summaryrefslogtreecommitdiffstats
path: root/kernel/locking/mutex.c
blob: 2048359f33d24785f15bb73228edd219b1b5f7fa (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
/*
 * kernel/locking/mutex.c
 *
 * Mutexes: blocking mutual exclusion locks
 *
 * Started by Ingo Molnar:
 *
 *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 *
 * Many thanks to Arjan van de Ven, Thomas Gleixner, Steven Rostedt and
 * David Howells for suggestions and improvements.
 *
 *  - Adaptive spinning for mutexes by Peter Zijlstra. (Ported to mainline
 *    from the -rt tree, where it was originally implemented for rtmutexes
 *    by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale
 *    and Sven Dietrich.
 *
 * Also see Documentation/locking/mutex-design.txt.
 */
#include <linux/mutex.h>
#include <linux/ww_mutex.h>
#include <linux/sched/signal.h>
#include <linux/sched/rt.h>
#include <linux/sched/wake_q.h>
#include <linux/sched/debug.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/debug_locks.h>
#include <linux/osq_lock.h>

#ifdef CONFIG_DEBUG_MUTEXES
# include "mutex-debug.h"
#else
# include "mutex.h"
#endif

void
__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
{
	atomic_long_set(&lock->owner, 0);
	spin_lock_init(&lock->wait_lock);
	INIT_LIST_HEAD(&lock->wait_list);
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
	osq_lock_init(&lock->osq);
#endif

	debug_mutex_init(lock, name, key);
}
EXPORT_SYMBOL(__mutex_init);

/*
 * @owner: contains: 'struct task_struct *' to the current lock owner,
 * NULL means not owned. Since task_struct pointers are aligned at
 * at least L1_CACHE_BYTES, we have low bits to store extra state.
 *
 * Bit0 indicates a non-empty waiter list; unlock must issue a wakeup.
 * Bit1 indicates unlock needs to hand the lock to the top-waiter
 * Bit2 indicates handoff has been done and we're waiting for pickup.
 */
#define MUTEX_FLAG_WAITERS	0x01
#define MUTEX_FLAG_HANDOFF	0x02
#define MUTEX_FLAG_PICKUP	0x04

#define MUTEX_FLAGS		0x07

static inline struct task_struct *__owner_task(unsigned long owner)
{
	return (struct task_struct *)(owner & ~MUTEX_FLAGS);
}

static inline unsigned long __owner_flags(unsigned long owner)
{
	return owner & MUTEX_FLAGS;
}

/*
 * Trylock variant that retuns the owning task on failure.
 */
static inline struct task_struct *__mutex_trylock_or_owner(struct mutex *lock)
{
	unsigned long owner, curr = (unsigned long)current;

	owner = atomic_long_read(&lock->owner);
	for (;;) { /* must loop, can race against a flag */
		unsigned long old, flags = __owner_flags(owner);
		unsigned long task = owner & ~MUTEX_FLAGS;

		if (task) {
			if (likely(task != curr))
				break;

			if (likely(!(flags & MUTEX_FLAG_PICKUP)))
				break;

			flags &= ~MUTEX_FLAG_PICKUP;
		} else {
#ifdef CONFIG_DEBUG_MUTEXES
			DEBUG_LOCKS_WARN_ON(flags & MUTEX_FLAG_PICKUP);
#endif
		}

		/*
		 * We set the HANDOFF bit, we must make sure it doesn't live
		 * past the point where we acquire it. This would be possible
		 * if we (accidentally) set the bit on an unlocked mutex.
		 */
		flags &= ~MUTEX_FLAG_HANDOFF;

		old = atomic_long_cmpxchg_acquire(&lock->owner, owner, curr | flags);
		if (old == owner)
			return NULL;

		owner = old;
	}

	return __owner_task(owner);
}

/*
 * Actual trylock that will work on any unlocked state.
 */
static inline bool __mutex_trylock(struct mutex *lock)
{
	return !__mutex_trylock_or_owner(lock);
}

#ifndef CONFIG_DEBUG_LOCK_ALLOC
/*
 * Lockdep annotations are contained to the slow paths for simplicity.
 * There is nothing that would stop spreading the lockdep annotations outwards
 * except more code.
 */

