Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Scheduler internal types and methods: */ #include <linux/sched.h> #include <linux/sched/autogroup.h> #include <linux/sched/clock.h> #include <linux/sched/coredump.h> #include <linux/sched/cpufreq.h> #include <linux/sched/cputime.h> #include <linux/sched/deadline.h> #include <linux/sched/debug.h> #include <linux/sched/hotplug.h> #include <linux/sched/idle.h> #include <linux/sched/init.h> #include <linux/sched/isolation.h> #include <linux/sched/jobctl.h> #include <linux/sched/loadavg.h> #include <linux/sched/mm.h> #include <linux/sched/nohz.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/prio.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/sched/smt.h> #include <linux/sched/stat.h> #include <linux/sched/sysctl.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/topology.h> #include <linux/sched/user.h> #include <linux/sched/wake_q.h> #include <linux/sched/xacct.h> #include <uapi/linux/sched/types.h> #include <linux/binfmts.h> #include <linux/blkdev.h> #include <linux/compat.h> #include <linux/context_tracking.h> #include <linux/cpufreq.h> #include <linux/cpuidle.h> #include <linux/cpuset.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/delayacct.h> #include <linux/energy_model.h> #include <linux/init_task.h> #include <linux/kprobes.h> #include <linux/kthread.h> #include <linux/membarrier.h> #include <linux/migrate.h> #include <linux/mmu_context.h> #include <linux/nmi.h> #include <linux/proc_fs.h> #include <linux/prefetch.h> #include <linux/profile.h> #include <linux/psi.h> #include <linux/rcupdate_wait.h> #include <linux/security.h> #include <linux/stop_machine.h> #include <linux/suspend.h> #include <linux/swait.h> #include <linux/syscalls.h> #include <linux/task_work.h> #include <linux/tsacct_kern.h> #include <asm/tlb.h> #ifdef CONFIG_PARAVIRT # include <asm/paravirt.h> #endif #include "cpupri.h" #include "cpudeadline.h" #ifdef CONFIG_SCHED_DEBUG # define SCHED_WARN_ON(x) WARN_ONCE(x, #x) #else # define SCHED_WARN_ON(x) ({ (void)(x), 0; }) #endif struct rq; struct cpuidle_state; /* task_struct::on_rq states: */ #define TASK_ON_RQ_QUEUED 1 #define TASK_ON_RQ_MIGRATING 2 extern __read_mostly int scheduler_running; extern unsigned long calc_load_update; extern atomic_long_t calc_load_tasks; extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq, long adjust); /* * Helpers for converting nanosecond timing to jiffy resolution */ #define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) /* * Increase resolution of nice-level calculations for 64-bit architectures. * The extra resolution improves shares distribution and load balancing of * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup * hierarchies, especially on larger systems. This is not a user-visible change * and does not change the user-interface for setting shares/weights. * * We increase resolution only if we have enough bits to allow this increased * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit * are pretty high and the returns do not justify the increased costs. * * Really only required when CONFIG_FAIR_GROUP_SCHED=y is also set, but to * increase coverage and consistency always enable it on 64-bit platforms. */ #ifdef CONFIG_64BIT # define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT) # define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT) # define scale_load_down(w) \ ({ \ unsigned long __w = (w); \ if (__w) \ __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \ __w; \ }) #else # define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT) # define scale_load(w) (w) # define scale_load_down(w) (w) #endif /* * Task weight (visible to users) and its load (invisible to users) have * independent resolution, but they should be well calibrated. We use * scale_load() and scale_load_down(w) to convert between them. The * following must be true: * * scale_load(sched_prio_to_weight[USER_PRIO(NICE_TO_PRIO(0))]) == NICE_0_LOAD * */ #define NICE_0_LOAD (1L << NICE_0_LOAD_SHIFT) /* * Single value that decides SCHED_DEADLINE internal math precision. * 10 -> just above 1us * 9 -> just above 0.5us */ #define DL_SCALE 10 /* * Single value that denotes runtime == period, ie unlimited time. */ #define RUNTIME_INF ((u64)~0ULL) static inline int idle_policy(int policy) { return policy == SCHED_IDLE; } static inline int fair_policy(int policy) { return policy == SCHED_NORMAL || policy == SCHED_BATCH; } static inline int rt_policy(int policy) { return policy == SCHED_FIFO || policy == SCHED_RR; } static inline int dl_policy(int policy) { return policy == SCHED_DEADLINE; } static inline bool valid_policy(int policy) { return idle_policy(policy) || fair_policy(policy) || rt_policy(policy) || dl_policy(policy); } static inline int task_has_idle_policy(struct task_struct *p) { return idle_policy(p->policy); } static inline int task_has_rt_policy(struct task_struct *p) { return rt_policy(p->policy); } static inline int task_has_dl_policy(struct task_struct *p) { return dl_policy(p->policy); } #define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT) /* * !! For sched_setattr_nocheck() (kernel) only !! * * This is actually gross. :( * * It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE * tasks, but still be able to sleep. We need this on platforms that cannot * atomically change clock frequency. Remove once fast switching will be * available on such platforms. * * SUGOV stands for SchedUtil GOVernor. */ #define SCHED_FLAG_SUGOV 0x10000000 #define SCHED_DL_FLAGS (SCHED_FLAG_RECLAIM | SCHED_FLAG_DL_OVERRUN | SCHED_FLAG_SUGOV) static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se) { #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL return unlikely(dl_se->flags & SCHED_FLAG_SUGOV); #else return false; #endif } /* * Tells if entity @a should preempt entity @b. */ static inline bool dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b) { return dl_entity_is_special(a) || dl_time_before(a->deadline, b->deadline); } /* * This is the priority-queue data structure of the RT scheduling class: */ struct rt_prio_array { DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */ struct list_head queue[MAX_RT_PRIO]; }; struct rt_bandwidth { /* nests inside the rq lock: */ raw_spinlock_t rt_runtime_lock; ktime_t rt_period; u64 rt_runtime; struct hrtimer rt_period_timer; unsigned int rt_period_active; }; void __dl_clear_params(struct task_struct *p); struct dl_bandwidth { raw_spinlock_t dl_runtime_lock; u64 dl_runtime; u64 dl_period; }; static inline int dl_bandwidth_enabled(void) { return sysctl_sched_rt_runtime >= 0; } /* * To keep the bandwidth of -deadline tasks under control * we need some place where: * - store the maximum -deadline bandwidth of each cpu; * - cache the fraction of bandwidth that is currently allocated in * each root domain; * * This is all done in the data structure below. It is similar to the * one used for RT-throttling (rt_bandwidth), with the main difference * that, since here we are only interested in admission control, we * do not decrease any runtime while the group "executes", neither we * need a timer to replenish it. * * With respect to SMP, bandwidth is given on a per root domain basis, * meaning that: * - bw (< 100%) is the deadline bandwidth of each CPU; * - total_bw is the currently allocated bandwidth in each root domain; */ struct dl_bw { raw_spinlock_t lock; u64 bw; u64 total_bw; }; static inline void __dl_update(struct dl_bw *dl_b, s64 bw); static inline void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus) { dl_b->total_bw -= tsk_bw; __dl_update(dl_b, (s32)tsk_bw / cpus); } static inline void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus) { dl_b->total_bw += tsk_bw; __dl_update(dl_b, -((s32)tsk_bw / cpus)); } static inline bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw) { return dl_b->bw != -1 && dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw; } extern void