aboutsummaryrefslogtreecommitdiff
path: root/kernel/locking/rtmutex.c
blob: 03b21135313cbefd19d3751aa878db61dfc1e5a6 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * RT-Mutexes: simple blocking mutual exclusion locks with PI support
 *
 * started by Ingo Molnar and Thomas Gleixner.
 *
 *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 *  Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
 *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
 *  Copyright (C) 2006 Esben Nielsen
 *
 *  See Documentation/locking/rt-mutex-design.rst for details.
 */
#include <linux/spinlock.h>
#include <linux/export.h>
#include <linux/sched/signal.h>
#include <linux/sched/rt.h>
#include <linux/sched/deadline.h>
#include <linux/sched/wake_q.h>
#include <linux/sched/debug.h>
#include <linux/timer.h>

#include "rtmutex_common.h"

/*
 * lock->owner state tracking:
 *
 * lock->owner holds the task_struct pointer of the owner. Bit 0
 * is used to keep track of the "lock has waiters" state.
 *
 * owner	bit0
 * NULL		0	lock is free (fast acquire possible)
 * NULL		1	lock is free and has waiters and the top waiter
 *				is going to take the lock*
 * taskpointer	0	lock is held (fast release possible)
 * taskpointer	1	lock is held and has waiters**
 *
 * The fast atomic compare exchange based acquire and release is only
 * possible when bit 0 of lock->owner is 0.
 *
 * (*) It also can be a transitional state when grabbing the lock
 * with ->wait_lock is held. To prevent any fast path cmpxchg to the lock,
 * we need to set the bit0 before looking at the lock, and the owner may be
 * NULL in this small time, hence this can be a transitional state.
 *
 * (**) There is a small time when bit 0 is set but there are no
 * waiters. This can happen when grabbing the lock in the slow path.
 * To prevent a cmpxchg of the owner releasing the lock, we need to
 * set this bit before looking at the lock.
 */

static void
rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
{
	unsigned long val = (unsigned long)owner;

	if (rt_mutex_has_waiters(lock))
		val |= RT_MUTEX_HAS_WAITERS;

	WRITE_ONCE(lock->owner, (struct task_struct *)val);
}

static inline void clear_rt_mutex_waiters(struct rt_mutex *lock)
{
	lock->owner = (struct task_struct *)
			((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
}

static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
{
	unsigned long owner, *p = (unsigned long *) &lock->owner;

	if (rt_mutex_has_waiters(lock))
		return;

	/*
	 * The rbtree has no waiters enqueued, now make sure that the
	 * lock->owner still has the waiters bit set, otherwise the
	 * following can happen:
	 *
	 * CPU 0	CPU 1		CPU2
	 * l->owner=T1
	 *		rt_mutex_lock(l)
	 *		lock(l->lock)
	 *		l->owner = T1 | HAS_WAITERS;
	 *		enqueue(T2)
	 *		boost()
	 *		  unlock(l->lock)
	 *		block()
	 *
	 *				rt_mutex_lock(l)
	 *				lock(l->lock)
	 *				l->owner = T1 | HAS_WAITERS;
	 *				enqueue(T3)
	 *				boost()
	 *				  unlock(l->lock)
	 *				block()
	 *		signal(->T2)	signal(->T3)
	 *		lock(l->lock)
	 *		dequeue(T2)
	 *		deboost()
	 *		  unlock(l->lock)
	 *				lock(l->lock)
	 *				dequeue(T3)
	 *				 ==> wait list is empty
	 *				deboost()
	 *				 unlock(l->lock)
	 *		lock(l->lock)
	 *		fixup_rt_mutex_waiters()
	 *		  if (wait_list_empty(l) {
	 *		    l->owner = owner
	 *		    owner = l->owner & ~HAS_WAITERS;
	 *		      ==> l->owner = T1
	 *		  }
	 *				lock(l->lock)
	 * rt_mutex_unlock(l)		fixup_rt_mutex_waiters()
	 *				  if (wait_list_empty(l) {
	 *				    owner = l->owner & ~HAS_WAITERS;
	 * cmpxchg(l->owner, T1, NULL)
	 *  ===> Success (l->owner = NULL)
	 *
	 *				    l->owner = owner
	 *				      ==> l->owner = T1
	 *				  }
	 *
	 * With the check for the waiter bit in place T3 on CPU2 will not
	 * overwrite. All tasks fiddling with the waiters bit are
	 * serialized by l->lock, so nothing else can modify the waiters
	 * bit. If the bit is set then nothing can change l->owner either
	 * so the simple RMW is safe. The cmpxchg() will simply fail if it
	 * happens in the middle of the RMW because the waiters bit is
	 * still set.
	 */
	owner = READ_ONCE(*p);
	if (owner & RT_MUTEX_HAS_WAITERS)
		WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
}

/*
 * We can speed up the acquire/release, if there's no debugging state to be
 * set up.
 */
#ifndef CONFIG_DEBUG_RT_MUTEXES
# define rt_mutex_cmpxchg_acquire(l,c,n) (cmpxchg_acquire(&l->owner, c, n) == c)
# define rt_mutex_cmpxchg_release(l,c,n) (cmpxchg_release(&l->owner, c, n) == c)

/*
 * Callers must hold the ->wait_lock -- which is the whole purpose as we force
 * all future threads that attempt to [Rmw] the lock to the slowpath. As such
 * relaxed semantics suffice.
 */
static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
{
	unsigned long owner, *p = (unsigned long *) &lock->owner;

	do {
		owner = *p;
	} while (cmpxchg_relaxed(p, owner,
				 owner | RT_MUTEX_HAS_WAITERS) != owner);
}

/*
 * Safe fastpath aware unlock:
 * 1) Clear the waiters bit
 * 2) Drop lock->wait_lock
 * 3) Try to unlock the lock with cmpxchg
 */
static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
					unsigned long flags)
	__releases(lock->wait_lock)
{
	struct task_struct *owner = rt_mutex_owner(lock);

	clear_rt_mutex_waiters(lock);
	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
	/*
	 * If a new waiter comes in between the unlock and the cmpxchg
	 * we have two situations:
	 *
	 * unlock(wait_lock);
	 *					lock(wait_lock);
	 * cmpxchg(p, owner, 0) == owner
	 *					mark_rt_mutex_waiters(lock);
	 *					acquire(lock);
	 * or:
	 *
	 * unlock(wait_lock);
	 *					lock(wait_lock);
	 *					mark_rt_mutex_waiters(lock);
	 *
	 * cmpxchg(p, owner, 0) != owner
	 *					enqueue_waiter();
	 *					unlock(wait_lock);
	 * lock(wait_lock);
	 * wake waiter();
	 * unlock(wait_lock);
	 *					lock(wait_lock);
	 *					acquire(lock);
	 */
	return rt_mutex_cmpxchg_release(lock, owner, NULL);
}