/*
 * Optimistic trylock that only works in the uncontended case. Make sure to
 * follow with a __mutex_trylock() before failing.
 */
static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
{
	unsigned long curr = (unsigned long)current;

	if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr))
		return true;

	return false;
}

static __always_inline bool __mutex_unlock_fast(struct mutex *lock)
{
	unsigned long curr = (unsigned long)current;

	if (atomic_long_cmpxchg_release(&lock->owner, curr, 0UL) == curr)
		return true;

	return false;
}
#endif

static inline void __mutex_set_flag(struct mutex *lock, unsigned long flag)
{
	atomic_long_or(flag, &lock->owner);
}

static inline void __mutex_clear_flag(struct mutex *lock, unsigned long flag)
{
	atomic_long_andnot(flag, &lock->owner);
}

static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_waiter *waiter)
{
	return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter;
}

/*
 * Give up ownership to a specific task, when @task = NULL, this is equivalent
 * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves
 * WAITERS. Provides RELEASE semantics like a regular unlock, the
 * __mutex_trylock() provides a matching ACQUIRE semantics for the handoff.
 */
static void __mutex_handoff(struct mutex *lock, struct task_struct *task)
{
	unsigned long owner = atomic_long_read(&lock->owner);

	for (;;) {
		unsigned long old, new;

#ifdef CONFIG_DEBUG_MUTEXES
		DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
		DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP);
#endif

		new = (owner & MUTEX_FLAG_WAITERS);
		new |= (unsigned long)task;
		if (task)
			new |= MUTEX_FLAG_PICKUP;

		old = atomic_long_cmpxchg_release(&lock->owner, owner, new);
		if (old == owner)
			break;

		owner = old;
	}
}

#ifndef CONFIG_DEBUG_LOCK_ALLOC
/*
 * We split the mutex lock/unlock logic into separate fastpath and
 * slowpath functions, to reduce the register pressure on the fastpath.
 * We also put the fastpath first in the kernel image, to make sure the
 * branch is predicted by the CPU as default-untaken.
 */
static void __sched __mutex_lock_slowpath(struct mutex *lock);

/**
 * mutex_lock - acquire the mutex
 * @lock: the mutex to be acquired
 *
 * Lock the mutex exclusively for this task. If the mutex is not
 * available right now, it will sleep until it can get it.
 *
 * The mutex must later on be released by the same task that
 * acquired it. Recursive locking is not allowed. The task
 * may not exit without first unlocking the mutex. Also, kernel
 * memory where the mutex resides must not be freed with
 * the mutex still locked. The mutex must first be initialized
 * (or statically defined) before it can be locked. memset()-ing
 * the mutex to 0 is not allowed.
 *
 * (The CONFIG_DEBUG_MUTEXES .config option turns on debugging
 * checks that will enforce the restrictions and will also do
 * deadlock debugging)
 *
 * This function is similar to (but not equivalent to) down().
 */
void __sched mutex_lock(struct mutex *lock)
{
	might_sleep();

	if (!__mutex_trylock_fast(lock))
		__mutex_lock_slowpath(lock);
}
EXPORT_SYMBOL(mutex_lock);
#endif

static __always_inline void
ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
{
#ifdef CONFIG_DEBUG_MUTEXES
	/*
	 * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
	 * but released with a normal mutex_unlock in this call.
	 *
	 * This should never happen, always use ww_mutex_unlock.
	 */
	DEBUG_LOCKS_WARN_ON(ww->ctx);

	/*
	 * Not quite done after calling ww_acquire_done() ?
	 */
	DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);

	if (ww_ctx->contending_lock) {
		/*
		 * After -EDEADLK you tried to
		 * acquire a different ww_mutex? Bad!
		 */
		DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);

		/*
		 * You called ww_mutex_lock after receiving -EDEADLK,
		 * but 'forgot' to unlock everything else first?
		 */
		DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
		ww_ctx->contending_lock = NULL;
	}

	/*
	 * Naughty, using a different class will lead to undefined behavior!
	 */
	DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
#endif
	ww_ctx->acquired++;
}

static inline bool __sched
__ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
{
	return a->stamp - b->stamp <= LONG_MAX &&
	       (a->stamp != b->stamp || a > b);
}

