for no-op
 *
 * Prepare pwqs for workqueue flushing.
 *
 * If @flush_color is non-negative, flush_color on all pwqs should be
 * -1.  If no pwq has in-flight commands at the specified color, all
 * pwq->flush_color's stay at -1 and %false is returned.  If any pwq
 * has in flight commands, its pwq->flush_color is set to
 * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq
 * wakeup logic is armed and %true is returned.
 *
 * The caller should have initialized @wq->first_flusher prior to
 * calling this function with non-negative @flush_color.  If
 * @flush_color is negative, no flush color update is done and %false
 * is returned.
 *
 * If @work_color is non-negative, all pwqs should have the same
 * work_color which is previous to @work_color and all will be
 * advanced to @work_color.
 *
 * CONTEXT:
 * mutex_lock(wq->flush_mutex).
 *
 * RETURNS:
 * %true if @flush_color >= 0 and there's something to flush.  %false
 * otherwise.
 */
static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
				      int flush_color, int work_color)
{
	bool wait = false;
	unsigned int cpu;

	if (flush_color >= 0) {
		BUG_ON(atomic_read(&wq->nr_pwqs_to_flush));
		atomic_set(&wq->nr_pwqs_to_flush, 1);
	}

	for_each_pwq_cpu(cpu, wq) {
		struct pool_workqueue *pwq = get_pwq(cpu, wq);
		struct worker_pool *pool = pwq->pool;

		spin_lock_irq(&pool->lock);

		if (flush_color >= 0) {
			BUG_ON(pwq->flush_color != -1);

			if (pwq->nr_in_flight[flush_color]) {
				pwq->flush_color = flush_color;
				atomic_inc(&wq->nr_pwqs_to_flush);
				wait = true;
			}
		}

		if (work_color >= 0) {
			BUG_ON(work_color != work_next_color(pwq->work_color));
			pwq->work_color = work_color;
		}

		spin_unlock_irq(&pool->lock);
	}

	if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush))
		complete(&wq->first_flusher->done);

	return wait;
}

/**
 * flush_workqueue - ensure that any scheduled work has run to completion.
 * @wq: workqueue to flush
 *
 * Forces execution of the workqueue and blocks until its completion.
 * This is typically used in driver shutdown handlers.
 *
 * We sleep until all works which were queued on entry have been handled,
 * but we are not livelocked by new incoming ones.
 */
void flush_workqueue(struct workqueue_struct *wq)
{
	struct wq_flusher this_flusher = {
		.list = LIST_HEAD_INIT(this_flusher.list),
		.flush_color = -1,
		.done = COMPLETION_INITIALIZER_ONSTACK(this_flusher.done),
	};
	int next_color;

	lock_map_acquire(&wq->lockdep_map);
	lock_map_release(&wq->lockdep_map);

	mutex_lock(&wq->flush_mutex);

	/*
	 * Start-to-wait phase
	 */
	next_color = work_next_color(wq->work_color);

	if (next_color != wq->flush_color) {
		/*
		 * Color space is not full.  The current work_color
		 * becomes our flush_color and work_color is advanced
		 * by one.
		 */
		BUG_ON(!list_empty(&wq->flusher_overflow));
		this_flusher.flush_color = wq->work_color;
		wq->work_color = next_color;

		if (!wq->first_flusher) {
			/* no flush in progress, become the first flusher */
			BUG_ON(wq->flush_color != this_flusher.flush_color);

			wq->first_flusher = &this_flusher;

			if (!flush_workqueue_prep_pwqs(wq, wq->flush_color,
						       wq->work_color)) {
				/* nothing to flush, done */
				wq->flush_color = next_color;
				wq->first_flusher = NULL;
				goto out_unlock;
			}
		} else {
			/* wait in queue */
			BUG_ON(wq->flush_color == this_flusher.flush_color);
			list_add_tail(&this_flusher.list, &wq->flusher_queue);
			flush_workqueue_prep_pwqs(wq, -1, wq->work_color);
		}
	} else {
		/*
		 * Oops, color space is full, wait on overflow queue.
		 * The next flush completion will assign us
		 * flush_color and transfer to flusher_queue.
		 */
		list_add_tail(&this_flusher.list, &wq->flusher_overflow);
	}

	mutex_unlock(&wq->flush_mutex);

	wait_for_completion(&this_flusher.done);

	/*
	 * Wake-up-and-cascade phase
	 *
	 * First flushers are responsible for cascading flushes and
	 * handling overflow.  Non-first flushers can simply return.
	 */
	if (wq->first_flusher != &this_flusher)
		return;

	mutex_lock(&wq->flush_mutex);

	/* we might have raced, check again with mutex held */
	if (wq->first_flusher != &this_flusher)
		goto out_unlock;

	wq->first_flusher = NULL;

	BUG_ON(!list_empty(&this_flusher.list));
	BUG_ON(wq->flush_color != this_flusher.flush_color);

	while (true) {
		struct wq_flusher *next, *tmp;

