1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* kernel/sched/core.c
*
* Core kernel scheduler code and related syscalls
*
* Copyright (C) 1991-2002 Linus Torvalds
*/
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
#undef CREATE_TRACE_POINTS
#include "sched.h"
#include <linux/nospec.h>
#include <linux/kcov.h>
#include <linux/scs.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
#include "../workqueue_internal.h"
#include "../../fs/io-wq.h"
#include "../smpboot.h"
#include "pelt.h"
#include "smp.h"
/*
* Export tracepoints that act as a bare tracehook (ie: have no trace event
* associated with them) to allow external modules to probe them.
*/
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_cfs_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
#ifdef CONFIG_SCHED_DEBUG
/*
* Debugging: various feature bits
*
* If SCHED_DEBUG is disabled, each compilation unit has its own copy of
* sysctl_sched_features, defined in sched.h, to allow constants propagation
* at compile time and compiler optimization based on features default.
*/
#define SCHED_FEAT(name, enabled) \
(1UL << __SCHED_FEAT_##name) * enabled |
const_debug unsigned int sysctl_sched_features =
#include "features.h"
0;
#undef SCHED_FEAT
/*
* Print a warning if need_resched is set for the given duration (if
* LATENCY_WARN is enabled).
*
* If sysctl_resched_latency_warn_once is set, only one warning will be shown
* per boot.
*/
__read_mostly int sysctl_resched_latency_warn_ms = 100;
__read_mostly int sysctl_resched_latency_warn_once = 1;
#endif /* CONFIG_SCHED_DEBUG */
/*
* Number of tasks to iterate in a single balance run.
* Limited because this is done with IRQs disabled.
*/
const_debug unsigned int sysctl_sched_nr_migrate = 32;
/*
* period over which we measure -rt task CPU usage in us.
* default: 1s
*/
unsigned int sysctl_sched_rt_period = 1000000;
__read_mostly int scheduler_running;
/*
* part of the period that we allow rt tasks to run in us.
* default: 0.95s
*/
int sysctl_sched_rt_runtime = 950000;
/*
* Serialization rules:
*
* Lock order:
*
* p->pi_lock
* rq->lock
* hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
*
* rq1->lock
* rq2->lock where: rq1 < rq2
*
* Regular state:
*
* Normal scheduling state is serialized by rq->lock. __schedule() takes the
* local CPU's rq->lock, it optionally removes the task from the runqueue and
* always looks at the local rq data structures to find the most eligible task
* to run next.
*
* Task enqueue is also under rq->lock, possibly taken from another CPU.
* Wakeups from another LLC domain might use an IPI to transfer the enqueue to
* the local CPU to avoid bouncing the runqueue state around [ see
* ttwu_queue_wakelist() ]
*
* Task wakeup, specifically wakeups that involve migration, are horribly
* complicated to avoid having to take two rq->locks.
*
* Special state:
*
* System-calls and anything external will use task_rq_lock() which acquires
* both p->pi_lock and rq->lock. As a consequence the state they change is
* stable while holding either lock:
*
* - sched_setaffinity()/
* set_cpus_allowed_ptr(): p->cpus_ptr, p->nr_cpus_allowed
* - set_user_nice(): p->se.load, p->*prio
* - __sched_setscheduler(): p->sched_class, p->policy, p->*prio,
* p->se.load, p->rt_priority,
* p->dl.dl_{runtime, deadline, period, flags, bw, density}
* - sched_setnuma(): p->numa_preferred_nid
* - sched_move_task()/
* cpu_cgroup_fork(): p->sched_task_group
* - uclamp_update_active() p->uclamp*
*
* p->state <- TASK_*:
*
* is changed locklessly using set_current_state(), __set_current_state() or
* set_special_state(), see their respective comments, or by
* try_to_wake_up(). This latter uses p->pi_lock to serialize against
* concurrent self.
*
* p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
*
* is set by activate_task() and cleared by deactivate_task(), under
* rq->lock. Non-zero indicates the task is runnable, the special
* ON_RQ_MIGRATING state is used for migration without holding both
* rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
*
* p->on_cpu <- { 0, 1 }:
*
* is set by prepare_task() and cleared by finish_task() such that it will be
* set before p is scheduled-in and cleared after p is scheduled-out, both
* under rq->lock. Non-zero indicates the task is running on its CPU.
*
* [ The astute reader will observe that it is possible for two tasks on one
* CPU to have ->on_cpu = 1 at the same time. ]
*
* task_cpu(p): is changed by set_task_cpu(), the rules are:
*
* - Don't call set_task_cpu() on a blocked task:
*
* We don't care what CPU we're not running on, this simplifies hotplug,
* the CPU assignment of blocked tasks isn't required to be valid.
*
* - for try_to_wake_up(), called under p->pi_lock:
*
* This allows try_to_wake_up() to only take one rq->lock, see its comment.
*
* - for migration called under rq->lock:
* [ see task_on_rq_migrating() in task_rq_lock() ]
*
* o move_queued_task()
* o detach_task()
*
* - for migration called under double_rq_lock():
*
* o __migrate_swap_task()
* o push_rt_task() / pull_rt_task()
* o push_dl_task() / pull_dl_task()
* o dl_task_offline_migration()
*
*/
/*
* __task_rq_lock - lock the rq @p resides on.
*/
struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
__acquires(rq->lock)
{
struct rq *rq;
lockdep_assert_held(&p->pi_lock);
for (;;) {
rq = task_rq(p);
raw_spin_lock(&rq->lock);
if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
rq_pin_lock(rq, rf);
return rq;
}
raw_spin_unlock(&rq->lock);
while (unlikely(task_on_rq_migrating(p)))
cpu_relax();
}
}
/*
* task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
*/
struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
__acquires(p->pi_lock)
__acquires(rq->lock)
{
struct rq *rq;
for (;;) {
raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
rq = task_rq(p);
raw_spin_lock(&rq->lock);
/*
* move_queued_task() task_rq_lock()
*
* ACQUIRE (rq->lock)
* [S] ->on_rq = MIGRATING [L] rq = task_rq()
* WMB (__set_task_cpu()) ACQUIRE (rq->lock);
* [S] ->cpu = new_cpu [L] task_rq()
* [L] ->on_rq
* RELEASE (rq->lock)
*
* If we observe the old CPU in task_rq_lock(), the acquire of
* the old rq->lock will fully serialize against the stores.
*
* If we observe the new CPU in task_rq_lock(), the address
* dependency headed by '[L] rq = task_rq()' and the acquire
* will pair with the WMB to ensure we then also see migrating.
*/
if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
rq_pin_lock(rq, rf);
return rq;
}
raw_spin_unlock(&rq->lock);
raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
while (unlikely(task_on_rq_migrating(p)))
cpu_relax();
}
}
/*
* RQ-clock updating methods:
*/
static void update_rq_clock_task(struct rq *rq, s64 delta)
{
/*
* In theory, the compile should just see 0 here, and optimize out the call
* to sched_rt_avg_update. But I don't trust it...
*/
s64 __maybe_unused steal = 0, irq_delta = 0;
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
/*
* Since irq_time is only updated on {soft,}irq_exit, we might run into
* this case when a previous update_rq_clock() happened inside a
* {soft,}irq region.
*
* When this happens, we stop ->clock_task and only update the
* prev_irq_time stamp to account for the part that fit, so that a next
* update will consume the rest. This ensures ->clock_task is
* monotonic.
*
* It does however cause some slight miss-attribution of {soft,}irq
* time, a more accurate solution would be to update the irq_time using
* the current rq->clock timestamp, except that would require using
* atomic ops.
*/
if (irq_delta > delta)
irq_delta = delta;
rq->prev_irq_time += irq_delta;
delta -= irq_delta;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
if (static_key_false((¶virt_steal_rq_enabled))) {
steal = paravirt_steal_clock(cpu_of(rq));
steal -= rq->prev_steal_time_rq;
if (unlikely(steal > delta))
steal = delta;
rq->prev_steal_time_rq += steal;
delta -= steal;
}
#endif
rq->clock_task += delta;
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
update_irq_load_avg(rq, irq_delta + steal);
#endif
update_rq_clock_pelt(rq, delta);
}
void update_rq_clock(struct rq *rq)
{
s64 delta;
lockdep_assert_held(&rq->lock);
if (rq->clock_update_flags & RQCF_ACT_SKIP)
return;
#ifdef CONFIG_SCHED_DEBUG
if (sched_feat(WARN_DOUBLE_CLOCK))
SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED);
rq->clock_update_flags |= RQCF_UPDATED;
#endif
delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
if (delta < 0)
return;
rq->clock += delta;
update_rq_clock_task(rq, delta);
}
#ifdef CONFIG_SCHED_HRTICK
/*
* Use HR-timers to deliver accurate preemption points.
*/
static void hrtick_clear(struct rq *rq)
{
if (hrtimer_active(&rq->hrtick_timer))
hrtimer_cancel(&rq->hrtick_timer);
}
/*
* High-resolution timer tick.
* Runs from hardirq context with interrupts disabled.
*/
static enum hrtimer_restart hrtick(struct hrtimer *timer)
{
struct rq *rq = container_of(timer, struct rq, hrtick_timer);
struct rq_flags rf;
WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
rq_lock(rq, &rf);
update_rq_clock(rq);
rq->curr->sched_class->task_tick(rq, rq->curr, 1);
rq_unlock(rq, &rf);
return HRTIMER_NORESTART;
}
#ifdef CONFIG_SMP
static void __hrtick_restart(struct rq *rq)
{
struct hrtimer *timer = &rq->hrtick_timer;
ktime_t time = rq->hrtick_time;
hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
}
/*
* called from hardirq (IPI) context
*/
static void __hrtick_start(void *arg)
{
struct rq *rq = arg;
struct rq_flags rf;
rq_lock(rq, &rf);
__hrtick_restart(rq);
rq_unlock(rq, &rf);
}
/*
* Called to set the hrtick timer state.
*
* called with rq->lock held and irqs disabled
*/
void hrtick_start(struct rq *rq, u64 delay)
{
struct hrtimer *timer = &rq->hrtick_timer;
s64 delta;
/*
* Don't schedule slices shorter than 10000ns, that just
* doesn't make sense and can cause timer DoS.
*/
delta = max_t(s64, delay, 10000LL);
rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
if (rq == this_rq())
__hrtick_restart(rq);
else
smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
}
#else
/*
* Called to set the hrtick timer state.
*
* called with rq->lock held and irqs disabled
*/
void hrtick_start(struct rq *rq, u64 delay)
{
/*
* Don't schedule slices shorter than 10000ns, that just
* doesn't make sense. Rely on vruntime for fairness.
*/
delay = max_t(u64, delay, 10000LL);
hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
HRTIMER_MODE_REL_PINNED_HARD);
}
#endif /* CONFIG_SMP */
static void hrtick_rq_init(struct rq *rq)
{
#ifdef CONFIG_SMP
INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq);
#endif
hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
rq->hrtick_timer.function = hrtick;
}
#else /* CONFIG_SCHED_HRTICK */
static inline void hrtick_clear(struct rq *rq)
{
}
static inline void hrtick_rq_init(struct rq *rq)
{
}
#endif /* CONFIG_SCHED_HRTICK */
/*
* cmpxchg based fetch_or, macro so it works for different integer types
*/
#define fetch_or(ptr, mask) \
({ \
typeof(ptr) _ptr = (ptr); \
typeof(mask) _mask = (mask); \
typeof(*_ptr) _old, _val = *_ptr; \
\
for (;;) { \
_old = cmpxchg(_ptr, _val, _val | _mask); \
if (_old == _val) \
break; \
_val = _old; \
} \
_old; \
})
#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
/*
* Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
* this avoids any races wrt polling state changes and thereby avoids
* spurious IPIs.
*/
static bool set_nr_and_not_polling(struct task_struct *p)
{
struct thread_info *ti = task_thread_info(p);
return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
}
/*
* Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
*
* If this returns true, then the idle task promises to call
* sched_ttwu_pending() and reschedule soon.
*/
static bool set_nr_if_polling(struct task_struct *p)
{
struct thread_info *ti = task_thread_info(p);
typeof(ti->flags) old, val = READ_ONCE(ti->flags);
for (;;) {
if (!(val & _TIF_POLLING_NRFLAG))
return false;
if (val & _TIF_NEED_RESCHED)
return true;
old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED);
if (old == val)
break;
val = old;
}
return true;
}
#else
static bool set_nr_and_not_polling(struct task_struct *p)
{
set_tsk_need_resched(p);
return true;
}
#ifdef CONFIG_SMP
static bool set_nr_if_polling(struct task_struct *p)
{
return false;
}
#endif
#endif
static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
struct wake_q_node *node = &task->wake_q;
/*
* Atomically grab the task, if ->wake_q is !nil already it means
* it's already queued (either by us or someone else) and will get the
* wakeup due to that.
*
* In order to ensure that a pending wakeup will observe our pending
* state, even in the failed case, an explicit smp_mb() must be used.
*/
smp_mb__before_atomic();
if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
return false;
/*
* The head is context local, there can be no concurrency.
*/
*head->lastp = node;
head->lastp = &node->next;
return true;
}
/**
* wake_q_add() - queue a wakeup for 'later' waking.
* @head: the wake_q_head to add @task to
* @task: the task to queue for 'later' wakeup
*
* Queue a task for later wakeup, most likely by the wake_up_q() call in the
* same context, _HOWEVER_ this is not guaranteed, the wakeup can come
* instantly.
*
* This function must be used as-if it were wake_up_process(); IOW the task
* must be ready to be woken at this location.
*/
void wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
if (__wake_q_add(head, task))
get_task_struct(task);
}
/**
* wake_q_add_safe() - safely queue a wakeup for 'later' waking.
* @head: the wake_q_head to add @task to
* @task: the task to queue for 'later' wakeup
*
* Queue a task for later wakeup, most likely by the wake_up_q() call in the
* same context, _HOWEVER_ this is not guaranteed, the wakeup can come
* instantly.
*
* This function must be used as-if it were wake_up_process(); IOW the task
* must be ready to be woken at this location.
*
* This function is essentially a task-safe equivalent to wake_q_add(). Callers
* that already hold reference to @task can call the 'safe' version and trust
* wake_q to do the right thing depending whether or not the @task is already
* queued for wakeup.
*/
void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
{
if (!__wake_q_add(head, task))
put_task_struct(task);
}
void wake_up_q(struct wake_q_head *head)
{
struct wake_q_node *node = head->first;
while (node != WAKE_Q_TAIL) {
struct task_struct *task;
task = container_of(node, struct task_struct, wake_q);
BUG_ON(!task);
/* Task can safely be re-inserted now: */
node = node->next;
task->wake_q.next = NULL;
/*
* wake_up_process() executes a full barrier, which pairs with
* the queueing in wake_q_add() so as not to miss wakeups.
*/
wake_up_process(task);
put_task_struct(task);
}
}
/*
* resched_curr - mark rq's current task 'to be rescheduled now'.
*
* On UP this means the setting of the need_resched flag, on SMP it
* might also involve a cross-CPU call to trigger the scheduler on
* the target CPU.
*/
void resched_curr(struct rq *rq)
{
struct task_struct *curr = rq->curr;
int cpu;
lockdep_assert_held(&rq->lock);
if (test_tsk_need_resched(curr))
return;
cpu = cpu_of(rq);
if (cpu == smp_processor_id()) {
set_tsk_need_resched(curr);
set_preempt_need_resched();
return;
}
if (set_nr_and_not_polling(curr))
smp_send_reschedule(cpu);
else
trace_sched_wake_idle_without_ipi(cpu);
}
void resched_cpu(int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
if (cpu_online(cpu) || cpu == smp_processor_id())
resched_curr(rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ_COMMON
/*
* In the semi idle case, use the nearest busy CPU for migrating timers
* from an idle CPU. This is good for power-savings.
*
* We don't do similar optimization for completely idle system, as
* selecting an idle CPU will add more delays to the timers than intended
* (as that CPU's timer base may not be uptodate wrt jiffies etc).
*/
int get_nohz_timer_target(void)
{
int i, cpu = smp_processor_id(), default_cpu = -1;
struct sched_domain *sd;
if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
if (!idle_cpu(cpu))
return cpu;
default_cpu = cpu;
}
rcu_read_lock();
for_each_domain(cpu, sd) {
for_each_cpu_and(i, sched_domain_span(sd),
housekeeping_cpumask(HK_FLAG_TIMER)) {
if (cpu == i)
continue;
if (!idle_cpu(i)) {
cpu = i;
goto unlock;
}
}
}
if (default_cpu == -1)
default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
cpu = default_cpu;
unlock:
rcu_read_unlock();
return cpu;
}
/*
* When add_timer_on() enqueues a timer into the timer wheel of an
* idle CPU then this timer might expire before the next timer event
* which is scheduled to wake up that CPU. In case of a completely
* idle system the next event might even be infinite time into the
* future. wake_up_idle_cpu() ensures that the CPU is woken up and
* leaves the inner idle loop so the newly added timer is taken into
* account when the CPU goes back to idle and evaluates the timer
* wheel for the next timer event.
*/
static void wake_up_idle_cpu(int cpu)
{
struct rq *rq = cpu_rq(cpu);
if (cpu == smp_processor_id())
return;
if (set_nr_and_not_polling(rq->idle))
smp_send_reschedule(cpu);
else
trace_sched_wake_idle_without_ipi(cpu);
}
static bool wake_up_full_nohz_cpu(int cpu)
{
/*
* We just need the target to call irq_exit() and re-evaluate
* the next tick. The nohz full kick at least implies that.
* If needed we can still optimize that later with an
* empty IRQ.
*/
if (cpu_is_offline(cpu))
return true; /* Don't try to wake offline CPUs. */
if (tick_nohz_full_cpu(cpu)) {
if (cpu != smp_processor_id() ||
tick_nohz_tick_stopped())
tick_nohz_full_kick_cpu(cpu);
return true;
}
return false;
}
/*
* Wake up the specified CPU. If the CPU is going offline, it is the
* caller's responsibility to deal with the lost wakeup, for example,
* by hooking into the CPU_DEAD notifier like timers and hrtimers do.
*/
void wake_up_nohz_cpu(int cpu)
{
if (!wake_up_full_nohz_cpu(cpu))
wake_up_idle_cpu(cpu);
}
static void nohz_csd_func(void *info)
{
struct rq *rq = info;
int cpu = cpu_of(rq);
unsigned int flags;
/*
* Release the rq::nohz_csd.
*/
flags = atomic_fetch_andnot(NOHZ_KICK_MASK | NOHZ_NEWILB_KICK, nohz_flags(cpu));
WARN_ON(!(flags & NOHZ_KICK_MASK));
rq->idle_balance = idle_cpu(cpu);
if (rq->idle_balance && !need_resched()) {
rq->nohz_idle_balance = flags;
raise_softirq_irqoff(SCHED_SOFTIRQ);
}
}
#endif /* CONFIG_NO_HZ_COMMON */
#ifdef CONFIG_NO_HZ_FULL
bool sched_can_stop_tick(struct rq *rq)
{
int fifo_nr_running;
/* Deadline tasks, even if single, need the tick */
if (rq->dl.dl_nr_running)
return false;
/*
* If there are more than one RR tasks, we need the tick to affect the
* actual RR behaviour.
*/
if (rq->rt.rr_nr_running) {
if (rq->rt.rr_nr_running == 1)
return true;
else
return false;
}
/*
* If there's no RR tasks, but FIFO tasks, we can skip the tick, no
* forced preemption between FIFO tasks.
*/
fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running;
if (fifo_nr_running)
return true;
/*
* If there are no DL,RR/FIFO tasks, there must only be CFS tasks left;
* if there's more than one we need the tick for involuntary
* preemption.
*/
if (rq->nr_running > 1)
return false;
return true;
}
#endif /* CONFIG_NO_HZ_FULL */
#endif /* CONFIG_SMP */
#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
(defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH)))
/*
* Iterate task_group tree rooted at *from, calling @down when first entering a
* node and @up when leaving it for the final time.
*
* Caller must hold rcu_lock or sufficient equivalent.
*/
int walk_tg_tree_from(struct task_group *from,
tg_visitor down, tg_visitor up, void *data)
{
struct task_group *parent, *child;
int ret;
parent = from;
down:
ret = (*down)(parent, data);
if (ret)
goto out;
list_for_each_entry_rcu(child, &parent->children, siblings) {
parent = child;
goto down;
up:
continue;
}
ret = (*up)(parent, data);
if (ret || parent == from)
goto out;
child = parent;
parent = parent->parent;
if (parent)
goto up;
out:
return ret;
}
int tg_nop(struct task_group *tg, void *data)
{
return 0;
}
#endif
static void set_load_weight(struct task_struct *p, bool update_load)
{
int prio = p->static_prio - MAX_RT_PRIO;
struct load_weight *load = &p->se.load;
/*
* SCHED_IDLE tasks get minimal weight:
*/
if (task_has_idle_policy(p)) {
load->weight = scale_load(WEIGHT_IDLEPRIO);
load->inv_weight = WMULT_IDLEPRIO;
return;
}
/*
* SCHED_OTHER tasks have to update their load when changing their
* weight
*/
if (update_load && p->sched_class == &fair_sched_class) {
reweight_task(p, prio);
} else {
load->weight = scale_load(sched_prio_to_weight[prio]);
load->inv_weight = sched_prio_to_wmult[prio];
}
}
#ifdef CONFIG_UCLAMP_TASK
/*
* Serializes updates of utilization clamp values
*
* The (slow-path) user-space triggers utilization clamp value updates which
* can require updates on (fast-path) scheduler's data structures used to
* support enqueue/dequeue operations.
* While the per-CPU rq lock protects fast-path update operations, user-space
* requests are serialized using a mutex to reduce the risk of conflicting
* updates or API abuses.
*/
static DEFINE_MUTEX(uclamp_mutex);
/* Max allowed minimum utilization */
unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
/* Max allowed maximum utilization */
unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
/*
* By default RT tasks run at the maximum performance point/capacity of the
* system. Uclamp enforces this by always setting UCLAMP_MIN of RT tasks to
* SCHED_CAPACITY_SCALE.
*
* This knob allows admins to change the default behavior when uclamp is being
* used. In battery powered devices, particularly, running at the maximum
* capacity and frequency will increase energy consumption and shorten the
* battery life.
*
* This knob only affects RT tasks that their uclamp_se->user_defined == false.
*
* This knob will not override the system default sched_util_clamp_min defined
* above.
*/
unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
/* All clamps are required to be less or equal than these values */
static struct uclamp_se uclamp_default[UCLAMP_CNT];
/*
* This static key is used to reduce the uclamp overhead in the fast path. It
* primarily disables the call to uclamp_rq_{inc, dec}() in
* enqueue/dequeue_task().
*
* This allows users to continue to enable uclamp in their kernel config with
* minimum uclamp overhead in the fast path.
*
* As soon as userspace modifies any of the uclamp knobs, the static key is
* enabled, since we have an actual users that make use of uclamp
* functionality.
*
* The knobs that would enable this static key are:
*
* * A task modifying its uclamp value with sched_setattr().
* * An admin modifying the sysctl_sched_uclamp_{min, max} via procfs.
* * An admin modifying the cgroup cpu.uclamp.{min, max}
*/
DEFINE_STATIC_KEY_FALSE(sched_uclamp_used);
/* Integer rounded range for each bucket */
#define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS)
#define for_each_clamp_id(clamp_id) \
for ((clamp_id) = 0; (clamp_id) < UCLAMP_CNT; (clamp_id)++)
static inline unsigned int uclamp_bucket_id(unsigned int clamp_value)
{
return clamp_value / UCLAMP_BUCKET_DELTA;
}
static inline unsigned int uclamp_none(enum uclamp_id clamp_id)
{
if (clamp_id == UCLAMP_MIN)
return 0;
return SCHED_CAPACITY_SCALE;
}
static inline void uclamp_se_set(struct uclamp_se *uc_se,
unsigned int value, bool user_defined)
{
uc_se->value = value;
uc_se->bucket_id = uclamp_bucket_id(value);
uc_se->user_defined = user_defined;
}
static inline unsigned int
uclamp_idle_value(struct rq *rq, enum uclamp_id clamp_id,
unsigned int clamp_value)
{
/*
* Avoid blocked utilization pushing up the frequency when we go
* idle (which drops the max-clamp) by retaining the last known
* max-clamp.
*/
if (clamp_id == UCLAMP_MAX) {
rq->uclamp_flags |= UCLAMP_FLAG_IDLE;
return clamp_value;
}
return uclamp_none(UCLAMP_MIN);
}
static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id,
unsigned int clamp_value)
{
/* Reset max-clamp retention only on idle exit */
if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE))
return;
WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value);
}
static inline
unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
unsigned int clamp_value)
{
struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket;
int bucket_id = UCLAMP_BUCKETS - 1;
/*
* Since both min and max clamps are max aggregated, find the
* top most bucket with tasks in.
*/
for ( ; bucket_id >= 0; bucket_id--) {
if (!bucket[bucket_id].tasks)
continue;
return bucket[bucket_id].value;
}
/* No tasks -- default clamp values */
return uclamp_idle_value(rq, clamp_id, clamp_value);
}
static void __uclamp_update_util_min_rt_default(struct task_struct *p)
{
unsigned int default_util_min;
struct uclamp_se *uc_se;
lockdep_assert_held(&p->pi_lock);
uc_se = &p->uclamp_req[UCLAMP_MIN];
/* Only sync if user didn't override the default */
if (uc_se->user_defined)
return;
default_util_min = sysctl_sched_uclamp_util_min_rt_default;
uclamp_se_set(uc_se, default_util_min, false);
}
static void uclamp_update_util_min_rt_default(struct task_struct *p)
{
struct rq_flags rf;
struct rq *rq;
if (!rt_task(p))
return;
/* Protect updates to p->uclamp_* */
rq = task_rq_lock(p, &rf);
__uclamp_update_util_min_rt_default(p);
task_rq_unlock(rq, p, &rf);
}
static void uclamp_sync_util_min_rt_default(void)
{
struct task_struct *g, *p;
/*
* copy_process() sysctl_uclamp
* uclamp_min_rt = X;
* write_lock(&tasklist_lock) read_lock(&tasklist_lock)
* // link thread smp_mb__after_spinlock()
* write_unlock(&tasklist_lock) read_unlock(&tasklist_lock);
* sched_post_fork() for_each_process_thread()
* __uclamp_sync_rt() __uclamp_sync_rt()
*
* Ensures that either sched_post_fork() will observe the new
* uclamp_min_rt or for_each_process_thread() will observe the new
* task.
*/
read_lock(&tasklist_lock);
smp_mb__after_spinlock();
read_unlock(&tasklist_lock);
rcu_read_lock();
for_each_process_thread(g, p)
uclamp_update_util_min_rt_default(p);
rcu_read_unlock();
}
static inline struct uclamp_se
uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
{
struct uclamp_se uc_req = p->uclamp_req[clamp_id];
#ifdef CONFIG_UCLAMP_TASK_GROUP
struct uclamp_se uc_max;
/*
* Tasks in autogroups or root task group will be
* restricted by system defaults.
*/
if (task_group_is_autogroup(task_group(p)))
return uc_req;
if (task_group(p) == &root_task_group)
return uc_req;
uc_max = task_group(p)->uclamp[clamp_id];
if (uc_req.value > uc_max.value || !uc_req.user_defined)
return uc_max;
#endif
return uc_req;
}
/*
* The effective clamp bucket index of a task depends on, by increasing
* priority:
* - the task specific clamp value, when explicitly requested from userspace
* - the task group effective clamp value, for tasks not either in the root
* group or in an autogroup
* - the system default clamp value, defined by the sysadmin
*/
static inline struct uclamp_se
uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id)
{
struct uclamp_se uc_req = uclamp_tg_restrict(p, clamp_id);
struct uclamp_se uc_max = uclamp_default[clamp_id];
/* System default restrictions always apply */
if (unlikely(uc_req.value > uc_max.value))
return uc_max;
return uc_req;
}
unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
{
struct uclamp_se uc_eff;
/* Task currently refcounted: use back-annotated (effective) value */
if (p->uclamp[clamp_id].active)
return (unsigned long)p->uclamp[clamp_id].value;
uc_eff = uclamp_eff_get(p, clamp_id);
return (unsigned long)uc_eff.value;
}
/*
* When a task is enqueued on a rq, the clamp bucket currently defined by the
* task's uclamp::bucket_id is refcounted on that rq. This also immediately
* updates the rq's clamp value if required.
*
* Tasks can have a task-specific value requested from user-space, track
* within each bucket the maximum value for tasks refcounted in it.
* This "local max aggregation" allows to track the exact "requested" value
* for each bucket when all its RUNNABLE tasks require the same clamp.
*/
static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
enum uclamp_id clamp_id)
{
struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
struct uclamp_se *uc_se = &p->uclamp[clamp_id];
struct uclamp_bucket *bucket;
lockdep_assert_held(&rq->lock);
/* Update task effective clamp */
p->uclamp[clamp_id] = uclamp_eff_get(p, clamp_id);
bucket = &uc_rq->bucket[uc_se->bucket_id];
bucket->tasks++;
uc_se->active = true;
uclamp_idle_reset(rq, clamp_id, uc_se->value);
/*
* Local max aggregation: rq buckets always track the max
* "requested" clamp value of its RUNNABLE tasks.
*/
if (bucket->tasks == 1 || uc_se->value > bucket->value)
bucket->value = uc_se->value;
if (uc_se->value > READ_ONCE(uc_rq->value))
WRITE_ONCE(uc_rq->value, uc_se->value);
}
/*
* When a task is dequeued from a rq, the clamp bucket refcounted by the task
* is released. If this is the last task reference counting the rq's max
* active clamp value, then the rq's clamp value is updated.
