summaryrefslogtreecommitdiff
path: root/kernel/locking/rtmutex.c
blob: fc605941b9b8914b38ce3caf5a7d06dfc5f1a6ad (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
/*
 * 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/rt-mutex-design.txt for details.
 */
#include <linux/spinlock.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/sched/deadline.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;

	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)
{
	if (!rt_mutex_has_waiters(lock))
		clear_rt_mutex_waiters(lock);
}

/*
 * We can speed up the acquire/release, if the architecture
 * supports cmpxchg and if there's no debugging state to be set up
 */
#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES)
# define rt_mutex_cmpxchg(l,c,n)	(cmpxchg(&l->owner, c, n) == c)
static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
{
	unsigned long owner, *p = (unsigned long *) &lock->owner;

	do {
		owner = *p;
	} while (cmpxchg(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)
	__releases(lock->wait_lock)
{
	struct task_struct *owner = rt_mutex_owner(lock);

	clear_rt_mutex_waiters(lock);
	raw_spin_unlock(&lock->wait_lock);
	/*
	 * 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(lock, owner, NULL);
}

#else
# define rt_mutex_cmpxchg(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)
	__releases(lock->wait_lock)
{
	lock->owner = NULL;
	raw_spin_unlock(&lock->wait_lock);
	return true;
}
#endif

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 (left->task->dl.deadline < right->task->dl.deadline);

	return 0;
}

static void
rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
{
	struct rb_node **link = &lock->waiters.rb_node;
	struct rb_node *parent = NULL;
	struct rt_mutex_waiter *entry;
	int leftmost = 1;

	while (*link) {
		parent = *link;
		entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
		if (rt_mutex_waiter_less(waiter, entry)) {
			link = &parent->rb_left;
		} else {
			link = &parent->rb_right;
			leftmost = 0;
		}
	}

	if (leftmost)
		lock->waiters_leftmost = &waiter->tree_entry;

	rb_link_node(&waiter->tree_entry, parent, link);
	rb_insert_color(&waiter->tree_entry, &lock->waiters);
}

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

	if (lock->waiters_leftmost == &waiter->tree_entry)
		lock->waiters_leftmost = rb_next(&waiter->tree_entry);

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

static void
rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
{
	struct rb_node **link = &task->pi_waiters.rb_node;
	struct rb_node *parent = NULL;
	struct rt_mutex_waiter *entry;
	int leftmost = 1;

	while (*link) {
		parent = *link;
		entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
		if (rt_mutex_waiter_less(waiter, entry)) {
			link = &parent->rb_left;
		} else {
			link = &parent->rb_right;
			leftmost = 0;
		}
	}

	if (leftmost)
		task->pi_waiters_leftmost = &waiter->pi_tree_entry;

	rb_link_node(&waiter->pi_tree_entry, parent, link);
	rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters);
}

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

	if (task->pi_waiters_leftmost == &waiter->pi_tree_entry)
		task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry);

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

/*
 * Calculate task priority from the waiter tree priority
 *
 * Return task->normal_prio when the waiter tree is empty or when
 * the waiter is not allowed to do priority boosting
 */
int rt_mutex_getprio(struct task_struct *task)
{
	if (likely(!task_has_pi_waiters(task)))
		return task->normal_prio;

	return min(task_top_pi_waiter(task)->prio,
		   task->normal_prio);
}

struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
{
	if (likely(!task_has_pi_waiters(task)))
		return NULL;

	return task_top_pi_waiter(task)->task;
}

/*
 * Called by sched_setscheduler() to check whether the priority change
 * is overruled by a possible priority boosting.
 */
int rt_mutex_check_prio(struct task_struct *task, int newprio)
{
	if (!task_has_pi_waiters(task))
		return 0;

	return task_top_pi_waiter(task)->task->prio <= newprio;
}

/*
 * Adjust the priority of a task, after its pi_waiters got modified.
 *
 * This can be both boosting and unboosting. task->pi_lock must be held.
 */
static void __rt_mutex_adjust_prio(struct task_struct *task)
{
	int prio = rt_mutex_getprio(task);

	if (task->prio != prio || dl_prio(prio))
		rt_mutex_setprio(task, prio);
}

/*
 * Adjust task priority (undo boosting). Called from the exit path of
 * rt_mutex_slowunlock() and rt_mutex_slowlock().
 *
 * (Note: We do this outside of the protection of lock->wait_lock to
 * allow the lock to be taken while or before we readjust the priority
 * of task. We do not use the spin_xx_mutex() variants here as we are
 * outside of the debug path.)
 */
static void rt_mutex_adjust_prio(struct task_struct *task)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&task->pi_lock, flags);
	__rt_mutex_adjust_prio(task);
	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
}

