summaryrefslogtreecommitdiffstats
path: root/kernel/rtmutex.c
blob: 013882e8349744955e28b04a58d796c644330ed1 (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
/*
 * 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/module.h>
#include <linux/sched.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 and 1
 * are used to keep track of the "owner is pending" and "lock has
 * waiters" state.
 *
 * owner	bit1	bit0
 * NULL		0	0	lock is free (fast acquire possible)
 * NULL		0	1	invalid state
 * NULL		1	0	Transitional State*
 * NULL		1	1	invalid state
 * taskpointer	0	0	lock is held (fast release possible)
 * taskpointer	0	1	task is pending owner
 * taskpointer	1	0	lock is held and has waiters
 * taskpointer	1	1	task is pending owner and lock has more waiters
 *
 * Pending ownership is assigned to the top (highest priority)
 * waiter of the lock, when the lock is released. The thread is woken
 * up and can now take the lock. Until the lock is taken (bit 0
 * cleared) a competing higher priority thread can steal the lock
 * which puts the woken up thread back on the waiters list.
 *
 * The fast atomic compare exchange based acquire and release is only
 * possible when bit 0 and 1 of lock->owner are 0.
 *
 * (*) There's a small time where the owner can be NULL and the
 * "lock has waiters" bit is set.  This can happen when grabbing the lock.
 * To prevent a cmpxchg of the owner releasing the lock, we need to set this
 * bit before looking at the lock, hence the reason this is a transitional
 * state.
 */

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

	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);
}
#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);
}
#endif

/*
 * Calculate task priority from the waiter list priority
 *
 * Return task->normal_prio when the waiter list 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)->pi_list_entry.prio,
		   task->normal_prio);
}

/*
 * 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)
		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;

	spin_lock_irqsave(&task->pi_lock, flags);
	__rt_mutex_adjust_prio(task);
	spin_unlock_irqrestore(&task->pi_lock, flags);
}

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

/*
 * Adjust the priority chain. Also used for deadlock detection.
 * Decreases task's usage by one - may thus free the task.
 * 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_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 deadlock_detect ? -EDEADLK : 0;
	}
 retry:
	/*
	 * Task can not go away as we did a get_task() before !
	 */
	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 || !waiter->task)
		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
	 * and made us the pending owner:
	 */
	if (orig_waiter && !orig_waiter->task)
		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 && (!task_has_pi_waiters(task) ||
			   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->list_entry.prio == task->prio)
		goto out_unlock_pi;

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

	/* Deadlock detection */
	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
		spin_unlock(&lock->wait_lock);
		ret = deadlock_detect ? -EDEADLK : 0;
		goto out_unlock_pi;
	}

	top_waiter = rt_mutex_top_waiter(lock);

	/* Requeue the waiter */
	plist_del(&waiter->list_entry, &lock->wait_list);
	waiter->list_entry.prio = task->prio;
	plist_add(&waiter->list_entry, &lock->wait_list);

	/* Release the task */
	spin_unlock_irqrestore(&task->pi_lock, flags);
	put_task_struct(task);

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

	if (waiter == rt_mutex_top_waiter(lock)) {
		/* Boost the owner */
		plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
		waiter->pi_list_entry.prio = waiter->list_entry.prio;
		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
		__rt_mutex_adjust_prio(task);

	} else if (top_waiter == waiter) {
		/* Deboost the owner */
		plist_del(&waiter->pi_list_entry, &task->pi_waiters);
		waiter = rt_mutex_top_waiter(lock);
		waiter->pi_list_entry.prio = waiter->list_entry.prio;
		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
		__rt_mutex_adjust_prio(task);
	}

	spin_unlock_irqrestore(&task->pi_lock, flags);

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

	if (!detect_deadlock && waiter != top_waiter)
		goto out_put_task;

	goto again;

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

	return ret;
}

/*
 * Optimization: check if we can steal the lock from the
 * assigned pending owner [which might not have taken the
 * lock yet]:
 */
static inline int try_to_steal_lock(struct rt_mutex *lock)
{
	struct task_struct *pendowner = rt_mutex_owner(lock);
	struct rt_mutex_waiter *next;
	unsigned long flags;

	if (!rt_mutex_owner_pending(lock))
		return 0;

	if (pendowner == current)
		return 1;

	spin_lock_irqsave(&pendowner->pi_lock, flags);
	if (current->prio >= pendowner->prio) {
		spin_unlock_irqrestore(&pendowner->pi_lock, flags);
		return 0;
	}