dl_change_utilization(struct task_struct *p, u64 new_bw); extern void init_dl_bw(struct dl_bw *dl_b); extern int sched_dl_global_validate(void); extern void sched_dl_do_global(void); extern int sched_dl_overflow(struct task_struct *p, int policy, const struct sched_attr *attr); extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr); extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr); extern bool __checkparam_dl(const struct sched_attr *attr); extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr); extern int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed); extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED #include <linux/cgroup.h> #include <linux/psi.h> struct cfs_rq; struct rt_rq; extern struct list_head task_groups; struct cfs_bandwidth { #ifdef CONFIG_CFS_BANDWIDTH raw_spinlock_t lock; ktime_t period; u64 quota; u64 runtime; s64 hierarchical_quota; u8 idle; u8 period_active; u8 distribute_running; u8 slack_started; struct hrtimer period_timer; struct hrtimer slack_timer; struct list_head throttled_cfs_rq; /* Statistics: */ int nr_periods; int nr_throttled; u64 throttled_time; #endif }; /* Task group related information */ struct task_group { struct cgroup_subsys_state css; #ifdef CONFIG_FAIR_GROUP_SCHED /* schedulable entities of this group on each CPU */ struct sched_entity **se; /* runqueue "owned" by this group on each CPU */ struct cfs_rq **cfs_rq; unsigned long shares; #ifdef CONFIG_SMP /* * load_avg can be heavily contended at clock tick time, so put * it in its own cacheline separated from the fields above which * will also be accessed at each tick. */ atomic_long_t load_avg ____cacheline_aligned; #endif #endif #ifdef CONFIG_RT_GROUP_SCHED struct sched_rt_entity **rt_se; struct rt_rq **rt_rq; struct rt_bandwidth rt_bandwidth; #endif struct rcu_head rcu; struct list_head list; struct task_group *parent; struct list_head siblings; struct list_head children; #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup *autogroup; #endif struct cfs_bandwidth cfs_bandwidth; #ifdef CONFIG_UCLAMP_TASK_GROUP /* The two decimal precision [%] value requested from user-space */ unsigned int uclamp_pct[UCLAMP_CNT]; /* Clamp values requested for a task group */ struct uclamp_se uclamp_req[UCLAMP_CNT]; /* Effective clamp values used for a task group */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif }; #ifdef CONFIG_FAIR_GROUP_SCHED #define ROOT_TASK_GROUP_LOAD NICE_0_LOAD /* * A weight of 0 or 1 can cause arithmetics problems. * A weight of a cfs_rq is the sum of weights of which entities * are queued on this cfs_rq, so a weight of a entity should not be * too large, so as the shares value of a task group. * (The default weight is 1024 - so there's no practical * limitation from this.) */ #define MIN_SHARES (1UL << 1) #define MAX_SHARES (1UL << 18) #endif typedef int (*tg_visitor)(struct task_group *, void *); extern int walk_tg_tree_from(struct task_group *from, tg_visitor down, tg_visitor up, void *data); /* * Iterate the full tree, calling @down when first entering a node and @up when * leaving it for the final time. * * Caller must hold rcu_lock or sufficient equivalent. */ static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) { return walk_tg_tree_from(&root_task_group, down, up, data); } extern int tg_nop(struct task_group *tg, void *data); extern void free_fair_sched_group(struct task_group *tg); extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent); extern void online_fair_sched_group(struct task_group *tg); extern void unregister_fair_sched_group(struct task_group *tg); extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, struct sched_entity *se, int cpu, struct sched_entity *parent); extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b); extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b); extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b); extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq); extern void free_rt_sched_group(struct task_group *tg); extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent); extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int cpu, struct sched_rt_entity *parent); extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us); extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us); extern long sched_group_rt_runtime(struct task_group *tg); extern long sched_group_rt_period(struct task_group *tg); extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); extern struct task_group *sched_create_group(struct task_group *parent); extern void sched_online_group(struct task_group *tg, struct task_group *parent); extern void sched_destroy_group(struct task_group *tg); extern void sched_offline_group(struct task_group *tg); extern void sched_move_task(struct task_struct *tsk); #ifdef CONFIG_FAIR_GROUP_SCHED extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); #ifdef CONFIG_SMP extern void set_task_rq_fair(struct sched_entity *se, struct cfs_rq *prev, struct cfs_rq *next); #else /* !CONFIG_SMP */ static inline void set_task_rq_fair(struct sched_entity *se, struct cfs_rq *prev, struct cfs_rq *next) { } #endif /* CONFIG_SMP */ #endif /* CONFIG_FAIR_GROUP_SCHED */ #else /* CONFIG_CGROUP_SCHED */ struct cfs_bandwidth { }; #endif /* CONFIG_CGROUP_SCHED */ /* CFS-related fields in a runqueue */ struct cfs_rq { struct load_weight load; unsigned long runnable_weight; unsigned int nr_running; unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */ unsigned int idle_h_nr_running; /* SCHED_IDLE */ u64 exec_clock; u64 min_vruntime; #ifndef CONFIG_64BIT u64 min_vruntime_copy; #endif struct rb_root_cached tasks_timeline; /* * 'curr' points to currently running entity on this cfs_rq. * It is set to NULL otherwise (i.e when none are currently running). */ struct sched_entity *curr; struct sched_entity *next; struct sched_entity *last; struct sched_entity *skip; #ifdef CONFIG_SCHED_DEBUG unsigned int nr_spread_over; #endif #ifdef CONFIG_SMP /* * CFS load tracking */ struct sched_avg avg; #ifndef CONFIG_64BIT u64 load_last_update_time_copy; #endif struct { raw_spinlock_t lock ____cacheline_aligned; int nr; unsigned long load_avg; unsigned long util_avg; unsigned long runnable_sum; } removed; #ifdef CONFIG_FAIR_GROUP_SCHED unsigned long tg_load_avg_contrib; long propagate; long prop_runnable_sum; /* * h_load = weight * f(tg) * * Where f(tg) is the recursive weight fraction assigned to * this group. */ unsigned long h_load; u64 last_h_load_update; struct sched_entity *h_load_next; #endif /* CONFIG_FAIR_GROUP_SCHED */ #endif /* CONFIG_SMP */ #ifdef CONFIG_FAIR_GROUP_SCHED struct rq *rq; /* CPU runqueue to which this cfs_rq is attached */ /* * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in * a hierarchy). Non-leaf lrqs hold other higher schedulable entities * (like users, containers etc.) * * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a CPU. * This list is used during load balance. */ int on_list; struct list_head leaf_cfs_rq_list; struct task_group *tg; /* group that "owns" this runqueue */ #ifdef CONFIG_CFS_BANDWIDTH int runtime_enabled; s64 runtime_remaining; u64 throttled_clock; u64 throttled_clock_task; u64 throttled_clock_task_time; int throttled; int throttle_count; struct list_head throttled_list; #endif /* CONFIG_CFS_BANDWIDTH */ #endif /* CONFIG_FAIR_GROUP_SCHED */ }; static inline int rt_bandwidth_enabled(void) { return sysctl_sched_rt_runtime >= 0; } /* RT IPI pull logic requires IRQ_WORK */ #if defined(CONFIG_IRQ_WORK) && defined(CONFIG_SMP) # define HAVE_RT_PUSH_IPI #endif /* Real-Time classes' related field in a runqueue: */ struct rt_rq { struct rt_prio_array active; unsigned int rt_nr_running; unsigned int rr_nr_running; #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED struct { int curr; /* highest queued rt task prio */ #ifdef CONFIG_SMP int next; /* next highest */ #endif } highest_prio; #endif #ifdef CONFIG_SMP unsigned long