*
* Both refcounted tasks and rq's cached clamp values are expected to be
* always valid. If it's detected they are not, as defensive programming,
* enforce the expected state and warn.
*/
static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
enum uclamp_id clamp_id)
{
struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
struct uclamp_se *uc_se = &p->uclamp[clamp_id];
struct uclamp_bucket *bucket;
unsigned int bkt_clamp;
unsigned int rq_clamp;
lockdep_assert_held(&rq->lock);
/*
* If sched_uclamp_used was enabled after task @p was enqueued,
* we could end up with unbalanced call to uclamp_rq_dec_id().
*
* In this case the uc_se->active flag should be false since no uclamp
* accounting was performed at enqueue time and we can just return
* here.
*
* Need to be careful of the following enqueue/dequeue ordering
* problem too
*
* enqueue(taskA)
* // sched_uclamp_used gets enabled
* enqueue(taskB)
* dequeue(taskA)
* // Must not decrement bucket->tasks here
* dequeue(taskB)
*
* where we could end up with stale data in uc_se and
* bucket[uc_se->bucket_id].
*
* The following check here eliminates the possibility of such race.
*/
if (unlikely(!uc_se->active))
return;
bucket = &uc_rq->bucket[uc_se->bucket_id];
SCHED_WARN_ON(!bucket->tasks);
if (likely(bucket->tasks))
bucket->tasks--;
uc_se->active = false;
/*
* Keep "local max aggregation" simple and accept to (possibly)
* overboost some RUNNABLE tasks in the same bucket.
* The rq clamp bucket value is reset to its base value whenever
* there are no more RUNNABLE tasks refcounting it.
*/
if (likely(bucket->tasks))
return;
rq_clamp = READ_ONCE(uc_rq->value);
/*
* Defensive programming: this should never happen. If it happens,
* e.g. due to future modification, warn and fixup the expected value.
*/
SCHED_WARN_ON(bucket->value > rq_clamp);
if (bucket->value >= rq_clamp) {
bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value);
WRITE_ONCE(uc_rq->value, bkt_clamp);
}
}
static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
{
enum uclamp_id clamp_id;
/*
* Avoid any overhead until uclamp is actually used by the userspace.
*
* The condition is constructed such that a NOP is generated when
* sched_uclamp_used is disabled.
*/
if (!static_branch_unlikely(&sched_uclamp_used))
return;
if (unlikely(!p->sched_class->uclamp_enabled))
return;
for_each_clamp_id(clamp_id)
uclamp_rq_inc_id(rq, p, clamp_id);
/* Reset clamp idle holding when there is one RUNNABLE task */
if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE;
}
static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
{
enum uclamp_id clamp_id;
/*
* Avoid any overhead until uclamp is actually used by the userspace.
*
* The condition is constructed such that a NOP is generated when
* sched_uclamp_used is disabled.
*/
if (!static_branch_unlikely(&sched_uclamp_used))
return;
if (unlikely(!p->sched_class->uclamp_enabled))
return;
for_each_clamp_id(clamp_id)
uclamp_rq_dec_id(rq, p, clamp_id);
}
static inline void
uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
{
struct rq_flags rf;
struct rq *rq;
/*
* Lock the task and the rq where the task is (or was) queued.
*
* We might lock the (previous) rq of a !RUNNABLE task, but that's the
* price to pay to safely serialize util_{min,max} updates with
* enqueues, dequeues and migration operations.
* This is the same locking schema used by __set_cpus_allowed_ptr().
*/
rq = task_rq_lock(p, &rf);
/*
* Setting the clamp bucket is serialized by task_rq_lock().
* If the task is not yet RUNNABLE and its task_struct is not
* affecting a valid clamp bucket, the next time it's enqueued,
* it will already see the updated clamp bucket value.
*/
if (p->uclamp[clamp_id].active) {
uclamp_rq_dec_id(rq, p, clamp_id);
uclamp_rq_inc_id(rq, p, clamp_id);
}
task_rq_unlock(rq, p, &rf);
}
#ifdef CONFIG_UCLAMP_TASK_GROUP
static inline void
uclamp_update_active_tasks(struct cgroup_subsys_state *css,
unsigned int clamps)
{
enum uclamp_id clamp_id;
struct css_task_iter it;
struct task_struct *p;
css_task_iter_start(css, 0, &it);
while ((p = css_task_iter_next(&it))) {
for_each_clamp_id(clamp_id) {
if ((0x1 << clamp_id) & clamps)
uclamp_update_active(p, clamp_id);
}
}
css_task_iter_end(&it);
}
static void cpu_util_update_eff(struct cgroup_subsys_state *css);
static void uclamp_update_root_tg(void)
{
struct task_group *tg = &root_task_group;
uclamp_se_set(&tg->uclamp_req[UCLAMP_MIN],
sysctl_sched_uclamp_util_min, false);
uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX],
sysctl_sched_uclamp_util_max, false);
rcu_read_lock();
cpu_util_update_eff(&root_task_group.css);
rcu_read_unlock();
}
#else
static void uclamp_update_root_tg(void) { }
#endif
int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
bool update_root_tg = false;
int old_min, old_max, old_min_rt;
int result;
mutex_lock(&uclamp_mutex);
old_min = sysctl_sched_uclamp_util_min;
old_max = sysctl_sched_uclamp_util_max;
old_min_rt = sysctl_sched_uclamp_util_min_rt_default;
result = proc_dointvec(table, write, buffer, lenp, ppos);
if (result)
goto undo;
if (!write)
goto done;
if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE ||
sysctl_sched_uclamp_util_min_rt_default > SCHED_CAPACITY_SCALE) {
result = -EINVAL;
goto undo;
}
if (old_min != sysctl_sched_uclamp_util_min) {
uclamp_se_set(&uclamp_default[UCLAMP_MIN],
sysctl_sched_uclamp_util_min, false);
update_root_tg = true;
}
if (old_max != sysctl_sched_uclamp_util_max) {
uclamp_se_set(&uclamp_default[UCLAMP_MAX],
sysctl_sched_uclamp_util_max, false);
update_root_tg = true;
}
if (update_root_tg) {
static_branch_enable(&sched_uclamp_used);
uclamp_update_root_tg();
}
if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) {
static_branch_enable(&sched_uclamp_used);
uclamp_sync_util_min_rt_default();
}
/*
* We update all RUNNABLE tasks only when task groups are in use.
* Otherwise, keep it simple and do just a lazy update at each next
* task enqueue time.
*/
goto done;
undo:
sysctl_sched_uclamp_util_min = old_min;
sysctl_sched_uclamp_util_max = old_max;
sysctl_sched_uclamp_util_min_rt_default = old_min_rt;
done:
mutex_unlock(&uclamp_mutex);
return result;
}
static int uclamp_validate(struct task_struct *p,
const struct sched_attr *attr)
{
int util_min = p->uclamp_req[UCLAMP_MIN].value;
int util_max = p->uclamp_req[UCLAMP_MAX].value;
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
util_min = attr->sched_util_min;
if (util_min + 1 > SCHED_CAPACITY_SCALE + 1)
return -EINVAL;
}
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
util_max = attr->sched_util_max;
if (util_max + 1 > SCHED_CAPACITY_SCALE + 1)
return -EINVAL;
}
if (util_min != -1 && util_max != -1 && util_min > util_max)
return -EINVAL;
/*
* We have valid uclamp attributes; make sure uclamp is enabled.
*
* We need to do that here, because enabling static branches is a
* blocking operation which obviously cannot be done while holding
* scheduler locks.
*/
static_branch_enable(&sched_uclamp_used);
return 0;
}
static bool uclamp_reset(const struct sched_attr *attr,
enum uclamp_id clamp_id,
struct uclamp_se *uc_se)
{
/* Reset on sched class change for a non user-defined clamp value. */
if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)) &&
!uc_se->user_defined)
return true;
/* Reset on sched_util_{min,max} == -1. */
if (clamp_id == UCLAMP_MIN &&
attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN &&
attr->sched_util_min == -1) {
return true;
}
if (clamp_id == UCLAMP_MAX &&
attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX &&
attr->sched_util_max == -1) {
return true;
}
return false;
}
static void __setscheduler_uclamp(struct task_struct *p,
const struct sched_attr *attr)
{
enum uclamp_id clamp_id;
for_each_clamp_id(clamp_id) {
struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
unsigned int value;
if (!uclamp_reset(attr, clamp_id, uc_se))
continue;
/*
* RT by default have a 100% boost value that could be modified
* at runtime.
*/
if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
value = sysctl_sched_uclamp_util_min_rt_default;
else
value = uclamp_none(clamp_id);
uclamp_se_set(uc_se, value, false);
}
if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
return;
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN &&
attr->sched_util_min != -1) {
uclamp_se_set(&p->uclamp_req[UCLAMP_MIN],
attr->sched_util_min, true);
}
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX &&
attr->sched_util_max != -1) {
uclamp_se_set(&p->uclamp_req[UCLAMP_MAX],
attr->sched_util_max, true);
}
}
static void uclamp_fork(struct task_struct *p)
{
enum uclamp_id clamp_id;
/*
* We don't need to hold task_rq_lock() when updating p->uclamp_* here
* as the task is still at its early fork stages.
*/
for_each_clamp_id(clamp_id)
p->uclamp[clamp_id].active = false;
if (likely(!p->sched_reset_on_fork))
return;
for_each_clamp_id(clamp_id) {
uclamp_se_set(&p->uclamp_req[clamp_id],
uclamp_none(clamp_id), false);
}
}
static void uclamp_post_fork(struct task_struct *p)
{
uclamp_update_util_min_rt_default(p);
}
static void __init init_uclamp_rq(struct rq *rq)
{
enum uclamp_id clamp_id;
struct uclamp_rq *uc_rq = rq->uclamp;
for_each_clamp_id(clamp_id) {
uc_rq[clamp_id] = (struct uclamp_rq) {
.value = uclamp_none(clamp_id)
};
}
rq->uclamp_flags = 0;
}
static void __init init_uclamp(void)
{
struct uclamp_se uc_max = {};
enum uclamp_id clamp_id;
int cpu;
for_each_possible_cpu(cpu)
init_uclamp_rq(cpu_rq(cpu));
for_each_clamp_id(clamp_id) {
uclamp_se_set(&init_task.uclamp_req[clamp_id],
uclamp_none(clamp_id), false);
}
/* System defaults allow max clamp values for both indexes */
uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX), false);
for_each_clamp_id(clamp_id) {
uclamp_default[clamp_id] = uc_max;
#ifdef CONFIG_UCLAMP_TASK_GROUP
root_task_group.uclamp_req[clamp_id] = uc_max;
root_task_group.uclamp[clamp_id] = uc_max;
#endif
}
}
#else /* CONFIG_UCLAMP_TASK */
static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { }
static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { }
static inline int uclamp_validate(struct task_struct *p,
const struct sched_attr *attr)
{
return -EOPNOTSUPP;
}
static void __setscheduler_uclamp(struct task_struct *p,
const struct sched_attr *attr) { }
static inline void uclamp_fork(struct task_struct *p) { }
static inline void uclamp_post_fork(struct task_struct *p) { }
static inline void init_uclamp(void) { }
#endif /* CONFIG_UCLAMP_TASK */
static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
if (!(flags & ENQUEUE_NOCLOCK))
update_rq_clock(rq);
if (!(flags & ENQUEUE_RESTORE)) {
sched_info_queued(rq, p);
psi_enqueue(p, flags & ENQUEUE_WAKEUP);
}
uclamp_rq_inc(rq, p);
p->sched_class->enqueue_task(rq, p, flags);
}
static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
if (!(flags & DEQUEUE_NOCLOCK))
update_rq_clock(rq);
if (!(flags & DEQUEUE_SAVE)) {
sched_info_dequeued(rq, p);
psi_dequeue(p, flags & DEQUEUE_SLEEP);
}
uclamp_rq_dec(rq, p);
p->sched_class->dequeue_task(rq, p, flags);
}
void activate_task(struct rq *rq, struct task_struct *p, int flags)
{
enqueue_task(rq, p, flags);
p->on_rq = TASK_ON_RQ_QUEUED;
}
void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{
p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
dequeue_task(rq, p, flags);
}
/*
* __normal_prio - return the priority that is based on the static prio
*/
static inline int __normal_prio(struct task_struct *p)
{
return p->static_prio;
}
/*
* Calculate the expected normal priority: i.e. priority
* without taking RT-inheritance into account. Might be
* boosted by interactivity modifiers. Changes upon fork,
* setprio syscalls, and whenever the interactivity
* estimator recalculates.
*/
static inline int normal_prio(struct task_struct *p)
{
int prio;
if (task_has_dl_policy(p))
prio = MAX_DL_PRIO-1;
else if (task_has_rt_policy(p))
prio = MAX_RT_PRIO-1 - p->rt_priority;
else
prio = __normal_prio(p);
return prio;
}
/*
* Calculate the current priority, i.e. the priority
* taken into account by the scheduler. This value might
* be boosted by RT tasks, or might be boosted by
* interactivity modifiers. Will be RT if the task got
* RT-boosted. If not then it returns p->normal_prio.
*/
static int effective_prio(struct task_struct *p)
{
p->normal_prio = normal_prio(p);
/*
* If we are RT tasks or we were boosted to RT priority,
* keep the priority unchanged. Otherwise, update priority
* to the normal priority:
*/
if (!rt_prio(p->prio))
return p->normal_prio;
return p->prio;
}
/**
* task_curr - is this task currently executing on a CPU?
* @p: the task in question.
*
* Return: 1 if the task is currently executing. 0 otherwise.
*/
inline int task_curr(const struct task_struct *p)
{
return cpu_curr(task_cpu(p)) == p;
}
/*
* switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
* use the balance_callback list if you want balancing.
*
* this means any call to check_class_changed() must be followed by a call to
* balance_callback().
*/
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
const struct sched_class *prev_class,
int oldprio)
{
if (prev_class != p->sched_class) {
if (prev_class->switched_from)
prev_class->switched_from(rq, p);
p->sched_class->switched_to(rq, p);
} else if (oldprio != p->prio || dl_task(p))
p->sched_class->prio_changed(rq, p, oldprio);
}
void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
{
if (p->sched_class == rq->curr->sched_class)
rq->curr->sched_class->check_preempt_curr(rq, p, flags);
else if (p->sched_class > rq->curr->sched_class)
resched_curr(rq);
/*
* A queue event has occurred, and we're going to schedule. In
* this case, we can save a useless back to back clock update.
*/
if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr))
rq_clock_skip_update(rq);
}
#ifdef CONFIG_SMP
static void
__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
static int __set_cpus_allowed_ptr(struct task_struct *p,
const struct cpumask *new_mask,
u32 flags);
static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
{
if (likely(!p->migration_disabled))
return;
if (p->cpus_ptr != &p->cpus_mask)
return;
/*
* Violates locking rules! see comment in __do_set_cpus_allowed().
*/
__do_set_cpus_allowed(p, cpumask_of(rq->cpu), SCA_MIGRATE_DISABLE);
}
void migrate_disable(void)
{
struct task_struct *p = current;
if (p->migration_disabled) {
p->migration_disabled++;
return;
}
preempt_disable();
this_rq()->nr_pinned++;
p->migration_disabled = 1;
preempt_enable();
}
EXPORT_SYMBOL_GPL(migrate_disable);
void migrate_enable(void)
{
struct task_struct *p = current;
if (p->migration_disabled > 1) {
p->migration_disabled--;
return;
}
/*
* Ensure stop_task runs either before or after this, and that
* __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
*/
preempt_disable();
if (p->cpus_ptr != &p->cpus_mask)
__set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE);
/*
* Mustn't clear migration_disabled() until cpus_ptr points back at the
* regular cpus_mask, otherwise things that race (eg.
* select_fallback_rq) get confused.
*/
barrier();
p->migration_disabled = 0;
this_rq()->nr_pinned--;
preempt_enable();
}
EXPORT_SYMBOL_GPL(migrate_enable);
static inline bool rq_has_pinned_tasks(struct rq *rq)
{
return rq->nr_pinned;
}
/*
* Per-CPU kthreads are allowed to run on !active && online CPUs, see
* __set_cpus_allowed_ptr() and select_fallback_rq().
*/
static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
{
/* When not in the task's cpumask, no point in looking further. */
if (!cpumask_test_cpu(cpu, p->cpus_ptr))
return false;
/* migrate_disabled() must be allowed to finish. */
if (is_migration_disabled(p))
return cpu_online(cpu);
/* Non kernel threads are not allowed during either online or offline. */
if (!(p->flags & PF_KTHREAD))
return cpu_active(cpu);
/* KTHREAD_IS_PER_CPU is always allowed. */
if (kthread_is_per_cpu(p))
return cpu_online(cpu);
/* Regular kernel threads don't get to stay during offline. */
if (cpu_dying(cpu))
return false;
/* But are allowed during online. */
return cpu_online(cpu);
}
/*
* This is how migration works:
*
* 1) we invoke migration_cpu_stop() on the target CPU using
* stop_one_cpu().
* 2) stopper starts to run (implicitly forcing the migrated thread
* off the CPU)
* 3) it checks whether the migrated task is still in the wrong runqueue.
* 4) if it's in the wrong runqueue then the migration thread removes
* it and puts it into the right queue.
* 5) stopper completes and stop_one_cpu() returns and the migration
* is done.
*/
/*
* move_queued_task - move a queued task to new rq.
*
* Returns (locked) new rq. Old rq's lock is released.
*/
static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
struct task_struct *p, int new_cpu)
{
lockdep_assert_held(&rq->lock);
deactivate_task(rq, p, DEQUEUE_NOCLOCK);
set_task_cpu(p, new_cpu);
rq_unlock(rq, rf);
rq = cpu_rq(new_cpu);
rq_lock(rq, rf);
BUG_ON(task_cpu(p) != new_cpu);
activate_task(rq, p, 0);
check_preempt_curr(rq, p, 0);
return rq;
}
struct migration_arg {
struct task_struct *task;
int dest_cpu;
struct set_affinity_pending *pending;
};
/*
* @refs: number of wait_for_completion()
* @stop_pending: is @stop_work in use
*/
struct set_affinity_pending {
refcount_t refs;
unsigned int stop_pending;
struct completion done;
struct cpu_stop_work stop_work;
struct migration_arg arg;
};
/*
* Move (not current) task off this CPU, onto the destination CPU. We're doing
* this because either it can't run here any more (set_cpus_allowed()
* away from this CPU, or CPU going down), or because we're
* attempting to rebalance this task on exec (sched_exec).
*
* So we race with normal scheduler movements, but that's OK, as long
* as the task is no longer on this CPU.
*/
static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
struct task_struct *p, int dest_cpu)
{
/* Affinity changed (again). */
if (!is_cpu_allowed(p, dest_cpu))
return rq;
update_rq_clock(rq);
rq = move_queued_task(rq, rf, p, dest_cpu);
return rq;
}
/*
* migration_cpu_stop - this will be executed by a highprio stopper thread
* and performs thread migration by bumping thread off CPU then
* 'pushing' onto another runqueue.
*/
static int migration_cpu_stop(void *data)
{
struct migration_arg *arg = data;
struct set_affinity_pending *pending = arg->pending;
struct task_struct *p = arg->task;
int dest_cpu = arg->dest_cpu;
struct rq *rq = this_rq();
bool complete = false;
struct rq_flags rf;
/*
* The original target CPU might have gone down and we might
* be on another CPU but it doesn't matter.
*/
local_irq_save(rf.flags);
/*
* We need to explicitly wake pending tasks before running
* __migrate_task() such that we will not miss enforcing cpus_ptr
* during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
*/
flush_smp_call_function_from_idle();
raw_spin_lock(&p->pi_lock);
rq_lock(rq, &rf);
/*
* If we were passed a pending, then ->stop_pending was set, thus
* p->migration_pending must have remained stable.
*/
WARN_ON_ONCE(pending && pending != p->migration_pending);
/*
* If task_rq(p) != rq, it cannot be migrated here, because we're
* holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
* we're holding p->pi_lock.
*/
if (task_rq(p) == rq) {
if (is_migration_disabled(p))
goto out;
if (pending) {
p->migration_pending = NULL;
complete = true;
}
if (dest_cpu < 0) {
if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask))
goto out;
dest_cpu = cpumask_any_distribute(&p->cpus_mask);
}
if (task_on_rq_queued(p))
rq = __migrate_task(rq, &rf, p, dest_cpu);
else
p->wake_cpu = dest_cpu;
/*
* XXX __migrate_task() can fail, at which point we might end
* up running on a dodgy CPU, AFAICT this can only happen
* during CPU hotplug, at which point we'll get pushed out
* anyway, so it's probably not a big deal.
*/
} else if (pending) {
/*
* This happens when we get migrated between migrate_enable()'s
* preempt_enable() and scheduling the stopper task. At that
* point we're a regular task again and not current anymore.
*
* A !PREEMPT kernel has a giant hole here, which makes it far
* more likely.
*/
/*
* The task moved before the stopper got to run. We're holding
* ->pi_lock, so the allowed mask is stable - if it got
* somewhere allowed, we're done.
*/
if (cpumask_test_cpu(task_cpu(p), p->cpus_ptr)) {
p->migration_pending = NULL;
complete = true;
goto out;
}
/*
* When migrate_enable() hits a rq mis-match we can't reliably
* determine is_migration_disabled() and so have to chase after
* it.
*/
WARN_ON_ONCE(!pending->stop_pending);
task_rq_unlock(rq, p, &rf);
stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
&pending->arg, &pending->stop_work);
return 0;
}
out:
if (pending)
pending->stop_pending = false;
task_rq_unlock(rq, p, &rf);
if (complete)
complete_all(&pending->done);
return 0;
}
int push_cpu_stop(void *arg)
{
struct rq *lowest_rq = NULL, *rq = this_rq();
struct task_struct *p = arg;
raw_spin_lock_irq(&p->pi_lock);
raw_spin_lock(&rq->lock);
if (task_rq(p) != rq)
goto out_unlock;
if (is_migration_disabled(p)) {
p->migration_flags |= MDF_PUSH;
goto out_unlock;
}
p->migration_flags &= ~MDF_PUSH;
if (p->sched_class->find_lock_rq)
lowest_rq = p->sched_class->find_lock_rq(p, rq);
if (!lowest_rq)
goto out_unlock;
// XXX validate p is still the highest prio task
if (task_rq(p) == rq) {
deactivate_task(rq, p, 0);
set_task_cpu(p, lowest_rq->cpu);
activate_task(lowest_rq, p, 0);
resched_curr(lowest_rq);
}
double_unlock_balance(rq, lowest_rq);
out_unlock:
rq->push_busy = false;
raw_spin_unlock(&rq->lock);
raw_spin_unlock_irq(&p->pi_lock);
put_task_struct(p);
return 0;
}
/*
* sched_class::set_cpus_allowed must do the below, but is not required to
* actually call this function.
*/
void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
{
if (flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) {
p->cpus_ptr = new_mask;
return;
}
cpumask_copy(&p->cpus_mask, new_mask);
p->nr_cpus_allowed = cpumask_weight(new_mask);
}
static void
__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
{
struct rq *rq = task_rq(p);
bool queued, running;
/*
* This here violates the locking rules for affinity, since we're only
* supposed to change these variables while holding both rq->lock and
* p->pi_lock.
*
* HOWEVER, it magically works, because ttwu() is the only code that
* accesses these variables under p->pi_lock and only does so after
* smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
* before finish_task().
*
* XXX do further audits, this smells like something putrid.
*/
if (flags & SCA_MIGRATE_DISABLE)
SCHED_WARN_ON(!p->on_cpu);
else
lockdep_assert_held(&p->pi_lock);
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued) {
/*
* Because __kthread_bind() calls this on blocked tasks without
* holding rq->lock.
*/
lockdep_assert_held(&rq->lock);
dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
}
if (running)
put_prev_task(rq, p);
p->sched_class->set_cpus_allowed(p, new_mask, flags);
if (queued)
enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
if (running)
set_next_task(rq, p);
}
void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{
__do_set_cpus_allowed(p, new_mask, 0);
}
/*
* This function is wildly self concurrent; here be dragons.
*
*
* When given a valid mask, __set_cpus_allowed_ptr() must block until the
* designated task is enqueued on an allowed CPU. If that task is currently
* running, we have to kick it out using the CPU stopper.
*
* Migrate-Disable comes along and tramples all over our nice sandcastle.
* Consider:
*
* Initial conditions: P0->cpus_mask = [0, 1]
*
* P0@CPU0 P1
*
* migrate_disable();
* <preempted>
* set_cpus_allowed_ptr(P0, [1]);
*
* P1 *cannot* return from this set_cpus_allowed_ptr() call until P0 executes
* its outermost migrate_enable() (i.e. it exits its Migrate-Disable region).
* This means we need the following scheme:
*
* P0@CPU0 P1
*
* migrate_disable();
* <preempted>
* set_cpus_allowed_ptr(P0, [1]);
* <blocks>
* <resumes>
* migrate_enable();
* __set_cpus_allowed_ptr();
* <wakes local stopper>
* `--> <woken on migration completion>
*
* Now the fun stuff: there may be several P1-like tasks, i.e. multiple
* concurrent set_cpus_allowed_ptr(P0, [*]) calls. CPU affinity changes of any
* task p are serialized by p->pi_lock, which we can leverage: the one that
* should come into effect at the end of the Migrate-Disable region is the last
* one. This means we only need to track a single cpumask (i.e. p->cpus_mask),
* but we still need to properly signal those waiting tasks at the appropriate
* moment.
*
* This is implemented using struct set_affinity_pending. The first
* __set_cpus_allowed_ptr() caller within a given Migrate-Disable region will
* setup an instance of that struct and install it on the targeted task_struct.
* Any and all further callers will reuse that instance. Those then wait for
* a completion signaled at the tail of the CPU stopper callback (1), triggered
* on the end of the Migrate-Disable region (i.e. outermost migrate_enable()).
*
*
* (1) In the cases covered above. There is one more where the completion is
* signaled within affine_move_task() itself: when a subsequent affinity request
* occurs after the stopper bailed out due to the targeted task still being
* Migrate-Disable. Consider:
*
* Initial conditions: P0->cpus_mask = [0, 1]
*
* CPU0 P1 P2
* <P0>
* migrate_disable();
* <preempted>
* set_cpus_allowed_ptr(P0, [1]);
* <blocks>
* <migration/0>
* migration_cpu_stop()
* is_migration_disabled()
* <bails>
* set_cpus_allowed_ptr(P0, [0, 1]);
* <signal completion>
* <awakes>
*
* Note that the above is safe vs a concurrent migrate_enable(), as any
* pending affinity completion is preceded by an uninstallation of
* p->migration_pending done with p->pi_lock held.
*/
static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flags *rf,
int dest_cpu, unsigned int flags)
{
struct set_affinity_pending my_pending = { }, *pending = NULL;
bool stop_pending, complete = false;
/* Can the task run on the task's current CPU? If so, we're done */
if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
struct task_struct *push_task = NULL;
if ((flags & SCA_MIGRATE_ENABLE) &&
(p->migration_flags & MDF_PUSH) && !rq->push_busy) {
rq->push_busy = true;
push_task = get_task_struct(p);
}
/*
* If there are pending waiters, but no pending stop_work,
* then complete now.
*/
pending = p->migration_pending;
if (pending && !pending->stop_pending) {
p->migration_pending = NULL;
complete = true;
}
task_rq_unlock(rq, p, rf);
if (push_task) {
stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
p, &rq->push_work);
}
if (complete)
complete_all(&pending->done);
return 0;
}
if (!(flags & SCA_MIGRATE_ENABLE)) {
/* serialized by p->pi_lock */
if (!p->migration_pending) {
/* Install the request */
refcount_set(&my_pending.refs, 1);
init_completion(&my_pending.done);
my_pending.arg = (struct migration_arg) {
.task = p,
.dest_cpu = -1, /* any */
.pending = &my_pending,
};
p->migration_pending = &my_pending;
} else {
pending = p->migration_pending;
refcount_inc(&pending->refs);
}
}
pending = p->migration_pending;
/*
* - !MIGRATE_ENABLE:
* we'll have installed a pending if there wasn't one already.
*
* - MIGRATE_ENABLE:
* we're here because the current CPU isn't matching anymore,
* the only way that can happen is because of a concurrent
* set_cpus_allowed_ptr() call, which should then still be
* pending completion.
*
* Either way, we really should have a @pending here.
*/
if (WARN_ON_ONCE(!pending)) {
task_rq_unlock(rq, p, rf);
return -EINVAL;
}
if (task_running(rq, p) || p->state == TASK_WAKING) {
/*
* MIGRATE_ENABLE gets here because 'p == current', but for
* anything else we cannot do is_migration_disabled(), punt
* and have the stopper function handle it all race-free.