/*
 * Wake up any waiters that may have to back off when the lock is held by the
 * given context.
 *
 * Due to the invariants on the wait list, this can only affect the first
 * waiter with a context.
 *
 * The current task must not be on the wait list.
 */
static void __sched
__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
{
	struct mutex_waiter *cur;

	lockdep_assert_held(&lock->wait_lock);

	list_for_each_entry(cur, &lock->wait_list, list) {
		if (!cur->ww_ctx)
			continue;

		if (cur->ww_ctx->acquired > 0 &&
		    __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) {
			debug_mutex_wake_waiter(lock, cur);
			wake_up_process(cur->task);
		}

		break;
	}
}

/*
 * After acquiring lock with fastpath or when we lost out in contested
 * slowpath, set ctx and wake up any waiters so they can recheck.
 */
static __always_inline void
ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	ww_mutex_lock_acquired(lock, ctx);

	lock->ctx = ctx;

	/*
	 * The lock->ctx update should be visible on all cores before
	 * the atomic read is done, otherwise contended waiters might be
	 * missed. The contended waiters will either see ww_ctx == NULL
	 * and keep spinning, or it will acquire wait_lock, add itself
	 * to waiter list and sleep.
	 */
	smp_mb(); /* ^^^ */

	/*
	 * Check if lock is contended, if not there is nobody to wake up
	 */
	if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS)))
		return;

	/*
	 * Uh oh, we raced in fastpath, wake up everyone in this case,
	 * so they can see the new lock->ctx.
	 */
	spin_lock(&lock->base.wait_lock);
	__ww_mutex_wakeup_for_backoff(&lock->base, ctx);
	spin_unlock(&lock->base.wait_lock);
}

/*
 * After acquiring lock in the slowpath set ctx.
 *
 * Unlike for the fast path, the caller ensures that waiters are woken up where
 * necessary.
 *
 * Callers must hold the mutex wait_lock.
 */
static __always_inline void
ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	ww_mutex_lock_acquired(lock, ctx);
	lock->ctx = ctx;
}

#ifdef CONFIG_MUTEX_SPIN_ON_OWNER

static inline
bool ww_mutex_spin_on_owner(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
			    struct mutex_waiter *waiter)
{
	struct ww_mutex *ww;

	ww = container_of(lock, struct ww_mutex, base);

	/*
	 * If ww->ctx is set the contents are undefined, only
	 * by acquiring wait_lock there is a guarantee that
	 * they are not invalid when reading.
	 *
	 * As such, when deadlock detection needs to be
	 * performed the optimistic spinning cannot be done.
	 *
	 * Check this in every inner iteration because we may
	 * be racing against another thread's ww_mutex_lock.
	 */
	if (ww_ctx->acquired > 0 && READ_ONCE(ww->ctx))
		return false;

	/*
	 * If we aren't on the wait list yet, cancel the spin
	 * if there are waiters. We want  to avoid stealing the
	 * lock from a waiter with an earlier stamp, since the
	 * other thread may already own a lock that we also
	 * need.
	 */
	if (!waiter && (atomic_long_read(&lock->owner) & MUTEX_FLAG_WAITERS))
		return false;

	/*
	 * Similarly, stop spinning if we are no longer the
	 * first waiter.
	 */
	if (waiter && !__mutex_waiter_is_first(lock, waiter))
		return false;

	return true;
}

/*
 * Look out! "owner" is an entirely speculative pointer access and not
 * reliable.
 *
 * "noinline" so that this function shows up on perf profiles.
 */
static noinline
bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner,
			 struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter)
{
	bool ret = true;

	rcu_read_lock();
	while (__mutex_owner(lock) == owner) {
		/*
		 * Ensure we emit the owner->on_cpu, dereference _after_
		 * checking lock->owner still matches owner. If that fails,
		 * owner might point to freed memory. If it still matches,
		 * the rcu_read_lock() ensures the memory stays valid.
		 */
		barrier();

		/*
		 * Use vcpu_is_preempted to detect lock holder preemption issue.
		 */
		if (!owner->on_cpu || need_resched() ||
				vcpu_is_preempted(task_cpu(owner))) {
			ret = false;
			break;
		}

		if (ww_ctx && !ww_mutex_spin_on_owner(lock, ww_ctx, waiter)) {
			ret = false;
			break;
		}

		cpu_relax();
	}
	rcu_read_unlock();

	return ret;
}

/*
 * Initial check for entering the mutex spinning loop
 */
static inline int mutex_can_spin_on_owner(struct mutex *lock)
{
	struct task_struct *owner;
	int retval = 1;

	if (need_resched())
		return 0;

	rcu_read_lock();
	owner = __mutex_owner(lock);