#else
# define rt_mutex_cmpxchg_acquire(l,c,n)	(0)
# define rt_mutex_cmpxchg_release(l,c,n)	(0)

static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
{
	lock->owner = (struct task_struct *)
			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
}

/*
 * Simple slow path only version: lock->owner is protected by lock->wait_lock.
 */
static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
					unsigned long flags)
	__releases(lock->wait_lock)
{
	lock->owner = NULL;
	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
	return true;
}
#endif

/*
 * Only use with rt_mutex_waiter_{less,equal}()
 */
#define task_to_waiter(p)	\
	&(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline }

static inline int
rt_mutex_waiter_less(struct rt_mutex_waiter *left,
		     struct rt_mutex_waiter *right)
{
	if (left->prio < right->prio)
		return 1;

	/*
	 * If both waiters have dl_prio(), we check the deadlines of the
	 * associated tasks.
	 * If left waiter has a dl_prio(), and we didn't return 1 above,
	 * then right waiter has a dl_prio() too.
	 */
	if (dl_prio(left->prio))
		return dl_time_before(left->deadline, right->deadline);

	return 0;
}

static inline int
rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
		      struct rt_mutex_waiter *right)
{
	if (left->prio != right->prio)
		return 0;

	/*
	 * If both waiters have dl_prio(), we check the deadlines of the
	 * associated tasks.
	 * If left waiter has a dl_prio(), and we didn't return 0 above,
	 * then right waiter has a dl_prio() too.
	 */
	if (dl_prio(left->prio))
		return left->deadline == right->deadline;

	return 1;
}

#define __node_2_waiter(node) \
	rb_entry((node), struct rt_mutex_waiter, tree_entry)

static inline bool __waiter_less(struct rb_node *a, const struct rb_node *b)
{
	return rt_mutex_waiter_less(__node_2_waiter(a), __node_2_waiter(b));
}

static void
rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
{
	rb_add_cached(&waiter->tree_entry, &lock->waiters, __waiter_less);
}

static void
rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
{
	if (RB_EMPTY_NODE(&waiter->tree_entry))
		return;

	rb_erase_cached(&waiter->tree_entry, &lock->waiters);
	RB_CLEAR_NODE(&waiter->tree_entry);
}

#define __node_2_pi_waiter(node) \
	rb_entry((node), struct rt_mutex_waiter, pi_tree_entry)

static inline bool __pi_waiter_less(struct rb_node *a, const struct rb_node *b)
{
	return rt_mutex_waiter_less(__node_2_pi_waiter(a), __node_2_pi_waiter(b));
}

static void
rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
{
	rb_add_cached(&waiter->pi_tree_entry, &task->pi_waiters, __pi_waiter_less);
}

static void
rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
{
	if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
		return;

	rb_erase_cached(&waiter->pi_tree_entry, &task->pi_waiters);
	RB_CLEAR_NODE(&waiter->pi_tree_entry);
}

static void rt_mutex_adjust_prio(struct task_struct *p)
{
	struct task_struct *pi_task = NULL;

	lockdep_assert_held(&p->pi_lock);

	if (task_has_pi_waiters(p))
		pi_task = task_top_pi_waiter(p)->task;

	rt_mutex_setprio(p, pi_task);
}

/*
 * Deadlock detection is conditional:
 *
 * If CONFIG_DEBUG_RT_MUTEXES=n, deadlock detection is only conducted
 * if the detect argument is == RT_MUTEX_FULL_CHAINWALK.
 *
 * If CONFIG_DEBUG_RT_MUTEXES=y, deadlock detection is always
 * conducted independent of the detect argument.
 *
 * If the waiter argument is NULL this indicates the deboost path and
 * deadlock detection is disabled independent of the detect argument
 * and the config settings.
 */
static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter,
					  enum rtmutex_chainwalk chwalk)
{
	/*
	 * This is just a wrapper function for the following call,
	 * because debug_rt_mutex_detect_deadlock() smells like a magic
	 * debug feature and I wanted to keep the cond function in the
	 * main source file along with the comments instead of having
	 * two of the same in the headers.
	 */
	return debug_rt_mutex_detect_deadlock(waiter, chwalk);
}

/*
 * Max number of times we'll walk the boosting chain:
 */
int max_lock_depth = 1024;

static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
{
	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
}

/*
 * Adjust the priority chain. Also used for deadlock detection.
 * Decreases task's usage by one - may thus free the task.
 *
 * @task:	the task owning the mutex (owner) for which a chain walk is
 *		probably needed
 * @chwalk:	do we have to carry out deadlock detection?
 * @orig_lock:	the mutex (can be NULL if we are walking the chain to recheck
 *		things for a task that has just got its priority adjusted, and
 *		is waiting on a mutex)
 * @next_lock:	the mutex on which the owner of @orig_lock was blocked before
 *		we dropped its pi_lock. Is never dereferenced, only used for
 *		comparison to detect lock chain changes.
 * @orig_waiter: rt_mutex_waiter struct for the task that has just donated
 *		its priority to the mutex owner (can be NULL in the case
 *		depicted above or if the top waiter is gone away and we are
 *		actually deboosting the owner)
 * @top_task:	the current top waiter
 *
 * Returns 0 or -EDEADLK.
 *
 * Chain walk basics and protection scope
 *
 * [R] refcount on task
 * [P] task->pi_lock held
 * [L] rtmutex->wait_lock held
 *
 * Step	Description				Protected by
 *	function arguments:
 *	@task					[R]
 *	@orig_lock if != NULL			@top_task is blocked on it
 *	@next_lock				Unprotected. Cannot be
 *						dereferenced. Only used for
 *						comparison.
 *	@orig_waiter if != NULL			@top_task is blocked on it
 *	@top_task				current, or in case of proxy
 *						locking protected by calling
 *						code
 *	again:
 *	  loop_sanity_check();
 *	retry:
 * [1]	  lock(task->pi_lock);			[R] acquire [P]
 * [2]	  waiter = task->pi_blocked_on;		[P]
 * [3]	  check_exit_conditions_1();		[P]
 * [4]	  lock = waiter->lock;			[P]
 * [5]	  if (!try_lock(lock->wait_lock)) {	[P] try to acquire [L]
 *	    unlock(task->pi_lock);		release [P]
 *	    goto retry;
 *	  }
 * [6]	  check_exit_conditions_2();		[P] + [L]
 * [7]	  requeue_lock_waiter(lock, waiter);	[P] + [L]
 * [8]	  unlock(task->pi_lock);		release [P]
 *	  put_task_struct(task);		release [R]
 * [9]	  check_exit_conditions_3();		[L]
 * [10]	  task = owner(lock);			[L]
 *	  get_task_struct(task);		[L] acquire [R]
 *	  lock(task->pi_lock);			[L] acquire [P]
 * [11]	  requeue_pi_waiter(tsk, waiters(lock));[P] + [L]
 * [12]	  check_exit_conditions_4();		[P] + [L]
 * [13]	  unlock(task->pi_lock);		release [P]
 *	  unlock(lock->wait_lock);		release [L]
 *	  goto again;
 */
static int rt_mutex_adjust_prio_chain(struct task_struct *task,
				      enum rtmutex_chainwalk chwalk,
				      struct rt_mutex *orig_lock,
				      struct rt_mutex *next_lock,
				      struct rt_mutex_waiter *orig_waiter,
				      struct task_struct *top_task)
{
	struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
	struct rt_mutex_waiter *prerequeue_top_waiter;
	int ret = 0, depth = 0;
	struct rt_mutex *lock;
	bool detect_deadlock;
	bool requeue = true;

	detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);