*/
stop_pending = pending->stop_pending;
if (!stop_pending)
pending->stop_pending = true;
if (flags & SCA_MIGRATE_ENABLE)
p->migration_flags &= ~MDF_PUSH;
task_rq_unlock(rq, p, rf);
if (!stop_pending) {
stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
&pending->arg, &pending->stop_work);
}
if (flags & SCA_MIGRATE_ENABLE)
return 0;
} else {
if (!is_migration_disabled(p)) {
if (task_on_rq_queued(p))
rq = move_queued_task(rq, rf, p, dest_cpu);
if (!pending->stop_pending) {
p->migration_pending = NULL;
complete = true;
}
}
task_rq_unlock(rq, p, rf);
if (complete)
complete_all(&pending->done);
}
wait_for_completion(&pending->done);
if (refcount_dec_and_test(&pending->refs))
wake_up_var(&pending->refs); /* No UaF, just an address */
/*
* Block the original owner of &pending until all subsequent callers
* have seen the completion and decremented the refcount
*/
wait_var_event(&my_pending.refs, !refcount_read(&my_pending.refs));
/* ARGH */
WARN_ON_ONCE(my_pending.stop_pending);
return 0;
}
/*
* Change a given task's CPU affinity. Migrate the thread to a
* proper CPU and schedule it away if the CPU it's executing on
* is removed from the allowed bitmask.
*
* NOTE: the caller must have a valid reference to the task, the
* task must not exit() & deallocate itself prematurely. The
* call is not atomic; no spinlocks may be held.
*/
static int __set_cpus_allowed_ptr(struct task_struct *p,
const struct cpumask *new_mask,
u32 flags)
{
const struct cpumask *cpu_valid_mask = cpu_active_mask;
unsigned int dest_cpu;
struct rq_flags rf;
struct rq *rq;
int ret = 0;
rq = task_rq_lock(p, &rf);
update_rq_clock(rq);
if (p->flags & PF_KTHREAD || is_migration_disabled(p)) {
/*
* Kernel threads are allowed on online && !active CPUs,
* however, during cpu-hot-unplug, even these might get pushed
* away if not KTHREAD_IS_PER_CPU.
*
* Specifically, migration_disabled() tasks must not fail the
* cpumask_any_and_distribute() pick below, esp. so on
* SCA_MIGRATE_ENABLE, otherwise we'll not call
* set_cpus_allowed_common() and actually reset p->cpus_ptr.
*/
cpu_valid_mask = cpu_online_mask;
}
/*
* Must re-check here, to close a race against __kthread_bind(),
* sched_setaffinity() is not guaranteed to observe the flag.
*/
if ((flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
ret = -EINVAL;
goto out;
}
if (!(flags & SCA_MIGRATE_ENABLE)) {
if (cpumask_equal(&p->cpus_mask, new_mask))
goto out;
if (WARN_ON_ONCE(p == current &&
is_migration_disabled(p) &&
!cpumask_test_cpu(task_cpu(p), new_mask))) {
ret = -EBUSY;
goto out;
}
}
/*
* Picking a ~random cpu helps in cases where we are changing affinity
* for groups of tasks (ie. cpuset), so that load balancing is not
* immediately required to distribute the tasks within their new mask.
*/
dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, new_mask);
if (dest_cpu >= nr_cpu_ids) {
ret = -EINVAL;
goto out;
}
__do_set_cpus_allowed(p, new_mask, flags);
return affine_move_task(rq, p, &rf, dest_cpu, flags);
out:
task_rq_unlock(rq, p, &rf);
return ret;
}
int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
{
return __set_cpus_allowed_ptr(p, new_mask, 0);
}
EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
#ifdef CONFIG_SCHED_DEBUG
/*
* We should never call set_task_cpu() on a blocked task,
* ttwu() will sort out the placement.
*/
WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
!p->on_rq);
/*
* Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING,
* because schedstat_wait_{start,end} rebase migrating task's wait_start
* time relying on p->on_rq.
*/
WARN_ON_ONCE(p->state == TASK_RUNNING &&
p->sched_class == &fair_sched_class &&
(p->on_rq && !task_on_rq_migrating(p)));
#ifdef CONFIG_LOCKDEP
/*
* The caller should hold either p->pi_lock or rq->lock, when changing
* a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
*
* sched_move_task() holds both and thus holding either pins the cgroup,
* see task_group().
*
* Furthermore, all task_rq users should acquire both locks, see
* task_rq_lock().
*/
WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
lockdep_is_held(&task_rq(p)->lock)));
#endif
/*
* Clearly, migrating tasks to offline CPUs is a fairly daft thing.
*/
WARN_ON_ONCE(!cpu_online(new_cpu));
WARN_ON_ONCE(is_migration_disabled(p));
#endif
trace_sched_migrate_task(p, new_cpu);
if (task_cpu(p) != new_cpu) {
if (p->sched_class->migrate_task_rq)
p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
rseq_migrate(p);
perf_event_task_migrate(p);
}
__set_task_cpu(p, new_cpu);
}
#ifdef CONFIG_NUMA_BALANCING
static void __migrate_swap_task(struct task_struct *p, int cpu)
{
if (task_on_rq_queued(p)) {
struct rq *src_rq, *dst_rq;
struct rq_flags srf, drf;
src_rq = task_rq(p);
dst_rq = cpu_rq(cpu);
rq_pin_lock(src_rq, &srf);
rq_pin_lock(dst_rq, &drf);
deactivate_task(src_rq, p, 0);
set_task_cpu(p, cpu);
activate_task(dst_rq, p, 0);
check_preempt_curr(dst_rq, p, 0);
rq_unpin_lock(dst_rq, &drf);
rq_unpin_lock(src_rq, &srf);
} else {
/*
* Task isn't running anymore; make it appear like we migrated
* it before it went to sleep. This means on wakeup we make the
* previous CPU our target instead of where it really is.
*/
p->wake_cpu = cpu;
}
}
struct migration_swap_arg {
struct task_struct *src_task, *dst_task;
int src_cpu, dst_cpu;
};
static int migrate_swap_stop(void *data)
{
struct migration_swap_arg *arg = data;
struct rq *src_rq, *dst_rq;
int ret = -EAGAIN;
if (!cpu_active(arg->src_cpu) || !cpu_active(arg->dst_cpu))
return -EAGAIN;
src_rq = cpu_rq(arg->src_cpu);
dst_rq = cpu_rq(arg->dst_cpu);
double_raw_lock(&arg->src_task->pi_lock,
&arg->dst_task->pi_lock);
double_rq_lock(src_rq, dst_rq);
if (task_cpu(arg->dst_task) != arg->dst_cpu)
goto unlock;
if (task_cpu(arg->src_task) != arg->src_cpu)
goto unlock;
if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr))
goto unlock;
if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr))
goto unlock;
__migrate_swap_task(arg->src_task, arg->dst_cpu);
__migrate_swap_task(arg->dst_task, arg->src_cpu);
ret = 0;
unlock:
double_rq_unlock(src_rq, dst_rq);
raw_spin_unlock(&arg->dst_task->pi_lock);
raw_spin_unlock(&arg->src_task->pi_lock);
return ret;
}
/*
* Cross migrate two tasks
*/
int migrate_swap(struct task_struct *cur, struct task_struct *p,
int target_cpu, int curr_cpu)
{
struct migration_swap_arg arg;
int ret = -EINVAL;
arg = (struct migration_swap_arg){
.src_task = cur,
.src_cpu = curr_cpu,
.dst_task = p,
.dst_cpu = target_cpu,
};
if (arg.src_cpu == arg.dst_cpu)
goto out;
/*
* These three tests are all lockless; this is OK since all of them
* will be re-checked with proper locks held further down the line.
*/
if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
goto out;
if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr))
goto out;
if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr))
goto out;
trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);
out:
return ret;
}
#endif /* CONFIG_NUMA_BALANCING */
/*
* wait_task_inactive - wait for a thread to unschedule.
*
* If @match_state is nonzero, it's the @p->state value just checked and
* not expected to change. If it changes, i.e. @p might have woken up,
* then return zero. When we succeed in waiting for @p to be off its CPU,
* we return a positive number (its total switch count). If a second call
* a short while later returns the same number, the caller can be sure that
* @p has remained unscheduled the whole time.
*
* The caller must ensure that the task *will* unschedule sometime soon,
* else this function might spin for a *long* time. This function can't
* be called with interrupts off, or it may introduce deadlock with
* smp_call_function() if an IPI is sent by the same process we are
* waiting to become inactive.
*/
unsigned long wait_task_inactive(struct task_struct *p, long match_state)
{
int running, queued;
struct rq_flags rf;
unsigned long ncsw;
struct rq *rq;
for (;;) {
/*
* We do the initial early heuristics without holding
* any task-queue locks at all. We'll only try to get
* the runqueue lock when things look like they will
* work out!
*/
rq = task_rq(p);
/*
* If the task is actively running on another CPU
* still, just relax and busy-wait without holding
* any locks.
*
* NOTE! Since we don't hold any locks, it's not
* even sure that "rq" stays as the right runqueue!
* But we don't care, since "task_running()" will
* return false if the runqueue has changed and p
* is actually now running somewhere else!
*/
while (task_running(rq, p)) {
if (match_state && unlikely(p->state != match_state))
return 0;
cpu_relax();
}
/*
* Ok, time to look more closely! We need the rq
* lock now, to be *sure*. If we're wrong, we'll
* just go back and repeat.
*/
rq = task_rq_lock(p, &rf);
trace_sched_wait_task(p);
running = task_running(rq, p);
queued = task_on_rq_queued(p);
ncsw = 0;
if (!match_state || p->state == match_state)
ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
task_rq_unlock(rq, p, &rf);
/*
* If it changed from the expected state, bail out now.
*/
if (unlikely(!ncsw))
break;
/*
* Was it really running after all now that we
* checked with the proper locks actually held?
*
* Oops. Go back and try again..
*/
if (unlikely(running)) {
cpu_relax();
continue;
}
/*
* It's not enough that it's not actively running,
* it must be off the runqueue _entirely_, and not
* preempted!
*
* So if it was still runnable (but just not actively
* running right now), it's preempted, and we should
* yield - it could be a while.
*/
if (unlikely(queued)) {
ktime_t to = NSEC_PER_SEC / HZ;
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_hrtimeout(&to, HRTIMER_MODE_REL);
continue;
}
/*
* Ahh, all good. It wasn't running, and it wasn't
* runnable, which means that it will never become
* running in the future either. We're all done!
*/
break;
}
return ncsw;
}
/***
* kick_process - kick a running thread to enter/exit the kernel
* @p: the to-be-kicked thread
*
* Cause a process which is running on another CPU to enter
* kernel-mode, without any delay. (to get signals handled.)
*
* NOTE: this function doesn't have to take the runqueue lock,
* because all it wants to ensure is that the remote task enters
* the kernel. If the IPI races and the task has been migrated
* to another CPU then no harm is done and the purpose has been
* achieved as well.
*/
void kick_process(struct task_struct *p)
{
int cpu;
preempt_disable();
cpu = task_cpu(p);
if ((cpu != smp_processor_id()) && task_curr(p))
smp_send_reschedule(cpu);
preempt_enable();
}
EXPORT_SYMBOL_GPL(kick_process);
/*
* ->cpus_ptr is protected by both rq->lock and p->pi_lock
*
* A few notes on cpu_active vs cpu_online:
*
* - cpu_active must be a subset of cpu_online
*
* - on CPU-up we allow per-CPU kthreads on the online && !active CPU,
* see __set_cpus_allowed_ptr(). At this point the newly online
* CPU isn't yet part of the sched domains, and balancing will not
* see it.
*
* - on CPU-down we clear cpu_active() to mask the sched domains and
* avoid the load balancer to place new tasks on the to be removed
* CPU. Existing tasks will remain running there and will be taken
* off.
*
* This means that fallback selection must not select !active CPUs.
* And can assume that any active CPU must be online. Conversely
* select_task_rq() below may allow selection of !active CPUs in order
* to satisfy the above rules.
*/
static int select_fallback_rq(int cpu, struct task_struct *p)
{
int nid = cpu_to_node(cpu);
const struct cpumask *nodemask = NULL;
enum { cpuset, possible, fail } state = cpuset;
int dest_cpu;
/*
* If the node that the CPU is on has been offlined, cpu_to_node()
* will return -1. There is no CPU on the node, and we should
* select the CPU on the other node.
*/
if (nid != -1) {
nodemask = cpumask_of_node(nid);
/* Look for allowed, online CPU in same node. */
for_each_cpu(dest_cpu, nodemask) {
if (!cpu_active(dest_cpu))
continue;
if (cpumask_test_cpu(dest_cpu, p->cpus_ptr))
return dest_cpu;
}
}
for (;;) {
/* Any allowed, online CPU? */
for_each_cpu(dest_cpu, p->cpus_ptr) {
if (!is_cpu_allowed(p, dest_cpu))
continue;
goto out;
}
/* No more Mr. Nice Guy. */
switch (state) {
case cpuset:
if (IS_ENABLED(CONFIG_CPUSETS)) {
cpuset_cpus_allowed_fallback(p);
state = possible;
break;
}
fallthrough;
case possible:
/*
* XXX When called from select_task_rq() we only
* hold p->pi_lock and again violate locking order.
*
* More yuck to audit.
*/
do_set_cpus_allowed(p, cpu_possible_mask);
state = fail;
break;
case fail:
BUG();
break;
}
}
out:
if (state != cpuset) {
/*
* Don't tell them about moving exiting tasks or
* kernel threads (both mm NULL), since they never
* leave kernel.
*/
if (p->mm && printk_ratelimit()) {
printk_deferred("process %d (%s) no longer affine to cpu%d\n",
task_pid_nr(p), p->comm, cpu);
}
}
return dest_cpu;
}
/*
* The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable.
*/
static inline
int select_task_rq(struct task_struct *p, int cpu, int wake_flags)
{
lockdep_assert_held(&p->pi_lock);
if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p))
cpu = p->sched_class->select_task_rq(p, cpu, wake_flags);
else
cpu = cpumask_any(p->cpus_ptr);
/*
* In order not to call set_task_cpu() on a blocking task we need
* to rely on ttwu() to place the task on a valid ->cpus_ptr
* CPU.
*
* Since this is common to all placement strategies, this lives here.
*
* [ this allows ->select_task() to simply return task_cpu(p) and
* not worry about this generic constraint ]
*/
if (unlikely(!is_cpu_allowed(p, cpu)))
cpu = select_fallback_rq(task_cpu(p), p);
return cpu;
}
void sched_set_stop_task(int cpu, struct task_struct *stop)
{
static struct lock_class_key stop_pi_lock;
struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
struct task_struct *old_stop = cpu_rq(cpu)->stop;
if (stop) {
/*
* Make it appear like a SCHED_FIFO task, its something
* userspace knows about and won't get confused about.
*
* Also, it will make PI more or less work without too
* much confusion -- but then, stop work should not
* rely on PI working anyway.
*/
sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m);
stop->sched_class = &stop_sched_class;
/*
* The PI code calls rt_mutex_setprio() with ->pi_lock held to
* adjust the effective priority of a task. As a result,
* rt_mutex_setprio() can trigger (RT) balancing operations,
* which can then trigger wakeups of the stop thread to push
* around the current task.
*
* The stop task itself will never be part of the PI-chain, it
* never blocks, therefore that ->pi_lock recursion is safe.
* Tell lockdep about this by placing the stop->pi_lock in its
* own class.
*/
lockdep_set_class(&stop->pi_lock, &stop_pi_lock);
}
cpu_rq(cpu)->stop = stop;
if (old_stop) {
/*
* Reset it back to a normal scheduling class so that
* it can die in pieces.
*/
old_stop->sched_class = &rt_sched_class;
}
}
#else /* CONFIG_SMP */
static inline int __set_cpus_allowed_ptr(struct task_struct *p,
const struct cpumask *new_mask,
u32 flags)
{
return set_cpus_allowed_ptr(p, new_mask);
}
static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { }
static inline bool rq_has_pinned_tasks(struct rq *rq)
{
return false;
}
#endif /* !CONFIG_SMP */
static void
ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
{
struct rq *rq;
if (!schedstat_enabled())
return;
rq = this_rq();
#ifdef CONFIG_SMP
if (cpu == rq->cpu) {
__schedstat_inc(rq->ttwu_local);
__schedstat_inc(p->se.statistics.nr_wakeups_local);
} else {
struct sched_domain *sd;
__schedstat_inc(p->se.statistics.nr_wakeups_remote);
rcu_read_lock();
for_each_domain(rq->cpu, sd) {
if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
__schedstat_inc(sd->ttwu_wake_remote);
break;
}
}
rcu_read_unlock();
}
if (wake_flags & WF_MIGRATED)
__schedstat_inc(p->se.statistics.nr_wakeups_migrate);
#endif /* CONFIG_SMP */
__schedstat_inc(rq->ttwu_count);
__schedstat_inc(p->se.statistics.nr_wakeups);
if (wake_flags & WF_SYNC)
__schedstat_inc(p->se.statistics.nr_wakeups_sync);
}
/*
* Mark the task runnable and perform wakeup-preemption.
*/
static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
struct rq_flags *rf)
{
check_preempt_curr(rq, p, wake_flags);
p->state = TASK_RUNNING;
trace_sched_wakeup(p);
#ifdef CONFIG_SMP
if (p->sched_class->task_woken) {
/*
* Our task @p is fully woken up and running; so it's safe to
* drop the rq->lock, hereafter rq is only used for statistics.
*/
rq_unpin_lock(rq, rf);
p->sched_class->task_woken(rq, p);
rq_repin_lock(rq, rf);
}
if (rq->idle_stamp) {
u64 delta = rq_clock(rq) - rq->idle_stamp;
u64 max = 2*rq->max_idle_balance_cost;
update_avg(&rq->avg_idle, delta);
if (rq->avg_idle > max)
rq->avg_idle = max;
rq->idle_stamp = 0;
}
#endif
}
static void
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
struct rq_flags *rf)
{
int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
lockdep_assert_held(&rq->lock);
if (p->sched_contributes_to_load)
rq->nr_uninterruptible--;
#ifdef CONFIG_SMP
if (wake_flags & WF_MIGRATED)
en_flags |= ENQUEUE_MIGRATED;
else
#endif
if (p->in_iowait) {
delayacct_blkio_end(p);
atomic_dec(&task_rq(p)->nr_iowait);
}
activate_task(rq, p, en_flags);
ttwu_do_wakeup(rq, p, wake_flags, rf);
}
/*
* Consider @p being inside a wait loop:
*
* for (;;) {
* set_current_state(TASK_UNINTERRUPTIBLE);
*
* if (CONDITION)
* break;
*
* schedule();
* }
* __set_current_state(TASK_RUNNING);
*
* between set_current_state() and schedule(). In this case @p is still
* runnable, so all that needs doing is change p->state back to TASK_RUNNING in
* an atomic manner.
*
* By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
* then schedule() must still happen and p->state can be changed to
* TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
* need to do a full wakeup with enqueue.
*
* Returns: %true when the wakeup is done,
* %false otherwise.
*/
static int ttwu_runnable(struct task_struct *p, int wake_flags)
{
struct rq_flags rf;
struct rq *rq;
int ret = 0;
rq = __task_rq_lock(p, &rf);
if (task_on_rq_queued(p)) {
/* check_preempt_curr() may use rq clock */
update_rq_clock(rq);
ttwu_do_wakeup(rq, p, wake_flags, &rf);
ret = 1;
}
__task_rq_unlock(rq, &rf);
return ret;
}
#ifdef CONFIG_SMP
void sched_ttwu_pending(void *arg)
{
struct llist_node *llist = arg;
struct rq *rq = this_rq();
struct task_struct *p, *t;
struct rq_flags rf;
if (!llist)
return;
/*
* rq::ttwu_pending racy indication of out-standing wakeups.
* Races such that false-negatives are possible, since they
* are shorter lived that false-positives would be.
*/
WRITE_ONCE(rq->ttwu_pending, 0);
rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
if (WARN_ON_ONCE(p->on_cpu))
smp_cond_load_acquire(&p->on_cpu, !VAL);
if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
set_task_cpu(p, cpu_of(rq));
ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
}
rq_unlock_irqrestore(rq, &rf);
}
void send_call_function_single_ipi(int cpu)
{
struct rq *rq = cpu_rq(cpu);
if (!set_nr_if_polling(rq->idle))
arch_send_call_function_single_ipi(cpu);
else
trace_sched_wake_idle_without_ipi(cpu);
}
/*
* Queue a task on the target CPUs wake_list and wake the CPU via IPI if
* necessary. The wakee CPU on receipt of the IPI will queue the task
* via sched_ttwu_wakeup() for activation so the wakee incurs the cost
* of the wakeup instead of the waker.
*/
static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
{
struct rq *rq = cpu_rq(cpu);
p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
WRITE_ONCE(rq->ttwu_pending, 1);
__smp_call_single_queue(cpu, &p->wake_entry.llist);
}
void wake_up_if_idle(int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct rq_flags rf;
rcu_read_lock();
if (!is_idle_task(rcu_dereference(rq->curr)))
goto out;
if (set_nr_if_polling(rq->idle)) {
trace_sched_wake_idle_without_ipi(cpu);
} else {
rq_lock_irqsave(rq, &rf);
if (is_idle_task(rq->curr))
smp_send_reschedule(cpu);
/* Else CPU is not idle, do nothing here: */
rq_unlock_irqrestore(rq, &rf);
}
out:
rcu_read_unlock();
}
bool cpus_share_cache(int this_cpu, int that_cpu)
{
return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}
static inline bool ttwu_queue_cond(int cpu, int wake_flags)
{
/*
* Do not complicate things with the async wake_list while the CPU is
* in hotplug state.
*/
if (!cpu_active(cpu))
return false;
/*
* If the CPU does not share cache, then queue the task on the
* remote rqs wakelist to avoid accessing remote data.
*/
if (!cpus_share_cache(smp_processor_id(), cpu))
return true;
/*
* If the task is descheduling and the only running task on the
* CPU then use the wakelist to offload the task activation to
* the soon-to-be-idle CPU as the current CPU is likely busy.
* nr_running is checked to avoid unnecessary task stacking.
*/
if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
return true;
return false;
}
static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
{
if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
if (WARN_ON_ONCE(cpu == smp_processor_id()))
return false;
sched_clock_cpu(cpu); /* Sync clocks across CPUs */
__ttwu_queue_wakelist(p, cpu, wake_flags);
return true;
}
return false;
}
#else /* !CONFIG_SMP */
static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
{
return false;
}
#endif /* CONFIG_SMP */
static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
{
struct rq *rq = cpu_rq(cpu);
struct rq_flags rf;
if (ttwu_queue_wakelist(p, cpu, wake_flags))
return;
rq_lock(rq, &rf);
update_rq_clock(rq);
ttwu_do_activate(rq, p, wake_flags, &rf);
rq_unlock(rq, &rf);
}
/*
* Notes on Program-Order guarantees on SMP systems.
*
* MIGRATION
*
* The basic program-order guarantee on SMP systems is that when a task [t]
* migrates, all its activity on its old CPU [c0] happens-before any subsequent
* execution on its new CPU [c1].
*
* For migration (of runnable tasks) this is provided by the following means:
*
* A) UNLOCK of the rq(c0)->lock scheduling out task t
* B) migration for t is required to synchronize *both* rq(c0)->lock and
* rq(c1)->lock (if not at the same time, then in that order).
* C) LOCK of the rq(c1)->lock scheduling in task
*
* Release/acquire chaining guarantees that B happens after A and C after B.
* Note: the CPU doing B need not be c0 or c1
*
* Example:
*
* CPU0 CPU1 CPU2
*
* LOCK rq(0)->lock
* sched-out X
* sched-in Y
* UNLOCK rq(0)->lock
*
* LOCK rq(0)->lock // orders against CPU0
* dequeue X
* UNLOCK rq(0)->lock
*
* LOCK rq(1)->lock
* enqueue X
* UNLOCK rq(1)->lock
*
* LOCK rq(1)->lock // orders against CPU2
* sched-out Z
* sched-in X
* UNLOCK rq(1)->lock
*
*
* BLOCKING -- aka. SLEEP + WAKEUP
*
* For blocking we (obviously) need to provide the same guarantee as for
* migration. However the means are completely different as there is no lock
* chain to provide order. Instead we do:
*
* 1) smp_store_release(X->on_cpu, 0) -- finish_task()
* 2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
*
* Example:
*
* CPU0 (schedule) CPU1 (try_to_wake_up) CPU2 (schedule)
*
* LOCK rq(0)->lock LOCK X->pi_lock
* dequeue X
* sched-out X
* smp_store_release(X->on_cpu, 0);
*
* smp_cond_load_acquire(&X->on_cpu, !VAL);
* X->state = WAKING
* set_task_cpu(X,2)
*
* LOCK rq(2)->lock
* enqueue X
* X->state = RUNNING
* UNLOCK rq(2)->lock
*
* LOCK rq(2)->lock // orders against CPU1
* sched-out Z
* sched-in X
* UNLOCK rq(2)->lock
*
* UNLOCK X->pi_lock
* UNLOCK rq(0)->lock
*
*
* However, for wakeups there is a second guarantee we must provide, namely we
* must ensure that CONDITION=1 done by the caller can not be reordered with
* accesses to the task state; see try_to_wake_up() and set_current_state().
*/
/**
* try_to_wake_up - wake up a thread
* @p: the thread to be awakened
* @state: the mask of task states that can be woken
* @wake_flags: wake modifier flags (WF_*)
*
* Conceptually does:
*
* If (@state & @p->state) @p->state = TASK_RUNNING.
*
* If the task was not queued/runnable, also place it back on a runqueue.
*
* This function is atomic against schedule() which would dequeue the task.
*
* It issues a full memory barrier before accessing @p->state, see the comment
* with set_current_state().
*
* Uses p->pi_lock to serialize against concurrent wake-ups.
*
* Relies on p->pi_lock stabilizing:
* - p->sched_class
* - p->cpus_ptr
* - p->sched_task_group
* in order to do migration, see its use of select_task_rq()/set_task_cpu().
*
* Tries really hard to only take one task_rq(p)->lock for performance.
* Takes rq->lock in:
* - ttwu_runnable() -- old rq, unavoidable, see comment there;
* - ttwu_queue() -- new rq, for enqueue of the task;
* - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
*
* As a consequence we race really badly with just about everything. See the
* many memory barriers and their comments for details.
*
* Return: %true if @p->state changes (an actual wakeup was done),
* %false otherwise.
*/
static int
try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
{
unsigned long flags;
int cpu, success = 0;
preempt_disable();
if (p == current) {
/*
* We're waking current, this means 'p->on_rq' and 'task_cpu(p)
* == smp_processor_id()'. Together this means we can special
* case the whole 'p->on_rq && ttwu_runnable()' case below
* without taking any locks.
*
* In particular:
* - we rely on Program-Order guarantees for all the ordering,
* - we're serialized against set_special_state() by virtue of
* it disabling IRQs (this allows not taking ->pi_lock).
*/
if (!(p->state & state))
goto out;
success = 1;
trace_sched_waking(p);
p->state = TASK_RUNNING;
trace_sched_wakeup(p);
goto out;
}
/*
* If we are going to wake up a thread waiting for CONDITION we
* need to ensure that CONDITION=1 done by the caller can not be
* reordered with p->state check below. This pairs with smp_store_mb()
* in set_current_state() that the waiting thread does.
*/
raw_spin_lock_irqsave(&p->pi_lock, flags);
smp_mb__after_spinlock();
if (!(p->state & state))
goto unlock;
trace_sched_waking(p);
/* We're going to change ->state: */
success = 1;
/*
* Ensure we load p->on_rq _after_ p->state, otherwise it would
* be possible to, falsely, observe p->on_rq == 0 and get stuck
* in smp_cond_load_acquire() below.
*
* sched_ttwu_pending() try_to_wake_up()
* STORE p->on_rq = 1 LOAD p->state
* UNLOCK rq->lock
*
* __schedule() (switch to task 'p')
* LOCK rq->lock smp_rmb();
* smp_mb__after_spinlock();
* UNLOCK rq->lock
*
* [task p]
* STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
*
* Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
* __schedule(). See the comment for smp_mb__after_spinlock().
*
* A similar smb_rmb() lives in try_invoke_on_locked_down_task().
*/
smp_rmb();
if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
goto unlock;
#ifdef CONFIG_SMP
/*
* Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
* possible to, falsely, observe p->on_cpu == 0.
*
* One must be running (->on_cpu == 1) in order to remove oneself
* from the runqueue.
*
* __schedule() (switch to task 'p') try_to_wake_up()
* STORE p->on_cpu = 1 LOAD p->on_rq
* UNLOCK rq->lock
*
* __schedule() (put 'p' to sleep)
* LOCK rq->lock smp_rmb();
* smp_mb__after_spinlock();
* STORE p->on_rq = 0 LOAD p->on_cpu
*
* Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
* __schedule(). See the comment for smp_mb__after_spinlock().
*
* Form a control-dep-acquire with p->on_rq == 0 above, to ensure
* schedule()'s deactivate_task() has 'happened' and p will no longer
* care about it's own p->state. See the comment in __schedule().
*/
smp_acquire__after_ctrl_dep();
/*
* We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
* == 0), which means we need to do an enqueue, change p->state to
* TASK_WAKING such that we can unlock p->pi_lock before doing the
* enqueue, such as ttwu_queue_wakelist().
*/
p->state = TASK_WAKING;
/*
* If the owning (remote) CPU is still in the middle of schedule() with
* this task as prev, considering queueing p on the remote CPUs wake_list
* which potentially sends an IPI instead of spinning on p->on_cpu to
* let the waker make forward progress. This is safe because IRQs are
* disabled and the IPI will deliver after on_cpu is cleared.
*
* Ensure we load task_cpu(p) after p->on_cpu:
*
* set_task_cpu(p, cpu);
* STORE p->cpu = @cpu
* __schedule() (switch to task 'p')
* LOCK rq->lock
* smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu)
* STORE p->on_cpu = 1 LOAD p->cpu
*
* to ensure we observe the correct CPU on which the task is currently
* scheduling.
