summaryrefslogtreecommitdiff
path: root/kernel/locking/locktorture.c
blob: 8402b3349dca40a53a82a34900165c1054ae2fff (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
/*
 * Module-based torture test facility for locking
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, you can access it online at
 * http://www.gnu.org/licenses/gpl-2.0.html.
 *
 * Copyright (C) IBM Corporation, 2014
 *
 * Authors: Paul E. McKenney <paulmck@us.ibm.com>
 *          Davidlohr Bueso <dave@stgolabs.net>
 *	Based on kernel/rcu/torture.c.
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/sched/rt.h>
#include <linux/spinlock.h>
#include <linux/rwlock.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <uapi/linux/sched/types.h>
#include <linux/rtmutex.h>
#include <linux/atomic.h>
#include <linux/moduleparam.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/percpu-rwsem.h>
#include <linux/torture.h>

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");

torture_param(int, nwriters_stress, -1,
	     "Number of write-locking stress-test threads");
torture_param(int, nreaders_stress, -1,
	     "Number of read-locking stress-test threads");
torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
torture_param(int, onoff_interval, 0,
	     "Time between CPU hotplugs (s), 0=disable");
torture_param(int, shuffle_interval, 3,
	     "Number of jiffies between shuffles, 0=disable");
torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
torture_param(int, stat_interval, 60,
	     "Number of seconds between stats printk()s");
torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
torture_param(bool, verbose, true,
	     "Enable verbose debugging printk()s");

static char *torture_type = "spin_lock";
module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type,
		 "Type of lock to torture (spin_lock, spin_lock_irq, mutex_lock, ...)");

static struct task_struct *stats_task;
static struct task_struct **writer_tasks;
static struct task_struct **reader_tasks;

static bool lock_is_write_held;
static bool lock_is_read_held;

struct lock_stress_stats {
	long n_lock_fail;
	long n_lock_acquired;
};

/* Forward reference. */
static void lock_torture_cleanup(void);

/*
 * Operations vector for selecting different types of tests.
 */
struct lock_torture_ops {
	void (*init)(void);
	int (*writelock)(void);
	void (*write_delay)(struct torture_random_state *trsp);
	void (*task_boost)(struct torture_random_state *trsp);
	void (*writeunlock)(void);
	int (*readlock)(void);
	void (*read_delay)(struct torture_random_state *trsp);
	void (*readunlock)(void);

	unsigned long flags; /* for irq spinlocks */
	const char *name;
};

struct lock_torture_cxt {
	int nrealwriters_stress;
	int nrealreaders_stress;
	bool debug_lock;
	atomic_t n_lock_torture_errors;
	struct lock_torture_ops *cur_ops;
	struct lock_stress_stats *lwsa; /* writer statistics */
	struct lock_stress_stats *lrsa; /* reader statistics */
};
static struct lock_torture_cxt cxt = { 0, 0, false,
				       ATOMIC_INIT(0),
				       NULL, NULL};
/*
 * Definitions for lock torture testing.
 */

static int torture_lock_busted_write_lock(void)
{
	return 0;  /* BUGGY, do not use in real life!!! */
}

static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
{
	const unsigned long longdelay_ms = 100;

	/* We want a long delay occasionally to force massive contention.  */
	if (!(torture_random(trsp) %
	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
		mdelay(longdelay_ms);
	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
		torture_preempt_schedule();  /* Allow test to be preempted. */
}

static void torture_lock_busted_write_unlock(void)
{
	  /* BUGGY, do not use in real life!!! */
}

static void torture_boost_dummy(struct torture_random_state *trsp)
{
	/* Only rtmutexes care about priority */
}

static struct lock_torture_ops lock_busted_ops = {
	.writelock	= torture_lock_busted_write_lock,
	.write_delay	= torture_lock_busted_write_delay,
	.task_boost     = torture_boost_dummy,
	.writeunlock	= torture_lock_busted_write_unlock,
	.readlock       = NULL,
	.read_delay     = NULL,
	.readunlock     = NULL,
	.name		= "lock_busted"
};

static DEFINE_SPINLOCK(torture_spinlock);

static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock)
{
	spin_lock(&torture_spinlock);
	return 0;
}

static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
{
	const unsigned long shortdelay_us = 2;
	const unsigned long longdelay_ms = 100;