	/*
	 * The (de)boosting is a step by step approach with a lot of
	 * pitfalls. We want this to be preemptible and we want hold a
	 * maximum of two locks per step. So we have to check
	 * carefully whether things change under us.
	 */
 again:
	/*
	 * We limit the lock chain length for each invocation.
	 */
	if (++depth > max_lock_depth) {
		static int prev_max;

		/*
		 * Print this only once. If the admin changes the limit,
		 * print a new message when reaching the limit again.
		 */
		if (prev_max != max_lock_depth) {
			prev_max = max_lock_depth;
			printk(KERN_WARNING "Maximum lock depth %d reached "
			       "task: %s (%d)\n", max_lock_depth,
			       top_task->comm, task_pid_nr(top_task));
		}
		put_task_struct(task);

		return -EDEADLK;
	}

	/*
	 * We are fully preemptible here and only hold the refcount on
	 * @task. So everything can have changed under us since the
	 * caller or our own code below (goto retry/again) dropped all
	 * locks.
	 */
 retry:
	/*
	 * [1] Task cannot go away as we did a get_task() before !
	 */
	raw_spin_lock_irq(&task->pi_lock);

	/*
	 * [2] Get the waiter on which @task is blocked on.
	 */
	waiter = task->pi_blocked_on;

	/*
	 * [3] check_exit_conditions_1() protected by task->pi_lock.
	 */

	/*
	 * Check whether the end of the boosting chain has been
	 * reached or the state of the chain has changed while we
	 * dropped the locks.
	 */
	if (!waiter)
		goto out_unlock_pi;

	/*
	 * Check the orig_waiter state. After we dropped the locks,
	 * the previous owner of the lock might have released the lock.
	 */
	if (orig_waiter && !rt_mutex_owner(orig_lock))
		goto out_unlock_pi;

	/*
	 * We dropped all locks after taking a refcount on @task, so
	 * the task might have moved on in the lock chain or even left
	 * the chain completely and blocks now on an unrelated lock or
	 * on @orig_lock.
	 *
	 * We stored the lock on which @task was blocked in @next_lock,
	 * so we can detect the chain change.
	 */
	if (next_lock != waiter->lock)
		goto out_unlock_pi;

	/*
	 * Drop out, when the task has no waiters. Note,
	 * top_waiter can be NULL, when we are in the deboosting
	 * mode!
	 */
	if (top_waiter) {
		if (!task_has_pi_waiters(task))
			goto out_unlock_pi;
		/*
		 * If deadlock detection is off, we stop here if we
		 * are not the top pi waiter of the task. If deadlock
		 * detection is enabled we continue, but stop the
		 * requeueing in the chain walk.
		 */
		if (top_waiter != task_top_pi_waiter(task)) {
			if (!detect_deadlock)
				goto out_unlock_pi;
			else
				requeue = false;
		}
	}

	/*
	 * If the waiter priority is the same as the task priority
	 * then there is no further priority adjustment necessary.  If
	 * deadlock detection is off, we stop the chain walk. If its
	 * enabled we continue, but stop the requeueing in the chain
	 * walk.
	 */
	if (rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
		if (!detect_deadlock)
			goto out_unlock_pi;
		else
			requeue = false;
	}

	/*
	 * [4] Get the next lock
	 */
	lock = waiter->lock;
	/*
	 * [5] We need to trylock here as we are holding task->pi_lock,
	 * which is the reverse lock order versus the other rtmutex
	 * operations.
	 */
	if (!raw_spin_trylock(&lock->wait_lock)) {
		raw_spin_unlock_irq(&task->pi_lock);
		cpu_relax();
		goto retry;
	}

	/*
	 * [6] check_exit_conditions_2() protected by task->pi_lock and
	 * lock->wait_lock.
	 *
	 * Deadlock detection. If the lock is the same as the original
	 * lock which caused us to walk the lock chain or if the
	 * current lock is owned by the task which initiated the chain
	 * walk, we detected a deadlock.
	 */
	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
		debug_rt_mutex_deadlock(chwalk, orig_waiter, lock);
		raw_spin_unlock(&lock->wait_lock);
		ret = -EDEADLK;
		goto out_unlock_pi;
	}

	/*
	 * If we just follow the lock chain for deadlock detection, no
	 * need to do all the requeue operations. To avoid a truckload
	 * of conditionals around the various places below, just do the
	 * minimum chain walk checks.
	 */
	if (!requeue) {
		/*
		 * No requeue[7] here. Just release @task [8]
		 */
		raw_spin_unlock(&task->pi_lock);
		put_task_struct(task);

		/*
		 * [9] check_exit_conditions_3 protected by lock->wait_lock.
		 * If there is no owner of the lock, end of chain.
		 */
		if (!rt_mutex_owner(lock)) {
			raw_spin_unlock_irq(&lock->wait_lock);
			return 0;
		}

		/* [10] Grab the next task, i.e. owner of @lock */
		task = get_task_struct(rt_mutex_owner(lock));
		raw_spin_lock(&task->pi_lock);

		/*
		 * No requeue [11] here. We just do deadlock detection.
		 *
		 * [12] Store whether owner is blocked
		 * itself. Decision is made after dropping the locks
		 */
		next_lock = task_blocked_on_lock(task);
		/*
		 * Get the top waiter for the next iteration
		 */
		top_waiter = rt_mutex_top_waiter(lock);

		/* [13] Drop locks */
		raw_spin_unlock(&task->pi_lock);
		raw_spin_unlock_irq(&lock->wait_lock);

		/* If owner is not blocked, end of chain. */
		if (!next_lock)
			goto out_put_task;
		goto again;
	}

	/*
	 * Store the current top waiter before doing the requeue
	 * operation on @lock. We need it for the boost/deboost
	 * decision below.
	 */
	prerequeue_top_waiter = rt_mutex_top_waiter(lock);

	/* [7] Requeue the waiter in the lock waiter tree. */
	rt_mutex_dequeue(lock, waiter);