*/
if (smp_load_acquire(&p->on_cpu) &&
ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
goto unlock;
/*
* If the owning (remote) CPU is still in the middle of schedule() with
* this task as prev, wait until it's done referencing the task.
*
* Pairs with the smp_store_release() in finish_task().
*
* This ensures that tasks getting woken will be fully ordered against
* their previous state and preserve Program Order.
*/
smp_cond_load_acquire(&p->on_cpu, !VAL);
cpu = select_task_rq(p, p->wake_cpu, wake_flags | WF_TTWU);
if (task_cpu(p) != cpu) {
if (p->in_iowait) {
delayacct_blkio_end(p);
atomic_dec(&task_rq(p)->nr_iowait);
}
wake_flags |= WF_MIGRATED;
psi_ttwu_dequeue(p);
set_task_cpu(p, cpu);
}
#else
cpu = task_cpu(p);
#endif /* CONFIG_SMP */
ttwu_queue(p, cpu, wake_flags);
unlock:
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
out:
if (success)
ttwu_stat(p, task_cpu(p), wake_flags);
preempt_enable();
return success;
}
/**
* try_invoke_on_locked_down_task - Invoke a function on task in fixed state
* @p: Process for which the function is to be invoked, can be @current.
* @func: Function to invoke.
* @arg: Argument to function.
*
* If the specified task can be quickly locked into a definite state
* (either sleeping or on a given runqueue), arrange to keep it in that
* state while invoking @func(@arg). This function can use ->on_rq and
* task_curr() to work out what the state is, if required. Given that
* @func can be invoked with a runqueue lock held, it had better be quite
* lightweight.
*
* Returns:
* @false if the task slipped out from under the locks.
* @true if the task was locked onto a runqueue or is sleeping.
* However, @func can override this by returning @false.
*/
bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg)
{
struct rq_flags rf;
bool ret = false;
struct rq *rq;
raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
if (p->on_rq) {
rq = __task_rq_lock(p, &rf);
if (task_rq(p) == rq)
ret = func(p, arg);
rq_unlock(rq, &rf);
} else {
switch (p->state) {
case TASK_RUNNING:
case TASK_WAKING:
break;
default:
smp_rmb(); // See smp_rmb() comment in try_to_wake_up().
if (!p->on_rq)
ret = func(p, arg);
}
}
raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
return ret;
}
/**
* wake_up_process - Wake up a specific process
* @p: The process to be woken up.
*
* Attempt to wake up the nominated process and move it to the set of runnable
* processes.
*
* Return: 1 if the process was woken up, 0 if it was already running.
*
* This function executes a full memory barrier before accessing the task state.
*/
int wake_up_process(struct task_struct *p)
{
return try_to_wake_up(p, TASK_NORMAL, 0);
}
EXPORT_SYMBOL(wake_up_process);
int wake_up_state(struct task_struct *p, unsigned int state)
{
return try_to_wake_up(p, state, 0);
}
/*
* Perform scheduler related setup for a newly forked process p.
* p is forked by current.
*
* __sched_fork() is basic setup used by init_idle() too:
*/
static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
{
p->on_rq = 0;
p->se.on_rq = 0;
p->se.exec_start = 0;
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
p->se.vruntime = 0;
INIT_LIST_HEAD(&p->se.group_node);
#ifdef CONFIG_FAIR_GROUP_SCHED
p->se.cfs_rq = NULL;
#endif
#ifdef CONFIG_SCHEDSTATS
/* Even if schedstat is disabled, there should not be garbage */
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif
RB_CLEAR_NODE(&p->dl.rb_node);
init_dl_task_timer(&p->dl);
init_dl_inactive_task_timer(&p->dl);
__dl_clear_params(p);
INIT_LIST_HEAD(&p->rt.run_list);
p->rt.timeout = 0;
p->rt.time_slice = sched_rr_timeslice;
p->rt.on_rq = 0;
p->rt.on_list = 0;
#ifdef CONFIG_PREEMPT_NOTIFIERS
INIT_HLIST_HEAD(&p->preempt_notifiers);
#endif
#ifdef CONFIG_COMPACTION
p->capture_control = NULL;
#endif
init_numa_balancing(clone_flags, p);
#ifdef CONFIG_SMP
p->wake_entry.u_flags = CSD_TYPE_TTWU;
p->migration_pending = NULL;
#endif
}
DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
#ifdef CONFIG_NUMA_BALANCING
void set_numabalancing_state(bool enabled)
{
if (enabled)
static_branch_enable(&sched_numa_balancing);
else
static_branch_disable(&sched_numa_balancing);
}
#ifdef CONFIG_PROC_SYSCTL
int sysctl_numa_balancing(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
int err;
int state = static_branch_likely(&sched_numa_balancing);
if (write && !capable(CAP_SYS_ADMIN))
return -EPERM;
t = *table;
t.data = &state;
err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
if (err < 0)
return err;
if (write)
set_numabalancing_state(state);
return err;
}
#endif
#endif
#ifdef CONFIG_SCHEDSTATS
DEFINE_STATIC_KEY_FALSE(sched_schedstats);
static bool __initdata __sched_schedstats = false;
static void set_schedstats(bool enabled)
{
if (enabled)
static_branch_enable(&sched_schedstats);
else
static_branch_disable(&sched_schedstats);
}
void force_schedstat_enabled(void)
{
if (!schedstat_enabled()) {
pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
static_branch_enable(&sched_schedstats);
}
}
static int __init setup_schedstats(char *str)
{
int ret = 0;
if (!str)
goto out;
/*
* This code is called before jump labels have been set up, so we can't
* change the static branch directly just yet. Instead set a temporary
* variable so init_schedstats() can do it later.
*/
if (!strcmp(str, "enable")) {
__sched_schedstats = true;
ret = 1;
} else if (!strcmp(str, "disable")) {
__sched_schedstats = false;
ret = 1;
}
out:
if (!ret)
pr_warn("Unable to parse schedstats=\n");
return ret;
}
__setup("schedstats=", setup_schedstats);
static void __init init_schedstats(void)
{
set_schedstats(__sched_schedstats);
}
#ifdef CONFIG_PROC_SYSCTL
int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
int err;
int state = static_branch_likely(&sched_schedstats);
if (write && !capable(CAP_SYS_ADMIN))
return -EPERM;
t = *table;
t.data = &state;
err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
if (err < 0)
return err;
if (write)
set_schedstats(state);
return err;
}
#endif /* CONFIG_PROC_SYSCTL */
#else /* !CONFIG_SCHEDSTATS */
static inline void init_schedstats(void) {}
#endif /* CONFIG_SCHEDSTATS */
/*
* fork()/clone()-time setup:
*/
int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
unsigned long flags;
__sched_fork(clone_flags, p);
/*
* We mark the process as NEW here. This guarantees that
* nobody will actually run it, and a signal or other external
* event cannot wake it up and insert it on the runqueue either.
*/
p->state = TASK_NEW;
/*
* Make sure we do not leak PI boosting priority to the child.
*/
p->prio = current->normal_prio;
uclamp_fork(p);
/*
* Revert to default priority/policy on fork if requested.
*/
if (unlikely(p->sched_reset_on_fork)) {
if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->policy = SCHED_NORMAL;
p->static_prio = NICE_TO_PRIO(0);
p->rt_priority = 0;
} else if (PRIO_TO_NICE(p->static_prio) < 0)
p->static_prio = NICE_TO_PRIO(0);
p->prio = p->normal_prio = __normal_prio(p);
set_load_weight(p, false);
/*
* We don't need the reset flag anymore after the fork. It has
* fulfilled its duty:
*/
p->sched_reset_on_fork = 0;
}
if (dl_prio(p->prio))
return -EAGAIN;
else if (rt_prio(p->prio))
p->sched_class = &rt_sched_class;
else
p->sched_class = &fair_sched_class;
init_entity_runnable_average(&p->se);
/*
* The child is not yet in the pid-hash so no cgroup attach races,
* and the cgroup is pinned to this child due to cgroup_fork()
* is ran before sched_fork().
*
* Silence PROVE_RCU.
*/
raw_spin_lock_irqsave(&p->pi_lock, flags);
rseq_migrate(p);
/*
* We're setting the CPU for the first time, we don't migrate,
* so use __set_task_cpu().
*/
__set_task_cpu(p, smp_processor_id());
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
#ifdef CONFIG_SCHED_INFO
if (likely(sched_info_on()))
memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP)
p->on_cpu = 0;
#endif
init_task_preempt_count(p);
#ifdef CONFIG_SMP
plist_node_init(&p->pushable_tasks, MAX_PRIO);
RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
return 0;
}
void sched_post_fork(struct task_struct *p)
{
uclamp_post_fork(p);
}
unsigned long to_ratio(u64 period, u64 runtime)
{
if (runtime == RUNTIME_INF)
return BW_UNIT;
/*
* Doing this here saves a lot of checks in all
* the calling paths, and returning zero seems
* safe for them anyway.
*/
if (period == 0)
return 0;
return div64_u64(runtime << BW_SHIFT, period);
}
/*
* wake_up_new_task - wake up a newly created task for the first time.
*
* This function will do some initial scheduler statistics housekeeping
* that must be done for every newly created context, then puts the task
* on the runqueue and wakes it.
*/
void wake_up_new_task(struct task_struct *p)
{
struct rq_flags rf;
struct rq *rq;
raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
/*
* Fork balancing, do it here and not earlier because:
* - cpus_ptr can change in the fork path
* - any previously selected CPU might disappear through hotplug
*
* Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
* as we're not fully set-up yet.
*/
p->recent_used_cpu = task_cpu(p);
rseq_migrate(p);
__set_task_cpu(p, select_task_rq(p, task_cpu(p), WF_FORK));
#endif
rq = __task_rq_lock(p, &rf);
update_rq_clock(rq);
post_init_entity_util_avg(p);
activate_task(rq, p, ENQUEUE_NOCLOCK);
trace_sched_wakeup_new(p);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
if (p->sched_class->task_woken) {
/*
* Nothing relies on rq->lock after this, so it's fine to
* drop it.
*/
rq_unpin_lock(rq, &rf);
p->sched_class->task_woken(rq, p);
rq_repin_lock(rq, &rf);
}
#endif
task_rq_unlock(rq, p, &rf);
}
#ifdef CONFIG_PREEMPT_NOTIFIERS
static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);
void preempt_notifier_inc(void)
{
static_branch_inc(&preempt_notifier_key);
}
EXPORT_SYMBOL_GPL(preempt_notifier_inc);
void preempt_notifier_dec(void)
{
static_branch_dec(&preempt_notifier_key);
}
EXPORT_SYMBOL_GPL(preempt_notifier_dec);
/**
* preempt_notifier_register - tell me when current is being preempted & rescheduled
* @notifier: notifier struct to register
*/
void preempt_notifier_register(struct preempt_notifier *notifier)
{
if (!static_branch_unlikely(&preempt_notifier_key))
WARN(1, "registering preempt_notifier while notifiers disabled\n");
hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
}
EXPORT_SYMBOL_GPL(preempt_notifier_register);
/**
* preempt_notifier_unregister - no longer interested in preemption notifications
* @notifier: notifier struct to unregister
*
* This is *not* safe to call from within a preemption notifier.
*/
void preempt_notifier_unregister(struct preempt_notifier *notifier)
{
hlist_del(¬ifier->link);
}
EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
struct preempt_notifier *notifier;
hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
notifier->ops->sched_in(notifier, raw_smp_processor_id());
}
static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
if (static_branch_unlikely(&preempt_notifier_key))
__fire_sched_in_preempt_notifiers(curr);
}
static void
__fire_sched_out_preempt_notifiers(struct task_struct *curr,
struct task_struct *next)
{
struct preempt_notifier *notifier;
hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
notifier->ops->sched_out(notifier, next);
}
static __always_inline void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
struct task_struct *next)
{
if (static_branch_unlikely(&preempt_notifier_key))
__fire_sched_out_preempt_notifiers(curr, next);
}
#else /* !CONFIG_PREEMPT_NOTIFIERS */
static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
}
static inline void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
struct task_struct *next)
{
}
#endif /* CONFIG_PREEMPT_NOTIFIERS */
static inline void prepare_task(struct task_struct *next)
{
#ifdef CONFIG_SMP
/*
* Claim the task as running, we do this before switching to it
* such that any running task will have this set.
*
* See the ttwu() WF_ON_CPU case and its ordering comment.
*/
WRITE_ONCE(next->on_cpu, 1);
#endif
}
static inline void finish_task(struct task_struct *prev)
{
#ifdef CONFIG_SMP
/*
* This must be the very last reference to @prev from this CPU. After
* p->on_cpu is cleared, the task can be moved to a different CPU. We
* must ensure this doesn't happen until the switch is completely
* finished.
*
* In particular, the load of prev->state in finish_task_switch() must
* happen before this.
*
* Pairs with the smp_cond_load_acquire() in try_to_wake_up().
*/
smp_store_release(&prev->on_cpu, 0);
#endif
}
#ifdef CONFIG_SMP
static void do_balance_callbacks(struct rq *rq, struct callback_head *head)
{
void (*func)(struct rq *rq);
struct callback_head *next;
lockdep_assert_held(&rq->lock);
while (head) {
func = (void (*)(struct rq *))head->func;
next = head->next;
head->next = NULL;
head = next;
func(rq);
}
}
static void balance_push(struct rq *rq);
struct callback_head balance_push_callback = {
.next = NULL,
.func = (void (*)(struct callback_head *))balance_push,
};
static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
{
struct callback_head *head = rq->balance_callback;
lockdep_assert_held(&rq->lock);
if (head)
rq->balance_callback = NULL;
return head;
}
static void __balance_callbacks(struct rq *rq)
{
do_balance_callbacks(rq, splice_balance_callbacks(rq));
}
static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
{
unsigned long flags;
if (unlikely(head)) {
raw_spin_lock_irqsave(&rq->lock, flags);
do_balance_callbacks(rq, head);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
}
#else
static inline void __balance_callbacks(struct rq *rq)
{
}
static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
{
return NULL;
}
static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
{
}
#endif
static inline void
prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
{
/*
* Since the runqueue lock will be released by the next
* task (which is an invalid locking op but in the case
* of the scheduler it's an obvious special-case), so we
* do an early lockdep release here:
*/
rq_unpin_lock(rq, rf);
spin_release(&rq->lock.dep_map, _THIS_IP_);
#ifdef CONFIG_DEBUG_SPINLOCK
/* this is a valid case when another task releases the spinlock */
rq->lock.owner = next;
#endif
}
static inline void finish_lock_switch(struct rq *rq)
{
/*
* If we are tracking spinlock dependencies then we have to
* fix up the runqueue lock - which gets 'carried over' from
* prev into current:
*/
spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
__balance_callbacks(rq);
raw_spin_unlock_irq(&rq->lock);
}
/*
* NOP if the arch has not defined these:
*/
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
#endif
#ifndef finish_arch_post_lock_switch
# define finish_arch_post_lock_switch() do { } while (0)
#endif
static inline void kmap_local_sched_out(void)
{
#ifdef CONFIG_KMAP_LOCAL
if (unlikely(current->kmap_ctrl.idx))
__kmap_local_sched_out();
#endif
}
static inline void kmap_local_sched_in(void)
{
#ifdef CONFIG_KMAP_LOCAL
if (unlikely(current->kmap_ctrl.idx))
__kmap_local_sched_in();
#endif
}
/**
* prepare_task_switch - prepare to switch tasks
* @rq: the runqueue preparing to switch
* @prev: the current task that is being switched out
* @next: the task we are going to switch to.
*
* This is called with the rq lock held and interrupts off. It must
* be paired with a subsequent finish_task_switch after the context
* switch.
*
* prepare_task_switch sets up locking and calls architecture specific
* hooks.
*/
static inline void
prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
kcov_prepare_switch(prev);
sched_info_switch(rq, prev, next);
perf_event_task_sched_out(prev, next);
rseq_preempt(prev);
fire_sched_out_preempt_notifiers(prev, next);
kmap_local_sched_out();
prepare_task(next);
prepare_arch_switch(next);
}
/**
* finish_task_switch - clean up after a task-switch
* @prev: the thread we just switched away from.
*
* finish_task_switch must be called after the context switch, paired
* with a prepare_task_switch call before the context switch.
* finish_task_switch will reconcile locking set up by prepare_task_switch,
* and do any other architecture-specific cleanup actions.
*
* Note that we may have delayed dropping an mm in context_switch(). If
* so, we finish that here outside of the runqueue lock. (Doing it
* with the lock held can cause deadlocks; see schedule() for
* details.)
*
* The context switch have flipped the stack from under us and restored the
* local variables which were saved when this task called schedule() in the
* past. prev == current is still correct but we need to recalculate this_rq
* because prev may have moved to another CPU.
*/
static struct rq *finish_task_switch(struct task_struct *prev)
__releases(rq->lock)
{
struct rq *rq = this_rq();
struct mm_struct *mm = rq->prev_mm;
long prev_state;
/*
* The previous task will have left us with a preempt_count of 2
* because it left us after:
*
* schedule()
* preempt_disable(); // 1
* __schedule()
* raw_spin_lock_irq(&rq->lock) // 2
*
* Also, see FORK_PREEMPT_COUNT.
*/
if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
"corrupted preempt_count: %s/%d/0x%x\n",
current->comm, current->pid, preempt_count()))
preempt_count_set(FORK_PREEMPT_COUNT);
rq->prev_mm = NULL;
/*
* A task struct has one reference for the use as "current".
* If a task dies, then it sets TASK_DEAD in tsk->state and calls
* schedule one last time. The schedule call will never return, and
* the scheduled task must drop that reference.
*
* We must observe prev->state before clearing prev->on_cpu (in
* finish_task), otherwise a concurrent wakeup can get prev
* running on another CPU and we could rave with its RUNNING -> DEAD
* transition, resulting in a double drop.
*/
prev_state = prev->state;
vtime_task_switch(prev);
perf_event_task_sched_in(prev, current);
finish_task(prev);
finish_lock_switch(rq);
finish_arch_post_lock_switch();
kcov_finish_switch(current);
/*
* kmap_local_sched_out() is invoked with rq::lock held and
* interrupts disabled. There is no requirement for that, but the
* sched out code does not have an interrupt enabled section.
* Restoring the maps on sched in does not require interrupts being
* disabled either.
*/
kmap_local_sched_in();
fire_sched_in_preempt_notifiers(current);
/*
* When switching through a kernel thread, the loop in
* membarrier_{private,global}_expedited() may have observed that
* kernel thread and not issued an IPI. It is therefore possible to
* schedule between user->kernel->user threads without passing though
* switch_mm(). Membarrier requires a barrier after storing to
* rq->curr, before returning to userspace, so provide them here:
*
* - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
* provided by mmdrop(),
* - a sync_core for SYNC_CORE.
*/
if (mm) {
membarrier_mm_sync_core_before_usermode(mm);
mmdrop(mm);
}
if (unlikely(prev_state == TASK_DEAD)) {
if (prev->sched_class->task_dead)
prev->sched_class->task_dead(prev);
/*
* Remove function-return probe instances associated with this
* task and put them back on the free list.
*/
kprobe_flush_task(prev);
/* Task is done with its stack. */
put_task_stack(prev);
put_task_struct_rcu_user(prev);
}
tick_nohz_task_switch();
return rq;
}
/**
* schedule_tail - first thing a freshly forked thread must call.
* @prev: the thread we just switched away from.
*/
asmlinkage __visible void schedule_tail(struct task_struct *prev)
__releases(rq->lock)
{
/*
* New tasks start with FORK_PREEMPT_COUNT, see there and
* finish_task_switch() for details.
*
* finish_task_switch() will drop rq->lock() and lower preempt_count
* and the preempt_enable() will end up enabling preemption (on
* PREEMPT_COUNT kernels).
*/
finish_task_switch(prev);
preempt_enable();
if (current->set_child_tid)
put_user(task_pid_vnr(current), current->set_child_tid);
calculate_sigpending();
}
/*
* context_switch - switch to the new MM and the new thread's register state.
*/
static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next, struct rq_flags *rf)
{
prepare_task_switch(rq, prev, next);
/*
* For paravirt, this is coupled with an exit in switch_to to
* combine the page table reload and the switch backend into
* one hypercall.
*/
arch_start_context_switch(prev);
/*
* kernel -> kernel lazy + transfer active
* user -> kernel lazy + mmgrab() active
*
* kernel -> user switch + mmdrop() active
* user -> user switch
*/
if (!next->mm) { // to kernel
enter_lazy_tlb(prev->active_mm, next);
next->active_mm = prev->active_mm;
if (prev->mm) // from user
mmgrab(prev->active_mm);
else
prev->active_mm = NULL;
} else { // to user
membarrier_switch_mm(rq, prev->active_mm, next->mm);
/*
* sys_membarrier() requires an smp_mb() between setting
* rq->curr / membarrier_switch_mm() and returning to userspace.
*
* The below provides this either through switch_mm(), or in
* case 'prev->active_mm == next->mm' through
* finish_task_switch()'s mmdrop().
*/
switch_mm_irqs_off(prev->active_mm, next->mm, next);
if (!prev->mm) { // from kernel
/* will mmdrop() in finish_task_switch(). */
rq->prev_mm = prev->active_mm;
prev->active_mm = NULL;
}
}
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
prepare_lock_switch(rq, next, rf);
/* Here we just switch the register state and the stack. */
switch_to(prev, next, prev);
barrier();
return finish_task_switch(prev);
}
/*
* nr_running and nr_context_switches:
*
* externally visible scheduler statistics: current number of runnable
* threads, total number of context switches performed since bootup.
*/
unsigned long nr_running(void)
{
unsigned long i, sum = 0;
for_each_online_cpu(i)
sum += cpu_rq(i)->nr_running;
return sum;
}
/*
* Check if only the current task is running on the CPU.
*
* Caution: this function does not check that the caller has disabled
* preemption, thus the result might have a time-of-check-to-time-of-use
* race. The caller is responsible to use it correctly, for example:
*
* - from a non-preemptible section (of course)
*
* - from a thread that is bound to a single CPU
*
* - in a loop with very short iterations (e.g. a polling loop)
*/
bool single_task_running(void)
{
return raw_rq()->nr_running == 1;
}
EXPORT_SYMBOL(single_task_running);
unsigned long long nr_context_switches(void)
{
int i;
unsigned long long sum = 0;
for_each_possible_cpu(i)
sum += cpu_rq(i)->nr_switches;
return sum;
}
/*
* Consumers of these two interfaces, like for example the cpuidle menu
* governor, are using nonsensical data. Preferring shallow idle state selection
* for a CPU that has IO-wait which might not even end up running the task when
* it does become runnable.
*/
unsigned long nr_iowait_cpu(int cpu)
{
return atomic_read(&cpu_rq(cpu)->nr_iowait);
}
/*
* IO-wait accounting, and how it's mostly bollocks (on SMP).
*
* The idea behind IO-wait account is to account the idle time that we could
* have spend running if it were not for IO. That is, if we were to improve the
* storage performance, we'd have a proportional reduction in IO-wait time.
*
* This all works nicely on UP, where, when a task blocks on IO, we account
* idle time as IO-wait, because if the storage were faster, it could've been
* running and we'd not be idle.
*
* This has been extended to SMP, by doing the same for each CPU. This however
* is broken.
*
* Imagine for instance the case where two tasks block on one CPU, only the one
* CPU will have IO-wait accounted, while the other has regular idle. Even
* though, if the storage were faster, both could've ran at the same time,
* utilising both CPUs.
*
* This means, that when looking globally, the current IO-wait accounting on
* SMP is a lower bound, by reason of under accounting.
*
* Worse, since the numbers are provided per CPU, they are sometimes
* interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
* associated with any one particular CPU, it can wake to another CPU than it
* blocked on. This means the per CPU IO-wait number is meaningless.
*
* Task CPU affinities can make all that even more 'interesting'.
*/
unsigned long nr_iowait(void)
{
unsigned long i, sum = 0;
for_each_possible_cpu(i)
sum += nr_iowait_cpu(i);
return sum;
}
#ifdef CONFIG_SMP
/*
* sched_exec - execve() is a valuable balancing opportunity, because at
* this point the task has the smallest effective memory and cache footprint.
*/
void sched_exec(void)
{
struct task_struct *p = current;
unsigned long flags;
int dest_cpu;
raw_spin_lock_irqsave(&p->pi_lock, flags);
dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), WF_EXEC);
if (dest_cpu == smp_processor_id())
goto unlock;
if (likely(cpu_active(dest_cpu))) {
struct migration_arg arg = { p, dest_cpu };
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
return;
}
unlock:
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}
#endif
DEFINE_PER_CPU(struct kernel_stat, kstat);
DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
EXPORT_PER_CPU_SYMBOL(kstat);
EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
/*
* The function fair_sched_class.update_curr accesses the struct curr
* and its field curr->exec_start; when called from task_sched_runtime(),
* we observe a high rate of cache misses in practice.
* Prefetching this data results in improved performance.
*/
static inline void prefetch_curr_exec_start(struct task_struct *p)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
struct sched_entity *curr = (&p->se)->cfs_rq->curr;
#else
struct sched_entity *curr = (&task_rq(p)->cfs)->curr;
#endif
prefetch(curr);
prefetch(&curr->exec_start);
}
/*
* Return accounted runtime for the task.
* In case the task is currently running, return the runtime plus current's
* pending runtime that have not been accounted yet.
*/
unsigned long long task_sched_runtime(struct task_struct *p)
{
struct rq_flags rf;
struct rq *rq;
u64 ns;
#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
/*
* 64-bit doesn't need locks to atomically read a 64-bit value.
* So we have a optimization chance when the task's delta_exec is 0.
* Reading ->on_cpu is racy, but this is ok.
*
* If we race with it leaving CPU, we'll take a lock. So we're correct.
* If we race with it entering CPU, unaccounted time is 0. This is
* indistinguishable from the read occurring a few cycles earlier.
* If we see ->on_cpu without ->on_rq, the task is leaving, and has
* been accounted, so we're correct here as well.
*/
if (!p->on_cpu || !task_on_rq_queued(p))
return p->se.sum_exec_runtime;
#endif
rq = task_rq_lock(p, &rf);
/*
* Must be ->curr _and_ ->on_rq. If dequeued, we would
* project cycles that may never be accounted to this
* thread, breaking clock_gettime().
*/
if (task_current(rq, p) && task_on_rq_queued(p)) {
prefetch_curr_exec_start(p);
update_rq_clock(rq);
p->sched_class->update_curr(rq);
}
ns = p->se.sum_exec_runtime;
task_rq_unlock(rq, p, &rf);
return ns;
}
#ifdef CONFIG_SCHED_DEBUG
static u64 cpu_resched_latency(struct rq *rq)
{
int latency_warn_ms = READ_ONCE(sysctl_resched_latency_warn_ms);
u64 resched_latency, now = rq_clock(rq);
static bool warned_once;
if (sysctl_resched_latency_warn_once && warned_once)
return 0;
if (!need_resched() || !latency_warn_ms)
return 0;
if (system_state == SYSTEM_BOOTING)
return 0;
if (!rq->last_seen_need_resched_ns) {
rq->last_seen_need_resched_ns = now;
rq->ticks_without_resched = 0;
return 0;
}
rq->ticks_without_resched++;
resched_latency = now - rq->last_seen_need_resched_ns;
if (resched_latency <= latency_warn_ms * NSEC_PER_MSEC)
return 0;
warned_once = true;
return resched_latency;
}
static int __init setup_resched_latency_warn_ms(char *str)
{
long val;
if ((kstrtol(str, 0, &val))) {
pr_warn("Unable to set resched_latency_warn_ms\n");
return 1;
}
sysctl_resched_latency_warn_ms = val;
return 1;
}
__setup("resched_latency_warn_ms=", setup_resched_latency_warn_ms);
#else
static inline u64 cpu_resched_latency(struct rq *rq) { return 0; }
#endif /* CONFIG_SCHED_DEBUG */
/*
* This function gets called by the timer code, with HZ frequency.
* We call it with interrupts disabled.
*/
void scheduler_tick(void)
{
int cpu = smp_processor_id();
struct rq *rq = cpu_rq(cpu);
struct task_struct *curr = rq->curr;
struct rq_flags rf;
unsigned long thermal_pressure;
u64 resched_latency;
arch_scale_freq_tick();
sched_clock_tick();
rq_lock(rq, &rf);
update_rq_clock(rq);
thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
curr->sched_class->task_tick(rq, curr, 0);
if (sched_feat(LATENCY_WARN))
resched_latency = cpu_resched_latency(rq);
calc_global_load_tick(rq);
rq_unlock(rq, &rf);
if (sched_feat(LATENCY_WARN) && resched_latency)
resched_latency_warn(cpu, resched_latency);
perf_event_task_tick();
#ifdef CONFIG_SMP
rq->idle_balance = idle_cpu(cpu);
trigger_load_balance(rq);
#endif
}
#ifdef CONFIG_NO_HZ_FULL
struct tick_work {
int cpu;
atomic_t state;
struct delayed_work work;
};
/* Values for ->state, see diagram below. */
#define TICK_SCHED_REMOTE_OFFLINE 0
#define TICK_SCHED_REMOTE_OFFLINING 1
#define TICK_SCHED_REMOTE_RUNNING 2
/*
* State diagram for ->state:
*
*
* TICK_SCHED_REMOTE_OFFLINE
* | ^
* | |
* | | sched_tick_remote()
* | |
* | |
* +--TICK_SCHED_REMOTE_OFFLINING
* | ^
* | |
* sched_tick_start() | | sched_tick_stop()
* | |
* V |
* TICK_SCHED_REMOTE_RUNNING
*
*
* Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
* and sched_tick_start() are happy to leave the state in RUNNING.