/*
 * 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
 * @deadlock_detect: 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.
 */
static int rt_mutex_adjust_prio_chain(struct task_struct *task,
				      int deadlock_detect,
				      struct rt_mutex *orig_lock,
				      struct rt_mutex *next_lock,
				      struct rt_mutex_waiter *orig_waiter,
				      struct task_struct *top_task)
{
	struct rt_mutex *lock;
	struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
	int detect_deadlock, ret = 0, depth = 0;
	unsigned long flags;

	detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,
							 deadlock_detect);

	/*
	 * 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:
	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;
	}
 retry:
	/*
	 * Task can not go away as we did a get_task() before !
	 */
	raw_spin_lock_irqsave(&task->pi_lock, flags);

	waiter = task->pi_blocked_on;
	/*
	 * 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 (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
			goto out_unlock_pi;
	}

	/*
	 * When deadlock detection is off then we check, if further
	 * priority adjustment is necessary.
	 */
	if (!detect_deadlock && waiter->prio == task->prio)
		goto out_unlock_pi;

	lock = waiter->lock;
	if (!raw_spin_trylock(&lock->wait_lock)) {
		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
		cpu_relax();
		goto retry;
	}

	/*
	 * 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(deadlock_detect, orig_waiter, lock);
		raw_spin_unlock(&lock->wait_lock);
		ret = -EDEADLK;
		goto out_unlock_pi;
	}

	top_waiter = rt_mutex_top_waiter(lock);

	/* Requeue the waiter */
	rt_mutex_dequeue(lock, waiter);
	waiter->prio = task->prio;
	rt_mutex_enqueue(lock, waiter);

	/* Release the task */
	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
	if (!rt_mutex_owner(lock)) {
		/*
		 * If the requeue above changed the top waiter, then we need
		 * to wake the new top waiter up to try to get the lock.
		 */

		if (top_waiter != rt_mutex_top_waiter(lock))
			wake_up_process(rt_mutex_top_waiter(lock)->task);
		raw_spin_unlock(&lock->wait_lock);
		goto out_put_task;
	}
	put_task_struct(task);

	/* Grab the next task */
	task = rt_mutex_owner(lock);
	get_task_struct(task);
	raw_spin_lock_irqsave(&task->pi_lock, flags);

	if (waiter == rt_mutex_top_waiter(lock)) {
		/* Boost the owner */
		rt_mutex_dequeue_pi(task, top_waiter);
		rt_mutex_enqueue_pi(task, waiter);
		__rt_mutex_adjust_prio(task);

	} else if (top_waiter == waiter) {
		/* Deboost the owner */
		rt_mutex_dequeue_pi(task, waiter);
		waiter = rt_mutex_top_waiter(lock);
		rt_mutex_enqueue_pi(task, waiter);
		__rt_mutex_adjust_prio(task);
	}

	/*
	 * 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);

	raw_spin_unlock_irqrestore(&task->pi_lock, flags);

	top_waiter = rt_mutex_top_waiter(lock);
	raw_spin_unlock(&lock->wait_lock);

	/*
	 * 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 (!detect_deadlock && waiter != top_waiter)
		goto out_put_task;

	goto again;

 out_unlock_pi:
	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 out_put_task:
	put_task_struct(task);