	/*
	 * Update the waiter prio fields now that we're dequeued.
	 *
	 * These values can have changed through either:
	 *
	 *   sys_sched_set_scheduler() / sys_sched_setattr()
	 *
	 * or
	 *
	 *   DL CBS enforcement advancing the effective deadline.
	 *
	 * Even though pi_waiters also uses these fields, and that tree is only
	 * updated in [11], we can do this here, since we hold [L], which
	 * serializes all pi_waiters access and rb_erase() does not care about
	 * the values of the node being removed.
	 */
	waiter->prio = task->prio;
	waiter->deadline = task->dl.deadline;

	rt_mutex_enqueue(lock, waiter);

	/* [8] Release the task */
	raw_spin_unlock(&task->pi_lock);
	put_task_struct(task);

	/*
	 * [9] check_exit_conditions_3 protected by lock->wait_lock.
	 *
	 * We must abort the chain walk if there is no lock owner even
	 * in the dead lock detection case, as we have nothing to
	 * follow here. This is the end of the chain we are walking.
	 */
	if (!rt_mutex_owner(lock)) {
		/*
		 * If the requeue [7] above changed the top waiter,
		 * then we need to wake the new top waiter up to try
		 * to get the lock.
		 */
		if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
			wake_up_process(rt_mutex_top_waiter(lock)->task);
		raw_spin_unlock_irq(&lock->wait_lock);
		return 0;
	}

	/* [10] Grab the next task, i.e. the owner of @lock */
	task = get_task_struct(rt_mutex_owner(lock));
	raw_spin_lock(&task->pi_lock);

	/* [11] requeue the pi waiters if necessary */
	if (waiter == rt_mutex_top_waiter(lock)) {
		/*
		 * The waiter became the new top (highest priority)
		 * waiter on the lock. Replace the previous top waiter
		 * in the owner tasks pi waiters tree with this waiter
		 * and adjust the priority of the owner.
		 */
		rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
		rt_mutex_enqueue_pi(task, waiter);
		rt_mutex_adjust_prio(task);

	} else if (prerequeue_top_waiter == waiter) {
		/*
		 * The waiter was the top waiter on the lock, but is
		 * no longer the top prority waiter. Replace waiter in
		 * the owner tasks pi waiters tree with the new top
		 * (highest priority) waiter and adjust the priority
		 * of the owner.
		 * The new top waiter is stored in @waiter so that
		 * @waiter == @top_waiter evaluates to true below and
		 * we continue to deboost the rest of the chain.
		 */
		rt_mutex_dequeue_pi(task, waiter);
		waiter = rt_mutex_top_waiter(lock);
		rt_mutex_enqueue_pi(task, waiter);
		rt_mutex_adjust_prio(task);
	} else {
		/*
		 * Nothing changed. No need to do any priority
		 * adjustment.
		 */
	}

	/*
	 * [12] check_exit_conditions_4() protected by task->pi_lock
	 * and lock->wait_lock. The actual decisions are made after we
	 * dropped the locks.
	 *
	 * Check whether the task which owns the current lock is pi
	 * blocked itself. If yes we store a pointer to the lock for
	 * the lock chain change detection above. After we dropped
	 * task->pi_lock next_lock cannot be dereferenced anymore.
	 */
	next_lock = task_blocked_on_lock(task);
	/*
	 * Store the top waiter of @lock for the end of chain walk
	 * decision below.
	 */
	top_waiter = rt_mutex_top_waiter(lock);

	/* [13] Drop the locks */
	raw_spin_unlock(&task->pi_lock);
	raw_spin_unlock_irq(&lock->wait_lock);

	/*
	 * Make the actual exit decisions [12], based on the stored
	 * values.
	 *
	 * We reached the end of the lock chain. Stop right here. No
	 * point to go back just to figure that out.
	 */
	if (!next_lock)
		goto out_put_task;

	/*
	 * If the current waiter is not the top waiter on the lock,
	 * then we can stop the chain walk here if we are not in full
	 * deadlock detection mode.
	 */
	if (!detect_deadlock && waiter != top_waiter)
		goto out_put_task;

	goto again;

 out_unlock_pi:
	raw_spin_unlock_irq(&task->pi_lock);
 out_put_task:
	put_task_struct(task);

	return ret;
}

/*
 * Try to take an rt-mutex
 *
 * Must be called with lock->wait_lock held and interrupts disabled
 *
 * @lock:   The lock to be acquired.
 * @task:   The task which wants to acquire the lock
 * @waiter: The waiter that is queued to the lock's wait tree if the
 *	    callsite called task_blocked_on_lock(), otherwise NULL
 */
static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
				struct rt_mutex_waiter *waiter)
{
	lockdep_assert_held(&lock->wait_lock);

	/*
	 * Before testing whether we can acquire @lock, we set the
	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
	 * other tasks which try to modify @lock into the slow path
	 * and they serialize on @lock->wait_lock.
	 *
	 * The RT_MUTEX_HAS_WAITERS bit can have a transitional state
	 * as explained at the top of this file if and only if:
	 *
	 * - There is a lock owner. The caller must fixup the
	 *   transient state if it does a trylock or leaves the lock
	 *   function due to a signal or timeout.
	 *
	 * - @task acquires the lock and there are no other
	 *   waiters. This is undone in rt_mutex_set_owner(@task) at
	 *   the end of this function.
	 */
	mark_rt_mutex_waiters(lock);

	/*
	 * If @lock has an owner, give up.
	 */
	if (rt_mutex_owner(lock))
		return 0;

	/*
	 * If @waiter != NULL, @task has already enqueued the waiter
	 * into @lock waiter tree. If @waiter == NULL then this is a
	 * trylock attempt.
	 */
	if (waiter) {
		/*
		 * If waiter is not the highest priority waiter of
		 * @lock, give up.
		 */
		if (waiter != rt_mutex_top_waiter(lock))
			return 0;

		/*
		 * We can acquire the lock. Remove the waiter from the
		 * lock waiters tree.
		 */
		rt_mutex_dequeue(lock, waiter);

	} else {
		/*
		 * If the lock has waiters already we check whether @task is
		 * eligible to take over the lock.
		 *
		 * If there are no other waiters, @task can acquire
		 * the lock.  @task->pi_blocked_on is NULL, so it does
		 * not need to be dequeued.
		 */
		if (rt_mutex_has_waiters(lock)) {
			/*
			 * If @task->prio is greater than or equal to
			 * the top waiter priority (kernel view),
			 * @task lost.
			 */
			if (!rt_mutex_waiter_less(task_to_waiter(task),
						  rt_mutex_top_waiter(lock)))
				return 0;

			/*
			 * The current top waiter stays enqueued. We
			 * don't have to change anything in the lock
			 * waiters order.
			 */
		} else {
			/*
			 * No waiters. Take the lock without the
			 * pi_lock dance.@task->pi_blocked_on is NULL
			 * and we have no waiters to enqueue in @task
			 * pi waiters tree.
			 */
			goto takeit;
		}
	}