*/
static struct tick_work __percpu *tick_work_cpu;
static void sched_tick_remote(struct work_struct *work)
{
struct delayed_work *dwork = to_delayed_work(work);
struct tick_work *twork = container_of(dwork, struct tick_work, work);
int cpu = twork->cpu;
struct rq *rq = cpu_rq(cpu);
struct task_struct *curr;
struct rq_flags rf;
u64 delta;
int os;
/*
* Handle the tick only if it appears the remote CPU is running in full
* dynticks mode. The check is racy by nature, but missing a tick or
* having one too much is no big deal because the scheduler tick updates
* statistics and checks timeslices in a time-independent way, regardless
* of when exactly it is running.
*/
if (!tick_nohz_tick_stopped_cpu(cpu))
goto out_requeue;
rq_lock_irq(rq, &rf);
curr = rq->curr;
if (cpu_is_offline(cpu))
goto out_unlock;
update_rq_clock(rq);
if (!is_idle_task(curr)) {
/*
* Make sure the next tick runs within a reasonable
* amount of time.
*/
delta = rq_clock_task(rq) - curr->se.exec_start;
WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
}
curr->sched_class->task_tick(rq, curr, 0);
calc_load_nohz_remote(rq);
out_unlock:
rq_unlock_irq(rq, &rf);
out_requeue:
/*
* Run the remote tick once per second (1Hz). This arbitrary
* frequency is large enough to avoid overload but short enough
* to keep scheduler internal stats reasonably up to date. But
* first update state to reflect hotplug activity if required.
*/
os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
if (os == TICK_SCHED_REMOTE_RUNNING)
queue_delayed_work(system_unbound_wq, dwork, HZ);
}
static void sched_tick_start(int cpu)
{
int os;
struct tick_work *twork;
if (housekeeping_cpu(cpu, HK_FLAG_TICK))
return;
WARN_ON_ONCE(!tick_work_cpu);
twork = per_cpu_ptr(tick_work_cpu, cpu);
os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
if (os == TICK_SCHED_REMOTE_OFFLINE) {
twork->cpu = cpu;
INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
queue_delayed_work(system_unbound_wq, &twork->work, HZ);
}
}
#ifdef CONFIG_HOTPLUG_CPU
static void sched_tick_stop(int cpu)
{
struct tick_work *twork;
int os;
if (housekeeping_cpu(cpu, HK_FLAG_TICK))
return;
WARN_ON_ONCE(!tick_work_cpu);
twork = per_cpu_ptr(tick_work_cpu, cpu);
/* There cannot be competing actions, but don't rely on stop-machine. */
os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
/* Don't cancel, as this would mess up the state machine. */
}
#endif /* CONFIG_HOTPLUG_CPU */
int __init sched_tick_offload_init(void)
{
tick_work_cpu = alloc_percpu(struct tick_work);
BUG_ON(!tick_work_cpu);
return 0;
}
#else /* !CONFIG_NO_HZ_FULL */
static inline void sched_tick_start(int cpu) { }
static inline void sched_tick_stop(int cpu) { }
#endif
#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \
defined(CONFIG_TRACE_PREEMPT_TOGGLE))
/*
* If the value passed in is equal to the current preempt count
* then we just disabled preemption. Start timing the latency.
*/
static inline void preempt_latency_start(int val)
{
if (preempt_count() == val) {
unsigned long ip = get_lock_parent_ip();
#ifdef CONFIG_DEBUG_PREEMPT
current->preempt_disable_ip = ip;
#endif
trace_preempt_off(CALLER_ADDR0, ip);
}
}
void preempt_count_add(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
/*
* Underflow?
*/
if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
return;
#endif
__preempt_count_add(val);
#ifdef CONFIG_DEBUG_PREEMPT
/*
* Spinlock count overflowing soon?
*/
DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
PREEMPT_MASK - 10);
#endif
preempt_latency_start(val);
}
EXPORT_SYMBOL(preempt_count_add);
NOKPROBE_SYMBOL(preempt_count_add);
/*
* If the value passed in equals to the current preempt count
* then we just enabled preemption. Stop timing the latency.
*/
static inline void preempt_latency_stop(int val)
{
if (preempt_count() == val)
trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
}
void preempt_count_sub(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
/*
* Underflow?
*/
if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
return;
/*
* Is the spinlock portion underflowing?
*/
if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
!(preempt_count() & PREEMPT_MASK)))
return;
#endif
preempt_latency_stop(val);
__preempt_count_sub(val);
}
EXPORT_SYMBOL(preempt_count_sub);
NOKPROBE_SYMBOL(preempt_count_sub);
#else
static inline void preempt_latency_start(int val) { }
static inline void preempt_latency_stop(int val) { }
#endif
static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
{
#ifdef CONFIG_DEBUG_PREEMPT
return p->preempt_disable_ip;
#else
return 0;
#endif
}
/*
* Print scheduling while atomic bug:
*/
static noinline void __schedule_bug(struct task_struct *prev)
{
/* Save this before calling printk(), since that will clobber it */
unsigned long preempt_disable_ip = get_preempt_disable_ip(current);
if (oops_in_progress)
return;
printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
prev->comm, prev->pid, preempt_count());
debug_show_held_locks(prev);
print_modules();
if (irqs_disabled())
print_irqtrace_events(prev);
if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
&& in_atomic_preempt_off()) {
pr_err("Preemption disabled at:");
print_ip_sym(KERN_ERR, preempt_disable_ip);
}
if (panic_on_warn)
panic("scheduling while atomic\n");
dump_stack();
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
/*
* Various schedule()-time debugging checks and statistics:
*/
static inline void schedule_debug(struct task_struct *prev, bool preempt)
{
#ifdef CONFIG_SCHED_STACK_END_CHECK
if (task_stack_end_corrupted(prev))
panic("corrupted stack end detected inside scheduler\n");
if (task_scs_end_corrupted(prev))
panic("corrupted shadow stack detected inside scheduler\n");
#endif
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
if (!preempt && prev->state && prev->non_block_count) {
printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
prev->comm, prev->pid, prev->non_block_count);
dump_stack();
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
#endif
if (unlikely(in_atomic_preempt_off())) {
__schedule_bug(prev);
preempt_count_set(PREEMPT_DISABLED);
}
rcu_sleep_check();
SCHED_WARN_ON(ct_state() == CONTEXT_USER);
profile_hit(SCHED_PROFILING, __builtin_return_address(0));
schedstat_inc(this_rq()->sched_count);
}
static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
struct rq_flags *rf)
{
#ifdef CONFIG_SMP
const struct sched_class *class;
/*
* We must do the balancing pass before put_prev_task(), such
* that when we release the rq->lock the task is in the same
* state as before we took rq->lock.
*
* We can terminate the balance pass as soon as we know there is
* a runnable task of @class priority or higher.
*/
for_class_range(class, prev->sched_class, &idle_sched_class) {
if (class->balance(rq, prev, rf))
break;
}
#endif
put_prev_task(rq, prev);
}
/*
* Pick up the highest-prio task:
*/
static inline struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
const struct sched_class *class;
struct task_struct *p;
/*
* Optimization: we know that if all tasks are in the fair class we can
* call that function directly, but only if the @prev task wasn't of a
* higher scheduling class, because otherwise those lose the
* opportunity to pull in more work from other CPUs.
*/
if (likely(prev->sched_class <= &fair_sched_class &&
rq->nr_running == rq->cfs.h_nr_running)) {
p = pick_next_task_fair(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
goto restart;
/* Assumes fair_sched_class->next == idle_sched_class */
if (!p) {
put_prev_task(rq, prev);
p = pick_next_task_idle(rq);
}
return p;
}
restart:
put_prev_task_balance(rq, prev, rf);
for_each_class(class) {
p = class->pick_next_task(rq);
if (p)
return p;
}
/* The idle class should always have a runnable task: */
BUG();
}
/*
* __schedule() is the main scheduler function.
*
* The main means of driving the scheduler and thus entering this function are:
*
* 1. Explicit blocking: mutex, semaphore, waitqueue, etc.
*
* 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
* paths. For example, see arch/x86/entry_64.S.
*
* To drive preemption between tasks, the scheduler sets the flag in timer
* interrupt handler scheduler_tick().
*
* 3. Wakeups don't really cause entry into schedule(). They add a
* task to the run-queue and that's it.
*
* Now, if the new task added to the run-queue preempts the current
* task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
* called on the nearest possible occasion:
*
* - If the kernel is preemptible (CONFIG_PREEMPTION=y):
*
* - in syscall or exception context, at the next outmost
* preempt_enable(). (this might be as soon as the wake_up()'s
* spin_unlock()!)
*
* - in IRQ context, return from interrupt-handler to
* preemptible context
*
* - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
* then at the next:
*
* - cond_resched() call
* - explicit schedule() call
* - return from syscall or exception to user-space
* - return from interrupt-handler to user-space
*
* WARNING: must be called with preemption disabled!
*/
static void __sched notrace __schedule(bool preempt)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
unsigned long prev_state;
struct rq_flags rf;
struct rq *rq;
int cpu;
cpu = smp_processor_id();
rq = cpu_rq(cpu);
prev = rq->curr;
schedule_debug(prev, preempt);
if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
hrtick_clear(rq);
local_irq_disable();
rcu_note_context_switch(preempt);
/*
* Make sure that signal_pending_state()->signal_pending() below
* can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
* done by the caller to avoid the race with signal_wake_up():
*
* __set_current_state(@state) signal_wake_up()
* schedule() set_tsk_thread_flag(p, TIF_SIGPENDING)
* wake_up_state(p, state)
* LOCK rq->lock LOCK p->pi_state
* smp_mb__after_spinlock() smp_mb__after_spinlock()
* if (signal_pending_state()) if (p->state & @state)
*
* Also, the membarrier system call requires a full memory barrier
* after coming from user-space, before storing to rq->curr.
*/
rq_lock(rq, &rf);
smp_mb__after_spinlock();
/* Promote REQ to ACT */
rq->clock_update_flags <<= 1;
update_rq_clock(rq);
switch_count = &prev->nivcsw;
/*
* We must load prev->state once (task_struct::state is volatile), such
* that:
*
* - we form a control dependency vs deactivate_task() below.
* - ptrace_{,un}freeze_traced() can change ->state underneath us.
*/
prev_state = prev->state;
if (!preempt && prev_state) {
if (signal_pending_state(prev_state, prev)) {
prev->state = TASK_RUNNING;
} else {
prev->sched_contributes_to_load =
(prev_state & TASK_UNINTERRUPTIBLE) &&
!(prev_state & TASK_NOLOAD) &&
!(prev->flags & PF_FROZEN);
if (prev->sched_contributes_to_load)
rq->nr_uninterruptible++;
/*
* __schedule() ttwu()
* prev_state = prev->state; if (p->on_rq && ...)
* if (prev_state) goto out;
* p->on_rq = 0; smp_acquire__after_ctrl_dep();
* p->state = TASK_WAKING
*
* Where __schedule() and ttwu() have matching control dependencies.
*
* After this, schedule() must not care about p->state any more.
*/
deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
if (prev->in_iowait) {
atomic_inc(&rq->nr_iowait);
delayacct_blkio_start();
}
}
switch_count = &prev->nvcsw;
}
next = pick_next_task(rq, prev, &rf);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
#ifdef CONFIG_SCHED_DEBUG
rq->last_seen_need_resched_ns = 0;
#endif
if (likely(prev != next)) {
rq->nr_switches++;
/*
* RCU users of rcu_dereference(rq->curr) may not see
* changes to task_struct made by pick_next_task().
*/
RCU_INIT_POINTER(rq->curr, next);
/*
* The membarrier system call requires each architecture
* to have a full memory barrier after updating
* rq->curr, before returning to user-space.
*
* Here are the schemes providing that barrier on the
* various architectures:
* - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
* switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
* - finish_lock_switch() for weakly-ordered
* architectures where spin_unlock is a full barrier,
* - switch_to() for arm64 (weakly-ordered, spin_unlock
* is a RELEASE barrier),
*/
++*switch_count;
migrate_disable_switch(rq, prev);
psi_sched_switch(prev, next, !task_on_rq_queued(prev));
trace_sched_switch(preempt, prev, next);
/* Also unlocks the rq: */
rq = context_switch(rq, prev, next, &rf);
} else {
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
rq_unpin_lock(rq, &rf);
__balance_callbacks(rq);
raw_spin_unlock_irq(&rq->lock);
}
}
void __noreturn do_task_dead(void)
{
/* Causes final put_task_struct in finish_task_switch(): */
set_special_state(TASK_DEAD);
/* Tell freezer to ignore us: */
current->flags |= PF_NOFREEZE;
__schedule(false);
BUG();
/* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
for (;;)
cpu_relax();
}
static inline void sched_submit_work(struct task_struct *tsk)
{
unsigned int task_flags;
if (!tsk->state)
return;
task_flags = tsk->flags;
/*
* If a worker went to sleep, notify and ask workqueue whether
* it wants to wake up a task to maintain concurrency.
* As this function is called inside the schedule() context,
* we disable preemption to avoid it calling schedule() again
* in the possible wakeup of a kworker and because wq_worker_sleeping()
* requires it.
*/
if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
preempt_disable();
if (task_flags & PF_WQ_WORKER)
wq_worker_sleeping(tsk);
else
io_wq_worker_sleeping(tsk);
preempt_enable_no_resched();
}
if (tsk_is_pi_blocked(tsk))
return;
/*
* If we are going to sleep and we have plugged IO queued,
* make sure to submit it to avoid deadlocks.
*/
if (blk_needs_flush_plug(tsk))
blk_schedule_flush_plug(tsk);
}
static void sched_update_worker(struct task_struct *tsk)
{
if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
if (tsk->flags & PF_WQ_WORKER)
wq_worker_running(tsk);
else
io_wq_worker_running(tsk);
}
}
asmlinkage __visible void __sched schedule(void)
{
struct task_struct *tsk = current;
sched_submit_work(tsk);
do {
preempt_disable();
__schedule(false);
sched_preempt_enable_no_resched();
} while (need_resched());
sched_update_worker(tsk);
}
EXPORT_SYMBOL(schedule);
/*
* synchronize_rcu_tasks() makes sure that no task is stuck in preempted
* state (have scheduled out non-voluntarily) by making sure that all
* tasks have either left the run queue or have gone into user space.
* As idle tasks do not do either, they must not ever be preempted
* (schedule out non-voluntarily).
*
* schedule_idle() is similar to schedule_preempt_disable() except that it
* never enables preemption because it does not call sched_submit_work().
*/
void __sched schedule_idle(void)
{
/*
* As this skips calling sched_submit_work(), which the idle task does
* regardless because that function is a nop when the task is in a
* TASK_RUNNING state, make sure this isn't used someplace that the
* current task can be in any other state. Note, idle is always in the
* TASK_RUNNING state.
*/
WARN_ON_ONCE(current->state);
do {
__schedule(false);
} while (need_resched());
}
#if defined(CONFIG_CONTEXT_TRACKING) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK)
asmlinkage __visible void __sched schedule_user(void)
{
/*
* If we come here after a random call to set_need_resched(),
* or we have been woken up remotely but the IPI has not yet arrived,
* we haven't yet exited the RCU idle mode. Do it here manually until
* we find a better solution.
*
* NB: There are buggy callers of this function. Ideally we
* should warn if prev_state != CONTEXT_USER, but that will trigger
* too frequently to make sense yet.
*/
enum ctx_state prev_state = exception_enter();
schedule();
exception_exit(prev_state);
}
#endif
/**
* schedule_preempt_disabled - called with preemption disabled
*
* Returns with preemption disabled. Note: preempt_count must be 1
*/
void __sched schedule_preempt_disabled(void)
{
sched_preempt_enable_no_resched();
schedule();
preempt_disable();
}
static void __sched notrace preempt_schedule_common(void)
{
do {
/*
* Because the function tracer can trace preempt_count_sub()
* and it also uses preempt_enable/disable_notrace(), if
* NEED_RESCHED is set, the preempt_enable_notrace() called
* by the function tracer will call this function again and
* cause infinite recursion.
*
* Preemption must be disabled here before the function
* tracer can trace. Break up preempt_disable() into two
* calls. One to disable preemption without fear of being
* traced. The other to still record the preemption latency,
* which can also be traced by the function tracer.
*/
preempt_disable_notrace();
preempt_latency_start(1);
__schedule(true);
preempt_latency_stop(1);
preempt_enable_no_resched_notrace();
/*
* Check again in case we missed a preemption opportunity
* between schedule and now.
*/
} while (need_resched());
}
#ifdef CONFIG_PREEMPTION
/*
* This is the entry point to schedule() from in-kernel preemption
* off of preempt_enable.
*/
asmlinkage __visible void __sched notrace preempt_schedule(void)
{
/*
* If there is a non-zero preempt_count or interrupts are disabled,
* we do not want to preempt the current task. Just return..
*/
if (likely(!preemptible()))
return;
preempt_schedule_common();
}
NOKPROBE_SYMBOL(preempt_schedule);
EXPORT_SYMBOL(preempt_schedule);
#ifdef CONFIG_PREEMPT_DYNAMIC
DEFINE_STATIC_CALL(preempt_schedule, __preempt_schedule_func);
EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
#endif
/**
* preempt_schedule_notrace - preempt_schedule called by tracing
*
* The tracing infrastructure uses preempt_enable_notrace to prevent
* recursion and tracing preempt enabling caused by the tracing
* infrastructure itself. But as tracing can happen in areas coming
* from userspace or just about to enter userspace, a preempt enable
* can occur before user_exit() is called. This will cause the scheduler
* to be called when the system is still in usermode.
*
* To prevent this, the preempt_enable_notrace will use this function
* instead of preempt_schedule() to exit user context if needed before
* calling the scheduler.
*/
asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
{
enum ctx_state prev_ctx;
if (likely(!preemptible()))
return;
do {
/*
* Because the function tracer can trace preempt_count_sub()
* and it also uses preempt_enable/disable_notrace(), if
* NEED_RESCHED is set, the preempt_enable_notrace() called
* by the function tracer will call this function again and
* cause infinite recursion.
*
* Preemption must be disabled here before the function
* tracer can trace. Break up preempt_disable() into two
* calls. One to disable preemption without fear of being
* traced. The other to still record the preemption latency,
* which can also be traced by the function tracer.
*/
preempt_disable_notrace();
preempt_latency_start(1);
/*
* Needs preempt disabled in case user_exit() is traced
* and the tracer calls preempt_enable_notrace() causing
* an infinite recursion.
*/
prev_ctx = exception_enter();
__schedule(true);
exception_exit(prev_ctx);
preempt_latency_stop(1);
preempt_enable_no_resched_notrace();
} while (need_resched());
}
EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
#ifdef CONFIG_PREEMPT_DYNAMIC
DEFINE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func);
EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
#endif
#endif /* CONFIG_PREEMPTION */
#ifdef CONFIG_PREEMPT_DYNAMIC
#include <linux/entry-common.h>
/*
* SC:cond_resched
* SC:might_resched
* SC:preempt_schedule
* SC:preempt_schedule_notrace
* SC:irqentry_exit_cond_resched
*
*
* NONE:
* cond_resched <- __cond_resched
* might_resched <- RET0
* preempt_schedule <- NOP
* preempt_schedule_notrace <- NOP
* irqentry_exit_cond_resched <- NOP
*
* VOLUNTARY:
* cond_resched <- __cond_resched
* might_resched <- __cond_resched
* preempt_schedule <- NOP
* preempt_schedule_notrace <- NOP
* irqentry_exit_cond_resched <- NOP
*
* FULL:
* cond_resched <- RET0
* might_resched <- RET0
* preempt_schedule <- preempt_schedule
* preempt_schedule_notrace <- preempt_schedule_notrace
* irqentry_exit_cond_resched <- irqentry_exit_cond_resched
*/
enum {
preempt_dynamic_none = 0,
preempt_dynamic_voluntary,
preempt_dynamic_full,
};
int preempt_dynamic_mode = preempt_dynamic_full;
int sched_dynamic_mode(const char *str)
{
if (!strcmp(str, "none"))
return preempt_dynamic_none;
if (!strcmp(str, "voluntary"))
return preempt_dynamic_voluntary;
if (!strcmp(str, "full"))
return preempt_dynamic_full;
return -EINVAL;
}
void sched_dynamic_update(int mode)
{
/*
* Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
* the ZERO state, which is invalid.
*/
static_call_update(cond_resched, __cond_resched);
static_call_update(might_resched, __cond_resched);
static_call_update(preempt_schedule, __preempt_schedule_func);
static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
switch (mode) {
case preempt_dynamic_none:
static_call_update(cond_resched, __cond_resched);
static_call_update(might_resched, (typeof(&__cond_resched)) __static_call_return0);
static_call_update(preempt_schedule, (typeof(&preempt_schedule)) NULL);
static_call_update(preempt_schedule_notrace, (typeof(&preempt_schedule_notrace)) NULL);
static_call_update(irqentry_exit_cond_resched, (typeof(&irqentry_exit_cond_resched)) NULL);
pr_info("Dynamic Preempt: none\n");
break;
case preempt_dynamic_voluntary:
static_call_update(cond_resched, __cond_resched);
static_call_update(might_resched, __cond_resched);
static_call_update(preempt_schedule, (typeof(&preempt_schedule)) NULL);
static_call_update(preempt_schedule_notrace, (typeof(&preempt_schedule_notrace)) NULL);
static_call_update(irqentry_exit_cond_resched, (typeof(&irqentry_exit_cond_resched)) NULL);
pr_info("Dynamic Preempt: voluntary\n");
break;
case preempt_dynamic_full:
static_call_update(cond_resched, (typeof(&__cond_resched)) __static_call_return0);
static_call_update(might_resched, (typeof(&__cond_resched)) __static_call_return0);
static_call_update(preempt_schedule, __preempt_schedule_func);
static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
pr_info("Dynamic Preempt: full\n");
break;
}
preempt_dynamic_mode = mode;
}
static int __init setup_preempt_mode(char *str)
{
int mode = sched_dynamic_mode(str);
if (mode < 0) {
pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
return 1;
}
sched_dynamic_update(mode);
return 0;
}
__setup("preempt=", setup_preempt_mode);
#endif /* CONFIG_PREEMPT_DYNAMIC */
/*
* This is the entry point to schedule() from kernel preemption
* off of irq context.
* Note, that this is called and return with irqs disabled. This will
* protect us against recursive calling from irq.
*/
asmlinkage __visible void __sched preempt_schedule_irq(void)
{
enum ctx_state prev_state;
/* Catch callers which need to be fixed */
BUG_ON(preempt_count() || !irqs_disabled());
prev_state = exception_enter();
do {
preempt_disable();
local_irq_enable();
__schedule(true);
local_irq_disable();
sched_preempt_enable_no_resched();
} while (need_resched());
exception_exit(prev_state);
}
int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
void *key)
{
WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC);
return try_to_wake_up(curr->private, mode, wake_flags);
}
EXPORT_SYMBOL(default_wake_function);
#ifdef CONFIG_RT_MUTEXES
static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
{
if (pi_task)
prio = min(prio, pi_task->prio);
return prio;
}
static inline int rt_effective_prio(struct task_struct *p, int prio)
{
struct task_struct *pi_task = rt_mutex_get_top_task(p);
return __rt_effective_prio(pi_task, prio);
}
/*
* rt_mutex_setprio - set the current priority of a task
* @p: task to boost
* @pi_task: donor task
*
* This function changes the 'effective' priority of a task. It does
* not touch ->normal_prio like __setscheduler().
*
* Used by the rt_mutex code to implement priority inheritance
* logic. Call site only calls if the priority of the task changed.
*/
void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
{
int prio, oldprio, queued, running, queue_flag =
DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
const struct sched_class *prev_class;
struct rq_flags rf;
struct rq *rq;
/* XXX used to be waiter->prio, not waiter->task->prio */
prio = __rt_effective_prio(pi_task, p->normal_prio);
/*
* If nothing changed; bail early.
*/
if (p->pi_top_task == pi_task && prio == p->prio && !dl_prio(prio))
return;
rq = __task_rq_lock(p, &rf);
update_rq_clock(rq);
/*
* Set under pi_lock && rq->lock, such that the value can be used under
* either lock.
*
* Note that there is loads of tricky to make this pointer cache work
* right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
* ensure a task is de-boosted (pi_task is set to NULL) before the
* task is allowed to run again (and can exit). This ensures the pointer
* points to a blocked task -- which guarantees the task is present.
*/
p->pi_top_task = pi_task;
/*
* For FIFO/RR we only need to set prio, if that matches we're done.
*/
if (prio == p->prio && !dl_prio(prio))
goto out_unlock;
/*
* Idle task boosting is a nono in general. There is one
* exception, when PREEMPT_RT and NOHZ is active:
*
* The idle task calls get_next_timer_interrupt() and holds
* the timer wheel base->lock on the CPU and another CPU wants
* to access the timer (probably to cancel it). We can safely
* ignore the boosting request, as the idle CPU runs this code
* with interrupts disabled and will complete the lock
* protected section without being interrupted. So there is no
* real need to boost.
*/
if (unlikely(p == rq->idle)) {
WARN_ON(p != rq->curr);
WARN_ON(p->pi_blocked_on);
goto out_unlock;
}
trace_sched_pi_setprio(p, pi_task);
oldprio = p->prio;
if (oldprio == prio)
queue_flag &= ~DEQUEUE_MOVE;
prev_class = p->sched_class;
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued)
dequeue_task(rq, p, queue_flag);
if (running)
put_prev_task(rq, p);
/*
* Boosting condition are:
* 1. -rt task is running and holds mutex A
* --> -dl task blocks on mutex A
*
* 2. -dl task is running and holds mutex A
* --> -dl task blocks on mutex A and could preempt the
* running task
*/
if (dl_prio(prio)) {
if (!dl_prio(p->normal_prio) ||
(pi_task && dl_prio(pi_task->prio) &&
dl_entity_preempt(&pi_task->dl, &p->dl))) {
p->dl.pi_se = pi_task->dl.pi_se;
queue_flag |= ENQUEUE_REPLENISH;
} else {
p->dl.pi_se = &p->dl;
}
p->sched_class = &dl_sched_class;
} else if (rt_prio(prio)) {
if (dl_prio(oldprio))
p->dl.pi_se = &p->dl;
if (oldprio < prio)
queue_flag |= ENQUEUE_HEAD;
p->sched_class = &rt_sched_class;
} else {
if (dl_prio(oldprio))
p->dl.pi_se = &p->dl;
if (rt_prio(oldprio))
p->rt.timeout = 0;
p->sched_class = &fair_sched_class;
}
p->prio = prio;
if (queued)
enqueue_task(rq, p, queue_flag);
if (running)
set_next_task(rq, p);
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
/* Avoid rq from going away on us: */
preempt_disable();
rq_unpin_lock(rq, &rf);
__balance_callbacks(rq);
raw_spin_unlock(&rq->lock);
preempt_enable();
}
#else
static inline int rt_effective_prio(struct task_struct *p, int prio)
{
return prio;
}
#endif
void set_user_nice(struct task_struct *p, long nice)
{
bool queued, running;
int old_prio;
struct rq_flags rf;
struct rq *rq;
if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
return;
/*
* We have to be careful, if called from sys_setpriority(),
* the task might be in the middle of scheduling on another CPU.
*/
rq = task_rq_lock(p, &rf);
update_rq_clock(rq);
/*
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
* it won't have any effect on scheduling until the task is
* SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
*/
if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->static_prio = NICE_TO_PRIO(nice);
goto out_unlock;
}
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued)
dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
if (running)
put_prev_task(rq, p);
p->static_prio = NICE_TO_PRIO(nice);
set_load_weight(p, true);
old_prio = p->prio;
p->prio = effective_prio(p);
if (queued)
enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
if (running)
set_next_task(rq, p);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
*/
p->sched_class->prio_changed(rq, p, old_prio);
out_unlock:
task_rq_unlock(rq, p, &rf);
}
EXPORT_SYMBOL(set_user_nice);
/*
* can_nice - check if a task can reduce its nice value
* @p: task
* @nice: nice value
*/
int can_nice(const struct task_struct *p, const int nice)
{
/* Convert nice value [19,-20] to rlimit style value [1,40]: */
int nice_rlim = nice_to_rlimit(nice);
return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
capable(CAP_SYS_NICE));
}
#ifdef __ARCH_WANT_SYS_NICE
/*
* sys_nice - change the priority of the current process.
* @increment: priority increment
*
* sys_setpriority is a more generic, but much slower function that
* does similar things.
*/
SYSCALL_DEFINE1(nice, int, increment)
{
long nice, retval;
/*
* Setpriority might change our priority at the same moment.
* We don't have to worry. Conceptually one call occurs first
* and we have a single winner.
*/
increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
nice = task_nice(current) + increment;
nice = clamp_val(nice, MIN_NICE, MAX_NICE);
if (increment < 0 && !can_nice(current, nice))
return -EPERM;
retval = security_task_setnice(current, nice);
if (retval)
return retval;
set_user_nice(current, nice);
return 0;
}
#endif
/**
* task_prio - return the priority value of a given task.
* @p: the task in question.
*
* Return: The priority value as seen by users in /proc.
*
* sched policy return value kernel prio user prio/nice
*
* normal, batch, idle [0 ... 39] [100 ... 139] 0/[-20 ... 19]
* fifo, rr [-2 ... -100] [98 ... 0] [1 ... 99]
* deadline -101 -1 0
*/
int task_prio(const struct task_struct *p)
{
return p->prio - MAX_RT_PRIO;
}
/**
* idle_cpu - is a given CPU idle currently?