	/* We want a short delay mostly to emulate likely code, and
	 * we want a long delay occasionally to force massive contention.
	 */
	if (!(torture_random(trsp) %
	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
		mdelay(longdelay_ms);
	if (!(torture_random(trsp) %
	      (cxt.nrealwriters_stress * 2 * shortdelay_us)))
		udelay(shortdelay_us);
	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
		torture_preempt_schedule();  /* Allow test to be preempted. */
}

static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock)
{
	spin_unlock(&torture_spinlock);
}

static struct lock_torture_ops spin_lock_ops = {
	.writelock	= torture_spin_lock_write_lock,
	.write_delay	= torture_spin_lock_write_delay,
	.task_boost     = torture_boost_dummy,
	.writeunlock	= torture_spin_lock_write_unlock,
	.readlock       = NULL,
	.read_delay     = NULL,
	.readunlock     = NULL,
	.name		= "spin_lock"
};

static int torture_spin_lock_write_lock_irq(void)
__acquires(torture_spinlock)
{
	unsigned long flags;

	spin_lock_irqsave(&torture_spinlock, flags);
	cxt.cur_ops->flags = flags;
	return 0;
}

static void torture_lock_spin_write_unlock_irq(void)
__releases(torture_spinlock)
{
	spin_unlock_irqrestore(&torture_spinlock, cxt.cur_ops->flags);
}

static struct lock_torture_ops spin_lock_irq_ops = {
	.writelock	= torture_spin_lock_write_lock_irq,
	.write_delay	= torture_spin_lock_write_delay,
	.task_boost     = torture_boost_dummy,
	.writeunlock	= torture_lock_spin_write_unlock_irq,
	.readlock       = NULL,
	.read_delay     = NULL,
	.readunlock     = NULL,
	.name		= "spin_lock_irq"
};

static DEFINE_RWLOCK(torture_rwlock);

static int torture_rwlock_write_lock(void) __acquires(torture_rwlock)
{
	write_lock(&torture_rwlock);
	return 0;
}

static void torture_rwlock_write_delay(struct torture_random_state *trsp)
{
	const unsigned long shortdelay_us = 2;
	const unsigned long longdelay_ms = 100;

	/* We want a short delay mostly to emulate likely code, and
	 * we want a long delay occasionally to force massive contention.
	 */
	if (!(torture_random(trsp) %
	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
		mdelay(longdelay_ms);
	else
		udelay(shortdelay_us);
}

static void torture_rwlock_write_unlock(void) __releases(torture_rwlock)
{
	write_unlock(&torture_rwlock);
}

static int torture_rwlock_read_lock(void) __acquires(torture_rwlock)
{
	read_lock(&torture_rwlock);
	return 0;
}

static void torture_rwlock_read_delay(struct torture_random_state *trsp)
{
	const unsigned long shortdelay_us = 10;
	const unsigned long longdelay_ms = 100;

	/* We want a short delay mostly to emulate likely code, and
	 * we want a long delay occasionally to force massive contention.
	 */
	if (!(torture_random(trsp) %
	      (cxt.nrealreaders_stress * 2000 * longdelay_ms)))
		mdelay(longdelay_ms);
	else
		udelay(shortdelay_us);
}

static void torture_rwlock_read_unlock(void) __releases(torture_rwlock)
{
	read_unlock(&torture_rwlock);
}

static struct lock_torture_ops rw_lock_ops = {
	.writelock	= torture_rwlock_write_lock,
	.write_delay	= torture_rwlock_write_delay,
	.task_boost     = torture_boost_dummy,
	.writeunlock	= torture_rwlock_write_unlock,
	.readlock       = torture_rwlock_read_lock,
	.read_delay     = torture_rwlock_read_delay,
	.readunlock     = torture_rwlock_read_unlock,
	.name		= "rw_lock"
};