rt_nr_migratory; unsigned long rt_nr_total; int overloaded; struct plist_head pushable_tasks; #endif /* CONFIG_SMP */ int rt_queued; int rt_throttled; u64 rt_time; u64 rt_runtime; /* Nests inside the rq lock: */ raw_spinlock_t rt_runtime_lock; #ifdef CONFIG_RT_GROUP_SCHED unsigned long rt_nr_boosted; struct rq *rq; struct task_group *tg; #endif }; static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq) { return rt_rq->rt_queued && rt_rq->rt_nr_running; } /* Deadline class' related fields in a runqueue */ struct dl_rq { /* runqueue is an rbtree, ordered by deadline */ struct rb_root_cached root; unsigned long dl_nr_running; #ifdef CONFIG_SMP /* * Deadline values of the currently executing and the * earliest ready task on this rq. Caching these facilitates * the decision whether or not a ready but not running task * should migrate somewhere else. */ struct { u64 curr; u64 next; } earliest_dl; unsigned long dl_nr_migratory; int overloaded; /* * Tasks on this rq that can be pushed away. They are kept in * an rb-tree, ordered by tasks' deadlines, with caching * of the leftmost (earliest deadline) element. */ struct rb_root_cached pushable_dl_tasks_root; #else struct dl_bw dl_bw; #endif /* * "Active utilization" for this runqueue: increased when a * task wakes up (becomes TASK_RUNNING) and decreased when a * task blocks */ u64 running_bw; /* * Utilization of the tasks "assigned" to this runqueue (including * the tasks that are in runqueue and the tasks that executed on this * CPU and blocked). Increased when a task moves to this runqueue, and * decreased when the task moves away (migrates, changes scheduling * policy, or terminates). * This is needed to compute the "inactive utilization" for the * runqueue (inactive utilization = this_bw - running_bw). */ u64 this_bw; u64 extra_bw; /* * Inverse of the fraction of CPU utilization that can be reclaimed * by the GRUB algorithm. */ u64 bw_ratio; }; #ifdef CONFIG_FAIR_GROUP_SCHED /* An entity is a task if it doesn't "own" a runqueue */ #define entity_is_task(se) (!se->my_q) #else #define entity_is_task(se) 1 #endif #ifdef CONFIG_SMP /* * XXX we want to get rid of these helpers and use the full load resolution. */ static inline long se_weight(struct sched_entity *se) { return scale_load_down(se->load.weight); } static inline long se_runnable(struct sched_entity *se) { return scale_load_down(se->runnable_weight); } static inline bool sched_asym_prefer(int a, int b) { return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b); } struct perf_domain { struct em_perf_domain *em_pd; struct perf_domain *next; struct rcu_head rcu; }; /* Scheduling group status flags */ #define SG_OVERLOAD 0x1 /* More than one runnable task on a CPU. */ #define SG_OVERUTILIZED 0x2 /* One or more CPUs are over-utilized. */ /* * We add the notion of a root-domain which will be used to define per-domain * variables. Each exclusive cpuset essentially defines an island domain by * fully partitioning the member CPUs from any other cpuset. Whenever a new * exclusive cpuset is created, we also create and attach a new root-domain * object. * */ struct root_domain { atomic_t refcount; atomic_t rto_count; struct rcu_head rcu; cpumask_var_t span; cpumask_var_t online; /* * Indicate pullable load on at least one CPU, e.g: * - More than one runnable task * - Running task is misfit */ int overload; /* Indicate one or more cpus over-utilized (tipping point) */ int overutilized; /* * The bit corresponding to a CPU gets set here if such CPU has more * than one runnable -deadline task (as it is below for RT tasks). */ cpumask_var_t dlo_mask; atomic_t dlo_count; struct dl_bw dl_bw; struct cpudl cpudl; #ifdef HAVE_RT_PUSH_IPI /* * For IPI pull requests, loop across the rto_mask. */ struct irq_work rto_push_work; raw_spinlock_t rto_lock; /* These are only updated and read within rto_lock */ int rto_loop; int rto_cpu; /* These atomics are updated outside of a lock */ atomic_t rto_loop_next; atomic_t rto_loop_start; #endif /* * The "RT overload" flag: it gets set if a CPU has more than * one runnable RT task. */ cpumask_var_t rto_mask; struct cpupri cpupri; unsigned long max_cpu_capacity; /* * NULL-terminated list of performance domains intersecting with the * CPUs of the rd. Protected by RCU. */ struct perf_domain __rcu *pd; }; extern void init_defrootdomain(void); extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); extern void sched_get_rd(struct root_domain *rd); extern void sched_put_rd(struct root_domain *rd); #ifdef HAVE_RT_PUSH_IPI extern void rto_push_irq_work_func(struct irq_work *work); #endif #endif /* CONFIG_SMP */ #ifdef CONFIG_UCLAMP_TASK /* * struct uclamp_bucket - Utilization clamp bucket * @value: utilization clamp value for tasks on this clamp bucket * @tasks: number of RUNNABLE tasks on this clamp bucket * * Keep track of how many tasks are RUNNABLE for a given utilization * clamp value. */ struct uclamp_bucket { unsigned long value : bits_per(SCHED_CAPACITY_SCALE); unsigned long tasks : BITS_PER_LONG - bits_per(SCHED_CAPACITY_SCALE); }; /* * struct uclamp_rq - rq's utilization clamp * @value: currently active clamp values for a rq * @bucket: utilization clamp buckets affecting a rq * * Keep track of RUNNABLE tasks on a rq to aggregate their clamp values. * A clamp value is affecting a rq when there is at least one task RUNNABLE * (or actually running) with that value. * * There are up to UCLAMP_CNT possible different clamp values, currently there * are only two: minimum utilization and maximum utilization. * * All utilization clamping values are MAX aggregated, since: * - for util_min: we want to run the CPU at least at the max of the minimum * utilization required by its currently RUNNABLE tasks. * - for util_max: we want to allow the CPU to run up to the max of the * maximum utilization allowed by its currently RUNNABLE tasks. * * Since on each system we expect only a limited number of different * utilization clamp values (UCLAMP_BUCKETS), use a simple array to track * the metrics required to compute all the per-rq utilization clamp values. */ struct uclamp_rq { unsigned int value; struct uclamp_bucket bucket[UCLAMP_BUCKETS]; }; DECLARE_STATIC_KEY_FALSE(sched_uclamp_used); #endif /* CONFIG_UCLAMP_TASK */ /* * This is the main, per-CPU runqueue data structure. * * Locking rule: those places that want to lock multiple runqueues * (such as the load balancing or the thread migration code), lock * acquire operations must be ordered by ascending &runqueue. */ struct rq { /* runqueue lock: */ raw_spinlock_t lock; /* * nr_running and cpu_load should be in the same cacheline because * remote CPUs use both these fields when doing load calculation. */ unsigned int nr_running; #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; unsigned int numa_migrate_on; #endif #ifdef CONFIG_NO_HZ_COMMON #ifdef CONFIG_SMP unsigned long last_load_update_tick; unsigned long last_blocked_load_update_tick; unsigned int has_blocked_load; #endif /* CONFIG_SMP */ unsigned int nohz_tick_stopped; atomic_t nohz_flags; #endif /* CONFIG_NO_HZ_COMMON */ unsigned long nr_load_updates; u64 nr_switches; #ifdef CONFIG_UCLAMP_TASK /* Utilization clamp values based on CPU's RUNNABLE tasks */ struct uclamp_rq uclamp[UCLAMP_CNT] ____cacheline_aligned; unsigned int uclamp_flags; #define UCLAMP_FLAG_IDLE 0x01 #endif struct cfs_rq cfs; struct rt_rq rt; struct dl_rq dl; #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this CPU: */ struct list_head leaf_cfs_rq_list; struct list_head *tmp_alone_branch; #endif /* CONFIG_FAIR_GROUP_SCHED */ /* * This is part of a global counter where only the total sum * over all CPUs matters. A task can increase this counter on * one CPU and if it got migrated afterwards it may decrease * it on another CPU. Always updated under the runqueue lock: */ unsigned long nr_uninterruptible; struct task_struct *curr; struct task_struct *idle; struct task_struct *stop; unsigned