* @cpu: the processor in question.
*
* Return: 1 if the CPU is currently idle. 0 otherwise.
*/
int idle_cpu(int cpu)
{
struct rq *rq = cpu_rq(cpu);
if (rq->curr != rq->idle)
return 0;
if (rq->nr_running)
return 0;
#ifdef CONFIG_SMP
if (rq->ttwu_pending)
return 0;
#endif
return 1;
}
/**
* available_idle_cpu - is a given CPU idle for enqueuing work.
* @cpu: the CPU in question.
*
* Return: 1 if the CPU is currently idle. 0 otherwise.
*/
int available_idle_cpu(int cpu)
{
if (!idle_cpu(cpu))
return 0;
if (vcpu_is_preempted(cpu))
return 0;
return 1;
}
/**
* idle_task - return the idle task for a given CPU.
* @cpu: the processor in question.
*
* Return: The idle task for the CPU @cpu.
*/
struct task_struct *idle_task(int cpu)
{
return cpu_rq(cpu)->idle;
}
#ifdef CONFIG_SMP
/*
* This function computes an effective utilization for the given CPU, to be
* used for frequency selection given the linear relation: f = u * f_max.
*
* The scheduler tracks the following metrics:
*
* cpu_util_{cfs,rt,dl,irq}()
* cpu_bw_dl()
*
* Where the cfs,rt and dl util numbers are tracked with the same metric and
* synchronized windows and are thus directly comparable.
*
* The cfs,rt,dl utilization are the running times measured with rq->clock_task
* which excludes things like IRQ and steal-time. These latter are then accrued
* in the irq utilization.
*
* The DL bandwidth number otoh is not a measured metric but a value computed
* based on the task model parameters and gives the minimal utilization
* required to meet deadlines.
*/
unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
unsigned long max, enum cpu_util_type type,
struct task_struct *p)
{
unsigned long dl_util, util, irq;
struct rq *rq = cpu_rq(cpu);
if (!uclamp_is_used() &&
type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
return max;
}
/*
* Early check to see if IRQ/steal time saturates the CPU, can be
* because of inaccuracies in how we track these -- see
* update_irq_load_avg().
*/
irq = cpu_util_irq(rq);
if (unlikely(irq >= max))
return max;
/*
* Because the time spend on RT/DL tasks is visible as 'lost' time to
* CFS tasks and we use the same metric to track the effective
* utilization (PELT windows are synchronized) we can directly add them
* to obtain the CPU's actual utilization.
*
* CFS and RT utilization can be boosted or capped, depending on
* utilization clamp constraints requested by currently RUNNABLE
* tasks.
* When there are no CFS RUNNABLE tasks, clamps are released and
* frequency will be gracefully reduced with the utilization decay.
*/
util = util_cfs + cpu_util_rt(rq);
if (type == FREQUENCY_UTIL)
util = uclamp_rq_util_with(rq, util, p);
dl_util = cpu_util_dl(rq);
/*
* For frequency selection we do not make cpu_util_dl() a permanent part
* of this sum because we want to use cpu_bw_dl() later on, but we need
* to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
* that we select f_max when there is no idle time.
*
* NOTE: numerical errors or stop class might cause us to not quite hit
* saturation when we should -- something for later.
*/
if (util + dl_util >= max)
return max;
/*
* OTOH, for energy computation we need the estimated running time, so
* include util_dl and ignore dl_bw.
*/
if (type == ENERGY_UTIL)
util += dl_util;
/*
* There is still idle time; further improve the number by using the
* irq metric. Because IRQ/steal time is hidden from the task clock we
* need to scale the task numbers:
*
* max - irq
* U' = irq + --------- * U
* max
*/
util = scale_irq_capacity(util, irq, max);
util += irq;
/*
* Bandwidth required by DEADLINE must always be granted while, for
* FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
* to gracefully reduce the frequency when no tasks show up for longer
* periods of time.
*
* Ideally we would like to set bw_dl as min/guaranteed freq and util +
* bw_dl as requested freq. However, cpufreq is not yet ready for such
* an interface. So, we only do the latter for now.
*/
if (type == FREQUENCY_UTIL)
util += cpu_bw_dl(rq);
return min(max, util);
}
unsigned long sched_cpu_util(int cpu, unsigned long max)
{
return effective_cpu_util(cpu, cpu_util_cfs(cpu_rq(cpu)), max,
ENERGY_UTIL, NULL);
}
#endif /* CONFIG_SMP */
/**
* find_process_by_pid - find a process with a matching PID value.
* @pid: the pid in question.
*
* The task of @pid, if found. %NULL otherwise.
*/
static struct task_struct *find_process_by_pid(pid_t pid)
{
return pid ? find_task_by_vpid(pid) : current;
}
/*
* sched_setparam() passes in -1 for its policy, to let the functions
* it calls know not to change it.
*/
#define SETPARAM_POLICY -1
static void __setscheduler_params(struct task_struct *p,
const struct sched_attr *attr)
{
int policy = attr->sched_policy;
if (policy == SETPARAM_POLICY)
policy = p->policy;
p->policy = policy;
if (dl_policy(policy))
__setparam_dl(p, attr);
else if (fair_policy(policy))
p->static_prio = NICE_TO_PRIO(attr->sched_nice);
/*
* __sched_setscheduler() ensures attr->sched_priority == 0 when
* !rt_policy. Always setting this ensures that things like
* getparam()/getattr() don't report silly values for !rt tasks.
*/
p->rt_priority = attr->sched_priority;
p->normal_prio = normal_prio(p);
set_load_weight(p, true);
}
/* Actually do priority change: must hold pi & rq lock. */
static void __setscheduler(struct rq *rq, struct task_struct *p,
const struct sched_attr *attr, bool keep_boost)
{
/*
* If params can't change scheduling class changes aren't allowed
* either.
*/
if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)
return;
__setscheduler_params(p, attr);
/*
* Keep a potential priority boosting if called from
* sched_setscheduler().
*/
p->prio = normal_prio(p);
if (keep_boost)
p->prio = rt_effective_prio(p, p->prio);
if (dl_prio(p->prio))
p->sched_class = &dl_sched_class;
else if (rt_prio(p->prio))
p->sched_class = &rt_sched_class;
else
p->sched_class = &fair_sched_class;
}
/*
* Check the target process has a UID that matches the current process's:
*/
static bool check_same_owner(struct task_struct *p)
{
const struct cred *cred = current_cred(), *pcred;
bool match;
rcu_read_lock();
pcred = __task_cred(p);
match = (uid_eq(cred->euid, pcred->euid) ||
uid_eq(cred->euid, pcred->uid));
rcu_read_unlock();
return match;
}
static int __sched_setscheduler(struct task_struct *p,
const struct sched_attr *attr,
bool user, bool pi)
{
int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
MAX_RT_PRIO - 1 - attr->sched_priority;
int retval, oldprio, oldpolicy = -1, queued, running;
int new_effective_prio, policy = attr->sched_policy;
const struct sched_class *prev_class;
struct callback_head *head;
struct rq_flags rf;
int reset_on_fork;
int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
struct rq *rq;
/* The pi code expects interrupts enabled */
BUG_ON(pi && in_interrupt());
recheck:
/* Double check policy once rq lock held: */
if (policy < 0) {
reset_on_fork = p->sched_reset_on_fork;
policy = oldpolicy = p->policy;
} else {
reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK);
if (!valid_policy(policy))
return -EINVAL;
}
if (attr->sched_flags & ~(SCHED_FLAG_ALL | SCHED_FLAG_SUGOV))
return -EINVAL;
/*
* Valid priorities for SCHED_FIFO and SCHED_RR are
* 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL,
* SCHED_BATCH and SCHED_IDLE is 0.
*/
if (attr->sched_priority > MAX_RT_PRIO-1)
return -EINVAL;
if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
(rt_policy(policy) != (attr->sched_priority != 0)))
return -EINVAL;
/*
* Allow unprivileged RT tasks to decrease priority:
*/
if (user && !capable(CAP_SYS_NICE)) {
if (fair_policy(policy)) {
if (attr->sched_nice < task_nice(p) &&
!can_nice(p, attr->sched_nice))
return -EPERM;
}
if (rt_policy(policy)) {
unsigned long rlim_rtprio =
task_rlimit(p, RLIMIT_RTPRIO);
/* Can't set/change the rt policy: */
if (policy != p->policy && !rlim_rtprio)
return -EPERM;
/* Can't increase priority: */
if (attr->sched_priority > p->rt_priority &&
attr->sched_priority > rlim_rtprio)
return -EPERM;
}
/*
* Can't set/change SCHED_DEADLINE policy at all for now
* (safest behavior); in the future we would like to allow
* unprivileged DL tasks to increase their relative deadline
* or reduce their runtime (both ways reducing utilization)
*/
if (dl_policy(policy))
return -EPERM;
/*
* Treat SCHED_IDLE as nice 20. Only allow a switch to
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
*/
if (task_has_idle_policy(p) && !idle_policy(policy)) {
if (!can_nice(p, task_nice(p)))
return -EPERM;
}
/* Can't change other user's priorities: */
if (!check_same_owner(p))
return -EPERM;
/* Normal users shall not reset the sched_reset_on_fork flag: */
if (p->sched_reset_on_fork && !reset_on_fork)
return -EPERM;
}
if (user) {
if (attr->sched_flags & SCHED_FLAG_SUGOV)
return -EINVAL;
retval = security_task_setscheduler(p);
if (retval)
return retval;
}
/* Update task specific "requested" clamps */
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) {
retval = uclamp_validate(p, attr);
if (retval)
return retval;
}
if (pi)
cpuset_read_lock();
/*
* Make sure no PI-waiters arrive (or leave) while we are
* changing the priority of the task:
*
* To be able to change p->policy safely, the appropriate
* runqueue lock must be held.
*/
rq = task_rq_lock(p, &rf);
update_rq_clock(rq);
/*
* Changing the policy of the stop threads its a very bad idea:
*/
if (p == rq->stop) {
retval = -EINVAL;
goto unlock;
}
/*
* If not changing anything there's no need to proceed further,
* but store a possible modification of reset_on_fork.
*/
if (unlikely(policy == p->policy)) {
if (fair_policy(policy) && attr->sched_nice != task_nice(p))
goto change;
if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
goto change;
if (dl_policy(policy) && dl_param_changed(p, attr))
goto change;
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
goto change;
p->sched_reset_on_fork = reset_on_fork;
retval = 0;
goto unlock;
}
change:
if (user) {
#ifdef CONFIG_RT_GROUP_SCHED
/*
* Do not allow realtime tasks into groups that have no runtime
* assigned.
*/
if (rt_bandwidth_enabled() && rt_policy(policy) &&
task_group(p)->rt_bandwidth.rt_runtime == 0 &&
!task_group_is_autogroup(task_group(p))) {
retval = -EPERM;
goto unlock;
}
#endif
#ifdef CONFIG_SMP
if (dl_bandwidth_enabled() && dl_policy(policy) &&
!(attr->sched_flags & SCHED_FLAG_SUGOV)) {
cpumask_t *span = rq->rd->span;
/*
* Don't allow tasks with an affinity mask smaller than
* the entire root_domain to become SCHED_DEADLINE. We
* will also fail if there's no bandwidth available.
*/
if (!cpumask_subset(span, p->cpus_ptr) ||
rq->rd->dl_bw.bw == 0) {
retval = -EPERM;
goto unlock;
}
}
#endif
}
/* Re-check policy now with rq lock held: */
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
policy = oldpolicy = -1;
task_rq_unlock(rq, p, &rf);
if (pi)
cpuset_read_unlock();
goto recheck;
}
/*
* If setscheduling to SCHED_DEADLINE (or changing the parameters
* of a SCHED_DEADLINE task) we need to check if enough bandwidth
* is available.
*/
if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) {
retval = -EBUSY;
goto unlock;
}
p->sched_reset_on_fork = reset_on_fork;
oldprio = p->prio;
if (pi) {
/*
* Take priority boosted tasks into account. If the new
* effective priority is unchanged, we just store the new
* normal parameters and do not touch the scheduler class and
* the runqueue. This will be done when the task deboost
* itself.
*/
new_effective_prio = rt_effective_prio(p, newprio);
if (new_effective_prio == oldprio)
queue_flags &= ~DEQUEUE_MOVE;
}
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued)
dequeue_task(rq, p, queue_flags);
if (running)
put_prev_task(rq, p);
prev_class = p->sched_class;
__setscheduler(rq, p, attr, pi);
__setscheduler_uclamp(p, attr);
if (queued) {
/*
* We enqueue to tail when the priority of a task is
* increased (user space view).
*/
if (oldprio < p->prio)
queue_flags |= ENQUEUE_HEAD;
enqueue_task(rq, p, queue_flags);
}
if (running)
set_next_task(rq, p);
check_class_changed(rq, p, prev_class, oldprio);
/* Avoid rq from going away on us: */
preempt_disable();
head = splice_balance_callbacks(rq);
task_rq_unlock(rq, p, &rf);
if (pi) {
cpuset_read_unlock();
rt_mutex_adjust_pi(p);
}
/* Run balance callbacks after we've adjusted the PI chain: */
balance_callbacks(rq, head);
preempt_enable();
return 0;
unlock:
task_rq_unlock(rq, p, &rf);
if (pi)
cpuset_read_unlock();
return retval;
}
static int _sched_setscheduler(struct task_struct *p, int policy,
const struct sched_param *param, bool check)
{
struct sched_attr attr = {
.sched_policy = policy,
.sched_priority = param->sched_priority,
.sched_nice = PRIO_TO_NICE(p->static_prio),
};
/* Fixup the legacy SCHED_RESET_ON_FORK hack. */
if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
policy &= ~SCHED_RESET_ON_FORK;
attr.sched_policy = policy;
}
return __sched_setscheduler(p, &attr, check, true);
}
/**
* sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
* @p: the task in question.
* @policy: new policy.
* @param: structure containing the new RT priority.
*
* Use sched_set_fifo(), read its comment.
*
* Return: 0 on success. An error code otherwise.
*
* NOTE that the task may be already dead.
*/
int sched_setscheduler(struct task_struct *p, int policy,
const struct sched_param *param)
{
return _sched_setscheduler(p, policy, param, true);
}
int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
{
return __sched_setscheduler(p, attr, true, true);
}
int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
{
return __sched_setscheduler(p, attr, false, true);
}
/**
* sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
* @p: the task in question.
* @policy: new policy.
* @param: structure containing the new RT priority.
*
* Just like sched_setscheduler, only don't bother checking if the
* current context has permission. For example, this is needed in
* stop_machine(): we create temporary high priority worker threads,
* but our caller might not have that capability.
*
* Return: 0 on success. An error code otherwise.
*/
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
const struct sched_param *param)
{
return _sched_setscheduler(p, policy, param, false);
}
/*
* SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
* incapable of resource management, which is the one thing an OS really should
* be doing.
*
* This is of course the reason it is limited to privileged users only.
*
* Worse still; it is fundamentally impossible to compose static priority
* workloads. You cannot take two correctly working static prio workloads
* and smash them together and still expect them to work.
*
* For this reason 'all' FIFO tasks the kernel creates are basically at:
*
* MAX_RT_PRIO / 2
*
* The administrator _MUST_ configure the system, the kernel simply doesn't
* know enough information to make a sensible choice.
*/
void sched_set_fifo(struct task_struct *p)
{
struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
}
EXPORT_SYMBOL_GPL(sched_set_fifo);
/*
* For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
*/
void sched_set_fifo_low(struct task_struct *p)
{
struct sched_param sp = { .sched_priority = 1 };
WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
}
EXPORT_SYMBOL_GPL(sched_set_fifo_low);
void sched_set_normal(struct task_struct *p, int nice)
{
struct sched_attr attr = {
.sched_policy = SCHED_NORMAL,
.sched_nice = nice,
};
WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
}
EXPORT_SYMBOL_GPL(sched_set_normal);
static int
do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{
struct sched_param lparam;
struct task_struct *p;
int retval;
if (!param || pid < 0)
return -EINVAL;
if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
return -EFAULT;
rcu_read_lock();
retval = -ESRCH;
p = find_process_by_pid(pid);
if (likely(p))
get_task_struct(p);
rcu_read_unlock();
if (likely(p)) {
retval = sched_setscheduler(p, policy, &lparam);
put_task_struct(p);
}
return retval;
}
/*
* Mimics kernel/events/core.c perf_copy_attr().
*/
static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
{
u32 size;
int ret;
/* Zero the full structure, so that a short copy will be nice: */
memset(attr, 0, sizeof(*attr));
ret = get_user(size, &uattr->size);
if (ret)
return ret;
/* ABI compatibility quirk: */
if (!size)
size = SCHED_ATTR_SIZE_VER0;
if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
goto err_size;
ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
if (ret) {
if (ret == -E2BIG)
goto err_size;
return ret;
}
if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) &&
size < SCHED_ATTR_SIZE_VER1)
return -EINVAL;
/*
* XXX: Do we want to be lenient like existing syscalls; or do we want
* to be strict and return an error on out-of-bounds values?
*/
attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);
return 0;
err_size:
put_user(sizeof(*attr), &uattr->size);
return -E2BIG;
}
/**
* sys_sched_setscheduler - set/change the scheduler policy and RT priority
* @pid: the pid in question.
* @policy: new policy.
* @param: structure containing the new RT priority.
*
* Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
{
if (policy < 0)
return -EINVAL;
return do_sched_setscheduler(pid, policy, param);
}
/**
* sys_sched_setparam - set/change the RT priority of a thread
* @pid: the pid in question.
* @param: structure containing the new RT priority.
*
* Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
{
return do_sched_setscheduler(pid, SETPARAM_POLICY, param);
}
/**
* sys_sched_setattr - same as above, but with extended sched_attr
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
* @flags: for future extension.
*/
SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
unsigned int, flags)
{
struct sched_attr attr;
struct task_struct *p;
int retval;
if (!uattr || pid < 0 || flags)
return -EINVAL;
retval = sched_copy_attr(uattr, &attr);
if (retval)
return retval;
if ((int)attr.sched_policy < 0)
return -EINVAL;
if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY)
attr.sched_policy = SETPARAM_POLICY;
rcu_read_lock();
retval = -ESRCH;
p = find_process_by_pid(pid);
if (likely(p))
get_task_struct(p);
rcu_read_unlock();
if (likely(p)) {
retval = sched_setattr(p, &attr);
put_task_struct(p);
}
return retval;
}
/**
* sys_sched_getscheduler - get the policy (scheduling class) of a thread
* @pid: the pid in question.
*
* Return: On success, the policy of the thread. Otherwise, a negative error
* code.
*/
SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
{
struct task_struct *p;
int retval;
if (pid < 0)
return -EINVAL;
retval = -ESRCH;
rcu_read_lock();
p = find_process_by_pid(pid);
if (p) {
retval = security_task_getscheduler(p);
if (!retval)
retval = p->policy
| (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
}
rcu_read_unlock();
return retval;
}
/**
* sys_sched_getparam - get the RT priority of a thread
* @pid: the pid in question.
* @param: structure containing the RT priority.
*
* Return: On success, 0 and the RT priority is in @param. Otherwise, an error
* code.
*/
SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
{
struct sched_param lp = { .sched_priority = 0 };
struct task_struct *p;
int retval;
if (!param || pid < 0)
return -EINVAL;
rcu_read_lock();
p = find_process_by_pid(pid);
retval = -ESRCH;
if (!p)
goto out_unlock;
retval = security_task_getscheduler(p);
if (retval)
goto out_unlock;
if (task_has_rt_policy(p))
lp.sched_priority = p->rt_priority;
rcu_read_unlock();
/*
* This one might sleep, we cannot do it with a spinlock held ...
*/
retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
return retval;
out_unlock:
rcu_read_unlock();
return retval;
}
/*
* Copy the kernel size attribute structure (which might be larger
* than what user-space knows about) to user-space.
*
* Note that all cases are valid: user-space buffer can be larger or
* smaller than the kernel-space buffer. The usual case is that both
* have the same size.
*/
static int
sched_attr_copy_to_user(struct sched_attr __user *uattr,
struct sched_attr *kattr,
unsigned int usize)
{
unsigned int ksize = sizeof(*kattr);
if (!access_ok(uattr, usize))
return -EFAULT;
/*
* sched_getattr() ABI forwards and backwards compatibility:
*
* If usize == ksize then we just copy everything to user-space and all is good.
*
* If usize < ksize then we only copy as much as user-space has space for,
* this keeps ABI compatibility as well. We skip the rest.
*
* If usize > ksize then user-space is using a newer version of the ABI,
* which part the kernel doesn't know about. Just ignore it - tooling can
* detect the kernel's knowledge of attributes from the attr->size value
* which is set to ksize in this case.
*/
kattr->size = min(usize, ksize);
if (copy_to_user(uattr, kattr, kattr->size))
return -EFAULT;
return 0;
}
/**
* sys_sched_getattr - similar to sched_getparam, but with sched_attr
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
* @usize: sizeof(attr) for fwd/bwd comp.
* @flags: for future extension.
*/
SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
unsigned int, usize, unsigned int, flags)
{
struct sched_attr kattr = { };
struct task_struct *p;
int retval;
if (!uattr || pid < 0 || usize > PAGE_SIZE ||
usize < SCHED_ATTR_SIZE_VER0 || flags)
return -EINVAL;
rcu_read_lock();
p = find_process_by_pid(pid);
retval = -ESRCH;
if (!p)
goto out_unlock;
retval = security_task_getscheduler(p);
if (retval)
goto out_unlock;
kattr.sched_policy = p->policy;
if (p->sched_reset_on_fork)
kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
if (task_has_dl_policy(p))
__getparam_dl(p, &kattr);
else if (task_has_rt_policy(p))
kattr.sched_priority = p->rt_priority;
else
kattr.sched_nice = task_nice(p);
#ifdef CONFIG_UCLAMP_TASK
/*
* This could race with another potential updater, but this is fine
* because it'll correctly read the old or the new value. We don't need
* to guarantee who wins the race as long as it doesn't return garbage.
*/
kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
#endif
rcu_read_unlock();
return sched_attr_copy_to_user(uattr, &kattr, usize);
out_unlock:
rcu_read_unlock();
return retval;
}
long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
cpumask_var_t cpus_allowed, new_mask;
struct task_struct *p;
int retval;
rcu_read_lock();
p = find_process_by_pid(pid);
if (!p) {
rcu_read_unlock();
return -ESRCH;
}
/* Prevent p going away */
get_task_struct(p);
rcu_read_unlock();
if (p->flags & PF_NO_SETAFFINITY) {
retval = -EINVAL;
goto out_put_task;
}
if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
retval = -ENOMEM;
goto out_put_task;
}
if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
retval = -ENOMEM;
goto out_free_cpus_allowed;
}
retval = -EPERM;
if (!check_same_owner(p)) {
rcu_read_lock();
if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
rcu_read_unlock();
goto out_free_new_mask;
}
rcu_read_unlock();
}
retval = security_task_setscheduler(p);
if (retval)
goto out_free_new_mask;
cpuset_cpus_allowed(p, cpus_allowed);
cpumask_and(new_mask, in_mask, cpus_allowed);
/*
* Since bandwidth control happens on root_domain basis,
* if admission test is enabled, we only admit -deadline
* tasks allowed to run on all the CPUs in the task's
* root_domain.
*/
#ifdef CONFIG_SMP
if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
rcu_read_lock();
if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) {
retval = -EBUSY;
rcu_read_unlock();
goto out_free_new_mask;
}
rcu_read_unlock();
}
#endif
again:
retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK);
if (!retval) {
cpuset_cpus_allowed(p, cpus_allowed);
if (!cpumask_subset(new_mask, cpus_allowed)) {
/*
* We must have raced with a concurrent cpuset
* update. Just reset the cpus_allowed to the
* cpuset's cpus_allowed
*/
cpumask_copy(new_mask, cpus_allowed);
goto again;
}
}
out_free_new_mask:
free_cpumask_var(new_mask);
out_free_cpus_allowed:
free_cpumask_var(cpus_allowed);
out_put_task:
put_task_struct(p);
return retval;
}
static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
struct cpumask *new_mask)
{
if (len < cpumask_size())
cpumask_clear(new_mask);
else if (len > cpumask_size())
len = cpumask_size();
return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
}
/**
* sys_sched_setaffinity - set the CPU affinity of a process
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
* @user_mask_ptr: user-space pointer to the new CPU mask
*
* Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
unsigned long __user *, user_mask_ptr)
{
cpumask_var_t new_mask;
int retval;
if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
return -ENOMEM;
retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
if (retval == 0)
retval = sched_setaffinity(pid, new_mask);
free_cpumask_var(new_mask);
return retval;
}
long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
struct task_struct *p;
unsigned long flags;
int retval;
rcu_read_lock();
retval = -ESRCH;
p = find_process_by_pid(pid);
if (!p)
goto out_unlock;
retval = security_task_getscheduler(p);
if (retval)
goto out_unlock;
raw_spin_lock_irqsave(&p->pi_lock, flags);
cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
out_unlock:
rcu_read_unlock();
return retval;
}
/**
* sys_sched_getaffinity - get the CPU affinity of a process
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
* @user_mask_ptr: user-space pointer to hold the current CPU mask
*
* Return: size of CPU mask copied to user_mask_ptr on success. An
* error code otherwise.
*/
SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
unsigned long __user *, user_mask_ptr)
{
int ret;
cpumask_var_t mask;
if ((len * BITS_PER_BYTE) < nr_cpu_ids)
return -EINVAL;
if (len & (sizeof(unsigned long)-1))
return -EINVAL;
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
ret = sched_getaffinity(pid, mask);
if (ret == 0) {
unsigned int retlen = min(len, cpumask_size());
if (copy_to_user(user_mask_ptr, mask, retlen))
ret = -EFAULT;
else
ret = retlen;
}
free_cpumask_var(mask);
return ret;
}
static void do_sched_yield(void)
{
struct rq_flags rf;
struct rq *rq;
rq = this_rq_lock_irq(&rf);
schedstat_inc(rq->yld_count);
current->sched_class->yield_task(rq);
preempt_disable();
rq_unlock_irq(rq, &rf);
sched_preempt_enable_no_resched();
schedule();
}
/**
* sys_sched_yield - yield the current processor to other threads.
*
* This function yields the current CPU to other tasks. If there are no
* other threads running on this CPU then this function will return.
*
* Return: 0.
*/
SYSCALL_DEFINE0(sched_yield)
{
do_sched_yield();
return 0;
}
#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
int __sched __cond_resched(void)
{
if (should_resched(0)) {
preempt_schedule_common();
return 1;
}
#ifndef CONFIG_PREEMPT_RCU
rcu_all_qs();
#endif
return 0;
}
EXPORT_SYMBOL(__cond_resched);
#endif
#ifdef CONFIG_PREEMPT_DYNAMIC
DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
EXPORT_STATIC_CALL_TRAMP(cond_resched);
DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
EXPORT_STATIC_CALL_TRAMP(might_resched);
#endif
/*
* __cond_resched_lock() - if a reschedule is pending, drop the given lock,
* call schedule, and on return reacquire the lock.
*
* This works OK both with and without CONFIG_PREEMPTION. We do strange low-level
* operations here to prevent schedule() from being called twice (once via
* spin_unlock(), once by hand).
*/
int __cond_resched_lock(spinlock_t *lock)
{
int resched = should_resched(PREEMPT_LOCK_OFFSET);
int ret = 0;
lockdep_assert_held(lock);
if (spin_needbreak(lock) || resched) {
spin_unlock(lock);
if (resched)
preempt_schedule_common();
else
cpu_relax();
ret = 1;
spin_lock(lock);
}
return ret;
}
EXPORT_SYMBOL(__cond_resched_lock);
int __cond_resched_rwlock_read(rwlock_t *lock)
{
int resched = should_resched(PREEMPT_LOCK_OFFSET);
int ret = 0;
lockdep_assert_held_read(lock);
if (rwlock_needbreak(lock) || resched) {
read_unlock(lock);
if (resched)
preempt_schedule_common();
else
cpu_relax();
ret = 1;
read_lock(lock);
}
return ret;
}
EXPORT_SYMBOL(__cond_resched_rwlock_read);
int __cond_resched_rwlock_write(rwlock_t *lock)
{
int resched = should_resched(PREEMPT_LOCK_OFFSET);
int ret = 0;
lockdep_assert_held_write(lock);
if (rwlock_needbreak(lock) || resched) {
write_unlock(lock);
if (resched)
preempt_schedule_common();
else
cpu_relax();
ret = 1;
write_lock(lock);
}
return ret;
}
EXPORT_SYMBOL(__cond_resched_rwlock_write);
/**
* yield - yield the current processor to other threads.
*
* Do not ever use this function, there's a 99% chance you're doing it wrong.
*
* The scheduler is at all times free to pick the calling task as the most
* eligible task to run, if removing the yield() call from your code breaks
* it, it's already broken.
*
* Typical broken usage is:
*
* while (!event)
* yield();
*
* where one assumes that yield() will let 'the other' process run that will
* make event true. If the current task is a SCHED_FIFO task that will never
* happen. Never use yield() as a progress guarantee!!
*
* If you want to use yield() to wait for something, use wait_event().
* If you want to use yield() to be 'nice' for others, use cond_resched().
* If you still want to use yield(), do not!
*/
void __sched yield(void)
{
set_current_state(TASK_RUNNING);
do_sched_yield();
}
EXPORT_SYMBOL(yield);
/**
* yield_to - yield the current processor to another thread in
* your thread group, or accelerate that thread toward the
* processor it's on.