		/* complete all the flushers sharing the current flush color */
		list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) {
			if (next->flush_color != wq->flush_color)
				break;
			list_del_init(&next->list);
			complete(&next->done);
		}

		BUG_ON(!list_empty(&wq->flusher_overflow) &&
		       wq->flush_color != work_next_color(wq->work_color));

		/* this flush_color is finished, advance by one */
		wq->flush_color = work_next_color(wq->flush_color);

		/* one color has been freed, handle overflow queue */
		if (!list_empty(&wq->flusher_overflow)) {
			/*
			 * Assign the same color to all overflowed
			 * flushers, advance work_color and append to
			 * flusher_queue.  This is the start-to-wait
			 * phase for these overflowed flushers.
			 */
			list_for_each_entry(tmp, &wq->flusher_overflow, list)
				tmp->flush_color = wq->work_color;

			wq->work_color = work_next_color(wq->work_color);

			list_splice_tail_init(&wq->flusher_overflow,
					      &wq->flusher_queue);
			flush_workqueue_prep_pwqs(wq, -1, wq->work_color);
		}

		if (list_empty(&wq->flusher_queue)) {
			BUG_ON(wq->flush_color != wq->work_color);
			break;
		}

		/*
		 * Need to flush more colors.  Make the next flusher
		 * the new first flusher and arm pwqs.
		 */
		BUG_ON(wq->flush_color == wq->work_color);
		BUG_ON(wq->flush_color != next->flush_color);

		list_del_init(&next->list);
		wq->first_flusher = next;

		if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1))
			break;

		/*
		 * Meh... this color is already done, clear first
		 * flusher and repeat cascading.
		 */
		wq->first_flusher = NULL;
	}

out_unlock:
	mutex_unlock(&wq->flush_mutex);
}
EXPORT_SYMBOL_GPL(flush_workqueue);

/**
 * drain_workqueue - drain a workqueue
 * @wq: workqueue to drain
 *
 * Wait until the workqueue becomes empty.  While draining is in progress,
 * only chain queueing is allowed.  IOW, only currently pending or running
 * work items on @wq can queue further work items on it.  @wq is flushed
 * repeatedly until it becomes empty.  The number of flushing is detemined
 * by the depth of chaining and should be relatively short.  Whine if it
 * takes too long.
 */
void drain_workqueue(struct workqueue_struct *wq)
{
	unsigned int flush_cnt = 0;
	unsigned int cpu;

	/*
	 * __queue_work() needs to test whether there are drainers, is much
	 * hotter than drain_workqueue() and already looks at @wq->flags.
	 * Use WQ_DRAINING so that queue doesn't have to check nr_drainers.
	 */
	spin_lock(&workqueue_lock);
	if (!wq->nr_drainers++)
		wq->flags |= WQ_DRAINING;
	spin_unlock(&workqueue_lock);
reflush:
	flush_workqueue(wq);

	for_each_pwq_cpu(cpu, wq) {
		struct pool_workqueue *pwq = get_pwq(cpu, wq);
		bool drained;

		spin_lock_irq(&pwq->pool->lock);
		drained = !pwq->nr_active && list_empty(&pwq->delayed_works);
		spin_unlock_irq(&pwq->pool->lock);

		if (drained)
			continue;

		if (++flush_cnt == 10 ||
		    (flush_cnt % 100 == 0 && flush_cnt <= 1000))
			pr_warn("workqueue %s: flush on destruction isn't complete after %u tries\n",
				wq->name, flush_cnt);
		goto reflush;
	}

	spin_lock(&workqueue_lock);
	if (!--wq->nr_drainers)
		wq->flags &= ~WQ_DRAINING;
	spin_unlock(&workqueue_lock);
}
EXPORT_SYMBOL_GPL(drain_workqueue);

static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
{
	struct worker *worker = NULL;
	struct worker_pool *pool;
	struct pool_workqueue *pwq;

	might_sleep();
	pool = get_work_pool(work);
	if (!pool)
		return false;

	spin_lock_irq(&pool->lock);
	/* see the comment in try_to_grab_pending() with the same code */
	pwq = get_work_pwq(work);
	if (pwq) {
		if (unlikely(pwq->pool != pool))
			goto already_gone;
	} else {
		worker = find_worker_executing_work(pool, work);
		if (!worker)
			goto already_gone;
		pwq = worker->current_pwq;
	}

	insert_wq_barrier(pwq, barr, work, worker);
	spin_unlock_irq(&pool->lock);