	/*
	 * Clear @task->pi_blocked_on. Requires protection by
	 * @task->pi_lock. Redundant operation for the @waiter == NULL
	 * case, but conditionals are more expensive than a redundant
	 * store.
	 */
	raw_spin_lock(&task->pi_lock);
	task->pi_blocked_on = NULL;
	/*
	 * Finish the lock acquisition. @task is the new owner. If
	 * other waiters exist we have to insert the highest priority
	 * waiter into @task->pi_waiters tree.
	 */
	if (rt_mutex_has_waiters(lock))
		rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
	raw_spin_unlock(&task->pi_lock);

takeit:
	/* We got the lock. */
	debug_rt_mutex_lock(lock);

	/*
	 * This either preserves the RT_MUTEX_HAS_WAITERS bit if there
	 * are still waiters or clears it.
	 */
	rt_mutex_set_owner(lock, task);

	return 1;
}

/*
 * Task blocks on lock.
 *
 * Prepare waiter and propagate pi chain
 *
 * This must be called with lock->wait_lock held and interrupts disabled
 */
static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
				   struct rt_mutex_waiter *waiter,
				   struct task_struct *task,
				   enum rtmutex_chainwalk chwalk)
{
	struct task_struct *owner = rt_mutex_owner(lock);
	struct rt_mutex_waiter *top_waiter = waiter;
	struct rt_mutex *next_lock;
	int chain_walk = 0, res;

	lockdep_assert_held(&lock->wait_lock);

	/*
	 * Early deadlock detection. We really don't want the task to
	 * enqueue on itself just to untangle the mess later. It's not
	 * only an optimization. We drop the locks, so another waiter
	 * can come in before the chain walk detects the deadlock. So
	 * the other will detect the deadlock and return -EDEADLOCK,
	 * which is wrong, as the other waiter is not in a deadlock
	 * situation.
	 */
	if (owner == task)
		return -EDEADLK;

	raw_spin_lock(&task->pi_lock);
	waiter->task = task;
	waiter->lock = lock;
	waiter->prio = task->prio;
	waiter->deadline = task->dl.deadline;

	/* Get the top priority waiter on the lock */
	if (rt_mutex_has_waiters(lock))
		top_waiter = rt_mutex_top_waiter(lock);
	rt_mutex_enqueue(lock, waiter);

	task->pi_blocked_on = waiter;

	raw_spin_unlock(&task->pi_lock);

	if (!owner)
		return 0;

	raw_spin_lock(&owner->pi_lock);
	if (waiter == rt_mutex_top_waiter(lock)) {
		rt_mutex_dequeue_pi(owner, top_waiter);
		rt_mutex_enqueue_pi(owner, waiter);

		rt_mutex_adjust_prio(owner);
		if (owner->pi_blocked_on)
			chain_walk = 1;
	} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
		chain_walk = 1;
	}

	/* Store the lock on which owner is blocked or NULL */
	next_lock = task_blocked_on_lock(owner);

	raw_spin_unlock(&owner->pi_lock);
	/*
	 * Even if full deadlock detection is on, if the owner is not
	 * blocked itself, we can avoid finding this out in the chain
	 * walk.
	 */
	if (!chain_walk || !next_lock)
		return 0;

	/*
	 * The owner can't disappear while holding a lock,
	 * so the owner struct is protected by wait_lock.
	 * Gets dropped in rt_mutex_adjust_prio_chain()!
	 */
	get_task_struct(owner);

	raw_spin_unlock_irq(&lock->wait_lock);

	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
					 next_lock, waiter, task);

	raw_spin_lock_irq(&lock->wait_lock);

	return res;
}

/*
 * Remove the top waiter from the current tasks pi waiter tree and
 * queue it up.
 *
 * Called with lock->wait_lock held and interrupts disabled.
 */
static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
				    struct rt_mutex *lock)
{
	struct rt_mutex_waiter *waiter;

	raw_spin_lock(&current->pi_lock);

	waiter = rt_mutex_top_waiter(lock);

	/*
	 * Remove it from current->pi_waiters and deboost.
	 *
	 * We must in fact deboost here in order to ensure we call
	 * rt_mutex_setprio() to update p->pi_top_task before the
	 * task unblocks.
	 */
	rt_mutex_dequeue_pi(current, waiter);
	rt_mutex_adjust_prio(current);

	/*
	 * As we are waking up the top waiter, and the waiter stays
	 * queued on the lock until it gets the lock, this lock
	 * obviously has waiters. Just set the bit here and this has
	 * the added benefit of forcing all new tasks into the
	 * slow path making sure no task of lower priority than
	 * the top waiter can steal this lock.
	 */
	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;

	/*
	 * We deboosted before waking the top waiter task such that we don't
	 * run two tasks with the 'same' priority (and ensure the
	 * p->pi_top_task pointer points to a blocked task). This however can
	 * lead to priority inversion if we would get preempted after the
	 * deboost but before waking our donor task, hence the preempt_disable()
	 * before unlock.
	 *
	 * Pairs with preempt_enable() in rt_mutex_postunlock();
	 */
	preempt_disable();
	wake_q_add(wake_q, waiter->task);
	raw_spin_unlock(&current->pi_lock);
}

/*
 * Remove a waiter from a lock and give up
 *
 * Must be called with lock->wait_lock held and interrupts disabled. I must
 * have just failed to try_to_take_rt_mutex().
 */
static void remove_waiter(struct rt_mutex *lock,
			  struct rt_mutex_waiter *waiter)
{
	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
	struct task_struct *owner = rt_mutex_owner(lock);
	struct rt_mutex *next_lock;

	lockdep_assert_held(&lock->wait_lock);

	raw_spin_lock(&current->pi_lock);
	rt_mutex_dequeue(lock, waiter);
	current->pi_blocked_on = NULL;
	raw_spin_unlock(&current->pi_lock);

	/*
	 * Only update priority if the waiter was the highest priority
	 * waiter of the lock and there is an owner to update.
	 */
	if (!owner || !is_top_waiter)
		return;

	raw_spin_lock(&owner->pi_lock);

	rt_mutex_dequeue_pi(owner, waiter);

	if (rt_mutex_has_waiters(lock))
		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));

	rt_mutex_adjust_prio(owner);

	/* Store the lock on which owner is blocked or NULL */
	next_lock = task_blocked_on_lock(owner);

	raw_spin_unlock(&owner->pi_lock);

	/*
	 * Don't walk the chain, if the owner task is not blocked
	 * itself.
	 */
	if (!next_lock)
		return;

	/* gets dropped in rt_mutex_adjust_prio_chain()! */
	get_task_struct(owner);

	raw_spin_unlock_irq(&lock->wait_lock);

	rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
				   next_lock, NULL, current);

	raw_spin_lock_irq(&lock->wait_lock);
}

/*
 * Recheck the pi chain, in case we got a priority setting
 *
 * Called from sched_setscheduler
 */
void rt_mutex_adjust_pi(struct task_struct *task)
{
	struct rt_mutex_waiter *waiter;
	struct rt_mutex *next_lock;
	unsigned long flags;

	raw_spin_lock_irqsave(&task->pi_lock, flags);

	waiter = task->pi_blocked_on;
	if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
		return;
	}
	next_lock = waiter->lock;
	raw_spin_unlock_irqrestore(&task->pi_lock, flags);