* @p: target task
* @preempt: whether task preemption is allowed or not
*
* It's the caller's job to ensure that the target task struct
* can't go away on us before we can do any checks.
*
* Return:
* true (>0) if we indeed boosted the target task.
* false (0) if we failed to boost the target.
* -ESRCH if there's no task to yield to.
*/
int __sched yield_to(struct task_struct *p, bool preempt)
{
struct task_struct *curr = current;
struct rq *rq, *p_rq;
unsigned long flags;
int yielded = 0;
local_irq_save(flags);
rq = this_rq();
again:
p_rq = task_rq(p);
/*
* If we're the only runnable task on the rq and target rq also
* has only one task, there's absolutely no point in yielding.
*/
if (rq->nr_running == 1 && p_rq->nr_running == 1) {
yielded = -ESRCH;
goto out_irq;
}
double_rq_lock(rq, p_rq);
if (task_rq(p) != p_rq) {
double_rq_unlock(rq, p_rq);
goto again;
}
if (!curr->sched_class->yield_to_task)
goto out_unlock;
if (curr->sched_class != p->sched_class)
goto out_unlock;
if (task_running(p_rq, p) || p->state)
goto out_unlock;
yielded = curr->sched_class->yield_to_task(rq, p);
if (yielded) {
schedstat_inc(rq->yld_count);
/*
* Make p's CPU reschedule; pick_next_entity takes care of
* fairness.
*/
if (preempt && rq != p_rq)
resched_curr(p_rq);
}
out_unlock:
double_rq_unlock(rq, p_rq);
out_irq:
local_irq_restore(flags);
if (yielded > 0)
schedule();
return yielded;
}
EXPORT_SYMBOL_GPL(yield_to);
int io_schedule_prepare(void)
{
int old_iowait = current->in_iowait;
current->in_iowait = 1;
blk_schedule_flush_plug(current);
return old_iowait;
}
void io_schedule_finish(int token)
{
current->in_iowait = token;
}
/*
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
*/
long __sched io_schedule_timeout(long timeout)
{
int token;
long ret;
token = io_schedule_prepare();
ret = schedule_timeout(timeout);
io_schedule_finish(token);
return ret;
}
EXPORT_SYMBOL(io_schedule_timeout);
void __sched io_schedule(void)
{
int token;
token = io_schedule_prepare();
schedule();
io_schedule_finish(token);
}
EXPORT_SYMBOL(io_schedule);
/**
* sys_sched_get_priority_max - return maximum RT priority.
* @policy: scheduling class.
*
* Return: On success, this syscall returns the maximum
* rt_priority that can be used by a given scheduling class.
* On failure, a negative error code is returned.
*/
SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
{
int ret = -EINVAL;
switch (policy) {
case SCHED_FIFO:
case SCHED_RR:
ret = MAX_RT_PRIO-1;
break;
case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
ret = 0;
break;
}
return ret;
}
/**
* sys_sched_get_priority_min - return minimum RT priority.
* @policy: scheduling class.
*
* Return: On success, this syscall returns the minimum
* rt_priority that can be used by a given scheduling class.
* On failure, a negative error code is returned.
*/
SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
{
int ret = -EINVAL;
switch (policy) {
case SCHED_FIFO:
case SCHED_RR:
ret = 1;
break;
case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
ret = 0;
}
return ret;
}
static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
{
struct task_struct *p;
unsigned int time_slice;
struct rq_flags rf;
struct rq *rq;
int retval;
if (pid < 0)
return -EINVAL;
retval = -ESRCH;
rcu_read_lock();
p = find_process_by_pid(pid);
if (!p)
goto out_unlock;
retval = security_task_getscheduler(p);
if (retval)
goto out_unlock;
rq = task_rq_lock(p, &rf);
time_slice = 0;
if (p->sched_class->get_rr_interval)
time_slice = p->sched_class->get_rr_interval(rq, p);
task_rq_unlock(rq, p, &rf);
rcu_read_unlock();
jiffies_to_timespec64(time_slice, t);
return 0;
out_unlock:
rcu_read_unlock();
return retval;
}
/**
* sys_sched_rr_get_interval - return the default timeslice of a process.
* @pid: pid of the process.
* @interval: userspace pointer to the timeslice value.
*
* this syscall writes the default timeslice value of a given process
* into the user-space timespec buffer. A value of '0' means infinity.
*
* Return: On success, 0 and the timeslice is in @interval. Otherwise,
* an error code.
*/
SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
struct __kernel_timespec __user *, interval)
{
struct timespec64 t;
int retval = sched_rr_get_interval(pid, &t);
if (retval == 0)
retval = put_timespec64(&t, interval);
return retval;
}
#ifdef CONFIG_COMPAT_32BIT_TIME
SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
struct old_timespec32 __user *, interval)
{
struct timespec64 t;
int retval = sched_rr_get_interval(pid, &t);
if (retval == 0)
retval = put_old_timespec32(&t, interval);
return retval;
}
#endif
void sched_show_task(struct task_struct *p)
{
unsigned long free = 0;
int ppid;
if (!try_get_task_stack(p))
return;
pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
if (p->state == TASK_RUNNING)
pr_cont(" running task ");
#ifdef CONFIG_DEBUG_STACK_USAGE
free = stack_not_used(p);
#endif
ppid = 0;
rcu_read_lock();
if (pid_alive(p))
ppid = task_pid_nr(rcu_dereference(p->real_parent));
rcu_read_unlock();
pr_cont(" stack:%5lu pid:%5d ppid:%6d flags:0x%08lx\n",
free, task_pid_nr(p), ppid,
(unsigned long)task_thread_info(p)->flags);
print_worker_info(KERN_INFO, p);
print_stop_info(KERN_INFO, p);
show_stack(p, NULL, KERN_INFO);
put_task_stack(p);
}
EXPORT_SYMBOL_GPL(sched_show_task);
static inline bool
state_filter_match(unsigned long state_filter, struct task_struct *p)
{
/* no filter, everything matches */
if (!state_filter)
return true;
/* filter, but doesn't match */
if (!(p->state & state_filter))
return false;
/*
* When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
* TASK_KILLABLE).
*/
if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE)
return false;
return true;
}
void show_state_filter(unsigned long state_filter)
{
struct task_struct *g, *p;
rcu_read_lock();
for_each_process_thread(g, p) {
/*
* reset the NMI-timeout, listing all files on a slow
* console might take a lot of time:
* Also, reset softlockup watchdogs on all CPUs, because
* another CPU might be blocked waiting for us to process
* an IPI.
*/
touch_nmi_watchdog();
touch_all_softlockup_watchdogs();
if (state_filter_match(state_filter, p))
sched_show_task(p);
}
#ifdef CONFIG_SCHED_DEBUG
if (!state_filter)
sysrq_sched_debug_show();
#endif
rcu_read_unlock();
/*
* Only show locks if all tasks are dumped:
*/
if (!state_filter)
debug_show_all_locks();
}
/**
* init_idle - set up an idle thread for a given CPU
* @idle: task in question
* @cpu: CPU the idle task belongs to
*
* NOTE: this function does not set the idle thread's NEED_RESCHED
* flag, to make booting more robust.
*/
void init_idle(struct task_struct *idle, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
__sched_fork(0, idle);
raw_spin_lock_irqsave(&idle->pi_lock, flags);
raw_spin_lock(&rq->lock);
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
idle->flags |= PF_IDLE;
scs_task_reset(idle);
kasan_unpoison_task_stack(idle);
#ifdef CONFIG_SMP
/*
* It's possible that init_idle() gets called multiple times on a task,
* in that case do_set_cpus_allowed() will not do the right thing.
*
* And since this is boot we can forgo the serialization.
*/
set_cpus_allowed_common(idle, cpumask_of(cpu), 0);
#endif
/*
* We're having a chicken and egg problem, even though we are
* holding rq->lock, the CPU isn't yet set to this CPU so the
* lockdep check in task_group() will fail.
*
* Similar case to sched_fork(). / Alternatively we could
* use task_rq_lock() here and obtain the other rq->lock.
*
* Silence PROVE_RCU
*/
rcu_read_lock();
__set_task_cpu(idle, cpu);
rcu_read_unlock();
rq->idle = idle;
rcu_assign_pointer(rq->curr, idle);
idle->on_rq = TASK_ON_RQ_QUEUED;
#ifdef CONFIG_SMP
idle->on_cpu = 1;
#endif
raw_spin_unlock(&rq->lock);
raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
/* Set the preempt count _outside_ the spinlocks! */
init_idle_preempt_count(idle, cpu);
/*
* The idle tasks have their own, simple scheduling class:
*/
idle->sched_class = &idle_sched_class;
ftrace_graph_init_idle_task(idle, cpu);
vtime_init_idle(idle, cpu);
#ifdef CONFIG_SMP
sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
#endif
}
#ifdef CONFIG_SMP
int cpuset_cpumask_can_shrink(const struct cpumask *cur,
const struct cpumask *trial)
{
int ret = 1;
if (!cpumask_weight(cur))
return ret;
ret = dl_cpuset_cpumask_can_shrink(cur, trial);
return ret;
}
int task_can_attach(struct task_struct *p,
const struct cpumask *cs_cpus_allowed)
{
int ret = 0;
/*
* Kthreads which disallow setaffinity shouldn't be moved
* to a new cpuset; we don't want to change their CPU
* affinity and isolating such threads by their set of
* allowed nodes is unnecessary. Thus, cpusets are not
* applicable for such threads. This prevents checking for
* success of set_cpus_allowed_ptr() on all attached tasks
* before cpus_mask may be changed.
*/
if (p->flags & PF_NO_SETAFFINITY) {
ret = -EINVAL;
goto out;
}
if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
cs_cpus_allowed))
ret = dl_task_can_attach(p, cs_cpus_allowed);
out:
return ret;
}
bool sched_smp_initialized __read_mostly;
#ifdef CONFIG_NUMA_BALANCING
/* Migrate current task p to target_cpu */
int migrate_task_to(struct task_struct *p, int target_cpu)
{
struct migration_arg arg = { p, target_cpu };
int curr_cpu = task_cpu(p);
if (curr_cpu == target_cpu)
return 0;
if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
return -EINVAL;
/* TODO: This is not properly updating schedstats */
trace_sched_move_numa(p, curr_cpu, target_cpu);
return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
}
/*
* Requeue a task on a given node and accurately track the number of NUMA
* tasks on the runqueues
*/
void sched_setnuma(struct task_struct *p, int nid)
{
bool queued, running;
struct rq_flags rf;
struct rq *rq;
rq = task_rq_lock(p, &rf);
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued)
dequeue_task(rq, p, DEQUEUE_SAVE);
if (running)
put_prev_task(rq, p);
p->numa_preferred_nid = nid;
if (queued)
enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
if (running)
set_next_task(rq, p);
task_rq_unlock(rq, p, &rf);
}
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_HOTPLUG_CPU
/*
* Ensure that the idle task is using init_mm right before its CPU goes
* offline.
*/
void idle_task_exit(void)
{
struct mm_struct *mm = current->active_mm;
BUG_ON(cpu_online(smp_processor_id()));
BUG_ON(current != this_rq()->idle);
if (mm != &init_mm) {
switch_mm(mm, &init_mm, current);
finish_arch_post_lock_switch();
}
/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
}
static int __balance_push_cpu_stop(void *arg)
{
struct task_struct *p = arg;
struct rq *rq = this_rq();
struct rq_flags rf;
int cpu;
raw_spin_lock_irq(&p->pi_lock);
rq_lock(rq, &rf);
update_rq_clock(rq);
if (task_rq(p) == rq && task_on_rq_queued(p)) {
cpu = select_fallback_rq(rq->cpu, p);
rq = __migrate_task(rq, &rf, p, cpu);
}
rq_unlock(rq, &rf);
raw_spin_unlock_irq(&p->pi_lock);
put_task_struct(p);
return 0;
}
static DEFINE_PER_CPU(struct cpu_stop_work, push_work);
/*
* Ensure we only run per-cpu kthreads once the CPU goes !active.
*
* This is enabled below SCHED_AP_ACTIVE; when !cpu_active(), but only
* effective when the hotplug motion is down.
*/
static void balance_push(struct rq *rq)
{
struct task_struct *push_task = rq->curr;
lockdep_assert_held(&rq->lock);
SCHED_WARN_ON(rq->cpu != smp_processor_id());
/*
* Ensure the thing is persistent until balance_push_set(.on = false);
*/
rq->balance_callback = &balance_push_callback;
/*
* Only active while going offline.
*/
if (!cpu_dying(rq->cpu))
return;
/*
* Both the cpu-hotplug and stop task are in this case and are
* required to complete the hotplug process.
*
* XXX: the idle task does not match kthread_is_per_cpu() due to
* histerical raisins.
*/
if (rq->idle == push_task ||
((push_task->flags & PF_KTHREAD) && kthread_is_per_cpu(push_task)) ||
is_migration_disabled(push_task)) {
/*
* If this is the idle task on the outgoing CPU try to wake
* up the hotplug control thread which might wait for the
* last task to vanish. The rcuwait_active() check is
* accurate here because the waiter is pinned on this CPU
* and can't obviously be running in parallel.
*
* On RT kernels this also has to check whether there are
* pinned and scheduled out tasks on the runqueue. They
* need to leave the migrate disabled section first.
*/
if (!rq->nr_running && !rq_has_pinned_tasks(rq) &&
rcuwait_active(&rq->hotplug_wait)) {
raw_spin_unlock(&rq->lock);
rcuwait_wake_up(&rq->hotplug_wait);
raw_spin_lock(&rq->lock);
}
return;
}
get_task_struct(push_task);
/*
* Temporarily drop rq->lock such that we can wake-up the stop task.
* Both preemption and IRQs are still disabled.
*/
raw_spin_unlock(&rq->lock);
stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
this_cpu_ptr(&push_work));
/*
* At this point need_resched() is true and we'll take the loop in
* schedule(). The next pick is obviously going to be the stop task
* which kthread_is_per_cpu() and will push this task away.
*/
raw_spin_lock(&rq->lock);
}
static void balance_push_set(int cpu, bool on)
{
struct rq *rq = cpu_rq(cpu);
struct rq_flags rf;
rq_lock_irqsave(rq, &rf);
if (on) {
WARN_ON_ONCE(rq->balance_callback);
rq->balance_callback = &balance_push_callback;
} else if (rq->balance_callback == &balance_push_callback) {
rq->balance_callback = NULL;
}
rq_unlock_irqrestore(rq, &rf);
}
/*
* Invoked from a CPUs hotplug control thread after the CPU has been marked
* inactive. All tasks which are not per CPU kernel threads are either
* pushed off this CPU now via balance_push() or placed on a different CPU
* during wakeup. Wait until the CPU is quiescent.
*/
static void balance_hotplug_wait(void)
{
struct rq *rq = this_rq();
rcuwait_wait_event(&rq->hotplug_wait,
rq->nr_running == 1 && !rq_has_pinned_tasks(rq),
TASK_UNINTERRUPTIBLE);
}
#else
static inline void balance_push(struct rq *rq)
{
}
static inline void balance_push_set(int cpu, bool on)
{
}
static inline void balance_hotplug_wait(void)
{
}
#endif /* CONFIG_HOTPLUG_CPU */
void set_rq_online(struct rq *rq)
{
if (!rq->online) {
const struct sched_class *class;
cpumask_set_cpu(rq->cpu, rq->rd->online);
rq->online = 1;
for_each_class(class) {
if (class->rq_online)
class->rq_online(rq);
}
}
}
void set_rq_offline(struct rq *rq)
{
if (rq->online) {
const struct sched_class *class;
for_each_class(class) {
if (class->rq_offline)
class->rq_offline(rq);
}
cpumask_clear_cpu(rq->cpu, rq->rd->online);
rq->online = 0;
}
}
/*
* used to mark begin/end of suspend/resume:
*/
static int num_cpus_frozen;
/*
* Update cpusets according to cpu_active mask. If cpusets are
* disabled, cpuset_update_active_cpus() becomes a simple wrapper
* around partition_sched_domains().
*
* If we come here as part of a suspend/resume, don't touch cpusets because we
* want to restore it back to its original state upon resume anyway.
*/
static void cpuset_cpu_active(void)
{
if (cpuhp_tasks_frozen) {
/*
* num_cpus_frozen tracks how many CPUs are involved in suspend
* resume sequence. As long as this is not the last online
* operation in the resume sequence, just build a single sched
* domain, ignoring cpusets.
*/
partition_sched_domains(1, NULL, NULL);
if (--num_cpus_frozen)
return;
/*
* This is the last CPU online operation. So fall through and
* restore the original sched domains by considering the
* cpuset configurations.
*/
cpuset_force_rebuild();
}
cpuset_update_active_cpus();
}
static int cpuset_cpu_inactive(unsigned int cpu)
{
if (!cpuhp_tasks_frozen) {
if (dl_cpu_busy(cpu))
return -EBUSY;
cpuset_update_active_cpus();
} else {
num_cpus_frozen++;
partition_sched_domains(1, NULL, NULL);
}
return 0;
}
int sched_cpu_activate(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct rq_flags rf;
/*
* Clear the balance_push callback and prepare to schedule
* regular tasks.
*/
balance_push_set(cpu, false);
#ifdef CONFIG_SCHED_SMT
/*
* When going up, increment the number of cores with SMT present.
*/
if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
static_branch_inc_cpuslocked(&sched_smt_present);
#endif
set_cpu_active(cpu, true);
if (sched_smp_initialized) {
sched_domains_numa_masks_set(cpu);
cpuset_cpu_active();
}
/*
* Put the rq online, if not already. This happens:
*
* 1) In the early boot process, because we build the real domains
* after all CPUs have been brought up.
*
* 2) At runtime, if cpuset_cpu_active() fails to rebuild the
* domains.
*/
rq_lock_irqsave(rq, &rf);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_online(rq);
}
rq_unlock_irqrestore(rq, &rf);
return 0;
}
int sched_cpu_deactivate(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct rq_flags rf;
int ret;
/*
* Remove CPU from nohz.idle_cpus_mask to prevent participating in
* load balancing when not active
*/
nohz_balance_exit_idle(rq);
set_cpu_active(cpu, false);
/*
* From this point forward, this CPU will refuse to run any task that
* is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively
* push those tasks away until this gets cleared, see
* sched_cpu_dying().
*/
balance_push_set(cpu, true);
/*
* We've cleared cpu_active_mask / set balance_push, wait for all
* preempt-disabled and RCU users of this state to go away such that
* all new such users will observe it.
*
* Specifically, we rely on ttwu to no longer target this CPU, see
* ttwu_queue_cond() and is_cpu_allowed().
*
* Do sync before park smpboot threads to take care the rcu boost case.
*/
synchronize_rcu();
rq_lock_irqsave(rq, &rf);
if (rq->rd) {
update_rq_clock(rq);
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
}
rq_unlock_irqrestore(rq, &rf);
#ifdef CONFIG_SCHED_SMT
/*
* When going down, decrement the number of cores with SMT present.
*/
if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
static_branch_dec_cpuslocked(&sched_smt_present);
#endif
if (!sched_smp_initialized)
return 0;
ret = cpuset_cpu_inactive(cpu);
if (ret) {
balance_push_set(cpu, false);
set_cpu_active(cpu, true);
return ret;
}
sched_domains_numa_masks_clear(cpu);
return 0;
}
static void sched_rq_cpu_starting(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
rq->calc_load_update = calc_load_update;
update_max_interval();
}
int sched_cpu_starting(unsigned int cpu)
{
sched_rq_cpu_starting(cpu);
sched_tick_start(cpu);
return 0;
}
#ifdef CONFIG_HOTPLUG_CPU
/*
* Invoked immediately before the stopper thread is invoked to bring the
* CPU down completely. At this point all per CPU kthreads except the
* hotplug thread (current) and the stopper thread (inactive) have been
* either parked or have been unbound from the outgoing CPU. Ensure that
* any of those which might be on the way out are gone.
*
* If after this point a bound task is being woken on this CPU then the
* responsible hotplug callback has failed to do it's job.
* sched_cpu_dying() will catch it with the appropriate fireworks.
*/
int sched_cpu_wait_empty(unsigned int cpu)
{
balance_hotplug_wait();
return 0;
}
/*
* Since this CPU is going 'away' for a while, fold any nr_active delta we
* might have. Called from the CPU stopper task after ensuring that the
* stopper is the last running task on the CPU, so nr_active count is
* stable. We need to take the teardown thread which is calling this into
* account, so we hand in adjust = 1 to the load calculation.
*
* Also see the comment "Global load-average calculations".
*/
static void calc_load_migrate(struct rq *rq)
{
long delta = calc_load_fold_active(rq, 1);
if (delta)
atomic_long_add(delta, &calc_load_tasks);
}
static void dump_rq_tasks(struct rq *rq, const char *loglvl)
{
struct task_struct *g, *p;
int cpu = cpu_of(rq);
lockdep_assert_held(&rq->lock);
printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running);
for_each_process_thread(g, p) {
if (task_cpu(p) != cpu)
continue;
if (!task_on_rq_queued(p))
continue;
printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm);
}
}
int sched_cpu_dying(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct rq_flags rf;
/* Handle pending wakeups and then migrate everything off */
sched_tick_stop(cpu);
rq_lock_irqsave(rq, &rf);
if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) {
WARN(true, "Dying CPU not properly vacated!");
dump_rq_tasks(rq, KERN_WARNING);
}
rq_unlock_irqrestore(rq, &rf);
calc_load_migrate(rq);
update_max_interval();
hrtick_clear(rq);
return 0;
}
#endif
void __init sched_init_smp(void)
{
sched_init_numa();
/*
* There's no userspace yet to cause hotplug operations; hence all the
* CPU masks are stable and all blatant races in the below code cannot
* happen.
*/
mutex_lock(&sched_domains_mutex);
sched_init_domains(cpu_active_mask);
mutex_unlock(&sched_domains_mutex);
/* Move init over to a non-isolated CPU */
if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
BUG();
sched_init_granularity();
init_sched_rt_class();
init_sched_dl_class();
sched_smp_initialized = true;
}
static int __init migration_init(void)
{
sched_cpu_starting(smp_processor_id());
return 0;
}
early_initcall(migration_init);
#else
void __init sched_init_smp(void)
{
sched_init_granularity();
}
#endif /* CONFIG_SMP */
int in_sched_functions(unsigned long addr)
{
return in_lock_functions(addr) ||
(addr >= (unsigned long)__sched_text_start
&& addr < (unsigned long)__sched_text_end);
}
#ifdef CONFIG_CGROUP_SCHED
/*
* Default task group.
* Every task in system belongs to this group at bootup.
*/
struct task_group root_task_group;
LIST_HEAD(task_groups);
/* Cacheline aligned slab cache for task_group */
static struct kmem_cache *task_group_cache __read_mostly;
#endif
DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
void __init sched_init(void)
{
unsigned long ptr = 0;
int i;
/* Make sure the linker didn't screw up */
BUG_ON(&idle_sched_class + 1 != &fair_sched_class ||
&fair_sched_class + 1 != &rt_sched_class ||
&rt_sched_class + 1 != &dl_sched_class);
#ifdef CONFIG_SMP
BUG_ON(&dl_sched_class + 1 != &stop_sched_class);
#endif
wait_bit_init();
#ifdef CONFIG_FAIR_GROUP_SCHED
ptr += 2 * nr_cpu_ids * sizeof(void **);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
ptr += 2 * nr_cpu_ids * sizeof(void **);
#endif
if (ptr) {
ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT);
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.se = (struct sched_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.cfs_rq = (struct cfs_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.rt_rq = (struct rt_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
#endif /* CONFIG_RT_GROUP_SCHED */
}
#ifdef CONFIG_CPUMASK_OFFSTACK
for_each_possible_cpu(i) {
per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
cpumask_size(), GFP_KERNEL, cpu_to_node(i));
per_cpu(select_idle_mask, i) = (cpumask_var_t)kzalloc_node(
cpumask_size(), GFP_KERNEL, cpu_to_node(i));
}
#endif /* CONFIG_CPUMASK_OFFSTACK */
init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime());
#ifdef CONFIG_SMP
init_defrootdomain();
#endif
#ifdef CONFIG_RT_GROUP_SCHED
init_rt_bandwidth(&root_task_group.rt_bandwidth,
global_rt_period(), global_rt_runtime());
#endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_CGROUP_SCHED
task_group_cache = KMEM_CACHE(task_group, 0);
list_add(&root_task_group.list, &task_groups);
INIT_LIST_HEAD(&root_task_group.children);
INIT_LIST_HEAD(&root_task_group.siblings);
autogroup_init(&init_task);
#endif /* CONFIG_CGROUP_SCHED */
for_each_possible_cpu(i) {
struct rq *rq;
rq = cpu_rq(i);
raw_spin_lock_init(&rq->lock);
rq->nr_running = 0;
rq->calc_load_active = 0;
rq->calc_load_update = jiffies + LOAD_FREQ;
init_cfs_rq(&rq->cfs);
init_rt_rq(&rq->rt);
init_dl_rq(&rq->dl);
#ifdef CONFIG_FAIR_GROUP_SCHED
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
/*
* How much CPU bandwidth does root_task_group get?
*
* In case of task-groups formed thr' the cgroup filesystem, it
* gets 100% of the CPU resources in the system. This overall
* system CPU resource is divided among the tasks of
* root_task_group and its child task-groups in a fair manner,
* based on each entity's (task or task-group's) weight
* (se->load.weight).
*
* In other words, if root_task_group has 10 tasks of weight
* 1024) and two child groups A0 and A1 (of weight 1024 each),
* then A0's share of the CPU resource is:
*
* A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
*
* We achieve this by letting root_task_group's tasks sit
* directly in rq->cfs (i.e root_task_group->se[] = NULL).
*/
init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
#endif
#ifdef CONFIG_SMP
rq->sd = NULL;
rq->rd = NULL;
rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
rq->balance_callback = &balance_push_callback;
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
rq->cpu = i;
rq->online = 0;
rq->idle_stamp = 0;
rq->avg_idle = 2*sysctl_sched_migration_cost;
rq->max_idle_balance_cost = sysctl_sched_migration_cost;
INIT_LIST_HEAD(&rq->cfs_tasks);
rq_attach_root(rq, &def_root_domain);
#ifdef CONFIG_NO_HZ_COMMON
rq->last_blocked_load_update_tick = jiffies;
atomic_set(&rq->nohz_flags, 0);
INIT_CSD(&rq->nohz_csd, nohz_csd_func, rq);
#endif
#ifdef CONFIG_HOTPLUG_CPU
rcuwait_init(&rq->hotplug_wait);
#endif
#endif /* CONFIG_SMP */
hrtick_rq_init(rq);
atomic_set(&rq->nr_iowait, 0);
}
set_load_weight(&init_task, false);
/*
* The boot idle thread does lazy MMU switching as well:
*/
mmgrab(&init_mm);
enter_lazy_tlb(&init_mm, current);
/*
* Make us the idle thread. Technically, schedule() should not be
* called from this thread, however somewhere below it might be,
* but because we are the idle thread, we just pick up running again
* when this runqueue becomes "idle".
*/
init_idle(current, smp_processor_id());
calc_load_update = jiffies + LOAD_FREQ;
#ifdef CONFIG_SMP
idle_thread_set_boot_cpu();
balance_push_set(smp_processor_id(), false);
#endif
init_sched_fair_class();
init_schedstats();
psi_init();
init_uclamp();
scheduler_running = 1;
}
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
static inline int preempt_count_equals(int preempt_offset)
{
int nested = preempt_count() + rcu_preempt_depth();
return (nested == preempt_offset);
}
void __might_sleep(const char *file, int line, int preempt_offset)
{
/*
* Blocking primitives will set (and therefore destroy) current->state,
* since we will exit with TASK_RUNNING make sure we enter with it,
* otherwise we will destroy state.