	/*
	 * As lock holder preemption issue, we both skip spinning if task is not
	 * on cpu or its cpu is preempted
	 */
	if (owner)
		retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
	rcu_read_unlock();

	/*
	 * If lock->owner is not set, the mutex has been released. Return true
	 * such that we'll trylock in the spin path, which is a faster option
	 * than the blocking slow path.
	 */
	return retval;
}

/*
 * Optimistic spinning.
 *
 * We try to spin for acquisition when we find that the lock owner
 * is currently running on a (different) CPU and while we don't
 * need to reschedule. The rationale is that if the lock owner is
 * running, it is likely to release the lock soon.
 *
 * The mutex spinners are queued up using MCS lock so that only one
 * spinner can compete for the mutex. However, if mutex spinning isn't
 * going to happen, there is no point in going through the lock/unlock
 * overhead.
 *
 * Returns true when the lock was taken, otherwise false, indicating
 * that we need to jump to the slowpath and sleep.
 *
 * The waiter flag is set to true if the spinner is a waiter in the wait
 * queue. The waiter-spinner will spin on the lock directly and concurrently
 * with the spinner at the head of the OSQ, if present, until the owner is
 * changed to itself.
 */
static __always_inline bool
mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
		      const bool use_ww_ctx, struct mutex_waiter *waiter)
{
	if (!waiter) {
		/*
		 * The purpose of the mutex_can_spin_on_owner() function is
		 * to eliminate the overhead of osq_lock() and osq_unlock()
		 * in case spinning isn't possible. As a waiter-spinner
		 * is not going to take OSQ lock anyway, there is no need
		 * to call mutex_can_spin_on_owner().
		 */
		if (!mutex_can_spin_on_owner(lock))
			goto fail;

		/*
		 * In order to avoid a stampede of mutex spinners trying to
		 * acquire the mutex all at once, the spinners need to take a
		 * MCS (queued) lock first before spinning on the owner field.
		 */
		if (!osq_lock(&lock->osq))
			goto fail;
	}

	for (;;) {
		struct task_struct *owner;

		/* Try to acquire the mutex... */
		owner = __mutex_trylock_or_owner(lock);
		if (!owner)
			break;

		/*
		 * There's an owner, wait for it to either
		 * release the lock or go to sleep.
		 */
		if (!mutex_spin_on_owner(lock, owner, ww_ctx, waiter))
			goto fail_unlock;

		/*
		 * The cpu_relax() call is a compiler barrier which forces
		 * everything in this loop to be re-loaded. We don't need
		 * memory barriers as we'll eventually observe the right
		 * values at the cost of a few extra spins.
		 */
		cpu_relax();
	}

	if (!waiter)
		osq_unlock(&lock->osq);

	return true;


fail_unlock:
	if (!waiter)
		osq_unlock(&lock->osq);

fail:
	/*
	 * If we fell out of the spin path because of need_resched(),
	 * reschedule now, before we try-lock the mutex. This avoids getting
	 * scheduled out right after we obtained the mutex.
	 */
	if (need_resched()) {
		/*
		 * We _should_ have TASK_RUNNING here, but just in case
		 * we do not, make it so, otherwise we might get stuck.
		 */
		__set_current_state(TASK_RUNNING);
		schedule_preempt_disabled();
	}

	return false;
}
#else
static __always_inline bool
mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
		      const bool use_ww_ctx, struct mutex_waiter *waiter)
{
	return false;
}
#endif

static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip);

/**
 * mutex_unlock - release the mutex
 * @lock: the mutex to be released
 *
 * Unlock a mutex that has been locked by this task previously.
 *
 * This function must not be used in interrupt context. Unlocking
 * of a not locked mutex is not allowed.
 *
 * This function is similar to (but not equivalent to) up().
 */
void __sched mutex_unlock(struct mutex *lock)
{
#ifndef CONFIG_DEBUG_LOCK_ALLOC
	if (__mutex_unlock_fast(lock))
		return;
#endif
	__mutex_unlock_slowpath(lock, _RET_IP_);
}
EXPORT_SYMBOL(mutex_unlock);