	return ret;
}

/*
 * Try to take an rt-mutex
 *
 * Must be called with lock->wait_lock held.
 *
 * @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 list. (could be NULL)
 */
static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
		struct rt_mutex_waiter *waiter)
{
	/*
	 * We have to be careful here if the atomic speedups are
	 * enabled, such that, when
	 *  - no other waiter is on the lock
	 *  - the lock has been released since we did the cmpxchg
	 * the lock can be released or taken while we are doing the
	 * checks and marking the lock with RT_MUTEX_HAS_WAITERS.
	 *
	 * The atomic acquire/release aware variant of
	 * mark_rt_mutex_waiters uses a cmpxchg loop. After setting
	 * the WAITERS bit, the atomic release / acquire can not
	 * happen anymore and lock->wait_lock protects us from the
	 * non-atomic case.
	 *
	 * Note, that this might set lock->owner =
	 * RT_MUTEX_HAS_WAITERS in the case the lock is not contended
	 * any more. This is fixed up when we take the ownership.
	 * This is the transitional state explained at the top of this file.
	 */
	mark_rt_mutex_waiters(lock);

	if (rt_mutex_owner(lock))
		return 0;

	/*
	 * It will get the lock because of one of these conditions:
	 * 1) there is no waiter
	 * 2) higher priority than waiters
	 * 3) it is top waiter
	 */
	if (rt_mutex_has_waiters(lock)) {
		if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
			if (!waiter || waiter != rt_mutex_top_waiter(lock))
				return 0;
		}
	}

	if (waiter || rt_mutex_has_waiters(lock)) {
		unsigned long flags;
		struct rt_mutex_waiter *top;

		raw_spin_lock_irqsave(&task->pi_lock, flags);

		/* remove the queued waiter. */
		if (waiter) {
			rt_mutex_dequeue(lock, waiter);
			task->pi_blocked_on = NULL;
		}

		/*
		 * We have to enqueue the top waiter(if it exists) into
		 * task->pi_waiters list.
		 */
		if (rt_mutex_has_waiters(lock)) {
			top = rt_mutex_top_waiter(lock);
			rt_mutex_enqueue_pi(task, top);
		}
		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
	}

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

	rt_mutex_set_owner(lock, task);

	rt_mutex_deadlock_account_lock(lock, task);

	return 1;
}

/*
 * Task blocks on lock.
 *
 * Prepare waiter and propagate pi chain
 *
 * This must be called with lock->wait_lock held.
 */
static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
				   struct rt_mutex_waiter *waiter,
				   struct task_struct *task,
				   int detect_deadlock)
{
	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;
	unsigned long flags;

	/*
	 * 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_irqsave(&task->pi_lock, flags);
	__rt_mutex_adjust_prio(task);
	waiter->task = task;
	waiter->lock = lock;
	waiter->prio = task->prio;

	/* 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_irqrestore(&task->pi_lock, flags);

	if (!owner)
		return 0;

	raw_spin_lock_irqsave(&owner->pi_lock, flags);
	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 (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
		chain_walk = 1;
	}

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

	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
	/*
	 * 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(&lock->wait_lock);

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

	raw_spin_lock(&lock->wait_lock);

	return res;
}

/*
 * Wake up the next waiter on the lock.
 *
 * Remove the top waiter from the current tasks pi waiter list and
 * wake it up.
 *
 * Called with lock->wait_lock held.
 */
static void wakeup_next_waiter(struct rt_mutex *lock)
{
	struct rt_mutex_waiter *waiter;
	unsigned long flags;

	raw_spin_lock_irqsave(&current->pi_lock, flags);

	waiter = rt_mutex_top_waiter(lock);

	/*
	 * Remove it from current->pi_waiters. We do not adjust a
	 * possible priority boost right now. We execute wakeup in the
	 * boosted mode and go back to normal after releasing
	 * lock->wait_lock.
	 */
	rt_mutex_dequeue_pi(current, waiter);

	/*
	 * 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;

	raw_spin_unlock_irqrestore(&current->pi_lock, flags);

	/*
	 * It's safe to dereference waiter as it cannot go away as
	 * long as we hold lock->wait_lock. The waiter task needs to
	 * acquire it in order to dequeue the waiter.
	 */
	wake_up_process(waiter->task);
}