*/
WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change,
"do not call blocking ops when !TASK_RUNNING; "
"state=%lx set at [<%p>] %pS\n",
current->state,
(void *)current->task_state_change,
(void *)current->task_state_change);
___might_sleep(file, line, preempt_offset);
}
EXPORT_SYMBOL(__might_sleep);
void ___might_sleep(const char *file, int line, int preempt_offset)
{
/* Ratelimiting timestamp: */
static unsigned long prev_jiffy;
unsigned long preempt_disable_ip;
/* WARN_ON_ONCE() by default, no rate limit required: */
rcu_sleep_check();
if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
!is_idle_task(current) && !current->non_block_count) ||
system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
oops_in_progress)
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
prev_jiffy = jiffies;
/* Save this before calling printk(), since that will clobber it: */
preempt_disable_ip = get_preempt_disable_ip(current);
printk(KERN_ERR
"BUG: sleeping function called from invalid context at %s:%d\n",
file, line);
printk(KERN_ERR
"in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
in_atomic(), irqs_disabled(), current->non_block_count,
current->pid, current->comm);
if (task_stack_end_corrupted(current))
printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
debug_show_held_locks(current);
if (irqs_disabled())
print_irqtrace_events(current);
if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
&& !preempt_count_equals(preempt_offset)) {
pr_err("Preemption disabled at:");
print_ip_sym(KERN_ERR, preempt_disable_ip);
}
dump_stack();
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
EXPORT_SYMBOL(___might_sleep);
void __cant_sleep(const char *file, int line, int preempt_offset)
{
static unsigned long prev_jiffy;
if (irqs_disabled())
return;
if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
return;
if (preempt_count() > preempt_offset)
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
prev_jiffy = jiffies;
printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line);
printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
in_atomic(), irqs_disabled(),
current->pid, current->comm);
debug_show_held_locks(current);
dump_stack();
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
EXPORT_SYMBOL_GPL(__cant_sleep);
#ifdef CONFIG_SMP
void __cant_migrate(const char *file, int line)
{
static unsigned long prev_jiffy;
if (irqs_disabled())
return;
if (is_migration_disabled(current))
return;
if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
return;
if (preempt_count() > 0)
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
prev_jiffy = jiffies;
pr_err("BUG: assuming non migratable context at %s:%d\n", file, line);
pr_err("in_atomic(): %d, irqs_disabled(): %d, migration_disabled() %u pid: %d, name: %s\n",
in_atomic(), irqs_disabled(), is_migration_disabled(current),
current->pid, current->comm);
debug_show_held_locks(current);
dump_stack();
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
EXPORT_SYMBOL_GPL(__cant_migrate);
#endif
#endif
#ifdef CONFIG_MAGIC_SYSRQ
void normalize_rt_tasks(void)
{
struct task_struct *g, *p;
struct sched_attr attr = {
.sched_policy = SCHED_NORMAL,
};
read_lock(&tasklist_lock);
for_each_process_thread(g, p) {
/*
* Only normalize user tasks:
*/
if (p->flags & PF_KTHREAD)
continue;
p->se.exec_start = 0;
schedstat_set(p->se.statistics.wait_start, 0);
schedstat_set(p->se.statistics.sleep_start, 0);
schedstat_set(p->se.statistics.block_start, 0);
if (!dl_task(p) && !rt_task(p)) {
/*
* Renice negative nice level userspace
* tasks back to 0:
*/
if (task_nice(p) < 0)
set_user_nice(p, 0);
continue;
}
__sched_setscheduler(p, &attr, false, false);
}
read_unlock(&tasklist_lock);
}
#endif /* CONFIG_MAGIC_SYSRQ */
#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
/*
* These functions are only useful for the IA64 MCA handling, or kdb.
*
* They can only be called when the whole system has been
* stopped - every CPU needs to be quiescent, and no scheduling
* activity can take place. Using them for anything else would
* be a serious bug, and as a result, they aren't even visible
* under any other configuration.
*/
/**
* curr_task - return the current task for a given CPU.
* @cpu: the processor in question.
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
*
* Return: The current task for @cpu.
*/
struct task_struct *curr_task(int cpu)
{
return cpu_curr(cpu);
}
#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */
#ifdef CONFIG_IA64
/**
* ia64_set_curr_task - set the current task for a given CPU.
* @cpu: the processor in question.
* @p: the task pointer to set.
*
* Description: This function must only be used when non-maskable interrupts
* are serviced on a separate stack. It allows the architecture to switch the
* notion of the current task on a CPU in a non-blocking manner. This function
* must be called with all CPU's synchronized, and interrupts disabled, the
* and caller must save the original value of the current task (see
* curr_task() above) and restore that value before reenabling interrupts and
* re-starting the system.
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
*/
void ia64_set_curr_task(int cpu, struct task_struct *p)
{
cpu_curr(cpu) = p;
}
#endif
#ifdef CONFIG_CGROUP_SCHED
/* task_group_lock serializes the addition/removal of task groups */
static DEFINE_SPINLOCK(task_group_lock);
static inline void alloc_uclamp_sched_group(struct task_group *tg,
struct task_group *parent)
{
#ifdef CONFIG_UCLAMP_TASK_GROUP
enum uclamp_id clamp_id;
for_each_clamp_id(clamp_id) {
uclamp_se_set(&tg->uclamp_req[clamp_id],
uclamp_none(clamp_id), false);
tg->uclamp[clamp_id] = parent->uclamp[clamp_id];
}
#endif
}
static void sched_free_group(struct task_group *tg)
{
free_fair_sched_group(tg);
free_rt_sched_group(tg);
autogroup_free(tg);
kmem_cache_free(task_group_cache, tg);
}
/* allocate runqueue etc for a new task group */
struct task_group *sched_create_group(struct task_group *parent)
{
struct task_group *tg;
tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
if (!tg)
return ERR_PTR(-ENOMEM);
if (!alloc_fair_sched_group(tg, parent))
goto err;
if (!alloc_rt_sched_group(tg, parent))
goto err;
alloc_uclamp_sched_group(tg, parent);
return tg;
err:
sched_free_group(tg);
return ERR_PTR(-ENOMEM);
}
void sched_online_group(struct task_group *tg, struct task_group *parent)
{
unsigned long flags;
spin_lock_irqsave(&task_group_lock, flags);
list_add_rcu(&tg->list, &task_groups);
/* Root should already exist: */
WARN_ON(!parent);
tg->parent = parent;
INIT_LIST_HEAD(&tg->children);
list_add_rcu(&tg->siblings, &parent->children);
spin_unlock_irqrestore(&task_group_lock, flags);
online_fair_sched_group(tg);
}
/* rcu callback to free various structures associated with a task group */
static void sched_free_group_rcu(struct rcu_head *rhp)
{
/* Now it should be safe to free those cfs_rqs: */
sched_free_group(container_of(rhp, struct task_group, rcu));
}
void sched_destroy_group(struct task_group *tg)
{
/* Wait for possible concurrent references to cfs_rqs complete: */
call_rcu(&tg->rcu, sched_free_group_rcu);
}
void sched_offline_group(struct task_group *tg)
{
unsigned long flags;
/* End participation in shares distribution: */
unregister_fair_sched_group(tg);
spin_lock_irqsave(&task_group_lock, flags);
list_del_rcu(&tg->list);
list_del_rcu(&tg->siblings);
spin_unlock_irqrestore(&task_group_lock, flags);
}
static void sched_change_group(struct task_struct *tsk, int type)
{
struct task_group *tg;
/*
* All callers are synchronized by task_rq_lock(); we do not use RCU
* which is pointless here. Thus, we pass "true" to task_css_check()
* to prevent lockdep warnings.
*/
tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
struct task_group, css);
tg = autogroup_task_group(tsk, tg);
tsk->sched_task_group = tg;
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->task_change_group)
tsk->sched_class->task_change_group(tsk, type);
else
#endif
set_task_rq(tsk, task_cpu(tsk));
}
/*
* Change task's runqueue when it moves between groups.
*
* The caller of this function should have put the task in its new group by
* now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
* its new group.
*/
void sched_move_task(struct task_struct *tsk)
{
int queued, running, queue_flags =
DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
struct rq_flags rf;
struct rq *rq;
rq = task_rq_lock(tsk, &rf);
update_rq_clock(rq);
running = task_current(rq, tsk);
queued = task_on_rq_queued(tsk);
if (queued)
dequeue_task(rq, tsk, queue_flags);
if (running)
put_prev_task(rq, tsk);
sched_change_group(tsk, TASK_MOVE_GROUP);
if (queued)
enqueue_task(rq, tsk, queue_flags);
if (running) {
set_next_task(rq, tsk);
/*
* After changing group, the running task may have joined a
* throttled one but it's still the running task. Trigger a
* resched to make sure that task can still run.
*/
resched_curr(rq);
}
task_rq_unlock(rq, tsk, &rf);
}
static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
{
return css ? container_of(css, struct task_group, css) : NULL;
}
static struct cgroup_subsys_state *
cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct task_group *parent = css_tg(parent_css);
struct task_group *tg;
if (!parent) {
/* This is early initialization for the top cgroup */
return &root_task_group.css;
}
tg = sched_create_group(parent);
if (IS_ERR(tg))
return ERR_PTR(-ENOMEM);
return &tg->css;
}
/* Expose task group only after completing cgroup initialization */
static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
struct task_group *parent = css_tg(css->parent);
if (parent)
sched_online_group(tg, parent);
#ifdef CONFIG_UCLAMP_TASK_GROUP
/* Propagate the effective uclamp value for the new group */
cpu_util_update_eff(css);
#endif
return 0;
}
static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
sched_offline_group(tg);
}
static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
/*
* Relies on the RCU grace period between css_released() and this.
*/
sched_free_group(tg);
}
/*
* This is called before wake_up_new_task(), therefore we really only
* have to set its group bits, all the other stuff does not apply.
*/
static void cpu_cgroup_fork(struct task_struct *task)
{
struct rq_flags rf;
struct rq *rq;
rq = task_rq_lock(task, &rf);
update_rq_clock(rq);
sched_change_group(task, TASK_SET_GROUP);
task_rq_unlock(rq, task, &rf);
}
static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
{
struct task_struct *task;
struct cgroup_subsys_state *css;
int ret = 0;
cgroup_taskset_for_each(task, css, tset) {
#ifdef CONFIG_RT_GROUP_SCHED
if (!sched_rt_can_attach(css_tg(css), task))
return -EINVAL;
#endif
/*
* Serialize against wake_up_new_task() such that if it's
* running, we're sure to observe its full state.
*/
raw_spin_lock_irq(&task->pi_lock);
/*
* Avoid calling sched_move_task() before wake_up_new_task()
* has happened. This would lead to problems with PELT, due to
* move wanting to detach+attach while we're not attached yet.
*/
if (task->state == TASK_NEW)
ret = -EINVAL;
raw_spin_unlock_irq(&task->pi_lock);
if (ret)
break;
}
return ret;
}
static void cpu_cgroup_attach(struct cgroup_taskset *tset)
{
struct task_struct *task;
struct cgroup_subsys_state *css;
cgroup_taskset_for_each(task, css, tset)
sched_move_task(task);
}
#ifdef CONFIG_UCLAMP_TASK_GROUP
static void cpu_util_update_eff(struct cgroup_subsys_state *css)
{
struct cgroup_subsys_state *top_css = css;
struct uclamp_se *uc_parent = NULL;
struct uclamp_se *uc_se = NULL;
unsigned int eff[UCLAMP_CNT];
enum uclamp_id clamp_id;
unsigned int clamps;
css_for_each_descendant_pre(css, top_css) {
uc_parent = css_tg(css)->parent
? css_tg(css)->parent->uclamp : NULL;
for_each_clamp_id(clamp_id) {
/* Assume effective clamps matches requested clamps */
eff[clamp_id] = css_tg(css)->uclamp_req[clamp_id].value;
/* Cap effective clamps with parent's effective clamps */
if (uc_parent &&
eff[clamp_id] > uc_parent[clamp_id].value) {
eff[clamp_id] = uc_parent[clamp_id].value;
}
}
/* Ensure protection is always capped by limit */
eff[UCLAMP_MIN] = min(eff[UCLAMP_MIN], eff[UCLAMP_MAX]);
/* Propagate most restrictive effective clamps */
clamps = 0x0;
uc_se = css_tg(css)->uclamp;
for_each_clamp_id(clamp_id) {
if (eff[clamp_id] == uc_se[clamp_id].value)
continue;
uc_se[clamp_id].value = eff[clamp_id];
uc_se[clamp_id].bucket_id = uclamp_bucket_id(eff[clamp_id]);
clamps |= (0x1 << clamp_id);
}
if (!clamps) {
css = css_rightmost_descendant(css);
continue;
}
/* Immediately update descendants RUNNABLE tasks */
uclamp_update_active_tasks(css, clamps);
}
}
/*
* Integer 10^N with a given N exponent by casting to integer the literal "1eN"
* C expression. Since there is no way to convert a macro argument (N) into a
* character constant, use two levels of macros.
*/
#define _POW10(exp) ((unsigned int)1e##exp)
#define POW10(exp) _POW10(exp)
struct uclamp_request {
#define UCLAMP_PERCENT_SHIFT 2
#define UCLAMP_PERCENT_SCALE (100 * POW10(UCLAMP_PERCENT_SHIFT))
s64 percent;
u64 util;
int ret;
};
static inline struct uclamp_request
capacity_from_percent(char *buf)
{
struct uclamp_request req = {
.percent = UCLAMP_PERCENT_SCALE,
.util = SCHED_CAPACITY_SCALE,
.ret = 0,
};
buf = strim(buf);
if (strcmp(buf, "max")) {
req.ret = cgroup_parse_float(buf, UCLAMP_PERCENT_SHIFT,
&req.percent);
if (req.ret)
return req;
if ((u64)req.percent > UCLAMP_PERCENT_SCALE) {
req.ret = -ERANGE;
return req;
}
req.util = req.percent << SCHED_CAPACITY_SHIFT;
req.util = DIV_ROUND_CLOSEST_ULL(req.util, UCLAMP_PERCENT_SCALE);
}
return req;
}
static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off,
enum uclamp_id clamp_id)
{
struct uclamp_request req;
struct task_group *tg;
req = capacity_from_percent(buf);
if (req.ret)
return req.ret;
static_branch_enable(&sched_uclamp_used);
mutex_lock(&uclamp_mutex);
rcu_read_lock();
tg = css_tg(of_css(of));
if (tg->uclamp_req[clamp_id].value != req.util)
uclamp_se_set(&tg->uclamp_req[clamp_id], req.util, false);
/*
* Because of not recoverable conversion rounding we keep track of the
* exact requested value
*/
tg->uclamp_pct[clamp_id] = req.percent;
/* Update effective clamps to track the most restrictive value */
cpu_util_update_eff(of_css(of));
rcu_read_unlock();
mutex_unlock(&uclamp_mutex);
return nbytes;
}
static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MIN);
}
static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
char *buf, size_t nbytes,
loff_t off)
{
return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MAX);
}
static inline void cpu_uclamp_print(struct seq_file *sf,
enum uclamp_id clamp_id)
{
struct task_group *tg;
u64 util_clamp;
u64 percent;
u32 rem;
rcu_read_lock();
tg = css_tg(seq_css(sf));
util_clamp = tg->uclamp_req[clamp_id].value;
rcu_read_unlock();
if (util_clamp == SCHED_CAPACITY_SCALE) {
seq_puts(sf, "max\n");
return;
}
percent = tg->uclamp_pct[clamp_id];
percent = div_u64_rem(percent, POW10(UCLAMP_PERCENT_SHIFT), &rem);
seq_printf(sf, "%llu.%0*u\n", percent, UCLAMP_PERCENT_SHIFT, rem);
}
static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
{
cpu_uclamp_print(sf, UCLAMP_MIN);
return 0;
}
static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
{
cpu_uclamp_print(sf, UCLAMP_MAX);
return 0;
}
#endif /* CONFIG_UCLAMP_TASK_GROUP */
#ifdef CONFIG_FAIR_GROUP_SCHED
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 shareval)
{
if (shareval > scale_load_down(ULONG_MAX))
shareval = MAX_SHARES;
return sched_group_set_shares(css_tg(css), scale_load(shareval));
}
static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
struct task_group *tg = css_tg(css);
return (u64) scale_load_down(tg->shares);
}
#ifdef CONFIG_CFS_BANDWIDTH
static DEFINE_MUTEX(cfs_constraints_mutex);
const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
/* More than 203 days if BW_SHIFT equals 20. */
static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
{
int i, ret = 0, runtime_enabled, runtime_was_enabled;
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
if (tg == &root_task_group)
return -EINVAL;
/*
* Ensure we have at some amount of bandwidth every period. This is
* to prevent reaching a state of large arrears when throttled via
* entity_tick() resulting in prolonged exit starvation.
*/
if (quota < min_cfs_quota_period || period < min_cfs_quota_period)
return -EINVAL;
/*
* Likewise, bound things on the other side by preventing insane quota
* periods. This also allows us to normalize in computing quota
* feasibility.
*/
if (period > max_cfs_quota_period)
return -EINVAL;
/*
* Bound quota to defend quota against overflow during bandwidth shift.
*/
if (quota != RUNTIME_INF && quota > max_cfs_runtime)
return -EINVAL;
/*
* Prevent race between setting of cfs_rq->runtime_enabled and
* unthrottle_offline_cfs_rqs().
*/
get_online_cpus();
mutex_lock(&cfs_constraints_mutex);
ret = __cfs_schedulable(tg, period, quota);
if (ret)
goto out_unlock;
runtime_enabled = quota != RUNTIME_INF;
runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
/*
* If we need to toggle cfs_bandwidth_used, off->on must occur
* before making related changes, and on->off must occur afterwards
*/
if (runtime_enabled && !runtime_was_enabled)
cfs_bandwidth_usage_inc();
raw_spin_lock_irq(&cfs_b->lock);
cfs_b->period = ns_to_ktime(period);
cfs_b->quota = quota;
__refill_cfs_bandwidth_runtime(cfs_b);
/* Restart the period timer (if active) to handle new period expiry: */
if (runtime_enabled)
start_cfs_bandwidth(cfs_b);
raw_spin_unlock_irq(&cfs_b->lock);
for_each_online_cpu(i) {
struct cfs_rq *cfs_rq = tg->cfs_rq[i];
struct rq *rq = cfs_rq->rq;
struct rq_flags rf;
rq_lock_irq(rq, &rf);
cfs_rq->runtime_enabled = runtime_enabled;
cfs_rq->runtime_remaining = 0;
if (cfs_rq->throttled)
unthrottle_cfs_rq(cfs_rq);
rq_unlock_irq(rq, &rf);
}
if (runtime_was_enabled && !runtime_enabled)
cfs_bandwidth_usage_dec();
out_unlock:
mutex_unlock(&cfs_constraints_mutex);
put_online_cpus();
return ret;
}
static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
{
u64 quota, period;
period = ktime_to_ns(tg->cfs_bandwidth.period);
if (cfs_quota_us < 0)
quota = RUNTIME_INF;
else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
quota = (u64)cfs_quota_us * NSEC_PER_USEC;
else
return -EINVAL;
return tg_set_cfs_bandwidth(tg, period, quota);
}
static long tg_get_cfs_quota(struct task_group *tg)
{
u64 quota_us;
if (tg->cfs_bandwidth.quota == RUNTIME_INF)
return -1;
quota_us = tg->cfs_bandwidth.quota;
do_div(quota_us, NSEC_PER_USEC);
return quota_us;
}
static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
{
u64 quota, period;
if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
return -EINVAL;
period = (u64)cfs_period_us * NSEC_PER_USEC;
quota = tg->cfs_bandwidth.quota;
return tg_set_cfs_bandwidth(tg, period, quota);
}
static long tg_get_cfs_period(struct task_group *tg)
{
u64 cfs_period_us;
cfs_period_us = ktime_to_ns(tg->cfs_bandwidth.period);
do_div(cfs_period_us, NSEC_PER_USEC);
return cfs_period_us;
}
static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return tg_get_cfs_quota(css_tg(css));
}
static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
struct cftype *cftype, s64 cfs_quota_us)
{
return tg_set_cfs_quota(css_tg(css), cfs_quota_us);
}
static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return tg_get_cfs_period(css_tg(css));
}
static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 cfs_period_us)
{
return tg_set_cfs_period(css_tg(css), cfs_period_us);
}
struct cfs_schedulable_data {
struct task_group *tg;
u64 period, quota;
};
/*
* normalize group quota/period to be quota/max_period
* note: units are usecs
*/
static u64 normalize_cfs_quota(struct task_group *tg,
struct cfs_schedulable_data *d)
{
u64 quota, period;
if (tg == d->tg) {
period = d->period;
quota = d->quota;
} else {
period = tg_get_cfs_period(tg);
quota = tg_get_cfs_quota(tg);
}
/* note: these should typically be equivalent */
if (quota == RUNTIME_INF || quota == -1)
return RUNTIME_INF;
return to_ratio(period, quota);
}
static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
{
struct cfs_schedulable_data *d = data;
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
s64 quota = 0, parent_quota = -1;
if (!tg->parent) {
quota = RUNTIME_INF;
} else {
struct cfs_bandwidth *parent_b = &tg->parent->cfs_bandwidth;
quota = normalize_cfs_quota(tg, d);
parent_quota = parent_b->hierarchical_quota;
/*
* Ensure max(child_quota) <= parent_quota. On cgroup2,
* always take the min. On cgroup1, only inherit when no
* limit is set:
*/
if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
quota = min(quota, parent_quota);
} else {
if (quota == RUNTIME_INF)
quota = parent_quota;
else if (parent_quota != RUNTIME_INF && quota > parent_quota)
return -EINVAL;
}
}
cfs_b->hierarchical_quota = quota;
return 0;
}
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
{
int ret;
struct cfs_schedulable_data data = {
.tg = tg,
.period = period,
.quota = quota,
};
if (quota != RUNTIME_INF) {
do_div(data.period, NSEC_PER_USEC);
do_div(data.quota, NSEC_PER_USEC);
}
rcu_read_lock();
ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
rcu_read_unlock();
return ret;
}
static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
{
struct task_group *tg = css_tg(seq_css(sf));
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods);
seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
if (schedstat_enabled() && tg != &root_task_group) {
u64 ws = 0;
int i;
for_each_possible_cpu(i)
ws += schedstat_val(tg->se[i]->statistics.wait_sum);
seq_printf(sf, "wait_sum %llu\n", ws);
}
return 0;
}
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
struct cftype *cft, s64 val)
{
return sched_group_set_rt_runtime(css_tg(css), val);
}
static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return sched_group_rt_runtime(css_tg(css));
}
static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 rt_period_us)
{
return sched_group_set_rt_period(css_tg(css), rt_period_us);
}
static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return sched_group_rt_period(css_tg(css));
}
#endif /* CONFIG_RT_GROUP_SCHED */
static struct cftype cpu_legacy_files[] = {
#ifdef CONFIG_FAIR_GROUP_SCHED
{
.name = "shares",
.read_u64 = cpu_shares_read_u64,
.write_u64 = cpu_shares_write_u64,
},
#endif
#ifdef CONFIG_CFS_BANDWIDTH
{
.name = "cfs_quota_us",
.read_s64 = cpu_cfs_quota_read_s64,
.write_s64 = cpu_cfs_quota_write_s64,
},
{
.name = "cfs_period_us",
.read_u64 = cpu_cfs_period_read_u64,
.write_u64 = cpu_cfs_period_write_u64,
},
{
.name = "stat",
.seq_show = cpu_cfs_stat_show,
},
#endif
#ifdef CONFIG_RT_GROUP_SCHED
{
.name = "rt_runtime_us",
.read_s64 = cpu_rt_runtime_read,
.write_s64 = cpu_rt_runtime_write,
},
{
.name = "rt_period_us",
.read_u64 = cpu_rt_period_read_uint,
.write_u64 = cpu_rt_period_write_uint,
},
#endif
#ifdef CONFIG_UCLAMP_TASK_GROUP
{
.name = "uclamp.min",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cpu_uclamp_min_show,
.write = cpu_uclamp_min_write,
},
{
.name = "uclamp.max",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cpu_uclamp_max_show,
.write = cpu_uclamp_max_write,
},
#endif
{ } /* Terminate */
};
static int cpu_extra_stat_show(struct seq_file *sf,
struct cgroup_subsys_state *css)
{
#ifdef CONFIG_CFS_BANDWIDTH
{
struct task_group *tg = css_tg(css);
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
u64 throttled_usec;
throttled_usec = cfs_b->throttled_time;
do_div(throttled_usec, NSEC_PER_USEC);
seq_printf(sf, "nr_periods %d\n"
"nr_throttled %d\n"
"throttled_usec %llu\n",
cfs_b->nr_periods, cfs_b->nr_throttled,
throttled_usec);
}
#endif
return 0;
}
#ifdef CONFIG_FAIR_GROUP_SCHED
static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
struct task_group *tg = css_tg(css);
u64 weight = scale_load_down(tg->shares);
return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024);
}
static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
struct cftype *cft, u64 weight)
{
/*
* cgroup weight knobs should use the common MIN, DFL and MAX
* values which are 1, 100 and 10000 respectively. While it loses
* a bit of range on both ends, it maps pretty well onto the shares
* value used by scheduler and the round-trip conversions preserve
* the original value over the entire range.
*/
if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX)
return -ERANGE;
weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL);
return sched_group_set_shares(css_tg(css), scale_load(weight));
}
static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
unsigned long weight = scale_load_down(css_tg(css)->shares);
int last_delta = INT_MAX;
int prio, delta;
/* find the closest nice value to the current weight */
for (prio = 0; prio < ARRAY_SIZE(sched_prio_to_weight); prio++) {
delta = abs(sched_prio_to_weight[prio] - weight);
if (delta >= last_delta)
break;
last_delta = delta;
}
return PRIO_TO_NICE(prio - 1 + MAX_RT_PRIO);
}
static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
struct cftype *cft, s64 nice)
{
unsigned long weight;
int idx;
if (nice < MIN_NICE || nice > MAX_NICE)
return -ERANGE;
idx = NICE_TO_PRIO(nice) - MAX_RT_PRIO;
idx = array_index_nospec(idx, 40);
weight = sched_prio_to_weight[idx];
return sched_group_set_shares(css_tg(css), scale_load(weight));
}
#endif
static void __maybe_unused cpu_period_quota_print(struct seq_file *sf,
long period, long quota)
{
if (quota < 0)
seq_puts(sf, "max");
else
seq_printf(sf, "%ld", quota);
seq_printf(sf, " %ld\n", period);
}
/* caller should put the current value in *@periodp before calling */
static int __maybe_unused cpu_period_quota_parse(char *buf,
u64 *periodp, u64 *quotap)
{
char tok[21]; /* U64_MAX */
if (sscanf(buf, "%20s %llu", tok, periodp) < 1)
return -EINVAL;
*periodp *= NSEC_PER_USEC;
if (sscanf(tok, "%llu", quotap))
*quotap *= NSEC_PER_USEC;
else if (!strcmp(tok, "max"))
*quotap = RUNTIME_INF;
else
return -EINVAL;
return 0;
}
#ifdef CONFIG_CFS_BANDWIDTH
static int cpu_max_show(struct seq_file *sf, void *v)
{
struct task_group *tg = css_tg(seq_css(sf));
cpu_period_quota_print(sf, tg_get_cfs_period(tg), tg_get_cfs_quota(tg));
return 0;
}
static ssize_t cpu_max_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct task_group *tg = css_tg(of_css(of));
u64 period = tg_get_cfs_period(tg);
u64 quota;
int ret;
ret = cpu_period_quota_parse(buf, &period, "a);
if (!ret)
ret = tg_set_cfs_bandwidth(tg, period, quota);
return ret ?: nbytes;
}
#endif
static struct cftype cpu_files[] = {
#ifdef CONFIG_FAIR_GROUP_SCHED
{
.name = "weight",
.flags = CFTYPE_NOT_ON_ROOT,
.read_u64 = cpu_weight_read_u64,
.write_u64 = cpu_weight_write_u64,
},
{
.name = "weight.nice",
.flags = CFTYPE_NOT_ON_ROOT,
.read_s64 = cpu_weight_nice_read_s64,
.write_s64 = cpu_weight_nice_write_s64,
},
#endif
#ifdef CONFIG_CFS_BANDWIDTH
{
.name = "max",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cpu_max_show,
.write = cpu_max_write,
},
#endif
#ifdef CONFIG_UCLAMP_TASK_GROUP
{
.name = "uclamp.min",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cpu_uclamp_min_show,
.write = cpu_uclamp_min_write,
},
{
.name = "uclamp.max",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cpu_uclamp_max_show,
.write = cpu_uclamp_max_write,
},
#endif
{ } /* terminate */
};
struct cgroup_subsys cpu_cgrp_subsys = {
.css_alloc = cpu_cgroup_css_alloc,
.css_online = cpu_cgroup_css_online,
.css_released = cpu_cgroup_css_released,
.css_free = cpu_cgroup_css_free,
.css_extra_stat_show = cpu_extra_stat_show,
.fork = cpu_cgroup_fork,
.can_attach = cpu_cgroup_can_attach,
.attach = cpu_cgroup_attach,
.legacy_cftypes = cpu_legacy_files,
.dfl_cftypes = cpu_files,
.early_init = true,
.threaded = true,
};
#endif /* CONFIG_CGROUP_SCHED */
void dump_cpu_task(int cpu)
{
pr_info("Task dump for CPU %d:\n", cpu);
sched_show_task(cpu_curr(cpu));
}
/*
* Nice levels are multiplicative, with a gentle 10% change for every
* nice level changed. I.e. when a CPU-bound task goes from nice 0 to
* nice 1, it will get ~10% less CPU time than another CPU-bound task
* that remained on nice 0.
*
* The "10% effect" is relative and cumulative: from _any_ nice level,
* if you go up 1 level, it's -10% CPU usage, if you go down 1 level
* it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
* If a task goes up by ~10% and another task goes down by ~10% then
* the relative distance between them is ~25%.)
*/
const int sched_prio_to_weight[40] = {
/* -20 */ 88761, 71755, 56483, 46273, 36291,
/* -15 */ 29154, 23254, 18705, 14949, 11916,
/* -10 */ 9548, 7620, 6100, 4904, 3906,
/* -5 */ 3121, 2501, 1991, 1586, 1277,
/* 0 */ 1024, 820, 655, 526, 423,
/* 5 */ 335, 272, 215, 172, 137,
/* 10 */ 110, 87, 70, 56, 45,
/* 15 */ 36, 29, 23, 18, 15,
};
/*
* Inverse (2^32/x) values of the sched_prio_to_weight[] array, precalculated.
*
* In cases where the weight does not change often, we can use the
* precalculated inverse to speed up arithmetics by turning divisions
* into multiplications:
*/
const u32 sched_prio_to_wmult[40] = {
/* -20 */ 48388, 59856, 76040, 92818, 118348,
/* -15 */ 147320, 184698, 229616, 287308, 360437,
/* -10 */ 449829, 563644, 704093, 875809, 1099582,
/* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326,
/* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587,
/* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126,
/* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717,
/* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};
void call_trace_sched_update_nr_running(struct rq *rq, int count)
{
trace_sched_update_nr_running_tp(rq, count);
}
|