summaryrefslogtreecommitdiffstats
path: root/include/linux/sched.h
blob: 32813c345115fb766ce18736ae2774f97920c986 (plain)
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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

/*
 * Define 'struct task_struct' and provide the main scheduler
 * APIs (schedule(), wakeup variants, etc.)
 */

#include <uapi/linux/sched.h>

#include <asm/current.h>

#include <linux/pid.h>
#include <linux/sem.h>
#include <linux/shm.h>
#include <linux/mutex.h>
#include <linux/plist.h>
#include <linux/hrtimer.h>
#include <linux/irqflags.h>
#include <linux/seccomp.h>
#include <linux/nodemask.h>
#include <linux/rcupdate.h>
#include <linux/refcount.h>
#include <linux/resource.h>
#include <linux/latencytop.h>
#include <linux/sched/prio.h>
#include <linux/sched/types.h>
#include <linux/signal_types.h>
#include <linux/syscall_user_dispatch.h>
#include <linux/mm_types_task.h>
#include <linux/task_io_accounting.h>
#include <linux/posix-timers.h>
#include <linux/rseq.h>
#include <linux/seqlock.h>
#include <linux/kcsan.h>
#include <asm/kmap_size.h>

/* task_struct member predeclarations (sorted alphabetically): */
struct audit_context;
struct backing_dev_info;
struct bio_list;
struct blk_plug;
struct bpf_local_storage;
struct capture_control;
struct cfs_rq;
struct fs_struct;
struct futex_pi_state;
struct io_context;
struct io_uring_task;
struct mempolicy;
struct nameidata;
struct nsproxy;
struct perf_event_context;
struct pid_namespace;
struct pipe_inode_info;
struct rcu_node;
struct reclaim_state;
struct robust_list_head;
struct root_domain;
struct rq;
struct sched_attr;
struct sched_param;
struct seq_file;
struct sighand_struct;
struct signal_struct;
struct task_delay_info;
struct task_group;

/*
 * Task state bitmask. NOTE! These bits are also
 * encoded in fs/proc/array.c: get_task_state().
 *
 * We have two separate sets of flags: task->state
 * is about runnability, while task->exit_state are
 * about the task exiting. Confusing, but this way
 * modifying one set can't modify the other one by
 * mistake.
 */

/* Used in tsk->state: */
#define TASK_RUNNING			0x0000
#define TASK_INTERRUPTIBLE		0x0001
#define TASK_UNINTERRUPTIBLE		0x0002
#define __TASK_STOPPED			0x0004
#define __TASK_TRACED			0x0008
/* Used in tsk->exit_state: */
#define EXIT_DEAD			0x0010
#define EXIT_ZOMBIE			0x0020
#define EXIT_TRACE			(EXIT_ZOMBIE | EXIT_DEAD)
/* Used in tsk->state again: */
#define TASK_PARKED			0x0040
#define TASK_DEAD			0x0080
#define TASK_WAKEKILL			0x0100
#define TASK_WAKING			0x0200
#define TASK_NOLOAD			0x0400
#define TASK_NEW			0x0800
#define TASK_STATE_MAX			0x1000

/* Convenience macros for the sake of set_current_state: */
#define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
#define TASK_STOPPED			(TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED			(TASK_WAKEKILL | __TASK_TRACED)

#define TASK_IDLE			(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)

/* Convenience macros for the sake of wake_up(): */
#define TASK_NORMAL			(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)

/* get_task_state(): */
#define TASK_REPORT			(TASK_RUNNING | TASK_INTERRUPTIBLE | \
					 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
					 __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \
					 TASK_PARKED)

#define task_is_traced(task)		((task->state & __TASK_TRACED) != 0)

#define task_is_stopped(task)		((task->state & __TASK_STOPPED) != 0)

#define task_is_stopped_or_traced(task)	((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)

#ifdef CONFIG_DEBUG_ATOMIC_SLEEP

/*
 * Special states are those that do not use the normal wait-loop pattern. See
 * the comment with set_special_state().
 */
#define is_special_task_state(state)				\
	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))

#define __set_current_state(state_value)			\
	do {							\
		WARN_ON_ONCE(is_special_task_state(state_value));\
		current->task_state_change = _THIS_IP_;		\
		current->state = (state_value);			\
	} while (0)

#define set_current_state(state_value)				\
	do {							\
		WARN_ON_ONCE(is_special_task_state(state_value));\
		current->task_state_change = _THIS_IP_;		\
		smp_store_mb(current->state, (state_value));	\
	} while (0)

#define set_special_state(state_value)					\
	do {								\
		unsigned long flags; /* may shadow */			\
		WARN_ON_ONCE(!is_special_task_state(state_value));	\
		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
		current->task_state_change = _THIS_IP_;			\
		current->state = (state_value);				\
		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
	} while (0)
#else
/*
 * set_current_state() includes a barrier so that the write of current->state
 * is correctly serialised wrt the caller's subsequent test of whether to
 * actually sleep:
 *
 *   for (;;) {
 *	set_current_state(TASK_UNINTERRUPTIBLE);
 *	if (CONDITION)
 *	   break;
 *
 *	schedule();
 *   }
 *   __set_current_state(TASK_RUNNING);
 *
 * If the caller does not need such serialisation (because, for instance, the
 * CONDITION test and condition change and wakeup are under the same lock) then
 * use __set_current_state().
 *
 * The above is typically ordered against the wakeup, which does:
 *
 *   CONDITION = 1;
 *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
 *
 * where wake_up_state()/try_to_wake_up() executes a full memory barrier before
 * accessing p->state.
 *
 * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
 * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
 * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
 *
 * However, with slightly different timing the wakeup TASK_RUNNING store can
 * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not
 * a problem either because that will result in one extra go around the loop
 * and our @cond test will save the day.
 *
 * Also see the comments of try_to_wake_up().
 */
#define __set_current_state(state_value)				\
	current->state = (state_value)

#define set_current_state(state_value)					\
	smp_store_mb(current->state, (state_value))

/*
 * set_special_state() should be used for those states when the blocking task
 * can not use the regular condition based wait-loop. In that case we must
 * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
 * will not collide with our state change.
 */
#define set_special_state(state_value)					\
	do {								\
		unsigned long flags; /* may shadow */			\
		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
		current->state = (state_value);				\
		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
	} while (0)

#endif

/* Task command name length: */
#define TASK_COMM_LEN			16

extern void scheduler_tick(void);

#define	MAX_SCHEDULE_TIMEOUT		LONG_MAX

extern long schedule_timeout(long timeout);
extern long schedule_timeout_interruptible(long timeout);
extern long schedule_timeout_killable(long timeout);
extern long schedule_timeout_uninterruptible(long timeout);
extern long schedule_timeout_idle(long timeout);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);
asmlinkage void preempt_schedule_irq(void);

extern int __must_check io_schedule_prepare(void);
extern void io_schedule_finish(int token);
extern long io_schedule_timeout(long timeout);
extern void io_schedule(void);

/**
 * struct prev_cputime - snapshot of system and user cputime
 * @utime: time spent in user mode
 * @stime: time spent in system mode
 * @lock: protects the above two fields
 *
 * Stores previous user/system time values such that we can guarantee
 * monotonicity.
 */
struct prev_cputime {
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
	u64				utime;
	u64				stime;
	raw_spinlock_t			lock;
#endif
};

enum vtime_state {
	/* Task is sleeping or running in a CPU with VTIME inactive: */
	VTIME_INACTIVE = 0,
	/* Task is idle */
	VTIME_IDLE,
	/* Task runs in kernelspace in a CPU with VTIME active: */
	VTIME_SYS,
	/* Task runs in userspace in a CPU with VTIME active: */
	VTIME_USER,
	/* Task runs as guests in a CPU with VTIME active: */
	VTIME_GUEST,
};

struct vtime {
	seqcount_t		seqcount;
	unsigned long long	starttime;
	enum vtime_state	state;
	unsigned int		cpu;
	u64			utime;
	u64			stime;
	u64			gtime;
};