	/* gets dropped in rt_mutex_adjust_prio_chain()! */
	get_task_struct(task);

	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
				   next_lock, NULL, task);
}

void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
{
	debug_rt_mutex_init_waiter(waiter);
	RB_CLEAR_NODE(&waiter->pi_tree_entry);
	RB_CLEAR_NODE(&waiter->tree_entry);
	waiter->task = NULL;
}

/**
 * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
 * @lock:		 the rt_mutex to take
 * @state:		 the state the task should block in (TASK_INTERRUPTIBLE
 *			 or TASK_UNINTERRUPTIBLE)
 * @timeout:		 the pre-initialized and started timer, or NULL for none
 * @waiter:		 the pre-initialized rt_mutex_waiter
 *
 * Must be called with lock->wait_lock held and interrupts disabled
 */
static int __sched
__rt_mutex_slowlock(struct rt_mutex *lock, int state,
		    struct hrtimer_sleeper *timeout,
		    struct rt_mutex_waiter *waiter)
{
	int ret = 0;

	for (;;) {
		/* Try to acquire the lock: */
		if (try_to_take_rt_mutex(lock, current, waiter))
			break;

		/*
		 * TASK_INTERRUPTIBLE checks for signals and
		 * timeout. Ignored otherwise.
		 */
		if (likely(state == TASK_INTERRUPTIBLE)) {
			/* Signal pending? */
			if (signal_pending(current))
				ret = -EINTR;
			if (timeout && !timeout->task)
				ret = -ETIMEDOUT;
			if (ret)
				break;
		}

		raw_spin_unlock_irq(&lock->wait_lock);

		debug_rt_mutex_print_deadlock(waiter);

		schedule();

		raw_spin_lock_irq(&lock->wait_lock);
		set_current_state(state);
	}

	__set_current_state(TASK_RUNNING);
	return ret;
}

static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
				     struct rt_mutex_waiter *w)
{
	/*
	 * If the result is not -EDEADLOCK or the caller requested
	 * deadlock detection, nothing to do here.
	 */
	if (res != -EDEADLOCK || detect_deadlock)
		return;

	/*
	 * Yell lowdly and stop the task right here.
	 */
	rt_mutex_print_deadlock(w);
	while (1) {
		set_current_state(TASK_INTERRUPTIBLE);
		schedule();
	}
}

/*
 * Slow path lock function:
 */
static int __sched
rt_mutex_slowlock(struct rt_mutex *lock, int state,
		  struct hrtimer_sleeper *timeout,
		  enum rtmutex_chainwalk chwalk)
{
	struct rt_mutex_waiter waiter;
	unsigned long flags;
	int ret = 0;

	rt_mutex_init_waiter(&waiter);

	/*
	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
	 * be called in early boot if the cmpxchg() fast path is disabled
	 * (debug, no architecture support). In this case we will acquire the
	 * rtmutex with lock->wait_lock held. But we cannot unconditionally
	 * enable interrupts in that early boot case. So we need to use the
	 * irqsave/restore variants.
	 */
	raw_spin_lock_irqsave(&lock->wait_lock, flags);

	/* Try to acquire the lock again: */
	if (try_to_take_rt_mutex(lock, current, NULL)) {
		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
		return 0;
	}

	set_current_state(state);

	/* Setup the timer, when timeout != NULL */
	if (unlikely(timeout))
		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);

	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);

	if (likely(!ret))
		/* sleep on the mutex */
		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);

	if (unlikely(ret)) {
		__set_current_state(TASK_RUNNING);
		remove_waiter(lock, &waiter);
		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
	}

	/*
	 * try_to_take_rt_mutex() sets the waiter bit
	 * unconditionally. We might have to fix that up.
	 */
	fixup_rt_mutex_waiters(lock);

	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);

	/* Remove pending timer: */
	if (unlikely(timeout))
		hrtimer_cancel(&timeout->timer);

	debug_rt_mutex_free_waiter(&waiter);

	return ret;
}

static inline int __rt_mutex_slowtrylock(struct rt_mutex *lock)
{
	int ret = try_to_take_rt_mutex(lock, current, NULL);

	/*
	 * try_to_take_rt_mutex() sets the lock waiters bit
	 * unconditionally. Clean this up.
	 */
	fixup_rt_mutex_waiters(lock);

	return ret;
}

/*
 * Slow path try-lock function:
 */
static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
{
	unsigned long flags;
	int ret;

	/*
	 * If the lock already has an owner we fail to get the lock.
	 * This can be done without taking the @lock->wait_lock as
	 * it is only being read, and this is a trylock anyway.
	 */
	if (rt_mutex_owner(lock))
		return 0;

	/*
	 * The mutex has currently no owner. Lock the wait lock and try to
	 * acquire the lock. We use irqsave here to support early boot calls.
	 */
	raw_spin_lock_irqsave(&lock->wait_lock, flags);

	ret = __rt_mutex_slowtrylock(lock);

	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);

	return ret;
}

/*
 * Slow path to release a rt-mutex.
 *
 * Return whether the current task needs to call rt_mutex_postunlock().
 */
static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
					struct wake_q_head *wake_q)
{
	unsigned long flags;

	/* irqsave required to support early boot calls */
	raw_spin_lock_irqsave(&lock->wait_lock, flags);

	debug_rt_mutex_unlock(lock);

	/*
	 * We must be careful here if the fast path is enabled. If we
	 * have no waiters queued we cannot set owner to NULL here
	 * because of:
	 *
	 * foo->lock->owner = NULL;
	 *			rtmutex_lock(foo->lock);   <- fast path
	 *			free = atomic_dec_and_test(foo->refcnt);
	 *			rtmutex_unlock(foo->lock); <- fast path
	 *			if (free)
	 *				kfree(foo);
	 * raw_spin_unlock(foo->lock->wait_lock);
	 *
	 * So for the fastpath enabled kernel:
	 *
	 * Nothing can set the waiters bit as long as we hold
	 * lock->wait_lock. So we do the following sequence:
	 *
	 *	owner = rt_mutex_owner(lock);
	 *	clear_rt_mutex_waiters(lock);
	 *	raw_spin_unlock(&lock->wait_lock);
	 *	if (cmpxchg(&lock->owner, owner, 0) == owner)
	 *		return;
	 *	goto retry;
	 *
	 * The fastpath disabled variant is simple as all access to
	 * lock->owner is serialized by lock->wait_lock:
	 *
	 *	lock->owner = NULL;
	 *	raw_spin_unlock(&lock->wait_lock);
	 */
	while (!rt_mutex_has_waiters(lock)) {
		/* Drops lock->wait_lock ! */
		if (unlock_rt_mutex_safe(lock, flags) == true)
			return false;
		/* Relock the rtmutex and try again */
		raw_spin_lock_irqsave(&lock->wait_lock, flags);
	}