	/*
	 * If @max_active is 1 or rescuer is in use, flushing another work
	 * item on the same workqueue may lead to deadlock.  Make sure the
	 * flusher is not running on the same workqueue by verifying write
	 * access.
	 */
	if (pwq->wq->saved_max_active == 1 || pwq->wq->flags & WQ_RESCUER)
		lock_map_acquire(&pwq->wq->lockdep_map);
	else
		lock_map_acquire_read(&pwq->wq->lockdep_map);
	lock_map_release(&pwq->wq->lockdep_map);

	return true;
already_gone:
	spin_unlock_irq(&pool->lock);
	return false;
}

/**
 * flush_work - wait for a work to finish executing the last queueing instance
 * @work: the work to flush
 *
 * Wait until @work has finished execution.  @work is guaranteed to be idle
 * on return if it hasn't been requeued since flush started.
 *
 * RETURNS:
 * %true if flush_work() waited for the work to finish execution,
 * %false if it was already idle.
 */
bool flush_work(struct work_struct *work)
{
	struct wq_barrier barr;

	lock_map_acquire(&work->lockdep_map);
	lock_map_release(&work->lockdep_map);

	if (start_flush_work(work, &barr)) {
		wait_for_completion(&barr.done);
		destroy_work_on_stack(&barr.work);
		return true;
	} else {
		return false;
	}
}
EXPORT_SYMBOL_GPL(flush_work);

static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
{
	unsigned long flags;
	int ret;

	do {
		ret = try_to_grab_pending(work, is_dwork, &flags);
		/*
		 * If someone else is canceling, wait for the same event it
		 * would be waiting for before retrying.
		 */
		if (unlikely(ret == -ENOENT))
			flush_work(work);
	} while (unlikely(ret < 0));

	/* tell other tasks trying to grab @work to back off */
	mark_work_canceling(work);
	local_irq_restore(flags);

	flush_work(work);
	clear_work_data(work);
	return ret;
}

/**
 * cancel_work_sync - cancel a work and wait for it to finish
 * @work: the work to cancel
 *
 * Cancel @work and wait for its execution to finish.  This function
 * can be used even if the work re-queues itself or migrates to
 * another workqueue.  On return from this function, @work is
 * guaranteed to be not pending or executing on any CPU.
 *
 * cancel_work_sync(&delayed_work->work) must not be used for
 * delayed_work's.  Use cancel_delayed_work_sync() instead.
 *
 * The caller must ensure that the workqueue on which @work was last
 * queued can't be destroyed before this function returns.
 *
 * RETURNS:
 * %true if @work was pending, %false otherwise.
 */
bool cancel_work_sync(struct work_struct *work)
{
	return __cancel_work_timer(work, false);
}
EXPORT_SYMBOL_GPL(cancel_work_sync);

/**
 * flush_delayed_work - wait for a dwork to finish executing the last queueing
 * @dwork: the delayed work to flush
 *
 * Delayed timer is cancelled and the pending work is queued for
 * immediate execution.  Like flush_work(), this function only
 * considers the last queueing instance of @dwork.
 *
 * RETURNS:
 * %true if flush_work() waited for the work to finish execution,
 * %false if it was already idle.
 */
bool flush_delayed_work(struct delayed_work *dwork)
{
	local_irq_disable();
	if (del_timer_sync(&dwork->timer))
		__queue_work(dwork->cpu, dwork->wq, &dwork->work);
	local_irq_enable();
	return flush_work(&dwork->work);
}
EXPORT_SYMBOL(flush_delayed_work);

/**
 * cancel_delayed_work - cancel a delayed work
 * @dwork: delayed_work to cancel
 *
 * Kill off a pending delayed_work.  Returns %true if @dwork was pending
 * and canceled; %false if wasn't pending.  Note that the work callback
 * function may still be running on return, unless it returns %true and the
 * work doesn't re-arm itself.  Explicitly flush or use
 * cancel_delayed_work_sync() to wait on it.
 *
 * This function is safe to call from any context including IRQ handler.
 */
bool cancel_delayed_work(struct delayed_work *dwork)
{
	unsigned long flags;
	int ret;

	do {
		ret = try_to_grab_pending(&dwork->work, true, &flags);
	} while (unlikely(ret == -EAGAIN));

	if (unlikely(ret < 0))
		return false;

	set_work_pool_and_clear_pending(&dwork->work,
					get_work_pool_id(&dwork->work));
	local_irq_restore(flags);
	return ret;
}
EXPORT_SYMBOL(cancel_delayed_work);

/**
 * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish
 * @dwork: the delayed work cancel
 *
 * This is cancel_work_sync() for delayed works.
 *
 * RETURNS:
 * %true if @dwork was pending, %false otherwise.
 */
bool cancel_delayed_work_sync(struct delayed_work *dwork)
{
	return __cancel_work_timer(&dwork->work, true);
}
EXPORT_SYMBOL(cancel_delayed_work_sync);

/**
 * schedule_work_on - put work task on a specific cpu
 * @cpu: cpu to put the work task on
 * @work: job to be done
 *
 * This puts a job on a specific cpu
 */
bool schedule_work_on(int cpu, struct work_struct *work)
{
	return queue_work_on(cpu, system_wq, work);
}
EXPORT_SYMBOL(schedule_work_on);