/*
 * Utilization clamp constraints.
 * @UCLAMP_MIN:	Minimum utilization
 * @UCLAMP_MAX:	Maximum utilization
 * @UCLAMP_CNT:	Utilization clamp constraints count
 */
enum uclamp_id {
	UCLAMP_MIN = 0,
	UCLAMP_MAX,
	UCLAMP_CNT
};

#ifdef CONFIG_SMP
extern struct root_domain def_root_domain;
extern struct mutex sched_domains_mutex;
#endif

struct sched_info {
#ifdef CONFIG_SCHED_INFO
	/* Cumulative counters: */

	/* # of times we have run on this CPU: */
	unsigned long			pcount;

	/* Time spent waiting on a runqueue: */
	unsigned long long		run_delay;

	/* Timestamps: */

	/* When did we last run on a CPU? */
	unsigned long long		last_arrival;

	/* When were we last queued to run? */
	unsigned long long		last_queued;

#endif /* CONFIG_SCHED_INFO */
};

/*
 * Integer metrics need fixed point arithmetic, e.g., sched/fair
 * has a few: load, load_avg, util_avg, freq, and capacity.
 *
 * We define a basic fixed point arithmetic range, and then formalize
 * all these metrics based on that basic range.
 */
# define SCHED_FIXEDPOINT_SHIFT		10
# define SCHED_FIXEDPOINT_SCALE		(1L << SCHED_FIXEDPOINT_SHIFT)

/* Increase resolution of cpu_capacity calculations */
# define SCHED_CAPACITY_SHIFT		SCHED_FIXEDPOINT_SHIFT
# define SCHED_CAPACITY_SCALE		(1L << SCHED_CAPACITY_SHIFT)

struct load_weight {
	unsigned long			weight;
	u32				inv_weight;
};

/**
 * struct util_est - Estimation utilization of FAIR tasks
 * @enqueued: instantaneous estimated utilization of a task/cpu
 * @ewma:     the Exponential Weighted Moving Average (EWMA)
 *            utilization of a task
 *
 * Support data structure to track an Exponential Weighted Moving Average
 * (EWMA) of a FAIR task's utilization. New samples are added to the moving
 * average each time a task completes an activation. Sample's weight is chosen
 * so that the EWMA will be relatively insensitive to transient changes to the
 * task's workload.
 *
 * The enqueued attribute has a slightly different meaning for tasks and cpus:
 * - task:   the task's util_avg at last task dequeue time
 * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU
 * Thus, the util_est.enqueued of a task represents the contribution on the
 * estimated utilization of the CPU where that task is currently enqueued.
 *
 * Only for tasks we track a moving average of the past instantaneous
 * estimated utilization. This allows to absorb sporadic drops in utilization
 * of an otherwise almost periodic task.
 *
 * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
 * updates. When a task is dequeued, its util_est should not be updated if its
 * util_avg has not been updated in the meantime.
 * This information is mapped into the MSB bit of util_est.enqueued at dequeue
 * time. Since max value of util_est.enqueued for a task is 1024 (PELT util_avg
 * for a task) it is safe to use MSB.
 */
struct util_est {
	unsigned int			enqueued;
	unsigned int			ewma;
#define UTIL_EST_WEIGHT_SHIFT		2
#define UTIL_AVG_UNCHANGED		0x80000000
} __attribute__((__aligned__(sizeof(u64))));

/*
 * The load/runnable/util_avg accumulates an infinite geometric series
 * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c).
 *
 * [load_avg definition]
 *
 *   load_avg = runnable% * scale_load_down(load)
 *
 * [runnable_avg definition]
 *
 *   runnable_avg = runnable% * SCHED_CAPACITY_SCALE
 *
 * [util_avg definition]
 *
 *   util_avg = running% * SCHED_CAPACITY_SCALE
 *
 * where runnable% is the time ratio that a sched_entity is runnable and
 * running% the time ratio that a sched_entity is running.
 *
 * For cfs_rq, they are the aggregated values of all runnable and blocked
 * sched_entities.
 *
 * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU
 * capacity scaling. The scaling is done through the rq_clock_pelt that is used
 * for computing those signals (see update_rq_clock_pelt())
 *
 * N.B., the above ratios (runnable% and running%) themselves are in the
 * range of [0, 1]. To do fixed point arithmetics, we therefore scale them
 * to as large a range as necessary. This is for example reflected by
 * util_avg's SCHED_CAPACITY_SCALE.
 *
 * [Overflow issue]
 *
 * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities
 * with the highest load (=88761), always runnable on a single cfs_rq,
 * and should not overflow as the number already hits PID_MAX_LIMIT.
 *
 * For all other cases (including 32-bit kernels), struct load_weight's
 * weight will overflow first before we do, because:
 *
 *    Max(load_avg) <= Max(load.weight)
 *
 * Then it is the load_weight's responsibility to consider overflow
 * issues.
 */
struct sched_avg {
	u64				last_update_time;
	u64				load_sum;
	u64				runnable_sum;
	u32				util_sum;
	u32				period_contrib;
	unsigned long			load_avg;
	unsigned long			runnable_avg;
	unsigned long			util_avg;
	struct util_est			util_est;
} ____cacheline_aligned;

struct sched_statistics {
#ifdef CONFIG_SCHEDSTATS
	u64				wait_start;
	u64				wait_max;
	u64				wait_count;
	u64				wait_sum;
	u64				iowait_count;
	u64				iowait_sum;

	u64				sleep_start;
	u64				sleep_max;
	s64				sum_sleep_runtime;

	u64				block_start;
	u64				block_max;
	u64				exec_max;
	u64				slice_max;

	u64				nr_migrations_cold;
	u64				nr_failed_migrations_affine;
	u64				nr_failed_migrations_running;
	u64				nr_failed_migrations_hot;
	u64				nr_forced_migrations;

	u64				nr_wakeups;
	u64				nr_wakeups_sync;
	u64				nr_wakeups_migrate;
	u64				nr_wakeups_local;
	u64				nr_wakeups_remote;
	u64				nr_wakeups_affine;
	u64				nr_wakeups_affine_attempts;
	u64				nr_wakeups_passive;
	u64				nr_wakeups_idle;
#endif
};

struct sched_entity {
	/* For load-balancing: */
	struct load_weight		load;
	struct rb_node			run_node;
	struct list_head		group_node;
	unsigned int			on_rq;

	u64				exec_start;
	u64				sum_exec_runtime;
	u64				vruntime;
	u64				prev_sum_exec_runtime;

	u64				nr_migrations;

	struct sched_statistics		statistics;

#ifdef CONFIG_FAIR_GROUP_SCHED
	int				depth;
	struct sched_entity		*parent;
	/* rq on which this entity is (to be) queued: */
	struct cfs_rq			*cfs_rq;
	/* rq "owned" by this entity/group: */
	struct cfs_rq			*my_q;
	/* cached value of my_q->h_nr_running */
	unsigned long			runnable_weight;
#endif

#ifdef CONFIG_SMP
	/*
	 * Per entity load average tracking.
	 *
	 * Put into separate cache line so it does not
	 * collide with read-mostly values above.
	 */
	struct sched_avg		avg;
#endif
};

struct sched_rt_entity {
	struct list_head		run_list;
	unsigned long			timeout;
	unsigned long			watchdog_stamp;
	unsigned int			time_slice;
	unsigned short			on_rq;
	unsigned short			on_list;

	struct sched_rt_entity		*back;
#ifdef CONFIG_RT_GROUP_SCHED
	struct sched_rt_entity		*parent;
	/* rq on which this entity is (to be) queued: */
	struct rt_rq			*rt_rq;
	/* rq "owned" by this entity/group: */
	struct rt_rq			*my_q;
#endif
} __randomize_layout;

struct sched_dl_entity {
	struct rb_node			rb_node;