/*
 * Remove a waiter from a lock and give up
 *
 * Must be called with lock->wait_lock held and
 * have just failed to try_to_take_rt_mutex().
 */
static void remove_waiter(struct rt_mutex *lock,
			  struct rt_mutex_waiter *waiter)
{
	int first = (waiter == rt_mutex_top_waiter(lock));
	struct task_struct *owner = rt_mutex_owner(lock);
	struct rt_mutex *next_lock = NULL;
	unsigned long flags;

	raw_spin_lock_irqsave(&current->pi_lock, flags);
	rt_mutex_dequeue(lock, waiter);
	current->pi_blocked_on = NULL;
	raw_spin_unlock_irqrestore(&current->pi_lock, flags);

	if (!owner)
		return;

	if (first) {

		raw_spin_lock_irqsave(&owner->pi_lock, flags);

		rt_mutex_dequeue_pi(owner, waiter);

		if (rt_mutex_has_waiters(lock)) {
			struct rt_mutex_waiter *next;

			next = rt_mutex_top_waiter(lock);
			rt_mutex_enqueue_pi(owner, next);
		}
		__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_irqrestore(&owner->pi_lock, flags);
	}

	if (!next_lock)
		return;

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

	raw_spin_unlock(&lock->wait_lock);

	rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);

	raw_spin_lock(&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 || (waiter->prio == task->prio &&
			!dl_prio(task->prio))) {
		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, 0, NULL, next_lock, NULL, task);
}

/**
 * __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
 *
 * lock->wait_lock must be held by the caller.
 */
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 (unlikely(state == TASK_INTERRUPTIBLE)) {
			/* Signal pending? */
			if (signal_pending(current))
				ret = -EINTR;
			if (timeout && !timeout->task)
				ret = -ETIMEDOUT;
			if (ret)
				break;
		}

		raw_spin_unlock(&lock->wait_lock);

		debug_rt_mutex_print_deadlock(waiter);

		schedule_rt_mutex(lock);

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

	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,
		  int detect_deadlock)
{
	struct rt_mutex_waiter waiter;
	int ret = 0;

	debug_rt_mutex_init_waiter(&waiter);
	RB_CLEAR_NODE(&waiter.pi_tree_entry);
	RB_CLEAR_NODE(&waiter.tree_entry);

	raw_spin_lock(&lock->wait_lock);

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

	set_current_state(state);

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

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

	if (likely(!ret))
		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);

	set_current_state(TASK_RUNNING);

	if (unlikely(ret)) {
		remove_waiter(lock, &waiter);
		rt_mutex_handle_deadlock(ret, detect_deadlock, &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(&lock->wait_lock);

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

	debug_rt_mutex_free_waiter(&waiter);

	return ret;
}

/*
 * Slow path try-lock function:
 */
static inline int
rt_mutex_slowtrylock(struct rt_mutex *lock)
{
	int ret = 0;

	raw_spin_lock(&lock->wait_lock);

	if (likely(rt_mutex_owner(lock) != current)) {

		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);
	}

	raw_spin_unlock(&lock->wait_lock);

	return ret;
}

/*
 * Slow path to release a rt-mutex:
 */
static void __sched
rt_mutex_slowunlock(struct rt_mutex *lock)
{
	raw_spin_lock(&lock->wait_lock);

	debug_rt_mutex_unlock(lock);

	rt_mutex_deadlock_account_unlock(current);

	/*
	 * 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) == true)
			return;
		/* Relock the rtmutex and try again */
		raw_spin_lock(&lock->wait_lock);
	}

	/*
	 * The wakeup next waiter path does not suffer from the above
	 * race. See the comments there.
	 */
	wakeup_next_waiter(lock);

	raw_spin_unlock(&lock->wait_lock);

	/* Undo pi boosting if necessary: */
	rt_mutex_adjust_prio(current);
}

/*
 * 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 detect_deadlock,
		  int (*slowfn)(struct rt_mutex *lock, int state,
				struct hrtimer_sleeper *timeout,
				int detect_deadlock))
{
	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
		rt_mutex_deadlock_account_lock(lock, current);
		return 0;
	} else
		return slowfn(lock, state, NULL, detect_deadlock);
}

static inline int
rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
			struct hrtimer_sleeper *timeout, int detect_deadlock,
			int (*slowfn)(struct rt_mutex *lock, int state,
				      struct hrtimer_sleeper *timeout,
				      int detect_deadlock))
{
	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
		rt_mutex_deadlock_account_lock(lock, current);
		return 0;
	} else
		return slowfn(lock, state, timeout, detect_deadlock);
}