	/*
	 * The wakeup next waiter path does not suffer from the above
	 * race. See the comments there.
	 *
	 * Queue the next waiter for wakeup once we release the wait_lock.
	 */
	mark_wakeup_next_waiter(wake_q, lock);
	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);

	return true; /* call rt_mutex_postunlock() */
}

/*
 * debug aware fast / slowpath lock,trylock,unlock
 *
 * The atomic acquire/release ops are compiled away, when either the
 * architecture does not support cmpxchg or when debugging is enabled.
 */
static inline int
rt_mutex_fastlock(struct rt_mutex *lock, int state,
		  int (*slowfn)(struct rt_mutex *lock, int state,
				struct hrtimer_sleeper *timeout,
				enum rtmutex_chainwalk chwalk))
{
	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
		return 0;

	return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
}

static inline int
rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
			struct hrtimer_sleeper *timeout,
			enum rtmutex_chainwalk chwalk,
			int (*slowfn)(struct rt_mutex *lock, int state,
				      struct hrtimer_sleeper *timeout,
				      enum rtmutex_chainwalk chwalk))
{
	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
		return 0;

	return slowfn(lock, state, timeout, chwalk);
}

static inline int
rt_mutex_fasttrylock(struct rt_mutex *lock,
		     int (*slowfn)(struct rt_mutex *lock))
{
	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
		return 1;

	return slowfn(lock);
}

/*
 * Performs the wakeup of the the top-waiter and re-enables preemption.
 */
void rt_mutex_postunlock(struct wake_q_head *wake_q)
{
	wake_up_q(wake_q);

	/* Pairs with preempt_disable() in rt_mutex_slowunlock() */
	preempt_enable();
}

static inline void
rt_mutex_fastunlock(struct rt_mutex *lock,
		    bool (*slowfn)(struct rt_mutex *lock,
				   struct wake_q_head *wqh))
{
	DEFINE_WAKE_Q(wake_q);

	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
		return;

	if (slowfn(lock, &wake_q))
		rt_mutex_postunlock(&wake_q);
}

static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass)
{
	might_sleep();

	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
 * rt_mutex_lock_nested - lock a rt_mutex
 *
 * @lock: the rt_mutex to be locked
 * @subclass: the lockdep subclass
 */
void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
{
	__rt_mutex_lock(lock, subclass);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);

#else /* !CONFIG_DEBUG_LOCK_ALLOC */

/**
 * rt_mutex_lock - lock a rt_mutex
 *
 * @lock: the rt_mutex to be locked
 */
void __sched rt_mutex_lock(struct rt_mutex *lock)
{
	__rt_mutex_lock(lock, 0);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock);
#endif

/**
 * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
 *
 * @lock:		the rt_mutex to be locked
 *
 * Returns:
 *  0		on success
 * -EINTR	when interrupted by a signal
 */
int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
{
	int ret;

	might_sleep();

	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
	ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
	if (ret)
		mutex_release(&lock->dep_map, _RET_IP_);

	return ret;
}
EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);

/*
 * Futex variant, must not use fastpath.
 */
int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
{
	return rt_mutex_slowtrylock(lock);
}

int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock)
{
	return __rt_mutex_slowtrylock(lock);
}

/**
 * rt_mutex_timed_lock - lock a rt_mutex interruptible
 *			the timeout structure is provided
 *			by the caller
 *
 * @lock:		the rt_mutex to be locked
 * @timeout:		timeout structure or NULL (no timeout)
 *
 * Returns:
 *  0		on success
 * -EINTR	when interrupted by a signal
 * -ETIMEDOUT	when the timeout expired
 */
int
rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
{
	int ret;

	might_sleep();

	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
	ret = rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
				       RT_MUTEX_MIN_CHAINWALK,
				       rt_mutex_slowlock);
	if (ret)
		mutex_release(&lock->dep_map, _RET_IP_);

	return ret;
}
EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);

/**
 * rt_mutex_trylock - try to lock a rt_mutex
 *
 * @lock:	the rt_mutex to be locked
 *
 * This function can only be called in thread context. It's safe to
 * call it from atomic regions, but not from hard interrupt or soft
 * interrupt context.
 *
 * Returns 1 on success and 0 on contention
 */
int __sched rt_mutex_trylock(struct rt_mutex *lock)
{
	int ret;

	if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq()))
		return 0;

	ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
	if (ret)
		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);

	return ret;
}
EXPORT_SYMBOL_GPL(rt_mutex_trylock);

/**
 * rt_mutex_unlock - unlock a rt_mutex
 *
 * @lock: the rt_mutex to be unlocked
 */
void __sched rt_mutex_unlock(struct rt_mutex *lock)
{
	mutex_release(&lock->dep_map, _RET_IP_);
	rt_mutex_fastunlock(lock, rt_mutex_slowunlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_unlock);

/**
 * __rt_mutex_futex_unlock - Futex variant, that since futex variants
 * do not use the fast-path, can be simple and will not need to retry.
 *
 * @lock:	The rt_mutex to be unlocked
 * @wake_q:	The wake queue head from which to get the next lock waiter
 */
bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
				    struct wake_q_head *wake_q)
{
	lockdep_assert_held(&lock->wait_lock);

	debug_rt_mutex_unlock(lock);

	if (!rt_mutex_has_waiters(lock)) {
		lock->owner = NULL;
		return false; /* done */
	}

	/*
	 * We've already deboosted, mark_wakeup_next_waiter() will
	 * retain preempt_disabled when we drop the wait_lock, to
	 * avoid inversion prior to the wakeup.  preempt_disable()
	 * therein pairs with rt_mutex_postunlock().
	 */
	mark_wakeup_next_waiter(wake_q, lock);

	return true; /* call postunlock() */
}

void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
{
	DEFINE_WAKE_Q(wake_q);
	unsigned long flags;
	bool postunlock;

	raw_spin_lock_irqsave(&lock->wait_lock, flags);
	postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);

	if (postunlock)
		rt_mutex_postunlock(&wake_q);
}

/**
 * rt_mutex_destroy - mark a mutex unusable
 * @lock: the mutex to be destroyed
 *
 * This function marks the mutex uninitialized, and any subsequent
 * use of the mutex is forbidden. The mutex must not be locked when
 * this function is called.
 */
void rt_mutex_destroy(struct rt_mutex *lock)
{
	WARN_ON(rt_mutex_is_locked(lock));
#ifdef CONFIG_DEBUG_RT_MUTEXES
	lock->magic = NULL;
#endif
}
EXPORT_SYMBOL_GPL(rt_mutex_destroy);