/**
 * schedule_work - put work task in global workqueue
 * @work: job to be done
 *
 * Returns %false if @work was already on the kernel-global workqueue and
 * %true otherwise.
 *
 * This puts a job in the kernel-global workqueue if it was not already
 * queued and leaves it in the same position on the kernel-global
 * workqueue otherwise.
 */
bool schedule_work(struct work_struct *work)
{
	return queue_work(system_wq, work);
}
EXPORT_SYMBOL(schedule_work);

/**
 * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
 * @cpu: cpu to use
 * @dwork: job to be done
 * @delay: number of jiffies to wait
 *
 * After waiting for a given time this puts a job in the kernel-global
 * workqueue on the specified CPU.
 */
bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
			      unsigned long delay)
{
	return queue_delayed_work_on(cpu, system_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work_on);

/**
 * schedule_delayed_work - put work task in global workqueue after delay
 * @dwork: job to be done
 * @delay: number of jiffies to wait or 0 for immediate execution
 *
 * After waiting for a given time this puts a job in the kernel-global
 * workqueue.
 */
bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay)
{
	return queue_delayed_work(system_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work);

/**
 * schedule_on_each_cpu - execute a function synchronously on each online CPU
 * @func: the function to call
 *
 * schedule_on_each_cpu() executes @func on each online CPU using the
 * system workqueue and blocks until all CPUs have completed.
 * schedule_on_each_cpu() is very slow.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int schedule_on_each_cpu(work_func_t func)
{
	int cpu;
	struct work_struct __percpu *works;

	works = alloc_percpu(struct work_struct);
	if (!works)
		return -ENOMEM;

	get_online_cpus();

	for_each_online_cpu(cpu) {
		struct work_struct *work = per_cpu_ptr(works, cpu);

		INIT_WORK(work, func);
		schedule_work_on(cpu, work);
	}

	for_each_online_cpu(cpu)
		flush_work(per_cpu_ptr(works, cpu));

	put_online_cpus();
	free_percpu(works);
	return 0;
}

/**
 * flush_scheduled_work - ensure that any scheduled work has run to completion.
 *
 * Forces execution of the kernel-global workqueue and blocks until its
 * completion.
 *
 * Think twice before calling this function!  It's very easy to get into
 * trouble if you don't take great care.  Either of the following situations
 * will lead to deadlock:
 *
 *	One of the work items currently on the workqueue needs to acquire
 *	a lock held by your code or its caller.
 *
 *	Your code is running in the context of a work routine.
 *
 * They will be detected by lockdep when they occur, but the first might not
 * occur very often.  It depends on what work items are on the workqueue and
 * what locks they need, which you have no control over.
 *
 * In most situations flushing the entire workqueue is overkill; you merely
 * need to know that a particular work item isn't queued and isn't running.
 * In such cases you should use cancel_delayed_work_sync() or
 * cancel_work_sync() instead.
 */
void flush_scheduled_work(void)
{
	flush_workqueue(system_wq);
}
EXPORT_SYMBOL(flush_scheduled_work);

/**
 * execute_in_process_context - reliably execute the routine with user context
 * @fn:		the function to execute
 * @ew:		guaranteed storage for the execute work structure (must
 *		be available when the work executes)
 *
 * Executes the function immediately if process context is available,
 * otherwise schedules the function for delayed execution.
 *
 * Returns:	0 - function was executed
 *		1 - function was scheduled for execution
 */
int execute_in_process_context(work_func_t fn, struct execute_work *ew)
{
	if (!in_interrupt()) {
		fn(&ew->work);
		return 0;
	}

	INIT_WORK(&ew->work, fn);
	schedule_work(&ew->work);

	return 1;
}
EXPORT_SYMBOL_GPL(execute_in_process_context);

int keventd_up(void)
{
	return system_wq != NULL;
}

static int alloc_pwqs(struct workqueue_struct *wq)
{
	/*
	 * pwqs are forced aligned according to WORK_STRUCT_FLAG_BITS.
	 * Make sure that the alignment isn't lower than that of
	 * unsigned long long.
	 */
	const size_t size = sizeof(struct pool_workqueue);
	const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS,
				   __alignof__(unsigned long long));

	if (!(wq->flags & WQ_UNBOUND))
		wq->pool_wq.pcpu = __alloc_percpu(size, align);
	else {
		void *ptr;

		/*
		 * Allocate enough room to align pwq and put an extra
		 * pointer at the end pointing back to the originally
		 * allocated pointer which will be used for free.
		 */
		ptr = kzalloc(size + align + sizeof(void *), GFP_KERNEL);
		if (ptr) {
			wq->pool_wq.single = PTR_ALIGN(ptr, align);
			*(void **)(wq->pool_wq.single + 1) = ptr;
		}
	}