static int torture_rwlock_write_lock_irq(void) __acquires(torture_rwlock)
{
	unsigned long flags;

	write_lock_irqsave(&torture_rwlock, flags);
	cxt.cur_ops->flags = flags;
	return 0;
}

static void torture_rwlock_write_unlock_irq(void)
__releases(torture_rwlock)
{
	write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
}

static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock)
{
	unsigned long flags;

	read_lock_irqsave(&torture_rwlock, flags);
	cxt.cur_ops->flags = flags;
	return 0;
}

static void torture_rwlock_read_unlock_irq(void)
__releases(torture_rwlock)
{
	read_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
}

static struct lock_torture_ops rw_lock_irq_ops = {
	.writelock	= torture_rwlock_write_lock_irq,
	.write_delay	= torture_rwlock_write_delay,
	.task_boost     = torture_boost_dummy,
	.writeunlock	= torture_rwlock_write_unlock_irq,
	.readlock       = torture_rwlock_read_lock_irq,
	.read_delay     = torture_rwlock_read_delay,
	.readunlock     = torture_rwlock_read_unlock_irq,
	.name		= "rw_lock_irq"
};

static DEFINE_MUTEX(torture_mutex);

static int torture_mutex_lock(void) __acquires(torture_mutex)
{
	mutex_lock(&torture_mutex);
	return 0;
}

static void torture_mutex_delay(struct torture_random_state *trsp)
{
	const unsigned long longdelay_ms = 100;

	/* We want a long delay occasionally to force massive contention.  */
	if (!(torture_random(trsp) %
	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
		mdelay(longdelay_ms * 5);
	else
		mdelay(longdelay_ms / 5);
	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
		torture_preempt_schedule();  /* Allow test to be preempted. */
}

static void torture_mutex_unlock(void) __releases(torture_mutex)
{
	mutex_unlock(&torture_mutex);
}

static struct lock_torture_ops mutex_lock_ops = {
	.writelock	= torture_mutex_lock,
	.write_delay	= torture_mutex_delay,
	.task_boost     = torture_boost_dummy,
	.writeunlock	= torture_mutex_unlock,
	.readlock       = NULL,
	.read_delay     = NULL,
	.readunlock     = NULL,
	.name		= "mutex_lock"
};

#include <linux/ww_mutex.h>
static DEFINE_WW_CLASS(torture_ww_class);
static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class);
static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class);
static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class);

static int torture_ww_mutex_lock(void)
__acquires(torture_ww_mutex_0)
__acquires(torture_ww_mutex_1)
__acquires(torture_ww_mutex_2)
{
	LIST_HEAD(list);
	struct reorder_lock {
		struct list_head link;
		struct ww_mutex *lock;
	} locks[3], *ll, *ln;
	struct ww_acquire_ctx ctx;

	locks[0].lock = &torture_ww_mutex_0;
	list_add(&locks[0].link, &list);

	locks[1].lock = &torture_ww_mutex_1;
	list_add(&locks[1].link, &list);

	locks[2].lock = &torture_ww_mutex_2;
	list_add(&locks[2].link, &list);

	ww_acquire_init(&ctx, &torture_ww_class);

	list_for_each_entry(ll, &list, link) {
		int err;

		err = ww_mutex_lock(ll->lock, &ctx);
		if (!err)
			continue;

		ln = ll;
		list_for_each_entry_continue_reverse(ln, &list, link)
			ww_mutex_unlock(ln->lock);

		if (err != -EDEADLK)
			return err;

		ww_mutex_lock_slow(ll->lock, &ctx);
		list_move(&ll->link, &list);
	}

	ww_acquire_fini(&ctx);
	return 0;
}

static void torture_ww_mutex_unlock(void)
__releases(torture_ww_mutex_0)
__releases(torture_ww_mutex_1)
__releases(torture_ww_mutex_2)
{
	ww_mutex_unlock(&torture_ww_mutex_0);
	ww_mutex_unlock(&torture_ww_mutex_1);
	ww_mutex_unlock(&torture_ww_mutex_2);
}

static struct lock_torture_ops ww_mutex_lock_ops = {
	.writelock	= torture_ww_mutex_lock,
	.write_delay	= torture_mutex_delay,
	.task_boost     = torture_boost_dummy,
	.writeunlock	= torture_ww_mutex_unlock,
	.readlock       = NULL,
	.read_delay     = NULL,
	.readunlock     = NULL,
	.name		= "ww_mutex_lock"
};