	/*
	 * Check if a waiter is enqueued on the pending owners
	 * pi_waiters list. Remove it and readjust pending owners
	 * priority.
	 */
	if (likely(!rt_mutex_has_waiters(lock))) {
		spin_unlock_irqrestore(&pendowner->pi_lock, flags);
		return 1;
	}

	/* No chain handling, pending owner is not blocked on anything: */
	next = rt_mutex_top_waiter(lock);
	plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
	__rt_mutex_adjust_prio(pendowner);
	spin_unlock_irqrestore(&pendowner->pi_lock, flags);

	/*
	 * We are going to steal the lock and a waiter was
	 * enqueued on the pending owners pi_waiters queue. So
	 * we have to enqueue this waiter into
	 * current->pi_waiters list. This covers the case,
	 * where current is boosted because it holds another
	 * lock and gets unboosted because the booster is
	 * interrupted, so we would delay a waiter with higher
	 * priority as current->normal_prio.
	 *
	 * Note: in the rare case of a SCHED_OTHER task changing
	 * its priority and thus stealing the lock, next->task
	 * might be current:
	 */
	if (likely(next->task != current)) {
		spin_lock_irqsave(&current->pi_lock, flags);
		plist_add(&next->pi_list_entry, &current->pi_waiters);
		__rt_mutex_adjust_prio(current);
		spin_unlock_irqrestore(&current->pi_lock, flags);
	}
	return 1;
}

/*
 * Try to take an rt-mutex
 *
 * This fails
 * - when the lock has a real owner
 * - when a different pending owner exists and has higher priority than current
 *
 * Must be called with lock->wait_lock held.
 */
static int try_to_take_rt_mutex(struct rt_mutex *lock)
{
	/*
	 * 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) && !try_to_steal_lock(lock))
		return 0;

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

	rt_mutex_set_owner(lock, current, 0);

	rt_mutex_deadlock_account_lock(lock, current);

	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,
				   int detect_deadlock)
{
	struct task_struct *owner = rt_mutex_owner(lock);
	struct rt_mutex_waiter *top_waiter = waiter;
	unsigned long flags;
	int chain_walk = 0, res;

	spin_lock_irqsave(&current->pi_lock, flags);
	__rt_mutex_adjust_prio(current);
	waiter->task = current;
	waiter->lock = lock;
	plist_node_init(&waiter->list_entry, current->prio);
	plist_node_init(&waiter->pi_list_entry, current->prio);

	/* Get the top priority waiter on the lock */
	if (rt_mutex_has_waiters(lock))
		top_waiter = rt_mutex_top_waiter(lock);
	plist_add(&waiter->list_entry, &lock->wait_list);

	current->pi_blocked_on = waiter;

	spin_unlock_irqrestore(&current->pi_lock, flags);

	if (waiter == rt_mutex_top_waiter(lock)) {
		spin_lock_irqsave(&owner->pi_lock, flags);
		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);

		__rt_mutex_adjust_prio(owner);
		if (owner->pi_blocked_on)
			chain_walk = 1;
		spin_unlock_irqrestore(&owner->pi_lock, flags);
	}
	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
		chain_walk = 1;

	if (!chain_walk)
		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);

	spin_unlock(&lock->wait_lock);

	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
					 current);

	spin_lock(&lock->wait_lock);

	return res;
}

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

	spin_lock_irqsave(&current->pi_lock, flags);

	waiter = rt_mutex_top_waiter(lock);
	plist_del(&waiter->list_entry, &lock->wait_list);

	/*
	 * 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.
	 */
	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
	pendowner = waiter->task;
	waiter->task = NULL;

	rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);

	spin_unlock_irqrestore(&current->pi_lock, flags);

	/*
	 * Clear the pi_blocked_on variable and enqueue a possible
	 * waiter into the pi_waiters list of the pending owner. This
	 * prevents that in case the pending owner gets unboosted a
	 * waiter with higher priority than pending-owner->normal_prio
	 * is blocked on the unboosted (pending) owner.
	 */
	spin_lock_irqsave(&pendowner->pi_lock, flags);