	/*
	 * Original scheduling parameters. Copied here from sched_attr
	 * during sched_setattr(), they will remain the same until
	 * the next sched_setattr().
	 */
	u64				dl_runtime;	/* Maximum runtime for each instance	*/
	u64				dl_deadline;	/* Relative deadline of each instance	*/
	u64				dl_period;	/* Separation of two instances (period) */
	u64				dl_bw;		/* dl_runtime / dl_period		*/
	u64				dl_density;	/* dl_runtime / dl_deadline		*/

	/*
	 * Actual scheduling parameters. Initialized with the values above,
	 * they are continuously updated during task execution. Note that
	 * the remaining runtime could be < 0 in case we are in overrun.
	 */
	s64				runtime;	/* Remaining runtime for this instance	*/
	u64				deadline;	/* Absolute deadline for this instance	*/
	unsigned int			flags;		/* Specifying the scheduler behaviour	*/

	/*
	 * Some bool flags:
	 *
	 * @dl_throttled tells if we exhausted the runtime. If so, the
	 * task has to wait for a replenishment to be performed at the
	 * next firing of dl_timer.
	 *
	 * @dl_boosted tells if we are boosted due to DI. If so we are
	 * outside bandwidth enforcement mechanism (but only until we
	 * exit the critical section);
	 *
	 * @dl_yielded tells if task gave up the CPU before consuming
	 * all its available runtime during the last job.
	 *
	 * @dl_non_contending tells if the task is inactive while still
	 * contributing to the active utilization. In other words, it
	 * indicates if the inactive timer has been armed and its handler
	 * has not been executed yet. This flag is useful to avoid race
	 * conditions between the inactive timer handler and the wakeup
	 * code.
	 *
	 * @dl_overrun tells if the task asked to be informed about runtime
	 * overruns.
	 */
	unsigned int			dl_throttled      : 1;
	unsigned int			dl_yielded        : 1;
	unsigned int			dl_non_contending : 1;
	unsigned int			dl_overrun	  : 1;

	/*
	 * Bandwidth enforcement timer. Each -deadline task has its
	 * own bandwidth to be enforced, thus we need one timer per task.
	 */
	struct hrtimer			dl_timer;

	/*
	 * Inactive timer, responsible for decreasing the active utilization
	 * at the "0-lag time". When a -deadline task blocks, it contributes
	 * to GRUB's active utilization until the "0-lag time", hence a
	 * timer is needed to decrease the active utilization at the correct
	 * time.
	 */
	struct hrtimer inactive_timer;

#ifdef CONFIG_RT_MUTEXES
	/*
	 * Priority Inheritance. When a DEADLINE scheduling entity is boosted
	 * pi_se points to the donor, otherwise points to the dl_se it belongs
	 * to (the original one/itself).
	 */
	struct sched_dl_entity *pi_se;
#endif
};

#ifdef CONFIG_UCLAMP_TASK
/* Number of utilization clamp buckets (shorter alias) */
#define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT

/*
 * Utilization clamp for a scheduling entity
 * @value:		clamp value "assigned" to a se
 * @bucket_id:		bucket index corresponding to the "assigned" value
 * @active:		the se is currently refcounted in a rq's bucket
 * @user_defined:	the requested clamp value comes from user-space
 *
 * The bucket_id is the index of the clamp bucket matching the clamp value
 * which is pre-computed and stored to avoid expensive integer divisions from
 * the fast path.
 *
 * The active bit is set whenever a task has got an "effective" value assigned,
 * which can be different from the clamp value "requested" from user-space.
 * This allows to know a task is refcounted in the rq's bucket corresponding
 * to the "effective" bucket_id.
 *
 * The user_defined bit is set whenever a task has got a task-specific clamp
 * value requested from userspace, i.e. the system defaults apply to this task
 * just as a restriction. This allows to relax default clamps when a less
 * restrictive task-specific value has been requested, thus allowing to
 * implement a "nice" semantic. For example, a task running with a 20%
 * default boost can still drop its own boosting to 0%.
 */
struct uclamp_se {
	unsigned int value		: bits_per(SCHED_CAPACITY_SCALE);
	unsigned int bucket_id		: bits_per(UCLAMP_BUCKETS);
	unsigned int active		: 1;
	unsigned int user_defined	: 1;
};
#endif /* CONFIG_UCLAMP_TASK */

union rcu_special {
	struct {
		u8			blocked;
		u8			need_qs;
		u8			exp_hint; /* Hint for performance. */
		u8			need_mb; /* Readers need smp_mb(). */
	} b; /* Bits. */
	u32 s; /* Set of bits. */
};

enum perf_event_task_context {
	perf_invalid_context = -1,
	perf_hw_context = 0,
	perf_sw_context,
	perf_nr_task_contexts,
};

struct wake_q_node {
	struct wake_q_node *next;
};

struct kmap_ctrl {
#ifdef CONFIG_KMAP_LOCAL
	int				idx;
	pte_t				pteval[KM_MAX_IDX];
#endif
};

struct task_struct {
#ifdef CONFIG_THREAD_INFO_IN_TASK
	/*
	 * For reasons of header soup (see current_thread_info()), this
	 * must be the first element of task_struct.
	 */
	struct thread_info		thread_info;
#endif
	/* -1 unrunnable, 0 runnable, >0 stopped: */
	volatile long			state;

	/*
	 * This begins the randomizable portion of task_struct. Only
	 * scheduling-critical items should be added above here.
	 */
	randomized_struct_fields_start

	void				*stack;
	refcount_t			usage;
	/* Per task flags (PF_*), defined further below: */
	unsigned int			flags;
	unsigned int			ptrace;

#ifdef CONFIG_SMP
	int				on_cpu;
	struct __call_single_node	wake_entry;
#ifdef CONFIG_THREAD_INFO_IN_TASK
	/* Current CPU: */
	unsigned int			cpu;
#endif
	unsigned int			wakee_flips;
	unsigned long			wakee_flip_decay_ts;
	struct task_struct		*last_wakee;

	/*
	 * recent_used_cpu is initially set as the last CPU used by a task
	 * that wakes affine another task. Waker/wakee relationships can
	 * push tasks around a CPU where each wakeup moves to the next one.
	 * Tracking a recently used CPU allows a quick search for a recently
	 * used CPU that may be idle.
	 */
	int				recent_used_cpu;
	int				wake_cpu;
#endif
	int				on_rq;

	int				prio;
	int				static_prio;
	int				normal_prio;
	unsigned int			rt_priority;

	const struct sched_class	*sched_class;
	struct sched_entity		se;
	struct sched_rt_entity		rt;
#ifdef CONFIG_CGROUP_SCHED
	struct task_group		*sched_task_group;
#endif
	struct sched_dl_entity		dl;

#ifdef CONFIG_UCLAMP_TASK
	/*
	 * Clamp values requested for a scheduling entity.
	 * Must be updated with task_rq_lock() held.
	 */
	struct uclamp_se		uclamp_req[UCLAMP_CNT];
	/*
	 * Effective clamp values used for a scheduling entity.
	 * Must be updated with task_rq_lock() held.
	 */
	struct uclamp_se		uclamp[UCLAMP_CNT];
#endif

#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* List of struct preempt_notifier: */
	struct hlist_head		preempt_notifiers;
#endif

#ifdef CONFIG_BLK_DEV_IO_TRACE
	unsigned int			btrace_seq;
#endif

	unsigned int			policy;
	int				nr_cpus_allowed;
	const cpumask_t			*cpus_ptr;
	cpumask_t			cpus_mask;
	void				*migration_pending;
#ifdef CONFIG_SMP
	unsigned short			migration_disabled;
#endif
	unsigned short			migration_flags;