#ifdef CONFIG_RT_MUTEXES
static DEFINE_RT_MUTEX(torture_rtmutex);

static int torture_rtmutex_lock(void) __acquires(torture_rtmutex)
{
	rt_mutex_lock(&torture_rtmutex);
	return 0;
}

static void torture_rtmutex_boost(struct torture_random_state *trsp)
{
	int policy;
	struct sched_param param;
	const unsigned int factor = 50000; /* yes, quite arbitrary */

	if (!rt_task(current)) {
		/*
		 * Boost priority once every ~50k operations. When the
		 * task tries to take the lock, the rtmutex it will account
		 * for the new priority, and do any corresponding pi-dance.
		 */
		if (trsp && !(torture_random(trsp) %
			      (cxt.nrealwriters_stress * factor))) {
			policy = SCHED_FIFO;
			param.sched_priority = MAX_RT_PRIO - 1;
		} else /* common case, do nothing */
			return;
	} else {
		/*
		 * The task will remain boosted for another ~500k operations,
		 * then restored back to its original prio, and so forth.
		 *
		 * When @trsp is nil, we want to force-reset the task for
		 * stopping the kthread.
		 */
		if (!trsp || !(torture_random(trsp) %
			       (cxt.nrealwriters_stress * factor * 2))) {
			policy = SCHED_NORMAL;
			param.sched_priority = 0;
		} else /* common case, do nothing */
			return;
	}

	sched_setscheduler_nocheck(current, policy, &param);
}

static void torture_rtmutex_delay(struct torture_random_state *trsp)
{
	const unsigned long shortdelay_us = 2;
	const unsigned long longdelay_ms = 100;

	/*
	 * We want a short delay mostly to emulate likely code, and
	 * we want a long delay occasionally to force massive contention.
	 */
	if (!(torture_random(trsp) %
	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
		mdelay(longdelay_ms);
	if (!(torture_random(trsp) %
	      (cxt.nrealwriters_stress * 2 * shortdelay_us)))
		udelay(shortdelay_us);
	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
		torture_preempt_schedule();  /* Allow test to be preempted. */
}

static void torture_rtmutex_unlock(void) __releases(torture_rtmutex)
{
	rt_mutex_unlock(&torture_rtmutex);
}

static struct lock_torture_ops rtmutex_lock_ops = {
	.writelock	= torture_rtmutex_lock,
	.write_delay	= torture_rtmutex_delay,
	.task_boost     = torture_rtmutex_boost,
	.writeunlock	= torture_rtmutex_unlock,
	.readlock       = NULL,
	.read_delay     = NULL,
	.readunlock     = NULL,
	.name		= "rtmutex_lock"
};
#endif

static DECLARE_RWSEM(torture_rwsem);
static int torture_rwsem_down_write(void) __acquires(torture_rwsem)
{
	down_write(&torture_rwsem);
	return 0;
}

static void torture_rwsem_write_delay(struct torture_random_state *trsp)
{
	const unsigned long longdelay_ms = 100;

	/* We want a long delay occasionally to force massive contention.  */
	if (!(torture_random(trsp) %
	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
		mdelay(longdelay_ms * 10);
	else
		mdelay(longdelay_ms / 10);
	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
		torture_preempt_schedule();  /* Allow test to be preempted. */
}

static void torture_rwsem_up_write(void) __releases(torture_rwsem)
{
	up_write(&torture_rwsem);
}

static int torture_rwsem_down_read(void) __acquires(torture_rwsem)
{
	down_read(&torture_rwsem);
	return 0;
}

static void torture_rwsem_read_delay(struct torture_random_state *trsp)
{
	const unsigned long longdelay_ms = 100;