/**
 * __rt_mutex_init - initialize the rt_mutex
 *
 * @lock:	The rt_mutex to be initialized
 * @name:	The lock name used for debugging
 * @key:	The lock class key used for debugging
 *
 * Initialize the rt_mutex to unlocked state.
 *
 * Initializing of a locked rt_mutex is not allowed
 */
void __rt_mutex_init(struct rt_mutex *lock, const char *name,
		     struct lock_class_key *key)
{
	lock->owner = NULL;
	raw_spin_lock_init(&lock->wait_lock);
	lock->waiters = RB_ROOT_CACHED;

	if (name && key)
		debug_rt_mutex_init(lock, name, key);
}
EXPORT_SYMBOL_GPL(__rt_mutex_init);

/**
 * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
 *				proxy owner
 *
 * @lock:	the rt_mutex to be locked
 * @proxy_owner:the task to set as owner
 *
 * No locking. Caller has to do serializing itself
 *
 * Special API call for PI-futex support. This initializes the rtmutex and
 * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not
 * possible at this point because the pi_state which contains the rtmutex
 * is not yet visible to other tasks.
 */
void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
				struct task_struct *proxy_owner)
{
	__rt_mutex_init(lock, NULL, NULL);
	debug_rt_mutex_proxy_lock(lock, proxy_owner);
	rt_mutex_set_owner(lock, proxy_owner);
}

/**
 * rt_mutex_proxy_unlock - release a lock on behalf of owner
 *
 * @lock:	the rt_mutex to be locked
 *
 * No locking. Caller has to do serializing itself
 *
 * Special API call for PI-futex support. This merrily cleans up the rtmutex
 * (debugging) state. Concurrent operations on this rt_mutex are not
 * possible because it belongs to the pi_state which is about to be freed
 * and it is not longer visible to other tasks.
 */
void rt_mutex_proxy_unlock(struct rt_mutex *lock)
{
	debug_rt_mutex_proxy_unlock(lock);
	rt_mutex_set_owner(lock, NULL);
}

/**
 * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
 * @lock:		the rt_mutex to take
 * @waiter:		the pre-initialized rt_mutex_waiter
 * @task:		the task to prepare
 *
 * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
 * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
 *
 * NOTE: does _NOT_ remove the @waiter on failure; must either call
 * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this.
 *
 * Returns:
 *  0 - task blocked on lock
 *  1 - acquired the lock for task, caller should wake it up
 * <0 - error
 *
 * Special API call for PI-futex support.
 */
int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
			      struct rt_mutex_waiter *waiter,
			      struct task_struct *task)
{
	int ret;

	lockdep_assert_held(&lock->wait_lock);

	if (try_to_take_rt_mutex(lock, task, NULL))
		return 1;

	/* We enforce deadlock detection for futexes */
	ret = task_blocks_on_rt_mutex(lock, waiter, task,
				      RT_MUTEX_FULL_CHAINWALK);

	if (ret && !rt_mutex_owner(lock)) {
		/*
		 * Reset the return value. We might have
		 * returned with -EDEADLK and the owner
		 * released the lock while we were walking the
		 * pi chain.  Let the waiter sort it out.
		 */
		ret = 0;
	}

	debug_rt_mutex_print_deadlock(waiter);

	return ret;
}

/**
 * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
 * @lock:		the rt_mutex to take
 * @waiter:		the pre-initialized rt_mutex_waiter
 * @task:		the task to prepare
 *
 * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
 * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
 *
 * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter
 * on failure.
 *
 * Returns:
 *  0 - task blocked on lock
 *  1 - acquired the lock for task, caller should wake it up
 * <0 - error
 *
 * Special API call for PI-futex support.
 */
int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
			      struct rt_mutex_waiter *waiter,
			      struct task_struct *task)
{
	int ret;

	raw_spin_lock_irq(&lock->wait_lock);
	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
	if (unlikely(ret))
		remove_waiter(lock, waiter);
	raw_spin_unlock_irq(&lock->wait_lock);

	return ret;
}

/**
 * rt_mutex_next_owner - return the next owner of the lock
 *
 * @lock: the rt lock query
 *
 * Returns the next owner of the lock or NULL
 *
 * Caller has to serialize against other accessors to the lock
 * itself.
 *
 * Special API call for PI-futex support
 */
struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
{
	if (!rt_mutex_has_waiters(lock))
		return NULL;

	return rt_mutex_top_waiter(lock)->task;
}

/**
 * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
 * @lock:		the rt_mutex we were woken on
 * @to:			the timeout, null if none. hrtimer should already have
 *			been started.
 * @waiter:		the pre-initialized rt_mutex_waiter
 *
 * Wait for the the lock acquisition started on our behalf by
 * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
 * rt_mutex_cleanup_proxy_lock().
 *
 * Returns:
 *  0 - success
 * <0 - error, one of -EINTR, -ETIMEDOUT
 *
 * Special API call for PI-futex support
 */
int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
			       struct hrtimer_sleeper *to,
			       struct rt_mutex_waiter *waiter)
{
	int ret;

	raw_spin_lock_irq(&lock->wait_lock);
	/* sleep on the mutex */
	set_current_state(TASK_INTERRUPTIBLE);
	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
	/*
	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
	 * have to fix that up.
	 */
	fixup_rt_mutex_waiters(lock);
	raw_spin_unlock_irq(&lock->wait_lock);

	return ret;
}

/**
 * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
 * @lock:		the rt_mutex we were woken on
 * @waiter:		the pre-initialized rt_mutex_waiter
 *
 * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or
 * rt_mutex_wait_proxy_lock().
 *
 * Unless we acquired the lock; we're still enqueued on the wait-list and can
 * in fact still be granted ownership until we're removed. Therefore we can
 * find we are in fact the owner and must disregard the
 * rt_mutex_wait_proxy_lock() failure.
 *
 * Returns:
 *  true  - did the cleanup, we done.
 *  false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
 *          caller should disregards its return value.
 *
 * Special API call for PI-futex support
 */
bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
				 struct rt_mutex_waiter *waiter)
{
	bool cleanup = false;

	raw_spin_lock_irq(&lock->wait_lock);
	/*
	 * Do an unconditional try-lock, this deals with the lock stealing
	 * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter()
	 * sets a NULL owner.
	 *
	 * We're not interested in the return value, because the subsequent
	 * test on rt_mutex_owner() will infer that. If the trylock succeeded,
	 * we will own the lock and it will have removed the waiter. If we
	 * failed the trylock, we're still not owner and we need to remove
	 * ourselves.
	 */
	try_to_take_rt_mutex(lock, current, waiter);
	/*
	 * Unless we're the owner; we're still enqueued on the wait_list.
	 * So check if we became owner, if not, take us off the wait_list.
	 */
	if (rt_mutex_owner(lock) != current) {
		remove_waiter(lock, waiter);
		cleanup = true;
	}
	/*
	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
	 * have to fix that up.
	 */
	fixup_rt_mutex_waiters(lock);

	raw_spin_unlock_irq(&lock->wait_lock);

	return cleanup;
}