	/* just in case, make sure it's actually aligned */
	BUG_ON(!IS_ALIGNED(wq->pool_wq.v, align));
	return wq->pool_wq.v ? 0 : -ENOMEM;
}

static void free_pwqs(struct workqueue_struct *wq)
{
	if (!(wq->flags & WQ_UNBOUND))
		free_percpu(wq->pool_wq.pcpu);
	else if (wq->pool_wq.single) {
		/* the pointer to free is stored right after the pwq */
		kfree(*(void **)(wq->pool_wq.single + 1));
	}
}

static int wq_clamp_max_active(int max_active, unsigned int flags,
			       const char *name)
{
	int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE;

	if (max_active < 1 || max_active > lim)
		pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n",
			max_active, name, 1, lim);

	return clamp_val(max_active, 1, lim);
}

struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
					       unsigned int flags,
					       int max_active,
					       struct lock_class_key *key,
					       const char *lock_name, ...)
{
	va_list args, args1;
	struct workqueue_struct *wq;
	unsigned int cpu;
	size_t namelen;

	/* determine namelen, allocate wq and format name */
	va_start(args, lock_name);
	va_copy(args1, args);
	namelen = vsnprintf(NULL, 0, fmt, args) + 1;

	wq = kzalloc(sizeof(*wq) + namelen, GFP_KERNEL);
	if (!wq)
		goto err;

	vsnprintf(wq->name, namelen, fmt, args1);
	va_end(args);
	va_end(args1);

	/*
	 * Workqueues which may be used during memory reclaim should
	 * have a rescuer to guarantee forward progress.
	 */
	if (flags & WQ_MEM_RECLAIM)
		flags |= WQ_RESCUER;

	max_active = max_active ?: WQ_DFL_ACTIVE;
	max_active = wq_clamp_max_active(max_active, flags, wq->name);

	/* init wq */
	wq->flags = flags;
	wq->saved_max_active = max_active;
	mutex_init(&wq->flush_mutex);
	atomic_set(&wq->nr_pwqs_to_flush, 0);
	INIT_LIST_HEAD(&wq->flusher_queue);
	INIT_LIST_HEAD(&wq->flusher_overflow);

	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
	INIT_LIST_HEAD(&wq->list);

	if (alloc_pwqs(wq) < 0)
		goto err;

	for_each_pwq_cpu(cpu, wq) {
		struct pool_workqueue *pwq = get_pwq(cpu, wq);

		BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK);
		pwq->pool = get_std_worker_pool(cpu, flags & WQ_HIGHPRI);
		pwq->wq = wq;
		pwq->flush_color = -1;
		pwq->max_active = max_active;
		INIT_LIST_HEAD(&pwq->delayed_works);
	}

	if (flags & WQ_RESCUER) {
		struct worker *rescuer;

		if (!alloc_mayday_mask(&wq->mayday_mask, GFP_KERNEL))
			goto err;

		wq->rescuer = rescuer = alloc_worker();
		if (!rescuer)
			goto err;

		rescuer->rescue_wq = wq;
		rescuer->task = kthread_create(rescuer_thread, rescuer, "%s",
					       wq->name);
		if (IS_ERR(rescuer->task))
			goto err;

		rescuer->task->flags |= PF_THREAD_BOUND;
		wake_up_process(rescuer->task);
	}

	/*
	 * workqueue_lock protects global freeze state and workqueues
	 * list.  Grab it, set max_active accordingly and add the new
	 * workqueue to workqueues list.
	 */
	spin_lock(&workqueue_lock);

	if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
		for_each_pwq_cpu(cpu, wq)
			get_pwq(cpu, wq)->max_active = 0;

	list_add(&wq->list, &workqueues);

	spin_unlock(&workqueue_lock);

	return wq;
err:
	if (wq) {
		free_pwqs(wq);
		free_mayday_mask(wq->mayday_mask);
		kfree(wq->rescuer);
		kfree(wq);
	}
	return NULL;
}
EXPORT_SYMBOL_GPL(__alloc_workqueue_key);

/**
 * destroy_workqueue - safely terminate a workqueue
 * @wq: target workqueue
 *
 * Safely destroy a workqueue. All work currently pending will be done first.
 */
void destroy_workqueue(struct workqueue_struct *wq)
{
	unsigned int cpu;

	/* drain it before proceeding with destruction */
	drain_workqueue(wq);

	/*
	 * wq list is used to freeze wq, remove from list after
	 * flushing is complete in case freeze races us.
	 */
	spin_lock(&workqueue_lock);
	list_del(&wq->list);
	spin_unlock(&workqueue_lock);