	/* We want a long delay occasionally to force massive contention.  */
	if (!(torture_random(trsp) %
	      (cxt.nrealreaders_stress * 2000 * longdelay_ms)))
		mdelay(longdelay_ms * 2);
	else
		mdelay(longdelay_ms / 2);
	if (!(torture_random(trsp) % (cxt.nrealreaders_stress * 20000)))
		torture_preempt_schedule();  /* Allow test to be preempted. */
}

static void torture_rwsem_up_read(void) __releases(torture_rwsem)
{
	up_read(&torture_rwsem);
}

static struct lock_torture_ops rwsem_lock_ops = {
	.writelock	= torture_rwsem_down_write,
	.write_delay	= torture_rwsem_write_delay,
	.task_boost     = torture_boost_dummy,
	.writeunlock	= torture_rwsem_up_write,
	.readlock       = torture_rwsem_down_read,
	.read_delay     = torture_rwsem_read_delay,
	.readunlock     = torture_rwsem_up_read,
	.name		= "rwsem_lock"
};

#include <linux/percpu-rwsem.h>
static struct percpu_rw_semaphore pcpu_rwsem;

void torture_percpu_rwsem_init(void)
{
	BUG_ON(percpu_init_rwsem(&pcpu_rwsem));
}

static int torture_percpu_rwsem_down_write(void) __acquires(pcpu_rwsem)
{
	percpu_down_write(&pcpu_rwsem);
	return 0;
}

static void torture_percpu_rwsem_up_write(void) __releases(pcpu_rwsem)
{
	percpu_up_write(&pcpu_rwsem);
}

static int torture_percpu_rwsem_down_read(void) __acquires(pcpu_rwsem)
{
	percpu_down_read(&pcpu_rwsem);
	return 0;
}

static void torture_percpu_rwsem_up_read(void) __releases(pcpu_rwsem)
{
	percpu_up_read(&pcpu_rwsem);
}

static struct lock_torture_ops percpu_rwsem_lock_ops = {
	.init		= torture_percpu_rwsem_init,
	.writelock	= torture_percpu_rwsem_down_write,
	.write_delay	= torture_rwsem_write_delay,
	.task_boost     = torture_boost_dummy,
	.writeunlock	= torture_percpu_rwsem_up_write,
	.readlock       = torture_percpu_rwsem_down_read,
	.read_delay     = torture_rwsem_read_delay,
	.readunlock     = torture_percpu_rwsem_up_read,
	.name		= "percpu_rwsem_lock"
};

/*
 * Lock torture writer kthread.  Repeatedly acquires and releases
 * the lock, checking for duplicate acquisitions.
 */
static int lock_torture_writer(void *arg)
{
	struct lock_stress_stats *lwsp = arg;
	static DEFINE_TORTURE_RANDOM(rand);

	VERBOSE_TOROUT_STRING("lock_torture_writer task started");
	set_user_nice(current, MAX_NICE);

	do {
		if ((torture_random(&rand) & 0xfffff) == 0)
			schedule_timeout_uninterruptible(1);

		cxt.cur_ops->task_boost(&rand);
		cxt.cur_ops->writelock();
		if (WARN_ON_ONCE(lock_is_write_held))
			lwsp->n_lock_fail++;
		lock_is_write_held = 1;
		if (WARN_ON_ONCE(lock_is_read_held))
			lwsp->n_lock_fail++; /* rare, but... */

		lwsp->n_lock_acquired++;
		cxt.cur_ops->write_delay(&rand);
		lock_is_write_held = 0;
		cxt.cur_ops->writeunlock();

		stutter_wait("lock_torture_writer");
	} while (!torture_must_stop());

	cxt.cur_ops->task_boost(NULL); /* reset prio */
	torture_kthread_stopping("lock_torture_writer");
	return 0;
}