/**
 * ww_mutex_unlock - release the w/w mutex
 * @lock: the mutex to be released
 *
 * Unlock a mutex that has been locked by this task previously with any of the
 * ww_mutex_lock* functions (with or without an acquire context). It is
 * forbidden to release the locks after releasing the acquire context.
 *
 * This function must not be used in interrupt context. Unlocking
 * of a unlocked mutex is not allowed.
 */
void __sched ww_mutex_unlock(struct ww_mutex *lock)
{
	/*
	 * The unlocking fastpath is the 0->1 transition from 'locked'
	 * into 'unlocked' state:
	 */
	if (lock->ctx) {
#ifdef CONFIG_DEBUG_MUTEXES
		DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
#endif
		if (lock->ctx->acquired > 0)
			lock->ctx->acquired--;
		lock->ctx = NULL;
	}

	mutex_unlock(&lock->base);
}
EXPORT_SYMBOL(ww_mutex_unlock);

static inline int __sched
__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter,
			    struct ww_acquire_ctx *ctx)
{
	struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
	struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx);
	struct mutex_waiter *cur;

	if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx))
		goto deadlock;

	/*
	 * If there is a waiter in front of us that has a context, then its
	 * stamp is earlier than ours and we must back off.
	 */
	cur = waiter;
	list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) {
		if (cur->ww_ctx)
			goto deadlock;
	}

	return 0;

deadlock:
#ifdef CONFIG_DEBUG_MUTEXES
	DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
	ctx->contending_lock = ww;
#endif
	return -EDEADLK;
}

static inline int __sched
__ww_mutex_add_waiter(struct mutex_waiter *waiter,
		      struct mutex *lock,
		      struct ww_acquire_ctx *ww_ctx)
{
	struct mutex_waiter *cur;
	struct list_head *pos;

	if (!ww_ctx) {
		list_add_tail(&waiter->list, &lock->wait_list);
		return 0;
	}

	/*
	 * Add the waiter before the first waiter with a higher stamp.
	 * Waiters without a context are skipped to avoid starving
	 * them.
	 */
	pos = &lock->wait_list;
	list_for_each_entry_reverse(cur, &lock->wait_list, list) {
		if (!cur->ww_ctx)
			continue;

		if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) {
			/* Back off immediately if necessary. */
			if (ww_ctx->acquired > 0) {
#ifdef CONFIG_DEBUG_MUTEXES
				struct ww_mutex *ww;

				ww = container_of(lock, struct ww_mutex, base);
				DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
				ww_ctx->contending_lock = ww;
#endif
				return -EDEADLK;
			}

			break;
		}

		pos = &cur->list;

		/*
		 * Wake up the waiter so that it gets a chance to back
		 * off.
		 */
		if (cur->ww_ctx->acquired > 0) {
			debug_mutex_wake_waiter(lock, cur);
			wake_up_process(cur->task);
		}
	}

	list_add_tail(&waiter->list, pos);
	return 0;
}

/*
 * Lock a mutex (possibly interruptible), slowpath:
 */
static __always_inline int __sched
__mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
		    struct lockdep_map *nest_lock, unsigned long ip,
		    struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
{
	struct mutex_waiter waiter;
	bool first = false;
	struct ww_mutex *ww;
	int ret;

	might_sleep();

	ww = container_of(lock, struct ww_mutex, base);
	if (use_ww_ctx && ww_ctx) {
		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
			return -EALREADY;
	}

	preempt_disable();
	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);

	if (__mutex_trylock(lock) ||
	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, NULL)) {
		/* got the lock, yay! */
		lock_acquired(&lock->dep_map, ip);
		if (use_ww_ctx && ww_ctx)
			ww_mutex_set_context_fastpath(ww, ww_ctx);
		preempt_enable();
		return 0;
	}

	spin_lock(&lock->wait_lock);
	/*
	 * After waiting to acquire the wait_lock, try again.
	 */
	if (__mutex_trylock(lock)) {
		if (use_ww_ctx && ww_ctx)
			__ww_mutex_wakeup_for_backoff(lock, ww_ctx);

		goto skip_wait;
	}

	debug_mutex_lock_common(lock, &waiter);
	debug_mutex_add_waiter(lock, &waiter, current);

	lock_contended(&lock->dep_map, ip);

	if (!use_ww_ctx) {
		/* add waiting tasks to the end of the waitqueue (FIFO): */
		list_add_tail(&waiter.list, &lock->wait_list);