#ifdef CONFIG_PREEMPT_RCU
	int				rcu_read_lock_nesting;
	union rcu_special		rcu_read_unlock_special;
	struct list_head		rcu_node_entry;
	struct rcu_node			*rcu_blocked_node;
#endif /* #ifdef CONFIG_PREEMPT_RCU */

#ifdef CONFIG_TASKS_RCU
	unsigned long			rcu_tasks_nvcsw;
	u8				rcu_tasks_holdout;
	u8				rcu_tasks_idx;
	int				rcu_tasks_idle_cpu;
	struct list_head		rcu_tasks_holdout_list;
#endif /* #ifdef CONFIG_TASKS_RCU */

#ifdef CONFIG_TASKS_TRACE_RCU
	int				trc_reader_nesting;
	int				trc_ipi_to_cpu;
	union rcu_special		trc_reader_special;
	bool				trc_reader_checked;
	struct list_head		trc_holdout_list;
#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */

	struct sched_info		sched_info;

	struct list_head		tasks;
#ifdef CONFIG_SMP
	struct plist_node		pushable_tasks;
	struct rb_node			pushable_dl_tasks;
#endif

	struct mm_struct		*mm;
	struct mm_struct		*active_mm;

	/* Per-thread vma caching: */
	struct vmacache			vmacache;

#ifdef SPLIT_RSS_COUNTING
	struct task_rss_stat		rss_stat;
#endif
	int				exit_state;
	int				exit_code;
	int				exit_signal;
	/* The signal sent when the parent dies: */
	int				pdeath_signal;
	/* JOBCTL_*, siglock protected: */
	unsigned long			jobctl;

	/* Used for emulating ABI behavior of previous Linux versions: */
	unsigned int			personality;

	/* Scheduler bits, serialized by scheduler locks: */
	unsigned			sched_reset_on_fork:1;
	unsigned			sched_contributes_to_load:1;
	unsigned			sched_migrated:1;
#ifdef CONFIG_PSI
	unsigned			sched_psi_wake_requeue:1;
#endif

	/* Force alignment to the next boundary: */
	unsigned			:0;

	/* Unserialized, strictly 'current' */

	/*
	 * This field must not be in the scheduler word above due to wakelist
	 * queueing no longer being serialized by p->on_cpu. However:
	 *
	 * p->XXX = X;			ttwu()
	 * schedule()			  if (p->on_rq && ..) // false
	 *   smp_mb__after_spinlock();	  if (smp_load_acquire(&p->on_cpu) && //true
	 *   deactivate_task()		      ttwu_queue_wakelist())
	 *     p->on_rq = 0;			p->sched_remote_wakeup = Y;
	 *
	 * guarantees all stores of 'current' are visible before
	 * ->sched_remote_wakeup gets used, so it can be in this word.
	 */
	unsigned			sched_remote_wakeup:1;

	/* Bit to tell LSMs we're in execve(): */
	unsigned			in_execve:1;
	unsigned			in_iowait:1;
#ifndef TIF_RESTORE_SIGMASK
	unsigned			restore_sigmask:1;
#endif
#ifdef CONFIG_MEMCG
	unsigned			in_user_fault:1;
#endif
#ifdef CONFIG_COMPAT_BRK
	unsigned			brk_randomized:1;
#endif
#ifdef CONFIG_CGROUPS
	/* disallow userland-initiated cgroup migration */
	unsigned			no_cgroup_migration:1;
	/* task is frozen/stopped (used by the cgroup freezer) */
	unsigned			frozen:1;
#endif
#ifdef CONFIG_BLK_CGROUP
	unsigned			use_memdelay:1;
#endif
#ifdef CONFIG_PSI
	/* Stalled due to lack of memory */
	unsigned			in_memstall:1;
#endif
#ifdef CONFIG_PAGE_OWNER
	/* Used by page_owner=on to detect recursion in page tracking. */
	unsigned			in_page_owner:1;
#endif

	unsigned long			atomic_flags; /* Flags requiring atomic access. */

	struct restart_block		restart_block;

	pid_t				pid;
	pid_t				tgid;

#ifdef CONFIG_STACKPROTECTOR
	/* Canary value for the -fstack-protector GCC feature: */
	unsigned long			stack_canary;
#endif
	/*
	 * Pointers to the (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with
	 * p->real_parent->pid)
	 */

	/* Real parent process: */
	struct task_struct __rcu	*real_parent;

	/* Recipient of SIGCHLD, wait4() reports: */
	struct task_struct __rcu	*parent;

	/*
	 * Children/sibling form the list of natural children:
	 */
	struct list_head		children;
	struct list_head		sibling;
	struct task_struct		*group_leader;

	/*
	 * 'ptraced' is the list of tasks this task is using ptrace() on.
	 *
	 * This includes both natural children and PTRACE_ATTACH targets.
	 * 'ptrace_entry' is this task's link on the p->parent->ptraced list.
	 */
	struct list_head		ptraced;
	struct list_head		ptrace_entry;

	/* PID/PID hash table linkage. */
	struct pid			*thread_pid;
	struct hlist_node		pid_links[PIDTYPE_MAX];
	struct list_head		thread_group;
	struct list_head		thread_node;

	struct completion		*vfork_done;

	/* CLONE_CHILD_SETTID: */
	int __user			*set_child_tid;

	/* CLONE_CHILD_CLEARTID: */
	int __user			*clear_child_tid;

	/* PF_IO_WORKER */
	void				*pf_io_worker;

	u64				utime;
	u64				stime;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
	u64				utimescaled;
	u64				stimescaled;
#endif
	u64				gtime;
	struct prev_cputime		prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
	struct vtime			vtime;
#endif

#ifdef CONFIG_NO_HZ_FULL
	atomic_t			tick_dep_mask;
#endif
	/* Context switch counts: */
	unsigned long			nvcsw;
	unsigned long			nivcsw;

	/* Monotonic time in nsecs: */
	u64				start_time;

	/* Boot based time in nsecs: */
	u64				start_boottime;

	/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
	unsigned long			min_flt;
	unsigned long			maj_flt;

	/* Empty if CONFIG_POSIX_CPUTIMERS=n */
	struct posix_cputimers		posix_cputimers;

#ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK
	struct posix_cputimers_work	posix_cputimers_work;
#endif

	/* Process credentials: */

	/* Tracer's credentials at attach: */
	const struct cred __rcu		*ptracer_cred;

	/* Objective and real subjective task credentials (COW): */
	const struct cred __rcu		*real_cred;

	/* Effective (overridable) subjective task credentials (COW): */
	const struct cred __rcu		*cred;

#ifdef CONFIG_KEYS
	/* Cached requested key. */
	struct key			*cached_requested_key;
#endif

	/*
	 * executable name, excluding path.
	 *
	 * - normally initialized setup_new_exec()
	 * - access it with [gs]et_task_comm()
	 * - lock it with task_lock()
	 */
	char				comm[TASK_COMM_LEN];

	struct nameidata		*nameidata;

#ifdef CONFIG_SYSVIPC
	struct sysv_sem			sysvsem;
	struct sysv_shm			sysvshm;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
	unsigned long			last_switch_count;
	unsigned long			last_switch_time;
#endif
	/* Filesystem information: */
	struct fs_struct		*fs;

	/* Open file information: */
	struct files_struct		*files;

#ifdef CONFIG_IO_URING
	struct io_uring_task		*io_uring;
#endif

	/* Namespaces: */
	struct nsproxy			*nsproxy;

	/* Signal handlers: */
	struct signal_struct		*signal;
	struct sighand_struct __rcu		*sighand;
	sigset_t			blocked;
	sigset_t			real_blocked;
	/* Restored if set_restore_sigmask() was used: */
	sigset_t			saved_sigmask;
	struct sigpending		pending;
	unsigned long			sas_ss_sp;
	size_t				sas_ss_size;
	unsigned int			sas_ss_flags;

	struct callback_head		*task_works;