/*
 * Lock torture reader kthread.  Repeatedly acquires and releases
 * the reader lock.
 */
static int lock_torture_reader(void *arg)
{
	struct lock_stress_stats *lrsp = arg;
	static DEFINE_TORTURE_RANDOM(rand);

	VERBOSE_TOROUT_STRING("lock_torture_reader task started");
	set_user_nice(current, MAX_NICE);

	do {
		if ((torture_random(&rand) & 0xfffff) == 0)
			schedule_timeout_uninterruptible(1);

		cxt.cur_ops->readlock();
		lock_is_read_held = 1;
		if (WARN_ON_ONCE(lock_is_write_held))
			lrsp->n_lock_fail++; /* rare, but... */

		lrsp->n_lock_acquired++;
		cxt.cur_ops->read_delay(&rand);
		lock_is_read_held = 0;
		cxt.cur_ops->readunlock();

		stutter_wait("lock_torture_reader");
	} while (!torture_must_stop());
	torture_kthread_stopping("lock_torture_reader");
	return 0;
}

/*
 * Create an lock-torture-statistics message in the specified buffer.
 */
static void __torture_print_stats(char *page,
				  struct lock_stress_stats *statp, bool write)
{
	bool fail = 0;
	int i, n_stress;
	long max = 0, min = statp ? statp[0].n_lock_acquired : 0;
	long long sum = 0;

	n_stress = write ? cxt.nrealwriters_stress : cxt.nrealreaders_stress;
	for (i = 0; i < n_stress; i++) {
		if (statp[i].n_lock_fail)
			fail = true;
		sum += statp[i].n_lock_acquired;
		if (max < statp[i].n_lock_fail)
			max = statp[i].n_lock_fail;
		if (min > statp[i].n_lock_fail)
			min = statp[i].n_lock_fail;
	}
	page += sprintf(page,
			"%s:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
			write ? "Writes" : "Reads ",
			sum, max, min, max / 2 > min ? "???" : "",
			fail, fail ? "!!!" : "");
	if (fail)
		atomic_inc(&cxt.n_lock_torture_errors);
}

/*
 * Print torture statistics.  Caller must ensure that there is only one
 * call to this function at a given time!!!  This is normally accomplished
 * by relying on the module system to only have one copy of the module
 * loaded, and then by giving the lock_torture_stats kthread full control
 * (or the init/cleanup functions when lock_torture_stats thread is not
 * running).
 */
static void lock_torture_stats_print(void)
{
	int size = cxt.nrealwriters_stress * 200 + 8192;
	char *buf;

	if (cxt.cur_ops->readlock)
		size += cxt.nrealreaders_stress * 200 + 8192;

	buf = kmalloc(size, GFP_KERNEL);
	if (!buf) {
		pr_err("lock_torture_stats_print: Out of memory, need: %d",
		       size);
		return;
	}

	__torture_print_stats(buf, cxt.lwsa, true);
	pr_alert("%s", buf);
	kfree(buf);

	if (cxt.cur_ops->readlock) {
		buf = kmalloc(size, GFP_KERNEL);
		if (!buf) {
			pr_err("lock_torture_stats_print: Out of memory, need: %d",
			       size);
			return;
		}

		__torture_print_stats(buf, cxt.lrsa, false);
		pr_alert("%s", buf);
		kfree(buf);
	}
}

/*
 * Periodically prints torture statistics, if periodic statistics printing
 * was specified via the stat_interval module parameter.
 *
 * No need to worry about fullstop here, since this one doesn't reference
 * volatile state or register callbacks.
 */
static int lock_torture_stats(void *arg)
{
	VERBOSE_TOROUT_STRING("lock_torture_stats task started");
	do {
		schedule_timeout_interruptible(stat_interval * HZ);
		lock_torture_stats_print();
		torture_shutdown_absorb("lock_torture_stats");
	} while (!torture_must_stop());
	torture_kthread_stopping("lock_torture_stats");
	return 0;
}

static inline void
lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
				const char *tag)
{
	pr_alert("%s" TORTURE_FLAG
		 "--- %s%s: nwriters_stress=%d nreaders_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
		 torture_type, tag, cxt.debug_lock ? " [debug]": "",
		 cxt.nrealwriters_stress, cxt.nrealreaders_stress, stat_interval,
		 verbose, shuffle_interval, stutter, shutdown_secs,
		 onoff_interval, onoff_holdoff);
}

static void lock_torture_cleanup(void)
{
	int i;

	if (torture_cleanup_begin())
		return;