#ifdef CONFIG_DEBUG_MUTEXES
		waiter.ww_ctx = MUTEX_POISON_WW_CTX;
#endif
	} else {
		/* Add in stamp order, waking up waiters that must back off. */
		ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx);
		if (ret)
			goto err_early_backoff;

		waiter.ww_ctx = ww_ctx;
	}

	waiter.task = current;

	if (__mutex_waiter_is_first(lock, &waiter))
		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);

	set_current_state(state);
	for (;;) {
		/*
		 * Once we hold wait_lock, we're serialized against
		 * mutex_unlock() handing the lock off to us, do a trylock
		 * before testing the error conditions to make sure we pick up
		 * the handoff.
		 */
		if (__mutex_trylock(lock))
			goto acquired;

		/*
		 * Check for signals and wound conditions while holding
		 * wait_lock. This ensures the lock cancellation is ordered
		 * against mutex_unlock() and wake-ups do not go missing.
		 */
		if (unlikely(signal_pending_state(state, current))) {
			ret = -EINTR;
			goto err;
		}

		if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) {
			ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx);
			if (ret)
				goto err;
		}

		spin_unlock(&lock->wait_lock);
		schedule_preempt_disabled();

		/*
		 * ww_mutex needs to always recheck its position since its waiter
		 * list is not FIFO ordered.
		 */
		if ((use_ww_ctx && ww_ctx) || !first) {
			first = __mutex_waiter_is_first(lock, &waiter);
			if (first)
				__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
		}

		set_current_state(state);
		/*
		 * Here we order against unlock; we must either see it change
		 * state back to RUNNING and fall through the next schedule(),
		 * or we must see its unlock and acquire.
		 */
		if (__mutex_trylock(lock) ||
		    (first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, &waiter)))
			break;

		spin_lock(&lock->wait_lock);
	}
	spin_lock(&lock->wait_lock);
acquired:
	__set_current_state(TASK_RUNNING);

	mutex_remove_waiter(lock, &waiter, current);
	if (likely(list_empty(&lock->wait_list)))
		__mutex_clear_flag(lock, MUTEX_FLAGS);

	debug_mutex_free_waiter(&waiter);

skip_wait:
	/* got the lock - cleanup and rejoice! */
	lock_acquired(&lock->dep_map, ip);

	if (use_ww_ctx && ww_ctx)
		ww_mutex_set_context_slowpath(ww, ww_ctx);

	spin_unlock(&lock->wait_lock);
	preempt_enable();
	return 0;

err:
	__set_current_state(TASK_RUNNING);
	mutex_remove_waiter(lock, &waiter, current);
err_early_backoff:
	spin_unlock(&lock->wait_lock);
	debug_mutex_free_waiter(&waiter);
	mutex_release(&lock->dep_map, 1, ip);
	preempt_enable();
	return ret;
}

static int __sched
__mutex_lock(struct mutex *lock, long state, unsigned int subclass,
	     struct lockdep_map *nest_lock, unsigned long ip)
{
	return __mutex_lock_common(lock, state, subclass, nest_lock, ip, NULL, false);
}

static int __sched
__ww_mutex_lock(struct mutex *lock, long state, unsigned int subclass,
		struct lockdep_map *nest_lock, unsigned long ip,
		struct ww_acquire_ctx *ww_ctx)
{
	return __mutex_lock_common(lock, state, subclass, nest_lock, ip, ww_ctx, true);
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC
void __sched
mutex_lock_nested(struct mutex *lock, unsigned int subclass)
{
	__mutex_lock(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_);
}