#ifdef CONFIG_AUDIT
#ifdef CONFIG_AUDITSYSCALL
	struct audit_context		*audit_context;
#endif
	kuid_t				loginuid;
	unsigned int			sessionid;
#endif
	struct seccomp			seccomp;
	struct syscall_user_dispatch	syscall_dispatch;

	/* Thread group tracking: */
	u64				parent_exec_id;
	u64				self_exec_id;

	/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
	spinlock_t			alloc_lock;

	/* Protection of the PI data structures: */
	raw_spinlock_t			pi_lock;

	struct wake_q_node		wake_q;

#ifdef CONFIG_RT_MUTEXES
	/* PI waiters blocked on a rt_mutex held by this task: */
	struct rb_root_cached		pi_waiters;
	/* Updated under owner's pi_lock and rq lock */
	struct task_struct		*pi_top_task;
	/* Deadlock detection and priority inheritance handling: */
	struct rt_mutex_waiter		*pi_blocked_on;
#endif

#ifdef CONFIG_DEBUG_MUTEXES
	/* Mutex deadlock detection: */
	struct mutex_waiter		*blocked_on;
#endif

#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
	int				non_block_count;
#endif

#ifdef CONFIG_TRACE_IRQFLAGS
	struct irqtrace_events		irqtrace;
	unsigned int			hardirq_threaded;
	u64				hardirq_chain_key;
	int				softirqs_enabled;
	int				softirq_context;
	int				irq_config;
#endif
#ifdef CONFIG_PREEMPT_RT
	int				softirq_disable_cnt;
#endif

#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH			48UL
	u64				curr_chain_key;
	int				lockdep_depth;
	unsigned int			lockdep_recursion;
	struct held_lock		held_locks[MAX_LOCK_DEPTH];
#endif

#if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP)
	unsigned int			in_ubsan;
#endif

	/* Journalling filesystem info: */
	void				*journal_info;

	/* Stacked block device info: */
	struct bio_list			*bio_list;

#ifdef CONFIG_BLOCK
	/* Stack plugging: */
	struct blk_plug			*plug;
#endif

	/* VM state: */
	struct reclaim_state		*reclaim_state;

	struct backing_dev_info		*backing_dev_info;

	struct io_context		*io_context;

#ifdef CONFIG_COMPACTION
	struct capture_control		*capture_control;
#endif
	/* Ptrace state: */
	unsigned long			ptrace_message;
	kernel_siginfo_t		*last_siginfo;

	struct task_io_accounting	ioac;
#ifdef CONFIG_PSI
	/* Pressure stall state */
	unsigned int			psi_flags;
#endif
#ifdef CONFIG_TASK_XACCT
	/* Accumulated RSS usage: */
	u64				acct_rss_mem1;
	/* Accumulated virtual memory usage: */
	u64				acct_vm_mem1;
	/* stime + utime since last update: */
	u64				acct_timexpd;
#endif
#ifdef CONFIG_CPUSETS
	/* Protected by ->alloc_lock: */
	nodemask_t			mems_allowed;
	/* Sequence number to catch updates: */
	seqcount_spinlock_t		mems_allowed_seq;
	int				cpuset_mem_spread_rotor;
	int				cpuset_slab_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
	/* Control Group info protected by css_set_lock: */
	struct css_set __rcu		*cgroups;
	/* cg_list protected by css_set_lock and tsk->alloc_lock: */
	struct list_head		cg_list;
#endif
#ifdef CONFIG_X86_CPU_RESCTRL
	u32				closid;
	u32				rmid;
#endif
#ifdef CONFIG_FUTEX
	struct robust_list_head __user	*robust_list;
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
	struct list_head		pi_state_list;
	struct futex_pi_state		*pi_state_cache;
	struct mutex			futex_exit_mutex;
	unsigned int			futex_state;
#endif
#ifdef CONFIG_PERF_EVENTS
	struct perf_event_context	*perf_event_ctxp[perf_nr_task_contexts];
	struct mutex			perf_event_mutex;
	struct list_head		perf_event_list;
#endif
#ifdef CONFIG_DEBUG_PREEMPT
	unsigned long			preempt_disable_ip;
#endif
#ifdef CONFIG_NUMA
	/* Protected by alloc_lock: */
	struct mempolicy		*mempolicy;
	short				il_prev;
	short				pref_node_fork;
#endif
#ifdef CONFIG_NUMA_BALANCING
	int				numa_scan_seq;
	unsigned int			numa_scan_period;
	unsigned int			numa_scan_period_max;
	int				numa_preferred_nid;
	unsigned long			numa_migrate_retry;
	/* Migration stamp: */
	u64				node_stamp;
	u64				last_task_numa_placement;
	u64				last_sum_exec_runtime;
	struct callback_head		numa_work;

	/*
	 * This pointer is only modified for current in syscall and
	 * pagefault context (and for tasks being destroyed), so it can be read
	 * from any of the following contexts:
	 *  - RCU read-side critical section
	 *  - current->numa_group from everywhere
	 *  - task's runqueue locked, task not running
	 */
	struct numa_group __rcu		*numa_group;

	/*
	 * numa_faults is an array split into four regions:
	 * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
	 * in this precise order.
	 *
	 * faults_memory: Exponential decaying average of faults on a per-node
	 * basis. Scheduling placement decisions are made based on these
	 * counts. The values remain static for the duration of a PTE scan.
	 * faults_cpu: Track the nodes the process was running on when a NUMA
	 * hinting fault was incurred.
	 * faults_memory_buffer and faults_cpu_buffer: Record faults per node
	 * during the current scan window. When the scan completes, the counts
	 * in faults_memory and faults_cpu decay and these values are copied.
	 */
	unsigned long			*numa_faults;
	unsigned long			total_numa_faults;

	/*
	 * numa_faults_locality tracks if faults recorded during the last
	 * scan window were remote/local or failed to migrate. The task scan
	 * period is adapted based on the locality of the faults with different
	 * weights depending on whether they were shared or private faults
	 */
	unsigned long			numa_faults_locality[3];

	unsigned long			numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */

#ifdef CONFIG_RSEQ
	struct rseq __user *rseq;
	u32 rseq_sig;
	/*
	 * RmW on rseq_event_mask must be performed atomically
	 * with respect to preemption.
	 */
	unsigned long rseq_event_mask;
#endif

	struct tlbflush_unmap_batch	tlb_ubc;

	union {
		refcount_t		rcu_users;
		struct rcu_head		rcu;
	};

	/* Cache last used pipe for splice(): */
	struct pipe_inode_info		*splice_pipe;

	struct page_frag		task_frag;

#ifdef CONFIG_TASK_DELAY_ACCT
	struct task_delay_info		*delays;
#endif

#ifdef CONFIG_FAULT_INJECTION
	int				make_it_fail;
	unsigned int			fail_nth;
#endif
	/*
	 * When (nr_dirtied >= nr_dirtied_pause), it's time to call
	 * balance_dirty_pages() for a dirty throttling pause:
	 */
	int				nr_dirtied;
	int				nr_dirtied_pause;
	/* Start of a write-and-pause period: */
	unsigned long			dirty_paused_when;

#ifdef CONFIG_LATENCYTOP
	int				latency_record_count;
	struct latency_record		latency_record[LT_SAVECOUNT];
#endif
	/*
	 * Time slack values; these are used to round up poll() and
	 * select() etc timeout values. These are in nanoseconds.
	 */
	u64				timer_slack_ns;
	u64				default_timer_slack_ns;

#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
	unsigned int			kasan_depth;
#endif

#ifdef CONFIG_KCSAN
	struct kcsan_ctx		kcsan_ctx;
#ifdef CONFIG_TRACE_IRQFLAGS
	struct irqtrace_events		kcsan_save_irqtrace;
#endif
#endif

#if IS_ENABLED(CONFIG_KUNIT)
	struct kunit			*kunit_test;
#endif

#ifdef CONFIG_FUNCTION_GRAPH_TRACER
	/* Index of current stored address in ret_stack: */
	int				curr_ret_stack;
	int				curr_ret_depth;