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

static inline void
rt_mutex_fastunlock(struct rt_mutex *lock,
		    void (*slowfn)(struct rt_mutex *lock))
{
	if (likely(rt_mutex_cmpxchg(lock, current, NULL)))
		rt_mutex_deadlock_account_unlock(current);
	else
		slowfn(lock);
}

/**
 * rt_mutex_lock - lock a rt_mutex
 *
 * @lock: the rt_mutex to be locked
 */
void __sched rt_mutex_lock(struct rt_mutex *lock)
{
	might_sleep();

	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock);

/**
 * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
 *
 * @lock: 		the rt_mutex to be locked
 * @detect_deadlock:	deadlock detection on/off
 *
 * Returns:
 *  0 		on success
 * -EINTR 	when interrupted by a signal
 * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
 */
int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock,
						 int detect_deadlock)
{
	might_sleep();

	return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE,
				 detect_deadlock, rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);

/**
 * 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)
 * @detect_deadlock:	deadlock detection on/off
 *
 * Returns:
 *  0 		on success
 * -EINTR 	when interrupted by a signal
 * -ETIMEDOUT	when the timeout expired
 * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
 */
int
rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout,
		    int detect_deadlock)
{
	might_sleep();

	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
				       detect_deadlock, rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);

/**
 * rt_mutex_trylock - try to lock a rt_mutex
 *
 * @lock:	the rt_mutex to be locked
 *
 * Returns 1 on success and 0 on contention
 */
int __sched rt_mutex_trylock(struct rt_mutex *lock)
{
	return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
}
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)
{
	rt_mutex_fastunlock(lock, rt_mutex_slowunlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_unlock);

/**
 * 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 lock
 *
 * @lock: the rt lock to be initialized
 *
 * Initialize the rt lock to unlocked state.
 *
 * Initializing of a locked rt lock is not allowed
 */
void __rt_mutex_init(struct rt_mutex *lock, const char *name)
{
	lock->owner = NULL;
	raw_spin_lock_init(&lock->wait_lock);
	lock->waiters = RB_ROOT;
	lock->waiters_leftmost = NULL;

	debug_rt_mutex_init(lock, name);
}
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
 */
void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
				struct task_struct *proxy_owner)
{
	__rt_mutex_init(lock, NULL);
	debug_rt_mutex_proxy_lock(lock, proxy_owner);
	rt_mutex_set_owner(lock, proxy_owner);
	rt_mutex_deadlock_account_lock(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
 */
void rt_mutex_proxy_unlock(struct rt_mutex *lock,
			   struct task_struct *proxy_owner)
{
	debug_rt_mutex_proxy_unlock(lock);
	rt_mutex_set_owner(lock, NULL);
	rt_mutex_deadlock_account_unlock(proxy_owner);
}

/**
 * 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
 * @detect_deadlock:	perform deadlock detection (1) or not (0)
 *
 * Returns:
 *  0 - task blocked on lock
 *  1 - acquired the lock for task, caller should wake it up
 * <0 - error
 *
 * Special API call for FUTEX_REQUEUE_PI support.
 */
int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
			      struct rt_mutex_waiter *waiter,
			      struct task_struct *task, int detect_deadlock)
{
	int ret;

	raw_spin_lock(&lock->wait_lock);

	if (try_to_take_rt_mutex(lock, task, NULL)) {
		raw_spin_unlock(&lock->wait_lock);
		return 1;
	}

	/* We enforce deadlock detection for futexes */
	ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);

	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;
	}

	if (unlikely(ret))
		remove_waiter(lock, waiter);

	raw_spin_unlock(&lock->wait_lock);

	debug_rt_mutex_print_deadlock(waiter);

	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_finish_proxy_lock() - Complete 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
 * @detect_deadlock:	perform deadlock detection (1) or not (0)
 *
 * Complete the lock acquisition started our behalf by another thread.
 *
 * Returns:
 *  0 - success
 * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
 *
 * Special API call for PI-futex requeue support
 */
int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
			       struct hrtimer_sleeper *to,
			       struct rt_mutex_waiter *waiter,
			       int detect_deadlock)
{
	int ret;

	raw_spin_lock(&lock->wait_lock);

	set_current_state(TASK_INTERRUPTIBLE);

	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);

	set_current_state(TASK_RUNNING);

	if (unlikely(ret))
		remove_waiter(lock, 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(&lock->wait_lock);

	return ret;
}