EXPORT_SYMBOL_GPL(mutex_lock_nested);

void __sched
_mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
{
	__mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_);
}
EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);

int __sched
mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
{
	return __mutex_lock(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_);
}
EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);

int __sched
mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
{
	return __mutex_lock(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_);
}
EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);

void __sched
mutex_lock_io_nested(struct mutex *lock, unsigned int subclass)
{
	int token;

	might_sleep();

	token = io_schedule_prepare();
	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
			    subclass, NULL, _RET_IP_, NULL, 0);
	io_schedule_finish(token);
}
EXPORT_SYMBOL_GPL(mutex_lock_io_nested);

static inline int
ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
	unsigned tmp;

	if (ctx->deadlock_inject_countdown-- == 0) {
		tmp = ctx->deadlock_inject_interval;
		if (tmp > UINT_MAX/4)
			tmp = UINT_MAX;
		else
			tmp = tmp*2 + tmp + tmp/2;

		ctx->deadlock_inject_interval = tmp;
		ctx->deadlock_inject_countdown = tmp;
		ctx->contending_lock = lock;

		ww_mutex_unlock(lock);

		return -EDEADLK;
	}
#endif

	return 0;
}

int __sched
ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	int ret;

	might_sleep();
	ret =  __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE,
			       0, ctx ? &ctx->dep_map : NULL, _RET_IP_,
			       ctx);
	if (!ret && ctx && ctx->acquired > 1)
		return ww_mutex_deadlock_injection(lock, ctx);

	return ret;
}
EXPORT_SYMBOL_GPL(ww_mutex_lock);

int __sched
ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	int ret;

	might_sleep();
	ret = __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE,
			      0, ctx ? &ctx->dep_map : NULL, _RET_IP_,
			      ctx);

	if (!ret && ctx && ctx->acquired > 1)
		return ww_mutex_deadlock_injection(lock, ctx);

	return ret;
}
EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible);

#endif

/*
 * Release the lock, slowpath:
 */
static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
{
	struct task_struct *next = NULL;
	DEFINE_WAKE_Q(wake_q);
	unsigned long owner;

	mutex_release(&lock->dep_map, 1, ip);

	/*
	 * Release the lock before (potentially) taking the spinlock such that
	 * other contenders can get on with things ASAP.
	 *
	 * Except when HANDOFF, in that case we must not clear the owner field,
	 * but instead set it to the top waiter.
	 */
	owner = atomic_long_read(&lock->owner);
	for (;;) {
		unsigned long old;

#ifdef CONFIG_DEBUG_MUTEXES
		DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
		DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP);
#endif

		if (owner & MUTEX_FLAG_HANDOFF)
			break;

		old = atomic_long_cmpxchg_release(&lock->owner, owner,
						  __owner_flags(owner));
		if (old == owner) {
			if (owner & MUTEX_FLAG_WAITERS)
				break;

			return;
		}

		owner = old;
	}

	spin_lock(&lock->wait_lock);
	debug_mutex_unlock(lock);
	if (!list_empty(&lock->wait_list)) {
		/* get the first entry from the wait-list: */
		struct mutex_waiter *waiter =
			list_first_entry(&lock->wait_list,
					 struct mutex_waiter, list);

		next = waiter->task;

		debug_mutex_wake_waiter(lock, waiter);
		wake_q_add(&wake_q, next);
	}

	if (owner & MUTEX_FLAG_HANDOFF)
		__mutex_handoff(lock, next);

	spin_unlock(&lock->wait_lock);

	wake_up_q(&wake_q);
}

#ifndef CONFIG_DEBUG_LOCK_ALLOC
/*
 * Here come the less common (and hence less performance-critical) APIs:
 * mutex_lock_interruptible() and mutex_trylock().
 */
static noinline int __sched
__mutex_lock_killable_slowpath(struct mutex *lock);

static noinline int __sched
__mutex_lock_interruptible_slowpath(struct mutex *lock);

/**
 * mutex_lock_interruptible() - Acquire the mutex, interruptible by signals.
 * @lock: The mutex to be acquired.
 *
 * Lock the mutex like mutex_lock().  If a signal is delivered while the
 * process is sleeping, this function will return without acquiring the
 * mutex.
 *
 * Context: Process context.
 * Return: 0 if the lock was successfully acquired or %-EINTR if a
 * signal arrived.
 */
int __sched mutex_lock_interruptible(struct mutex *lock)
{
	might_sleep();

	if (__mutex_trylock_fast(lock))
		return 0;

	return __mutex_lock_interruptible_slowpath(lock);
}

EXPORT_SYMBOL(mutex_lock_interruptible);