	/* sanity check */
	for_each_pwq_cpu(cpu, wq) {
		struct pool_workqueue *pwq = get_pwq(cpu, wq);
		int i;

		for (i = 0; i < WORK_NR_COLORS; i++)
			BUG_ON(pwq->nr_in_flight[i]);
		BUG_ON(pwq->nr_active);
		BUG_ON(!list_empty(&pwq->delayed_works));
	}

	if (wq->flags & WQ_RESCUER) {
		kthread_stop(wq->rescuer->task);
		free_mayday_mask(wq->mayday_mask);
		kfree(wq->rescuer);
	}

	free_pwqs(wq);
	kfree(wq);
}
EXPORT_SYMBOL_GPL(destroy_workqueue);

/**
 * pwq_set_max_active - adjust max_active of a pwq
 * @pwq: target pool_workqueue
 * @max_active: new max_active value.
 *
 * Set @pwq->max_active to @max_active and activate delayed works if
 * increased.
 *
 * CONTEXT:
 * spin_lock_irq(pool->lock).
 */
static void pwq_set_max_active(struct pool_workqueue *pwq, int max_active)
{
	pwq->max_active = max_active;

	while (!list_empty(&pwq->delayed_works) &&
	       pwq->nr_active < pwq->max_active)
		pwq_activate_first_delayed(pwq);
}

/**
 * workqueue_set_max_active - adjust max_active of a workqueue
 * @wq: target workqueue
 * @max_active: new max_active value.
 *
 * Set max_active of @wq to @max_active.
 *
 * CONTEXT:
 * Don't call from IRQ context.
 */
void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
{
	unsigned int cpu;

	max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);

	spin_lock(&workqueue_lock);

	wq->saved_max_active = max_active;

	for_each_pwq_cpu(cpu, wq) {
		struct pool_workqueue *pwq = get_pwq(cpu, wq);
		struct worker_pool *pool = pwq->pool;

		spin_lock_irq(&pool->lock);

		if (!(wq->flags & WQ_FREEZABLE) ||
		    !(pool->flags & POOL_FREEZING))
			pwq_set_max_active(pwq, max_active);

		spin_unlock_irq(&pool->lock);
	}

	spin_unlock(&workqueue_lock);
}
EXPORT_SYMBOL_GPL(workqueue_set_max_active);

/**
 * workqueue_congested - test whether a workqueue is congested
 * @cpu: CPU in question
 * @wq: target workqueue
 *
 * Test whether @wq's cpu workqueue for @cpu is congested.  There is
 * no synchronization around this function and the test result is
 * unreliable and only useful as advisory hints or for debugging.
 *
 * RETURNS:
 * %true if congested, %false otherwise.
 */
bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq)
{
	struct pool_workqueue *pwq = get_pwq(cpu, wq);

	return !list_empty(&pwq->delayed_works);
}
EXPORT_SYMBOL_GPL(workqueue_congested);

/**
 * work_busy - test whether a work is currently pending or running
 * @work: the work to be tested
 *
 * Test whether @work is currently pending or running.  There is no
 * synchronization around this function and the test result is
 * unreliable and only useful as advisory hints or for debugging.
 *
 * RETURNS:
 * OR'd bitmask of WORK_BUSY_* bits.
 */
unsigned int work_busy(struct work_struct *work)
{
	struct worker_pool *pool = get_work_pool(work);
	unsigned long flags;
	unsigned int ret = 0;

	if (work_pending(work))
		ret |= WORK_BUSY_PENDING;

	if (pool) {
		spin_lock_irqsave(&pool->lock, flags);
		if (find_worker_executing_work(pool, work))
			ret |= WORK_BUSY_RUNNING;
		spin_unlock_irqrestore(&pool->lock, flags);
	}

	return ret;
}
EXPORT_SYMBOL_GPL(work_busy);

/*
 * CPU hotplug.
 *
 * There are two challenges in supporting CPU hotplug.  Firstly, there
 * are a lot of assumptions on strong associations among work, pwq and
 * pool which make migrating pending and scheduled works very
 * difficult to implement without impacting hot paths.  Secondly,
 * worker pools serve mix of short, long and very long running works making
 * blocked draining impractical.
 *
 * This is solved by allowing the pools to be disassociated from the CPU
 * running as an unbound one and allowing it to be reattached later if the
 * cpu comes back online.
 */

static void wq_unbind_fn(struct work_struct *work)
{
	int cpu = smp_processor_id();
	struct worker_pool *pool;
	struct worker *worker;
	int i;

	for_each_std_worker_pool(pool, cpu) {
		BUG_ON(cpu != smp_processor_id());

		mutex_lock(&pool->assoc_mutex);
		spin_lock_irq(&pool->lock);

		/*
		 * We've claimed all manager positions.  Make all workers
		 * unbound and set DISASSOCIATED.  Before this, all workers
		 * except for the ones which are still executing works from
		 * before the last CPU down must be on the cpu.  After
		 * this, they may become diasporas.
		 */
		list_for_each_entry(worker, &pool->idle_list, entry)
			worker->flags |= WORKER_UNBOUND;

		for_each_busy_worker(worker, i, pool)
			worker->flags |= WORKER_UNBOUND;

		pool->flags |= POOL_DISASSOCIATED;

		spin_unlock_irq(&pool->lock);
		mutex_unlock(&pool->assoc_mutex);