long next_balance; struct mm_struct *prev_mm; unsigned int clock_update_flags; u64 clock; /* Ensure that all clocks are in the same cache line */ u64 clock_task ____cacheline_aligned; u64 clock_pelt; unsigned long lost_idle_time; atomic_t nr_iowait; #ifdef CONFIG_MEMBARRIER int membarrier_state; #endif #ifdef CONFIG_SMP struct root_domain *rd; struct sched_domain __rcu *sd; unsigned long cpu_capacity; unsigned long cpu_capacity_orig; struct callback_head *balance_callback; unsigned char idle_balance; unsigned long misfit_task_load; /* For active balancing */ int active_balance; int push_cpu; struct cpu_stop_work active_balance_work; /* CPU of this runqueue: */ int cpu; int online; struct list_head cfs_tasks; struct sched_avg avg_rt; struct sched_avg avg_dl; #ifdef CONFIG_HAVE_SCHED_AVG_IRQ struct sched_avg avg_irq; #endif u64 idle_stamp; u64 avg_idle; /* This is used to determine avg_idle's max value */ u64 max_idle_balance_cost; #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING u64 prev_irq_time; #endif #ifdef CONFIG_PARAVIRT u64 prev_steal_time; #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING u64 prev_steal_time_rq; #endif /* calc_load related fields */ unsigned long calc_load_update; long calc_load_active; #ifdef CONFIG_SCHED_HRTICK #ifdef CONFIG_SMP int hrtick_csd_pending; call_single_data_t hrtick_csd; #endif struct hrtimer hrtick_timer; ktime_t hrtick_time; #endif #ifdef CONFIG_SCHEDSTATS /* latency stats */ struct sched_info rq_sched_info; unsigned long long rq_cpu_time; /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ /* sys_sched_yield() stats */ unsigned int yld_count; /* schedule() stats */ unsigned int sched_count; unsigned int sched_goidle; /* try_to_wake_up() stats */ unsigned int ttwu_count; unsigned int ttwu_local; #endif #ifdef CONFIG_SMP struct llist_head wake_list; #endif #ifdef CONFIG_CPU_IDLE /* Must be inspected within a rcu lock section */ struct cpuidle_state *idle_state; #endif }; #ifdef CONFIG_FAIR_GROUP_SCHED /* CPU runqueue to which this cfs_rq is attached */ static inline struct rq *rq_of(struct cfs_rq *cfs_rq) { return cfs_rq->rq; } #else static inline struct rq *rq_of(struct cfs_rq *cfs_rq) { return container_of(cfs_rq, struct rq, cfs); } #endif static inline int cpu_of(struct rq *rq) { #ifdef CONFIG_SMP return rq->cpu; #else return 0; #endif } #ifdef CONFIG_SCHED_SMT extern void __update_idle_core(struct rq *rq); static inline void update_idle_core(struct rq *rq) { if (static_branch_unlikely(&sched_smt_present)) __update_idle_core(rq); } #else static inline void update_idle_core(struct rq *rq) { } #endif DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() this_cpu_ptr(&runqueues) #define task_rq(p) cpu_rq(task_cpu(p)) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() raw_cpu_ptr(&runqueues) extern void update_rq_clock(struct rq *rq); static inline u64 __rq_clock_broken(struct rq *rq) { return READ_ONCE(rq->clock); } /* * rq::clock_update_flags bits * * %RQCF_REQ_SKIP - will request skipping of clock update on the next * call to __schedule(). This is an optimisation to avoid * neighbouring rq clock updates. * * %RQCF_ACT_SKIP - is set from inside of __schedule() when skipping is * in effect and calls to update_rq_clock() are being ignored. * * %RQCF_UPDATED - is a debug flag that indicates whether a call has been * made to update_rq_clock() since the last time rq::lock was pinned. * * If inside of __schedule(), clock_update_flags will have been * shifted left (a left shift is a cheap operation for the fast path * to promote %RQCF_REQ_SKIP to %RQCF_ACT_SKIP), so you must use, * * if (rq-clock_update_flags >= RQCF_UPDATED) * * to check if %RQCF_UPADTED is set. It'll never be shifted more than * one position though, because the next rq_unpin_lock() will shift it * back. */ #define RQCF_REQ_SKIP 0x01 #define RQCF_ACT_SKIP 0x02 #define RQCF_UPDATED 0x04 static inline void assert_clock_updated(struct rq *rq) { /* * The only reason for not seeing a clock update since the * last rq_pin_lock() is if we're currently skipping updates. */ SCHED_WARN_ON(rq->clock_update_flags < RQCF_ACT_SKIP); } static inline u64 rq_clock(struct rq *rq) { lockdep_assert_held(&rq->lock); assert_clock_updated(rq); return rq->clock; } static inline u64 rq_clock_task(struct rq *rq) { lockdep_assert_held(&rq->lock); assert_clock_updated(rq); return rq->clock_task; } static inline void rq_clock_skip_update(struct rq *rq) { lockdep_assert_held(&rq->lock); rq->clock_update_flags |= RQCF_REQ_SKIP; } /* * See rt task throttling, which is the only time a skip * request is cancelled. */ static inline void rq_clock_cancel_skipupdate(struct rq *rq) { lockdep_assert_held(&rq->lock); rq->clock_update_flags &= ~RQCF_REQ_SKIP; } struct rq_flags { unsigned long flags; struct pin_cookie cookie; #ifdef CONFIG_SCHED_DEBUG /* * A copy of (rq::clock_update_flags & RQCF_UPDATED) for the * current pin context is stashed here in case it needs to be * restored in rq_repin_lock(). */ unsigned int clock_update_flags; #endif }; static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf) { rf->cookie = lockdep_pin_lock(&rq->lock); #ifdef CONFIG_SCHED_DEBUG rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP); rf->clock_update_flags = 0; #endif } static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf) { #ifdef CONFIG_SCHED_DEBUG if (rq->clock_update_flags > RQCF_ACT_SKIP) rf->clock_update_flags = RQCF_UPDATED; #endif lockdep_unpin_lock(&rq->lock, rf->cookie); } static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf) { lockdep_repin_lock(&rq->lock, rf->cookie); #ifdef CONFIG_SCHED_DEBUG /* * Restore the value we stashed in @rf for this pin context. */ rq->clock_update_flags |= rf->clock_update_flags; #endif } struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) __acquires(rq->lock); struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) __acquires(p->pi_lock) __acquires(rq->lock); static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) __releases(rq->lock) { rq_unpin_lock(rq, rf); raw_spin_unlock(&rq->lock); } static inline void task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) __releases(rq->lock) __releases(p->pi_lock) { rq_unpin_lock(rq, rf); raw_spin_unlock(&rq->lock); raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); } static inline void rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) __acquires(rq->lock) { raw_spin_lock_irqsave(&rq->lock, rf->flags); rq_pin_lock(rq, rf); } static inline void rq_lock_irq(struct rq *rq, struct rq_flags *rf) __acquires(rq->lock) { raw_spin_lock_irq(&rq->lock); rq_pin_lock(rq, rf); } static inline void rq_lock(struct rq *rq, struct rq_flags *rf) __acquires(rq->lock) { raw_spin_lock(&rq->lock); rq_pin_lock(rq, rf); } static inline void rq_relock(struct rq *rq, struct rq_flags *rf) __acquires(rq->lock) { raw_spin_lock(&rq->lock); rq_repin_lock(rq, rf); } static inline void rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) __releases(rq->lock) { rq_unpin_lock(rq, rf); raw_spin_unlock_irqrestore(&rq->lock, rf->flags); } static inline void rq_unlock_irq(struct rq *rq, struct rq_flags *rf) __releases(rq->lock) { rq_unpin_lock(rq, rf); raw_spin_unlock_irq(&rq->lock); } static inline void rq_unlock(struct rq *rq, struct rq_flags *rf) __releases(rq->lock) { rq_unpin_lock(rq, rf); raw_spin_unlock(&rq->lock); } static inline struct rq * this_rq_lock_irq(struct rq_flags *rf) __acquires(rq->lock) { struct rq *rq; local_irq_disable(); rq = this_rq(); rq_lock(rq, rf); return rq; } #ifdef CONFIG_NUMA enum numa_topology_type { NUMA_DIRECT, NUMA_GLUELESS_MESH, NUMA_BACKPLANE, }; extern enum numa_topology_type sched_numa_topology_type; extern int sched_max_numa_distance; extern bool find_numa_distance(int distance); extern void sched_init_numa(void); extern void sched_domains_numa_masks_set(unsigned int cpu); extern void sched_domains_numa_masks_clear(unsigned int