/**
 * mutex_lock_killable() - Acquire the mutex, interruptible by fatal signals.
 * @lock: The mutex to be acquired.
 *
 * Lock the mutex like mutex_lock().  If a signal which will be fatal to
 * the current process is delivered while the process is sleeping, this
 * function will return without acquiring the mutex.
 *
 * Context: Process context.
 * Return: 0 if the lock was successfully acquired or %-EINTR if a
 * fatal signal arrived.
 */
int __sched mutex_lock_killable(struct mutex *lock)
{
	might_sleep();

	if (__mutex_trylock_fast(lock))
		return 0;

	return __mutex_lock_killable_slowpath(lock);
}
EXPORT_SYMBOL(mutex_lock_killable);

/**
 * mutex_lock_io() - Acquire the mutex and mark the process as waiting for I/O
 * @lock: The mutex to be acquired.
 *
 * Lock the mutex like mutex_lock().  While the task is waiting for this
 * mutex, it will be accounted as being in the IO wait state by the
 * scheduler.
 *
 * Context: Process context.
 */
void __sched mutex_lock_io(struct mutex *lock)
{
	int token;

	token = io_schedule_prepare();
	mutex_lock(lock);
	io_schedule_finish(token);
}
EXPORT_SYMBOL_GPL(mutex_lock_io);

static noinline void __sched
__mutex_lock_slowpath(struct mutex *lock)
{
	__mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
}

static noinline int __sched
__mutex_lock_killable_slowpath(struct mutex *lock)
{
	return __mutex_lock(lock, TASK_KILLABLE, 0, NULL, _RET_IP_);
}

static noinline int __sched
__mutex_lock_interruptible_slowpath(struct mutex *lock)
{
	return __mutex_lock(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_);
}

static noinline int __sched
__ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	return __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE, 0, NULL,
			       _RET_IP_, ctx);
}

static noinline int __sched
__ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
					    struct ww_acquire_ctx *ctx)
{
	return __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE, 0, NULL,
			       _RET_IP_, ctx);
}

#endif

/**
 * mutex_trylock - try to acquire the mutex, without waiting
 * @lock: the mutex to be acquired
 *
 * Try to acquire the mutex atomically. Returns 1 if the mutex
 * has been acquired successfully, and 0 on contention.
 *
 * NOTE: this function follows the spin_trylock() convention, so
 * it is negated from the down_trylock() return values! Be careful
 * about this when converting semaphore users to mutexes.
 *
 * This function must not be used in interrupt context. The
 * mutex must be released by the same task that acquired it.
 */
int __sched mutex_trylock(struct mutex *lock)
{
	bool locked = __mutex_trylock(lock);

	if (locked)
		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);

	return locked;
}
EXPORT_SYMBOL(mutex_trylock);

#ifndef CONFIG_DEBUG_LOCK_ALLOC
int __sched
ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	might_sleep();

	if (__mutex_trylock_fast(&lock->base)) {
		if (ctx)
			ww_mutex_set_context_fastpath(lock, ctx);
		return 0;
	}

	return __ww_mutex_lock_slowpath(lock, ctx);
}
EXPORT_SYMBOL(ww_mutex_lock);

int __sched
ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
	might_sleep();

	if (__mutex_trylock_fast(&lock->base)) {
		if (ctx)
			ww_mutex_set_context_fastpath(lock, ctx);
		return 0;
	}

	return __ww_mutex_lock_interruptible_slowpath(lock, ctx);
}
EXPORT_SYMBOL(ww_mutex_lock_interruptible);

#endif

/**
 * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
 * @cnt: the atomic which we are to dec
 * @lock: the mutex to return holding if we dec to 0
 *
 * return true and hold lock if we dec to 0, return false otherwise
 */
int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
{
	/* dec if we can't possibly hit 0 */
	if (atomic_add_unless(cnt, -1, 1))
		return 0;
	/* we might hit 0, so take the lock */
	mutex_lock(lock);
	if (!atomic_dec_and_test(cnt)) {
		/* when we actually did the dec, we didn't hit 0 */
		mutex_unlock(lock);
		return 0;
	}
	/* we hit 0, and we hold the lock */
	return 1;
}
EXPORT_SYMBOL(atomic_dec_and_mutex_lock);