	/*
	 * Indicates early cleanup, meaning that the test has not run,
	 * such as when passing bogus args when loading the module. As
	 * such, only perform the underlying torture-specific cleanups,
	 * and avoid anything related to locktorture.
	 */
	if (!cxt.lwsa && !cxt.lrsa)
		goto end;

	if (writer_tasks) {
		for (i = 0; i < cxt.nrealwriters_stress; i++)
			torture_stop_kthread(lock_torture_writer,
					     writer_tasks[i]);
		kfree(writer_tasks);
		writer_tasks = NULL;
	}

	if (reader_tasks) {
		for (i = 0; i < cxt.nrealreaders_stress; i++)
			torture_stop_kthread(lock_torture_reader,
					     reader_tasks[i]);
		kfree(reader_tasks);
		reader_tasks = NULL;
	}

	torture_stop_kthread(lock_torture_stats, stats_task);
	lock_torture_stats_print();  /* -After- the stats thread is stopped! */

	if (atomic_read(&cxt.n_lock_torture_errors))
		lock_torture_print_module_parms(cxt.cur_ops,
						"End of test: FAILURE");
	else if (torture_onoff_failures())
		lock_torture_print_module_parms(cxt.cur_ops,
						"End of test: LOCK_HOTPLUG");
	else
		lock_torture_print_module_parms(cxt.cur_ops,
						"End of test: SUCCESS");

	kfree(cxt.lwsa);
	kfree(cxt.lrsa);

end:
	torture_cleanup_end();
}

static int __init lock_torture_init(void)
{
	int i, j;
	int firsterr = 0;
	static struct lock_torture_ops *torture_ops[] = {
		&lock_busted_ops,
		&spin_lock_ops, &spin_lock_irq_ops,
		&rw_lock_ops, &rw_lock_irq_ops,
		&mutex_lock_ops,
		&ww_mutex_lock_ops,
#ifdef CONFIG_RT_MUTEXES
		&rtmutex_lock_ops,
#endif
		&rwsem_lock_ops,
		&percpu_rwsem_lock_ops,
	};

	if (!torture_init_begin(torture_type, verbose))
		return -EBUSY;

	/* Process args and tell the world that the torturer is on the job. */
	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
		cxt.cur_ops = torture_ops[i];
		if (strcmp(torture_type, cxt.cur_ops->name) == 0)
			break;
	}
	if (i == ARRAY_SIZE(torture_ops)) {
		pr_alert("lock-torture: invalid torture type: \"%s\"\n",
			 torture_type);
		pr_alert("lock-torture types:");
		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
			pr_alert(" %s", torture_ops[i]->name);
		pr_alert("\n");
		firsterr = -EINVAL;
		goto unwind;
	}

	if (nwriters_stress == 0 && nreaders_stress == 0) {
		pr_alert("lock-torture: must run at least one locking thread\n");
		firsterr = -EINVAL;
		goto unwind;
	}

	if (cxt.cur_ops->init)
		cxt.cur_ops->init();

	if (nwriters_stress >= 0)
		cxt.nrealwriters_stress = nwriters_stress;
	else
		cxt.nrealwriters_stress = 2 * num_online_cpus();

#ifdef CONFIG_DEBUG_MUTEXES
	if (strncmp(torture_type, "mutex", 5) == 0)
		cxt.debug_lock = true;
#endif
#ifdef CONFIG_DEBUG_RT_MUTEXES
	if (strncmp(torture_type, "rtmutex", 7) == 0)
		cxt.debug_lock = true;
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
	if ((strncmp(torture_type, "spin", 4) == 0) ||
	    (strncmp(torture_type, "rw_lock", 7) == 0))
		cxt.debug_lock = true;
#endif