cpu); extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu); #else static inline void sched_init_numa(void) { } static inline void sched_domains_numa_masks_set(unsigned int cpu) { } static inline void sched_domains_numa_masks_clear(unsigned int cpu) { } static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu) { return nr_cpu_ids; } #endif #ifdef CONFIG_NUMA_BALANCING /* The regions in numa_faults array from task_struct */ enum numa_faults_stats { NUMA_MEM = 0, NUMA_CPU, NUMA_MEMBUF, NUMA_CPUBUF }; extern void sched_setnuma(struct task_struct *p, int node); extern int migrate_task_to(struct task_struct *p, int cpu); extern int migrate_swap(struct task_struct *p, struct task_struct *t, int cpu, int scpu); extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p); #else static inline void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) { } #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_SMP static inline void queue_balance_callback(struct rq *rq, struct callback_head *head, void (*func)(struct rq *rq)) { lockdep_assert_held(&rq->lock); if (unlikely(head->next)) return; head->func = (void (*)(struct callback_head *))func; head->next = rq->balance_callback; rq->balance_callback = head; } extern void sched_ttwu_pending(void); #define rcu_dereference_check_sched_domain(p) \ rcu_dereference_check((p), \ lockdep_is_held(&sched_domains_mutex)) /* * The domain tree (rq->sd) is protected by RCU's quiescent state transition. * See destroy_sched_domains: call_rcu for details. * * The domain tree of any CPU may only be accessed from within * preempt-disabled sections. */ #define for_each_domain(cpu, __sd) \ for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \ __sd; __sd = __sd->parent) #define for_each_lower_domain(sd) for (; sd; sd = sd->child) /** * highest_flag_domain - Return highest sched_domain containing flag. * @cpu: The CPU whose highest level of sched domain is to * be returned. * @flag: The flag to check for the highest sched_domain * for the given CPU. * * Returns the highest sched_domain of a CPU which contains the given flag. */ static inline struct sched_domain *highest_flag_domain(int cpu, int flag) { struct sched_domain *sd, *hsd = NULL; for_each_domain(cpu, sd) { if (!(sd->flags & flag)) break; hsd = sd; } return hsd; } static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) { struct sched_domain *sd; for_each_domain(cpu, sd) { if (sd->flags & flag) break; } return sd; } DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc); DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa); DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity); extern struct static_key_false sched_asym_cpucapacity; struct sched_group_capacity { atomic_t ref; /* * CPU capacity of this group, SCHED_CAPACITY_SCALE being max capacity * for a single CPU. */ unsigned long capacity; unsigned long min_capacity; /* Min per-CPU capacity in group */ unsigned long max_capacity; /* Max per-CPU capacity in group */ unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ #ifdef CONFIG_SCHED_DEBUG int id; #endif unsigned long cpumask[0]; /* Balance mask */ }; struct sched_group { struct sched_group *next; /* Must be a circular list */ atomic_t ref; unsigned int group_weight; struct sched_group_capacity *sgc; int asym_prefer_cpu; /* CPU of highest priority in group */ /* * The CPUs this group covers. * * NOTE: this field is variable length. (Allocated dynamically * by attaching extra space to the end of the structure, * depending on how many CPUs the kernel has booted up with) */ unsigned long cpumask[0]; }; static inline struct cpumask *sched_group_span(struct sched_group *sg) { return to_cpumask(sg->cpumask); } /* * See build_balance_mask(). */ static inline struct cpumask *group_balance_mask(struct sched_group *sg) { return to_cpumask(sg->sgc->cpumask); } /** * group_first_cpu - Returns the first CPU in the cpumask of a sched_group. * @group: The group whose first CPU is to be returned. */ static inline unsigned int group_first_cpu(struct sched_group *group) { return cpumask_first(sched_group_span(group)); } extern int group_balance_cpu(struct sched_group *sg); #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) void register_sched_domain_sysctl(void); void dirty_sched_domain_sysctl(int cpu); void unregister_sched_domain_sysctl(void); #else static inline void register_sched_domain_sysctl(void) { } static inline void dirty_sched_domain_sysctl(int cpu) { } static inline void unregister_sched_domain_sysctl(void) { } #endif extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf); #else static inline void sched_ttwu_pending(void) { } static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; } #endif /* CONFIG_SMP */ #include "stats.h" #include "autogroup.h" #ifdef CONFIG_CGROUP_SCHED /* * Return the group to which this tasks belongs. * * We cannot use task_css() and friends because the cgroup subsystem * changes that value before the cgroup_subsys::attach() method is called, * therefore we cannot pin it and might observe the wrong value. * * The same is true for autogroup's p->signal->autogroup->tg, the autogroup * core changes this before calling sched_move_task(). * * Instead we use a 'copy' which is updated from sched_move_task() while * holding both task_struct::pi_lock and rq::lock. */ static inline struct task_group *task_group(struct task_struct *p) { return p->sched_task_group; } /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { #if defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED) struct task_group *tg = task_group(p); #endif #ifdef CONFIG_FAIR_GROUP_SCHED set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]); p->se.cfs_rq = tg->cfs_rq[cpu]; p->se.parent = tg->se[cpu]; #endif #ifdef CONFIG_RT_GROUP_SCHED p->rt.rt_rq = tg->rt_rq[cpu]; p->rt.parent = tg->rt_se[cpu]; #endif } #else /* CONFIG_CGROUP_SCHED */ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } static inline struct task_group *task_group(struct task_struct *p) { return NULL; } #endif /* CONFIG_CGROUP_SCHED */ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) { set_task_rq(p, cpu); #ifdef CONFIG_SMP /* * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be * successfully executed on another CPU. We must ensure that updates of * per-task data have been completed by this moment. */ smp_wmb(); #ifdef CONFIG_THREAD_INFO_IN_TASK WRITE_ONCE(p->cpu, cpu); #else WRITE_ONCE(task_thread_info(p)->cpu, cpu); #endif p->wake_cpu = cpu; #endif } /* * Tunables that become constants when CONFIG_SCHED_DEBUG is off: */ #ifdef CONFIG_SCHED_DEBUG # include <linux/static_key.h> # define const_debug __read_mostly #else # define const_debug const #endif #define SCHED_FEAT(name, enabled) \ __SCHED_FEAT_##name , enum { #include "features.h" __SCHED_FEAT_NR, }; #undef SCHED_FEAT #ifdef CONFIG_SCHED_DEBUG /* * To support run-time toggling of sched features, all the translation units * (but core.c) reference the sysctl_sched_features defined in core.c. */ extern const_debug unsigned int sysctl_sched_features; #ifdef CONFIG_JUMP_LABEL #define SCHED_FEAT(name, enabled) \ static __always_inline bool static_branch_##name(struct static_key *key) \ { \ return static_key_##enabled(key); \ } #include "features.h" #undef SCHED_FEAT extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x])) #else /* !CONFIG_JUMP_LABEL */ #define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) #endif /* CONFIG_JUMP_LABEL */ #else /* !SCHED_DEBUG */ /* * Each translation unit has its own copy of sysctl_sched_features to allow * constants propagation at compile time and compiler optimization based on * features default. */ #define SCHED_FEAT(name, enabled) \ (1UL << __SCHED_FEAT_##name) * enabled | static const_debug __maybe_unused unsigned int sysctl_sched_features = #include "features.h" 0; #undef SCHED_FEAT #define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) #endif /* SCHED_DEBUG */ extern struct static_key_false sched_numa_balancing; extern struct