	/* Stack of return addresses for return function tracing: */
	struct ftrace_ret_stack		*ret_stack;

	/* Timestamp for last schedule: */
	unsigned long long		ftrace_timestamp;

	/*
	 * Number of functions that haven't been traced
	 * because of depth overrun:
	 */
	atomic_t			trace_overrun;

	/* Pause tracing: */
	atomic_t			tracing_graph_pause;
#endif

#ifdef CONFIG_TRACING
	/* State flags for use by tracers: */
	unsigned long			trace;

	/* Bitmask and counter of trace recursion: */
	unsigned long			trace_recursion;
#endif /* CONFIG_TRACING */

#ifdef CONFIG_KCOV
	/* See kernel/kcov.c for more details. */

	/* Coverage collection mode enabled for this task (0 if disabled): */
	unsigned int			kcov_mode;

	/* Size of the kcov_area: */
	unsigned int			kcov_size;

	/* Buffer for coverage collection: */
	void				*kcov_area;

	/* KCOV descriptor wired with this task or NULL: */
	struct kcov			*kcov;

	/* KCOV common handle for remote coverage collection: */
	u64				kcov_handle;

	/* KCOV sequence number: */
	int				kcov_sequence;

	/* Collect coverage from softirq context: */
	unsigned int			kcov_softirq;
#endif

#ifdef CONFIG_MEMCG
	struct mem_cgroup		*memcg_in_oom;
	gfp_t				memcg_oom_gfp_mask;
	int				memcg_oom_order;

	/* Number of pages to reclaim on returning to userland: */
	unsigned int			memcg_nr_pages_over_high;

	/* Used by memcontrol for targeted memcg charge: */
	struct mem_cgroup		*active_memcg;
#endif

#ifdef CONFIG_BLK_CGROUP
	struct request_queue		*throttle_queue;
#endif

#ifdef CONFIG_UPROBES
	struct uprobe_task		*utask;
#endif
#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
	unsigned int			sequential_io;
	unsigned int			sequential_io_avg;
#endif
	struct kmap_ctrl		kmap_ctrl;
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
	unsigned long			task_state_change;
#endif
	int				pagefault_disabled;
#ifdef CONFIG_MMU
	struct task_struct		*oom_reaper_list;
#endif
#ifdef CONFIG_VMAP_STACK
	struct vm_struct		*stack_vm_area;
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
	/* A live task holds one reference: */
	refcount_t			stack_refcount;
#endif
#ifdef CONFIG_LIVEPATCH
	int patch_state;
#endif
#ifdef CONFIG_SECURITY
	/* Used by LSM modules for access restriction: */
	void				*security;
#endif
#ifdef CONFIG_BPF_SYSCALL
	/* Used by BPF task local storage */
	struct bpf_local_storage __rcu	*bpf_storage;
#endif

#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
	unsigned long			lowest_stack;
	unsigned long			prev_lowest_stack;
#endif

#ifdef CONFIG_X86_MCE
	void __user			*mce_vaddr;
	__u64				mce_kflags;
	u64				mce_addr;
	__u64				mce_ripv : 1,
					mce_whole_page : 1,
					__mce_reserved : 62;
	struct callback_head		mce_kill_me;
#endif

#ifdef CONFIG_KRETPROBES
	struct llist_head               kretprobe_instances;
#endif

	/*
	 * New fields for task_struct should be added above here, so that
	 * they are included in the randomized portion of task_struct.
	 */
	randomized_struct_fields_end

	/* CPU-specific state of this task: */
	struct thread_struct		thread;

	/*
	 * WARNING: on x86, 'thread_struct' contains a variable-sized
	 * structure.  It *MUST* be at the end of 'task_struct'.
	 *
	 * Do not put anything below here!
	 */
};

static inline struct pid *task_pid(struct task_struct *task)
{
	return task->thread_pid;
}

/*
 * the helpers to get the task's different pids as they are seen
 * from various namespaces
 *
 * task_xid_nr()     : global id, i.e. the id seen from the init namespace;
 * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
 *                     current.
 * task_xid_nr_ns()  : id seen from the ns specified;
 *
 * see also pid_nr() etc in include/linux/pid.h
 */
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);

static inline pid_t task_pid_nr(struct task_struct *tsk)
{
	return tsk->pid;
}

static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
}

static inline pid_t task_pid_vnr(struct task_struct *tsk)
{
	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
}


static inline pid_t task_tgid_nr(struct task_struct *tsk)
{
	return tsk->tgid;
}

/**
 * pid_alive - check that a task structure is not stale
 * @p: Task structure to be checked.
 *
 * Test if a process is not yet dead (at most zombie state)
 * If pid_alive fails, then pointers within the task structure
 * can be stale and must not be dereferenced.
 *
 * Return: 1 if the process is alive. 0 otherwise.
 */
static inline int pid_alive(const struct task_struct *p)
{
	return p->thread_pid != NULL;
}

static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
}

static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
{
	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
}


static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
}

static inline pid_t task_session_vnr(struct task_struct *tsk)
{
	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
}

static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns);
}

static inline pid_t task_tgid_vnr(struct task_struct *tsk)
{
	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL);
}

static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
{
	pid_t pid = 0;

	rcu_read_lock();
	if (pid_alive(tsk))
		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
	rcu_read_unlock();

	return pid;
}

static inline pid_t task_ppid_nr(const struct task_struct *tsk)
{
	return task_ppid_nr_ns(tsk, &init_pid_ns);
}

/* Obsolete, do not use: */
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
{
	return task_pgrp_nr_ns(tsk, &init_pid_ns);
}

#define TASK_REPORT_IDLE	(TASK_REPORT + 1)
#define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)

static inline unsigned int task_state_index(struct task_struct *tsk)
{
	unsigned int tsk_state = READ_ONCE(tsk->state);
	unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;

	BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);

	if (tsk_state == TASK_IDLE)
		state = TASK_REPORT_IDLE;

	return fls(state);
}

static inline char task_index_to_char(unsigned int state)
{
	static const char state_char[] = "RSDTtXZPI";

	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1);

	return state_char[state];
}

static inline char task_state_to_char(struct task_struct *tsk)
{
	return task_index_to_char(task_state_index(tsk));
}

/**
 * is_global_init - check if a task structure is init. Since init
 * is free to have sub-threads we need to check tgid.
 * @tsk: Task structure to be checked.
 *
 * Check if a task structure is the first user space task the kernel created.
 *
 * Return: 1 if the task structure is init. 0 otherwise.
 */
static inline int is_global_init(struct task_struct *tsk)
{
	return task_tgid_nr(tsk) == 1;
}

extern struct pid *cad_pid;

/*
 * Per process flags
 */
#define PF_VCPU			0x00000001	/* I'm a virtual CPU */
#define PF_IDLE			0x00000002	/* I am an IDLE thread */
#define PF_EXITING		0x00000004	/* Getting shut down */
#define PF_IO_WORKER		0x00000010	/* Task is an IO worker */
#define PF_WQ_WORKER		0x00000020	/* I'm a workqueue worker */
#define PF_FORKNOEXEC		0x00000040	/* Forked but didn't exec */
#define PF_MCE_PROCESS		0x00000080      /* Process policy on mce errors */
#define PF_SUPERPRIV		0x00000100	/* Used super-user privileges */
#define PF_DUMPCORE		0x00000200	/* Dumped core */
#define PF_SIGNALED		0x00000400	/* Killed by a signal */
#define PF_MEMALLOC		0x00000800	/* Allocating memory */
#define PF_NPROC_EXCEEDED	0x00001000	/* set_user() noticed that RLIMIT_NPROC was exceeded */
#define PF_USED_MATH		0x00002000	/* If unset the fpu must be initialized before use */
#define PF_USED_ASYNC		0x00004000	/* Used async_schedule*(), used by module init */
#define PF_NOFREEZE		0x00008000	/* This thread should not be frozen */
#define PF_FROZEN		0x00010000	/* Frozen for system suspend */
#define PF_KSWAPD		0x00020000	/* I am kswapd */
#define PF_MEMALLOC_NOFS	0x00040000	/* All allocation requests will inherit GFP_NOFS */
#define PF_MEMALLOC_NOIO	0x00080000	/* All allocation requests will inherit GFP_NOIO */
#define PF_LOCAL_THROTTLE	0x00100000	/* Throttle writes only against the bdi I write to,
						 * I am cleaning dirty pages from some other bdi. */
#define PF_KTHREAD		0x00200000	/* I am a kernel thread */
#define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
#define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
#define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
#define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
#define PF_MEMALLOC_PIN		0x10000000	/* Allocation context constrained to zones which allow long term pinning. */
#define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
#define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */

/*
 * Only the _current_ task can read/write to tsk->flags, but other
 * tasks can access tsk->flags in readonly mode for example
 * with tsk_used_math (like during threaded core dumping).
 * There is however an exception to this rule during ptrace
 * or during fork: the ptracer task is allowed to write to the
 * child->flags of its traced child (same goes for fork, the parent
 * can write to the child->flags), because we're guaranteed the
 * child is not running and in turn not changing child->flags
 * at the same time the parent does it.
 */
#define clear_stopped_child_used_math(child)	do { (child)->flags &= ~PF_USED_MATH; } while (0)
#define set_stopped_child_used_math(child)	do { (child)->flags |= PF_USED_MATH; } while (0)
#define clear_used_math()			clear_stopped_child_used_math(current)
#define set_used_math()				set_stopped_child_used_math(current)

#define conditional_stopped_child_used_math(condition, child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)

#define conditional_used_math(condition)	conditional_stopped_child_used_math(condition, current)

#define copy_to_stopped_child_used_math(child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)

/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
#define tsk_used_math(p)			((p)->flags & PF_USED_MATH)
#define used_math()				tsk_used_math(current)

static inline bool is_percpu_thread(void)
{
#ifdef CONFIG_SMP
	return (current->flags & PF_NO_SETAFFINITY) &&
		(current->nr_cpus_allowed  == 1);
#else
	return true;
#endif
}

/* Per-process atomic flags. */
#define PFA_NO_NEW_PRIVS		0	/* May not gain new privileges. */
#define PFA_SPREAD_PAGE			1	/* Spread page cache over cpuset */
#define PFA_SPREAD_SLAB			2	/* Spread some slab caches over cpuset */
#define PFA_SPEC_SSB_DISABLE		3	/* Speculative Store Bypass disabled */
#define PFA_SPEC_SSB_FORCE_DISABLE	4	/* Speculative Store Bypass force disabled*/
#define PFA_SPEC_IB_DISABLE		5	/* Indirect branch speculation restricted */
#define PFA_SPEC_IB_FORCE_DISABLE	6	/* Indirect branch speculation permanently restricted */
#define PFA_SPEC_SSB_NOEXEC		7	/* Speculative Store Bypass clear on execve() */

#define TASK_PFA_TEST(name, func)					\
	static inline bool task_##func(struct task_struct *p)		\
	{ return test_bit(PFA_##name, &p->atomic_flags); }

#define TASK_PFA_SET(name, func)					\
	static inline void task_set_##func(struct task_struct *p)	\
	{ set_bit(PFA_##name, &p->atomic_flags); }

#define TASK_PFA_CLEAR(name, func)					\
	static inline void task_clear_##func(struct task_struct *p)	\
	{ clear_bit(PFA_##name, &p->atomic_flags); }

TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs)
TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs)

TASK_PFA_TEST(SPREAD_PAGE, spread_page)
TASK_PFA_SET(SPREAD_PAGE, spread_page)
TASK_PFA_CLEAR(SPREAD_PAGE, spread_page)

TASK_PFA_TEST(SPREAD_SLAB, spread_slab)
TASK_PFA_SET(SPREAD_SLAB, spread_slab)
TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)

TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable)
TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable)
TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable)

TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec)
TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec)
TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec)

TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)

TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable)
TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable)
TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable)

TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)

static inline void
current_restore_flags(unsigned long orig_flags, unsigned long flags)
{
	current->flags &= ~flags;
	current->flags |= orig_flags & flags;
}

extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
#ifdef CONFIG_SMP
extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
#else
static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{
}
static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
{
	if (!cpumask_test_cpu(0, new_mask))
		return -EINVAL;
	return 0;
}
#endif

extern int yield_to(struct task_struct *p, bool preempt);
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);

/**
 * task_nice - return the nice value of a given task.
 * @p: the task in question.
 *
 * Return: The nice value [ -20 ... 0 ... 19 ].
 */
static inline int task_nice(const struct task_struct *p)
{
	return PRIO_TO_NICE((p)->static_prio);
}

extern int can_nice(const struct task_struct *p, const int nice);
extern int task_curr(const struct task_struct *p);
extern int idle_cpu(int cpu);
extern int available_idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
extern void sched_set_fifo(struct task_struct *p);
extern void sched_set_fifo_low(struct task_struct *p);
extern void sched_set_normal(struct task_struct *p, int nice);
extern int sched_setattr(struct task_struct *, const struct sched_attr *);
extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *);
extern struct task_struct *idle_task(int cpu);

/**
 * is_idle_task - is the specified task an idle task?
 * @p: the task in question.
 *
 * Return: 1 if @p is an idle task. 0 otherwise.
 */
static __always_inline bool is_idle_task(const struct task_struct *p)
{
	return !!(p->flags & PF_IDLE);
}

extern struct task_struct *curr_task(int cpu);
extern void ia64_set_curr_task(int cpu, struct task_struct *p);

void yield(void);

union thread_union {
#ifndef CONFIG_ARCH_TASK_STRUCT_ON_STACK
	struct task_struct task;
#endif
#ifndef CONFIG_THREAD_INFO_IN_TASK
	struct thread_info thread_info;
#endif
	unsigned long stack[THREAD_SIZE/sizeof(long)];
};

#ifndef CONFIG_THREAD_INFO_IN_TASK
extern struct thread_info init_thread_info;
#endif

extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)];

#ifdef CONFIG_THREAD_INFO_IN_TASK
static inline struct thread_info *task_thread_info(struct task_struct *task)
{
	return &task->thread_info;
}
#elif !defined(__HAVE_THREAD_FUNCTIONS)
# define task_thread_info(task)	((struct thread_info *)(task)->stack)
#endif

/*
 * find a task by one of its numerical ids
 *
 * find_task_by_pid_ns():
 *      finds a task by its pid in the specified namespace
 * find_task_by_vpid():
 *      finds a task by its virtual pid
 *
 * see also find_vpid() etc in include/linux/pid.h
 */

extern struct task_struct *find_task_by_vpid(pid_t nr);
extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns);

/*
 * find a task by its virtual pid and get the task struct
 */
extern struct task_struct *find_get_task_by_vpid(pid_t nr);

extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
extern void wake_up_new_task(struct task_struct *tsk);

#ifdef CONFIG_SMP
extern void kick_process(struct task_struct *tsk);
#else
static inline void kick_process(struct task_struct *tsk) { }
#endif

extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);

static inline void set_task_comm(struct task_struct *tsk, const char *from)
{
	__set_task_comm(tsk, from, false);
}

extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk);
#define get_task_comm(buf, tsk) ({			\
	BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN);	\
	__get_task_comm(buf, sizeof(buf), tsk);		\
})

#ifdef CONFIG_SMP
static __always_inline void scheduler_ipi(void)
{
	/*
	 * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
	 * TIF_NEED_RESCHED remotely (for the first time) will also send
	 * this IPI.
	 */
	preempt_fold_need_resched();
}
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
#else
static inline void scheduler_ipi(void) { }
static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state)
{
	return 1;
}
#endif