		/*
		 * Call schedule() so that we cross rq->lock and thus can
		 * guarantee sched callbacks see the %WORKER_UNBOUND flag.
		 * This is necessary as scheduler callbacks may be invoked
		 * from other cpus.
		 */
		schedule();

		/*
		 * Sched callbacks are disabled now.  Zap nr_running.
		 * After this, nr_running stays zero and need_more_worker()
		 * and keep_working() are always true as long as the
		 * worklist is not empty.  This pool now behaves as an
		 * unbound (in terms of concurrency management) pool which
		 * are served by workers tied to the pool.
		 */
		atomic_set(&pool->nr_running, 0);

		/*
		 * With concurrency management just turned off, a busy
		 * worker blocking could lead to lengthy stalls.  Kick off
		 * unbound chain execution of currently pending work items.
		 */
		spin_lock_irq(&pool->lock);
		wake_up_worker(pool);
		spin_unlock_irq(&pool->lock);
	}
}

/*
 * Workqueues should be brought up before normal priority CPU notifiers.
 * This will be registered high priority CPU notifier.
 */
static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb,
					       unsigned long action,
					       void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;
	struct worker_pool *pool;

	switch (action & ~CPU_TASKS_FROZEN) {
	case CPU_UP_PREPARE:
		for_each_std_worker_pool(pool, cpu) {
			struct worker *worker;

			if (pool->nr_workers)
				continue;

			worker = create_worker(pool);
			if (!worker)
				return NOTIFY_BAD;

			spin_lock_irq(&pool->lock);
			start_worker(worker);
			spin_unlock_irq(&pool->lock);
		}
		break;

	case CPU_DOWN_FAILED:
	case CPU_ONLINE:
		for_each_std_worker_pool(pool, cpu) {
			mutex_lock(&pool->assoc_mutex);
			spin_lock_irq(&pool->lock);

			pool->flags &= ~POOL_DISASSOCIATED;
			rebind_workers(pool);

			spin_unlock_irq(&pool->lock);
			mutex_unlock(&pool->assoc_mutex);
		}
		break;
	}
	return NOTIFY_OK;
}

/*
 * Workqueues should be brought down after normal priority CPU notifiers.
 * This will be registered as low priority CPU notifier.
 */
static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb,
						 unsigned long action,
						 void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;
	struct work_struct unbind_work;

	switch (action & ~CPU_TASKS_FROZEN) {
	case CPU_DOWN_PREPARE:
		/* unbinding should happen on the local CPU */
		INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn);
		queue_work_on(cpu, system_highpri_wq, &unbind_work);
		flush_work(&unbind_work);
		break;
	}
	return NOTIFY_OK;
}

#ifdef CONFIG_SMP

struct work_for_cpu {
	struct work_struct work;
	long (*fn)(void *);
	void *arg;
	long ret;
};

static void work_for_cpu_fn(struct work_struct *work)
{
	struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work);

	wfc->ret = wfc->fn(wfc->arg);
}

/**
 * work_on_cpu - run a function in user context on a particular cpu
 * @cpu: the cpu to run on
 * @fn: the function to run
 * @arg: the function arg
 *
 * This will return the value @fn returns.
 * It is up to the caller to ensure that the cpu doesn't go offline.
 * The caller must not hold any locks which would prevent @fn from completing.
 */
long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
{
	struct work_for_cpu wfc = { .fn = fn, .arg = arg };

	INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
	schedule_work_on(cpu, &wfc.work);
	flush_work(&wfc.work);
	return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);
#endif /* CONFIG_SMP */

#ifdef CONFIG_FREEZER

/**
 * freeze_workqueues_begin - begin freezing workqueues
 *
 * Start freezing workqueues.  After this function returns, all freezable
 * workqueues will queue new works to their frozen_works list instead of
 * pool->worklist.
 *
 * CONTEXT:
 * Grabs and releases workqueue_lock and pool->lock's.
 */
void freeze_workqueues_begin(void)
{
	unsigned int cpu;

	spin_lock(&workqueue_lock);

	BUG_ON(workqueue_freezing);
	workqueue_freezing = true;

	for_each_wq_cpu(cpu) {
		struct worker_pool *pool;
		struct workqueue_struct *wq;

		for_each_std_worker_pool(pool, cpu) {
			spin_lock_irq(&pool->lock);