static_key_false sched_schedstats; static inline u64 global_rt_period(void) { return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; } static inline u64 global_rt_runtime(void) { if (sysctl_sched_rt_runtime < 0) return RUNTIME_INF; return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; } static inline int task_current(struct rq *rq, struct task_struct *p) { return rq->curr == p; } static inline int task_running(struct rq *rq, struct task_struct *p) { #ifdef CONFIG_SMP return p->on_cpu; #else return task_current(rq, p); #endif } static inline int task_on_rq_queued(struct task_struct *p) { return p->on_rq == TASK_ON_RQ_QUEUED; } static inline int task_on_rq_migrating(struct task_struct *p) { return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING; } /* * wake flags */ #define WF_SYNC 0x01 /* Waker goes to sleep after wakeup */ #define WF_FORK 0x02 /* Child wakeup after fork */ #define WF_MIGRATED 0x4 /* Internal use, task got migrated */ /* * To aid in avoiding the subversion of "niceness" due to uneven distribution * of tasks with abnormal "nice" values across CPUs the contribution that * each task makes to its run queue's load is weighted according to its * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a * scaled version of the new time slice allocation that they receive on time * slice expiry etc. */ #define WEIGHT_IDLEPRIO 3 #define WMULT_IDLEPRIO 1431655765 extern const int sched_prio_to_weight[40]; extern const u32 sched_prio_to_wmult[40]; /* * {de,en}queue flags: * * DEQUEUE_SLEEP - task is no longer runnable * ENQUEUE_WAKEUP - task just became runnable * * SAVE/RESTORE - an otherwise spurious dequeue/enqueue, done to ensure tasks * are in a known state which allows modification. Such pairs * should preserve as much state as possible. * * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location * in the runqueue. * * ENQUEUE_HEAD - place at front of runqueue (tail if not specified) * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline) * ENQUEUE_MIGRATED - the task was migrated during wakeup * */ #define DEQUEUE_SLEEP 0x01 #define DEQUEUE_SAVE 0x02 /* Matches ENQUEUE_RESTORE */ #define DEQUEUE_MOVE 0x04 /* Matches ENQUEUE_MOVE */ #define DEQUEUE_NOCLOCK 0x08 /* Matches ENQUEUE_NOCLOCK */ #define ENQUEUE_WAKEUP 0x01 #define ENQUEUE_RESTORE 0x02 #define ENQUEUE_MOVE 0x04 #define ENQUEUE_NOCLOCK 0x08 #define ENQUEUE_HEAD 0x10 #define ENQUEUE_REPLENISH 0x20 #ifdef CONFIG_SMP #define ENQUEUE_MIGRATED 0x40 #else #define ENQUEUE_MIGRATED 0x00 #endif #define RETRY_TASK ((void *)-1UL) struct sched_class { const struct sched_class *next; #ifdef CONFIG_UCLAMP_TASK int uclamp_enabled; #endif void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); void (*yield_task) (struct rq *rq); bool (*yield_to_task)(struct rq *rq, struct task_struct *p, bool preempt); void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags); /* * Both @prev and @rf are optional and may be NULL, in which case the * caller must already have invoked put_prev_task(rq, prev, rf). * * Otherwise it is the responsibility of the pick_next_task() to call * put_prev_task() on the @prev task or something equivalent, IFF it * returns a next task. * * In that case (@rf != NULL) it may return RETRY_TASK when it finds a * higher prio class has runnable tasks. */ struct task_struct * (*pick_next_task)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); void (*put_prev_task)(struct rq *rq, struct task_struct *p); void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first); #ifdef CONFIG_SMP int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); void (*migrate_task_rq)(struct task_struct *p, int new_cpu); void (*task_woken)(struct rq *this_rq, struct task_struct *task); void (*set_cpus_allowed)(struct task_struct *p, const struct cpumask *newmask); void (*rq_online)(struct rq *rq); void (*rq_offline)(struct rq *rq); #endif void (*task_tick)(struct rq *rq, struct task_struct *p, int queued); void (*task_fork)(struct task_struct *p); void (*task_dead)(struct task_struct *p); /* * The switched_from() call is allowed to drop rq->lock, therefore we * cannot assume the switched_from/switched_to pair is serliazed by * rq->lock. They are however serialized by p->pi_lock. */ void (*switched_from)(struct rq *this_rq, struct task_struct *task); void (*switched_to) (struct rq *this_rq, struct task_struct *task); void (*prio_changed) (struct rq *this_rq, struct task_struct *task, int oldprio); unsigned int (*get_rr_interval)(struct rq *rq, struct task_struct *task); void (*update_curr)(struct rq *rq); #define TASK_SET_GROUP 0 #define TASK_MOVE_GROUP 1 #ifdef CONFIG_FAIR_GROUP_SCHED void (*task_change_group)(struct task_struct *p, int type); #endif }; static inline void put_prev_task(struct rq *rq, struct task_struct *prev) { WARN_ON_ONCE(rq->curr != prev); prev->sched_class->put_prev_task(rq, prev); } static inline void set_next_task(struct rq *rq, struct task_struct *next) { WARN_ON_ONCE(rq->curr != next); next->sched_class->set_next_task(rq, next, false); } #ifdef CONFIG_SMP #define sched_class_highest (&stop_sched_class) #else #define sched_class_highest (&dl_sched_class) #endif #define for_class_range(class, _from, _to) \ for (class = (_from); class != (_to); class = class->next) #define for_each_class(class) \ for_class_range(class, sched_class_highest, NULL) extern const struct sched_class stop_sched_class; extern const struct sched_class dl_sched_class; extern const struct sched_class rt_sched_class; extern const struct sched_class fair_sched_class; extern const struct sched_class idle_sched_class; static inline bool sched_stop_runnable(struct rq *rq) { return rq->stop && task_on_rq_queued(rq->stop); } static inline bool sched_dl_runnable(struct rq *rq) { return rq->dl.dl_nr_running > 0; } static inline bool sched_rt_runnable(struct rq *rq) { return rq->rt.rt_queued > 0; } static inline bool sched_fair_runnable(struct rq *rq) { return rq->cfs.nr_running > 0; } #ifdef CONFIG_SMP extern void update_group_capacity(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq); extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask); #endif #ifdef CONFIG_CPU_IDLE static inline void idle_set_state(struct rq *rq, struct cpuidle_state *idle_state) { rq->idle_state = idle_state; } static inline struct cpuidle_state *idle_get_state(struct rq *rq) { SCHED_WARN_ON(!rcu_read_lock_held()); return rq->idle_state; } #else static inline void idle_set_state(struct rq *rq, struct cpuidle_state *idle_state) { } static inline struct cpuidle_state *idle_get_state(struct rq *rq) { return NULL; } #endif extern void schedule_idle(void); extern void sysrq_sched_debug_show(void); extern void sched_init_granularity(void); extern void update_max_interval(void); extern void init_sched_dl_class(void); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); extern void reweight_task(struct task_struct *p, int prio); extern void resched_curr(struct rq *rq); extern void resched_cpu(int cpu); extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); extern struct dl_bandwidth def_dl_bandwidth; extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); extern void init_dl_task_timer(struct sched_dl_entity *dl_se); extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se); extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq); #define BW_SHIFT 20 #define BW_UNIT (1 << BW_SHIFT) #define RATIO_SHIFT 8 #define MAX_BW_BITS (64 - BW_SHIFT) #define MAX_BW ((1ULL << MAX_BW_BITS) - 1) unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); extern void post_init_entity_util_avg(struct task_struct *p); #ifdef CONFIG_NO_HZ_FULL extern bool sched_can_stop_tick(struct rq *rq); extern int __init sched_tick_offload_init(void); /* * Tick may be needed by tasks in the runqueue depending on their policy and * requirements. If tick is needed, lets send the target an IPI to kick it out of * nohz mode if necessary. */ static inline void