/*
 * Set thread flags in other task's structures.
 * See asm/thread_info.h for TIF_xxxx flags available:
 */
static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
	set_ti_thread_flag(task_thread_info(tsk), flag);
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
	clear_ti_thread_flag(task_thread_info(tsk), flag);
}

static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag,
					  bool value)
{
	update_ti_thread_flag(task_thread_info(tsk), flag, value);
}

static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
	return test_ti_thread_flag(task_thread_info(tsk), flag);
}

static inline void set_tsk_need_resched(struct task_struct *tsk)
{
	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}

static inline void clear_tsk_need_resched(struct task_struct *tsk)
{
	clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}

static inline int test_tsk_need_resched(struct task_struct *tsk)
{
	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
}

/*
 * cond_resched() and cond_resched_lock(): latency reduction via
 * explicit rescheduling in places that are safe. The return
 * value indicates whether a reschedule was done in fact.
 * cond_resched_lock() will drop the spinlock before scheduling,
 */
#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
extern int __cond_resched(void);

#ifdef CONFIG_PREEMPT_DYNAMIC

DECLARE_STATIC_CALL(cond_resched, __cond_resched);

static __always_inline int _cond_resched(void)
{
	return static_call_mod(cond_resched)();
}

#else

static inline int _cond_resched(void)
{
	return __cond_resched();
}

#endif /* CONFIG_PREEMPT_DYNAMIC */

#else

static inline int _cond_resched(void) { return 0; }

#endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */

#define cond_resched() ({			\
	___might_sleep(__FILE__, __LINE__, 0);	\
	_cond_resched();			\
})

extern int __cond_resched_lock(spinlock_t *lock);
extern int __cond_resched_rwlock_read(rwlock_t *lock);
extern int __cond_resched_rwlock_write(rwlock_t *lock);

#define cond_resched_lock(lock) ({				\
	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
	__cond_resched_lock(lock);				\
})

#define cond_resched_rwlock_read(lock) ({			\
	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
	__cond_resched_rwlock_read(lock);			\
})

#define cond_resched_rwlock_write(lock) ({			\
	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
	__cond_resched_rwlock_write(lock);			\
})

static inline void cond_resched_rcu(void)
{
#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
	rcu_read_unlock();
	cond_resched();
	rcu_read_lock();
#endif
}

/*
 * Does a critical section need to be broken due to another
 * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
 * but a general need for low latency)
 */
static inline int spin_needbreak(spinlock_t *lock)
{
#ifdef CONFIG_PREEMPTION
	return spin_is_contended(lock);
#else
	return 0;
#endif
}

/*
 * Check if a rwlock is contended.
 * Returns non-zero if there is another task waiting on the rwlock.
 * Returns zero if the lock is not contended or the system / underlying
 * rwlock implementation does not support contention detection.
 * Technically does not depend on CONFIG_PREEMPTION, but a general need
 * for low latency.
 */
static inline int rwlock_needbreak(rwlock_t *lock)
{
#ifdef CONFIG_PREEMPTION
	return rwlock_is_contended(lock);
#else
	return 0;
#endif
}

static __always_inline bool need_resched(void)
{
	return unlikely(tif_need_resched());
}

/*
 * Wrappers for p->thread_info->cpu access. No-op on UP.
 */
#ifdef CONFIG_SMP

static inline unsigned int task_cpu(const struct task_struct *p)
{
#ifdef CONFIG_THREAD_INFO_IN_TASK
	return READ_ONCE(p->cpu);
#else
	return READ_ONCE(task_thread_info(p)->cpu);
#endif
}

extern void set_task_cpu(struct task_struct *p, unsigned int cpu);

#else

static inline unsigned int task_cpu(const struct task_struct *p)
{
	return 0;
}

static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
{
}

#endif /* CONFIG_SMP */

/*
 * In order to reduce various lock holder preemption latencies provide an
 * interface to see if a vCPU is currently running or not.
 *
 * This allows us to terminate optimistic spin loops and block, analogous to
 * the native optimistic spin heuristic of testing if the lock owner task is
 * running or not.
 */
#ifndef vcpu_is_preempted
static inline bool vcpu_is_preempted(int cpu)
{
	return false;
}
#endif

extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);

#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk)	TASK_SIZE
#endif

#ifdef CONFIG_SMP
/* Returns effective CPU energy utilization, as seen by the scheduler */
unsigned long sched_cpu_util(int cpu, unsigned long max);
#endif /* CONFIG_SMP */

#ifdef CONFIG_RSEQ

/*
 * Map the event mask on the user-space ABI enum rseq_cs_flags
 * for direct mask checks.
 */
enum rseq_event_mask_bits {
	RSEQ_EVENT_PREEMPT_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT,
	RSEQ_EVENT_SIGNAL_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT,
	RSEQ_EVENT_MIGRATE_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT,
};

enum rseq_event_mask {
	RSEQ_EVENT_PREEMPT	= (1U << RSEQ_EVENT_PREEMPT_BIT),
	RSEQ_EVENT_SIGNAL	= (1U << RSEQ_EVENT_SIGNAL_BIT),
	RSEQ_EVENT_MIGRATE	= (1U << RSEQ_EVENT_MIGRATE_BIT),
};

static inline void rseq_set_notify_resume(struct task_struct *t)
{
	if (t->rseq)
		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
}

void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);

static inline void rseq_handle_notify_resume(struct ksignal *ksig,
					     struct pt_regs *regs)
{
	if (current->rseq)
		__rseq_handle_notify_resume(ksig, regs);
}

static inline void rseq_signal_deliver(struct ksignal *ksig,
				       struct pt_regs *regs)
{
	preempt_disable();
	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
	preempt_enable();
	rseq_handle_notify_resume(ksig, regs);
}

/* rseq_preempt() requires preemption to be disabled. */
static inline void rseq_preempt(struct task_struct *t)
{
	__set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask);
	rseq_set_notify_resume(t);
}

/* rseq_migrate() requires preemption to be disabled. */
static inline void rseq_migrate(struct task_struct *t)
{
	__set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask);
	rseq_set_notify_resume(t);
}

/*
 * If parent process has a registered restartable sequences area, the
 * child inherits. Unregister rseq for a clone with CLONE_VM set.
 */
static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
{
	if (clone_flags & CLONE_VM) {
		t->rseq = NULL;
		t->rseq_sig = 0;
		t->rseq_event_mask = 0;
	} else {
		t->rseq = current->rseq;
		t->rseq_sig = current->rseq_sig;
		t->rseq_event_mask = current->rseq_event_mask;
	}
}

static inline void rseq_execve(struct task_struct *t)
{
	t->rseq = NULL;
	t->rseq_sig = 0;
	t->rseq_event_mask = 0;
}

#else

static inline void rseq_set_notify_resume(struct task_struct *t)
{
}
static inline void rseq_handle_notify_resume(struct ksignal *ksig,
					     struct pt_regs *regs)
{
}
static inline void rseq_signal_deliver(struct ksignal *ksig,
				       struct pt_regs *regs)
{
}
static inline void rseq_preempt(struct task_struct *t)
{
}
static inline void rseq_migrate(struct task_struct *t)
{
}
static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
{
}
static inline void rseq_execve(struct task_struct *t)
{
}

#endif

#ifdef CONFIG_DEBUG_RSEQ

void rseq_syscall(struct pt_regs *regs);

#else

static inline void rseq_syscall(struct pt_regs *regs)
{
}

#endif

const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq);
char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len);
int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq);

const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq);
const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);

int sched_trace_rq_cpu(struct rq *rq);
int sched_trace_rq_cpu_capacity(struct rq *rq);
int sched_trace_rq_nr_running(struct rq *rq);

const struct cpumask *sched_trace_rd_span(struct root_domain *rd);

#endif