			WARN_ON_ONCE(pool->flags & POOL_FREEZING);
			pool->flags |= POOL_FREEZING;

			list_for_each_entry(wq, &workqueues, list) {
				struct pool_workqueue *pwq = get_pwq(cpu, wq);

				if (pwq && pwq->pool == pool &&
				    (wq->flags & WQ_FREEZABLE))
					pwq->max_active = 0;
			}

			spin_unlock_irq(&pool->lock);
		}
	}

	spin_unlock(&workqueue_lock);
}

/**
 * freeze_workqueues_busy - are freezable workqueues still busy?
 *
 * Check whether freezing is complete.  This function must be called
 * between freeze_workqueues_begin() and thaw_workqueues().
 *
 * CONTEXT:
 * Grabs and releases workqueue_lock.
 *
 * RETURNS:
 * %true if some freezable workqueues are still busy.  %false if freezing
 * is complete.
 */
bool freeze_workqueues_busy(void)
{
	unsigned int cpu;
	bool busy = false;

	spin_lock(&workqueue_lock);

	BUG_ON(!workqueue_freezing);

	for_each_wq_cpu(cpu) {
		struct workqueue_struct *wq;
		/*
		 * nr_active is monotonically decreasing.  It's safe
		 * to peek without lock.
		 */
		list_for_each_entry(wq, &workqueues, list) {
			struct pool_workqueue *pwq = get_pwq(cpu, wq);

			if (!pwq || !(wq->flags & WQ_FREEZABLE))
				continue;

			BUG_ON(pwq->nr_active < 0);
			if (pwq->nr_active) {
				busy = true;
				goto out_unlock;
			}
		}
	}
out_unlock:
	spin_unlock(&workqueue_lock);
	return busy;
}

/**
 * thaw_workqueues - thaw workqueues
 *
 * Thaw workqueues.  Normal queueing is restored and all collected
 * frozen works are transferred to their respective pool worklists.
 *
 * CONTEXT:
 * Grabs and releases workqueue_lock and pool->lock's.
 */
void thaw_workqueues(void)
{
	unsigned int cpu;

	spin_lock(&workqueue_lock);

	if (!workqueue_freezing)
		goto out_unlock;

	for_each_wq_cpu(cpu) {
		struct worker_pool *pool;
		struct workqueue_struct *wq;

		for_each_std_worker_pool(pool, cpu) {
			spin_lock_irq(&pool->lock);

			WARN_ON_ONCE(!(pool->flags & POOL_FREEZING));
			pool->flags &= ~POOL_FREEZING;

			list_for_each_entry(wq, &workqueues, list) {
				struct pool_workqueue *pwq = get_pwq(cpu, wq);

				if (!pwq || pwq->pool != pool ||
				    !(wq->flags & WQ_FREEZABLE))
					continue;

				/* restore max_active and repopulate worklist */
				pwq_set_max_active(pwq, wq->saved_max_active);
			}

			wake_up_worker(pool);

			spin_unlock_irq(&pool->lock);
		}
	}

	workqueue_freezing = false;
out_unlock:
	spin_unlock(&workqueue_lock);
}
#endif /* CONFIG_FREEZER */

static int __init init_workqueues(void)
{
	unsigned int cpu;

	/* make sure we have enough bits for OFFQ pool ID */
	BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) <
		     WORK_CPU_END * NR_STD_WORKER_POOLS);

	cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP);
	hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN);

	/* initialize CPU pools */
	for_each_wq_cpu(cpu) {
		struct worker_pool *pool;

		for_each_std_worker_pool(pool, cpu) {
			spin_lock_init(&pool->lock);
			pool->cpu = cpu;
			pool->flags |= POOL_DISASSOCIATED;
			INIT_LIST_HEAD(&pool->worklist);
			INIT_LIST_HEAD(&pool->idle_list);
			hash_init(pool->busy_hash);

			init_timer_deferrable(&pool->idle_timer);
			pool->idle_timer.function = idle_worker_timeout;
			pool->idle_timer.data = (unsigned long)pool;

			setup_timer(&pool->mayday_timer, pool_mayday_timeout,
				    (unsigned long)pool);

			mutex_init(&pool->assoc_mutex);
			ida_init(&pool->worker_ida);

			/* alloc pool ID */
			BUG_ON(worker_pool_assign_id(pool));
		}
	}

	/* create the initial worker */
	for_each_online_wq_cpu(cpu) {
		struct worker_pool *pool;

		for_each_std_worker_pool(pool, cpu) {
			struct worker *worker;

			if (cpu != WORK_CPU_UNBOUND)
				pool->flags &= ~POOL_DISASSOCIATED;

			worker = create_worker(pool);
			BUG_ON(!worker);
			spin_lock_irq(&pool->lock);
			start_worker(worker);
			spin_unlock_irq(&pool->lock);
		}
	}

	system_wq = alloc_workqueue("events", 0, 0);
	system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0);
	system_long_wq = alloc_workqueue("events_long", 0, 0);
	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
					    WQ_UNBOUND_MAX_ACTIVE);
	system_freezable_wq = alloc_workqueue("events_freezable",
					      WQ_FREEZABLE, 0);
	BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
	       !system_unbound_wq || !system_freezable_wq);
	return 0;
}
early_initcall(init_workqueues);