	WARN_ON(!pendowner->pi_blocked_on);
	WARN_ON(pendowner->pi_blocked_on != waiter);
	WARN_ON(pendowner->pi_blocked_on->lock != lock);

	pendowner->pi_blocked_on = NULL;

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

		next = rt_mutex_top_waiter(lock);
		plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
	}
	spin_unlock_irqrestore(&pendowner->pi_lock, flags);

	wake_up_process(pendowner);
}

/*
 * Remove a waiter from a lock
 *
 * Must be called with lock->wait_lock held
 */
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);
	unsigned long flags;
	int chain_walk = 0;

	spin_lock_irqsave(&current->pi_lock, flags);
	plist_del(&waiter->list_entry, &lock->wait_list);
	waiter->task = NULL;
	current->pi_blocked_on = NULL;
	spin_unlock_irqrestore(&current->pi_lock, flags);

	if (first && owner != current) {

		spin_lock_irqsave(&owner->pi_lock, flags);

		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);

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

			next = rt_mutex_top_waiter(lock);
			plist_add(&next->pi_list_entry, &owner->pi_waiters);
		}
		__rt_mutex_adjust_prio(owner);

		if (owner->pi_blocked_on)
			chain_walk = 1;

		spin_unlock_irqrestore(&owner->pi_lock, flags);
	}

	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));

	if (!chain_walk)
		return;

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

	spin_unlock(&lock->wait_lock);

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

	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;
	unsigned long flags;

	spin_lock_irqsave(&task->pi_lock, flags);

	waiter = task->pi_blocked_on;
	if (!waiter || waiter->list_entry.prio == task->prio) {
		spin_unlock_irqrestore(&task->pi_lock, flags);
		return;
	}

	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, NULL, task);
}

/*
 * 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);
	waiter.task = NULL;

	spin_lock(&lock->wait_lock);

	/* Try to acquire the lock again: */
	if (try_to_take_rt_mutex(lock)) {
		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;
	}

	for (;;) {
		/* Try to acquire the lock: */
		if (try_to_take_rt_mutex(lock))
			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;
		}

		/*
		 * waiter.task is NULL the first time we come here and
		 * when we have been woken up by the previous owner
		 * but the lock got stolen by a higher prio task.
		 */
		if (!waiter.task) {
			ret = task_blocks_on_rt_mutex(lock, &waiter,
						      detect_deadlock);
			/*
			 * If we got woken up by the owner then start loop
			 * all over without going into schedule to try
			 * to get the lock now:
			 */
			if (unlikely(!waiter.task)) {
				/*
				 * Reset the return value. We might
				 * have returned with -EDEADLK and the
				 * owner released the lock while we
				 * were walking the pi chain.
				 */
				ret = 0;
				continue;
			}
			if (unlikely(ret))
				break;
		}

		spin_unlock(&lock->wait_lock);

		debug_rt_mutex_print_deadlock(&waiter);

		if (waiter.task)
			schedule_rt_mutex(lock);

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

	set_current_state(TASK_RUNNING);

	if (unlikely(waiter.task))
		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);

	spin_unlock(&lock->wait_lock);

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

	/*
	 * Readjust priority, when we did not get the lock. We might
	 * have been the pending owner and boosted. Since we did not
	 * take the lock, the PI boost has to go.
	 */
	if (unlikely(ret))
		rt_mutex_adjust_prio(current);

	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;

	spin_lock(&lock->wait_lock);

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

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

	spin_unlock(&lock->wait_lock);

	return ret;
}

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

	debug_rt_mutex_unlock(lock);

	rt_mutex_deadlock_account_unlock(current);

	if (!rt_mutex_has_waiters(lock)) {
		lock->owner = NULL;
		spin_unlock(&lock->wait_lock);
		return;
	}

	wakeup_next_waiter(lock);

	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
 * -ETIMEOUT	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;
	spin_lock_init(&lock->wait_lock);
	plist_head_init(&lock->wait_list, &lock->wait_lock);

	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, 0);
	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, 0);
	rt_mutex_deadlock_account_unlock(proxy_owner);
}

/**
 * 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;
}
OpenPOWER on IntegriCloud