sched_update_tick_dependency(struct rq *rq) { int cpu; if (!tick_nohz_full_enabled()) return; cpu = cpu_of(rq); if (!tick_nohz_full_cpu(cpu)) return; if (sched_can_stop_tick(rq)) tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED); else tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED); } #else static inline int sched_tick_offload_init(void) { return 0; } static inline void sched_update_tick_dependency(struct rq *rq) { } #endif static inline void add_nr_running(struct rq *rq, unsigned count) { unsigned prev_nr = rq->nr_running; rq->nr_running = prev_nr + count; #ifdef CONFIG_SMP if (prev_nr < 2 && rq->nr_running >= 2) { if (!READ_ONCE(rq->rd->overload)) WRITE_ONCE(rq->rd->overload, 1); } #endif sched_update_tick_dependency(rq); } static inline void sub_nr_running(struct rq *rq, unsigned count) { rq->nr_running -= count; /* Check if we still need preemption */ sched_update_tick_dependency(rq); } extern void activate_task(struct rq *rq, struct task_struct *p, int flags); extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); extern const_debug unsigned int sysctl_sched_nr_migrate; extern const_debug unsigned int sysctl_sched_migration_cost; #ifdef CONFIG_SCHED_HRTICK /* * Use hrtick when: * - enabled by features * - hrtimer is actually high res */ static inline int hrtick_enabled(struct rq *rq) { if (!sched_feat(HRTICK)) return 0; if (!cpu_active(cpu_of(rq))) return 0; return hrtimer_is_hres_active(&rq->hrtick_timer); } void hrtick_start(struct rq *rq, u64 delay); #else static inline int hrtick_enabled(struct rq *rq) { return 0; } #endif /* CONFIG_SCHED_HRTICK */ #ifndef arch_scale_freq_capacity static __always_inline unsigned long arch_scale_freq_capacity(int cpu) { return SCHED_CAPACITY_SCALE; } #endif #ifdef CONFIG_SMP #ifdef CONFIG_PREEMPTION static inline void double_rq_lock(struct rq *rq1, struct rq *rq2); /* * fair double_lock_balance: Safely acquires both rq->locks in a fair * way at the expense of forcing extra atomic operations in all * invocations. This assures that the double_lock is acquired using the * same underlying policy as the spinlock_t on this architecture, which * reduces latency compared to the unfair variant below. However, it * also adds more overhead and therefore may reduce throughput. */ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) __releases(this_rq->lock) __acquires(busiest->lock) __acquires(this_rq->lock) { raw_spin_unlock(&this_rq->lock); double_rq_lock(this_rq, busiest); return 1; } #else /* * Unfair double_lock_balance: Optimizes throughput at the expense of * latency by eliminating extra atomic operations when the locks are * already in proper order on entry. This favors lower CPU-ids and will * grant the double lock to lower CPUs over higher ids under contention, * regardless of entry order into the function. */ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) __releases(this_rq->lock) __acquires(busiest->lock) __acquires(this_rq->lock) { int ret = 0; if (unlikely(!raw_spin_trylock(&busiest->lock))) { if (busiest < this_rq) { raw_spin_unlock(&this_rq->lock); raw_spin_lock(&busiest->lock); raw_spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); ret = 1; } else raw_spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); } return ret; } #endif /* CONFIG_PREEMPTION */ /* * double_lock_balance - lock the busiest runqueue, this_rq is locked already. */ static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest) { if (unlikely(!irqs_disabled())) { /* printk() doesn't work well under rq->lock */ raw_spin_unlock(&this_rq->lock); BUG_ON(1); } return _double_lock_balance(this_rq, busiest); } static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) __releases(busiest->lock) { raw_spin_unlock(&busiest->lock); lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); } static inline void double_lock(spinlock_t *l1, spinlock_t *l2) { if (l1 > l2) swap(l1, l2); spin_lock(l1); spin_lock_nested(l2, SINGLE_DEPTH_NESTING); } static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2) { if (l1 > l2) swap(l1, l2); spin_lock_irq(l1); spin_lock_nested(l2, SINGLE_DEPTH_NESTING); } static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2) { if (l1 > l2) swap(l1, l2); raw_spin_lock(l1); raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING); } /* * double_rq_lock - safely lock two runqueues * * Note this does not disable interrupts like task_rq_lock, * you need to do so manually before calling. */ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2) __acquires(rq1->lock) __acquires(rq2->lock) { BUG_ON(!irqs_disabled()); if (rq1 == rq2) { raw_spin_lock(&rq1->lock); __acquire(rq2->lock); /* Fake it out ;) */ } else { if (rq1 < rq2) { raw_spin_lock(&rq1->lock); raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); } else { raw_spin_lock(&rq2->lock); raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); } } } /* * double_rq_unlock - safely unlock two runqueues * * Note this does not restore interrupts like task_rq_unlock, * you need to do so manually after calling. */ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) __releases(rq1->lock) __releases(rq2->lock) { raw_spin_unlock(&rq1->lock); if (rq1 != rq2) raw_spin_unlock(&rq2->lock); else __release(rq2->lock); } extern void set_rq_online (struct rq *rq); extern void set_rq_offline(struct rq *rq); extern bool sched_smp_initialized; #else /* CONFIG_SMP */ /* * double_rq_lock - safely lock two runqueues * * Note this does not disable interrupts like task_rq_lock, * you need to do so manually before calling. */ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2) __acquires(rq1->lock) __acquires(rq2->lock) { BUG_ON(!irqs_disabled()); BUG_ON(rq1 != rq2); raw_spin_lock(&rq1->lock); __acquire(rq2->lock); /* Fake it out ;) */ } /* * double_rq_unlock - safely unlock two runqueues * * Note this does not restore interrupts like task_rq_unlock, * you need to do so manually after calling. */ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) __releases(rq1->lock) __releases(rq2->lock) { BUG_ON(rq1 != rq2); raw_spin_unlock(&rq1->lock); __release(rq2->lock); } #endif extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq); extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq); #ifdef CONFIG_SCHED_DEBUG extern bool sched_debug_enabled; extern void print_cfs_stats(struct seq_file *m, int cpu); extern void print_rt_stats(struct seq_file *m, int cpu); extern void print_dl_stats(struct seq_file *m, int cpu); extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq); #ifdef CONFIG_NUMA_BALANCING extern void show_numa_stats(struct task_struct *p, struct seq_file *m); extern void print_numa_stats(struct seq_file *m, int node, unsigned long tsf, unsigned long tpf, unsigned long gsf, unsigned long gpf); #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_SCHED_DEBUG */ extern void init_cfs_rq(struct cfs_rq *cfs_rq); extern void init_rt_rq(struct rt_rq *rt_rq); extern void init_dl_rq(struct dl_rq *dl_rq); extern void cfs_bandwidth_usage_inc(void); extern void cfs_bandwidth_usage_dec(void); #ifdef CONFIG_NO_HZ_COMMON #define NOHZ_BALANCE_KICK_BIT 0 #define NOHZ_STATS_KICK_BIT 1 #define NOHZ_BALANCE_KICK BIT(NOHZ_BALANCE_KICK_BIT) #define NOHZ_STATS_KICK BIT(NOHZ_STATS_KICK_BIT) #define NOHZ_KICK_MASK (NOHZ_BALANCE_KICK | NOHZ_STATS_KICK) #define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) extern void nohz_balance_exit_idle(struct rq *rq); #else static inline void nohz_balance_exit_idle(struct rq *rq) { } #endif #ifdef CONFIG_SMP static inline void __dl_update(struct dl_bw *dl_b, s64 bw) { struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw); int i; RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), "sched RCU must be held"); for_each_cpu_and(i, rd->span, cpu_active_mask) { struct rq *rq = cpu_rq(i); rq->dl.extra_bw += bw; } } #else static inline void __dl_update(struct dl_bw *dl_b, s64 bw) { struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw); dl->extra_bw += bw; } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING struct irqtime { u64 total; u64 tick_delta; u64 irq_start_time; struct u64_stats_sync sync; }; DECLARE_PER_CPU(struct irqtime, cpu_irqtime); /* * Returns the irqtime minus the softirq time computed by ksoftirqd. * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime * and never move forward. */ static inline u64 irq_time_read(int cpu) { struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu); unsigned int seq; u64 total; do { seq = __u64_stats_fetch_begin(&irqtime->sync); total = irqtime->total; } while (__u64_stats_fetch_retry(&irqtime->sync, seq)); return total; } #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ #ifdef CONFIG_CPU_FREQ DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); /** * cpufreq_update_util - Take a note about CPU utilization changes. * @rq: Runqueue to carry out the update for. * @flags: Update reason flags. * * This function is called by the scheduler on the CPU whose utilization is * being updated. * * It can only be called from RCU-sched read-side critical sections. * * The way cpufreq is currently arranged requires it to evaluate the CPU * performance state (frequency/voltage) on a regular basis to prevent it from * being stuck in a completely inadequate performance level for too long. * That is not guaranteed to happen if the updates are only triggered from CFS * and DL, though, because they may not be coming in if only RT tasks are * active all the time (or there are RT tasks only). * * As a workaround for that issue, this function is called periodically by the * RT sched class to trigger extra cpufreq updates to prevent it from stalling, * but that really is a band-aid. Going forward it should be replaced with * solutions targeted more specifically at RT tasks. */ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) { struct update_util_data *data; data = rcu_dereference_sched(*per_cpu_ptr(&cpufreq_update_util_data, cpu_of(rq))); if (data) data->func(data, rq_clock(rq), flags); } #else static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif /* CONFIG_CPU_FREQ */ #ifdef CONFIG_UCLAMP_TASK unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); /** * uclamp_util_with - clamp @util with @rq and @p effective uclamp values. * @rq: The rq to clamp against. Must not be NULL. * @util: The util value to clamp. * @p: The task to clamp against. Can be NULL if you want to clamp * against @rq only. * * Clamps the passed @util to the max(@rq, @p) effective uclamp values. * * If sched_uclamp_used static key is disabled, then just return the util * without any clamping since uclamp aggregation at the rq level in the fast * path is disabled, rendering this operation a NOP. * * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It * will return the correct effective uclamp value of the task even if the * static key is disabled. */ static __always_inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util, struct task_struct *p) { unsigned int min_util; unsigned int max_util; if (!static_branch_likely(&sched_uclamp_used)) return util; min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value); max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value); if (p) { min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN)); max_util = max(max_util, uclamp_eff_value(p, UCLAMP_MAX)); } /* * Since CPU's {min,max}_util clamps are MAX aggregated considering * RUNNABLE tasks with _different_ clamps, we can end up with an * inversion. Fix it now when the clamps are applied. */ if (unlikely(min_util >= max_util)) return min_util; return clamp(util, min_util, max_util); } static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) { return uclamp_util_with(rq, util, NULL); } /* * When uclamp is compiled in, the aggregation at rq level is 'turned off' * by default in the fast path and only gets turned on once userspace performs * an operation that requires it. * * Returns true if userspace opted-in to use uclamp and aggregation at rq level * hence is active. */ static inline bool uclamp_is_used(void) { return static_branch_likely(&sched_uclamp_used); } #else /* CONFIG_UCLAMP_TASK */ static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util, struct task_struct *p) { return util; } static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) { return util; } static inline bool uclamp_is_used(void) { return false; } #endif /* CONFIG_UCLAMP_TASK */ #ifdef arch_scale_freq_capacity # ifndef arch_scale_freq_invariant # define arch_scale_freq_invariant() true # endif #else # define arch_scale_freq_invariant() false #endif #ifdef CONFIG_SMP static inline unsigned long capacity_orig_of(int cpu) { return cpu_rq(cpu)->cpu_capacity_orig; } #endif /** * enum schedutil_type - CPU utilization type * @FREQUENCY_UTIL: Utilization used to select frequency * @ENERGY_UTIL: Utilization used during energy calculation * * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time * need to be aggregated differently depending on the usage made of them. This * enum is used within schedutil_freq_util() to differentiate the types of * utilization expected by the callers, and adjust the aggregation accordingly. */ enum schedutil_type { FREQUENCY_UTIL, ENERGY_UTIL, }; #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, unsigned long max, enum schedutil_type type, struct task_struct *p); static inline unsigned long cpu_bw_dl(struct rq *rq) { return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT; } static inline unsigned long cpu_util_dl(struct rq *rq) { return READ_ONCE(rq->avg_dl.util_avg); } static inline unsigned long cpu_util_cfs(struct rq *rq) { unsigned long util = READ_ONCE(rq->cfs.avg.util_avg); if (sched_feat(UTIL_EST)) { util = max_t(unsigned long, util, READ_ONCE(rq->cfs.avg.util_est.enqueued)); } return util; } static inline unsigned long cpu_util_rt(struct rq *rq) { return READ_ONCE(rq->avg_rt.util_avg); } #else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ static inline unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, unsigned long max, enum schedutil_type type, struct task_struct *p) { return 0; } #endif /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ #ifdef CONFIG_HAVE_SCHED_AVG_IRQ static inline unsigned long cpu_util_irq(struct rq *rq) { return rq->avg_irq.util_avg; } static inline unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max) { util *= (max - irq); util /= max; return util; } #else static inline unsigned long cpu_util_irq(struct rq *rq) { return 0; } static inline unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max) { return util; } #endif #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) #define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus))) DECLARE_STATIC_KEY_FALSE(sched_energy_present); static inline bool sched_energy_enabled(void) { return static_branch_unlikely(&sched_energy_present); } #else /* ! (CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL) */ #define perf_domain_span(pd) NULL static inline bool sched_energy_enabled(void) { return false; } #endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ #ifdef CONFIG_MEMBARRIER /* * The scheduler provides memory barriers required by membarrier between: * - prior user-space memory accesses and store to rq->membarrier_state, * - store to rq->membarrier_state and following user-space memory accesses. * In the same way it provides those guarantees around store to rq->curr. */ static inline void membarrier_switch_mm(struct rq *rq, struct mm_struct *prev_mm, struct mm_struct *next_mm) { int membarrier_state; if (prev_mm == next_mm) return; membarrier_state = atomic_read(&next_mm->membarrier_state); if (READ_ONCE(rq->membarrier_state) == membarrier_state) return; WRITE_ONCE(rq->membarrier_state, membarrier_state); } #else static inline void membarrier_switch_mm(struct rq *rq, struct mm_struct *prev_mm, struct mm_struct *next_mm) { } #endif |