	/* Initialize the statistics so that each run gets its own numbers. */
	if (nwriters_stress) {
		lock_is_write_held = 0;
		cxt.lwsa = kmalloc_array(cxt.nrealwriters_stress,
					 sizeof(*cxt.lwsa),
					 GFP_KERNEL);
		if (cxt.lwsa == NULL) {
			VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory");
			firsterr = -ENOMEM;
			goto unwind;
		}

		for (i = 0; i < cxt.nrealwriters_stress; i++) {
			cxt.lwsa[i].n_lock_fail = 0;
			cxt.lwsa[i].n_lock_acquired = 0;
		}
	}

	if (cxt.cur_ops->readlock) {
		if (nreaders_stress >= 0)
			cxt.nrealreaders_stress = nreaders_stress;
		else {
			/*
			 * By default distribute evenly the number of
			 * readers and writers. We still run the same number
			 * of threads as the writer-only locks default.
			 */
			if (nwriters_stress < 0) /* user doesn't care */
				cxt.nrealwriters_stress = num_online_cpus();
			cxt.nrealreaders_stress = cxt.nrealwriters_stress;
		}

		if (nreaders_stress) {
			lock_is_read_held = 0;
			cxt.lrsa = kmalloc_array(cxt.nrealreaders_stress,
						 sizeof(*cxt.lrsa),
						 GFP_KERNEL);
			if (cxt.lrsa == NULL) {
				VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory");
				firsterr = -ENOMEM;
				kfree(cxt.lwsa);
				cxt.lwsa = NULL;
				goto unwind;
			}

			for (i = 0; i < cxt.nrealreaders_stress; i++) {
				cxt.lrsa[i].n_lock_fail = 0;
				cxt.lrsa[i].n_lock_acquired = 0;
			}
		}
	}

	lock_torture_print_module_parms(cxt.cur_ops, "Start of test");

	/* Prepare torture context. */
	if (onoff_interval > 0) {
		firsterr = torture_onoff_init(onoff_holdoff * HZ,
					      onoff_interval * HZ);
		if (firsterr)
			goto unwind;
	}
	if (shuffle_interval > 0) {
		firsterr = torture_shuffle_init(shuffle_interval);
		if (firsterr)
			goto unwind;
	}
	if (shutdown_secs > 0) {
		firsterr = torture_shutdown_init(shutdown_secs,
						 lock_torture_cleanup);
		if (firsterr)
			goto unwind;
	}
	if (stutter > 0) {
		firsterr = torture_stutter_init(stutter);
		if (firsterr)
			goto unwind;
	}

	if (nwriters_stress) {
		writer_tasks = kcalloc(cxt.nrealwriters_stress,
				       sizeof(writer_tasks[0]),
				       GFP_KERNEL);
		if (writer_tasks == NULL) {
			VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
			firsterr = -ENOMEM;
			goto unwind;
		}
	}

	if (cxt.cur_ops->readlock) {
		reader_tasks = kcalloc(cxt.nrealreaders_stress,
				       sizeof(reader_tasks[0]),
				       GFP_KERNEL);
		if (reader_tasks == NULL) {
			VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
			kfree(writer_tasks);
			writer_tasks = NULL;
			firsterr = -ENOMEM;
			goto unwind;
		}
	}

	/*
	 * Create the kthreads and start torturing (oh, those poor little locks).
	 *
	 * TODO: Note that we interleave writers with readers, giving writers a
	 * slight advantage, by creating its kthread first. This can be modified
	 * for very specific needs, or even let the user choose the policy, if
	 * ever wanted.
	 */
	for (i = 0, j = 0; i < cxt.nrealwriters_stress ||
		    j < cxt.nrealreaders_stress; i++, j++) {
		if (i >= cxt.nrealwriters_stress)
			goto create_reader;

		/* Create writer. */
		firsterr = torture_create_kthread(lock_torture_writer, &cxt.lwsa[i],
						  writer_tasks[i]);
		if (firsterr)
			goto unwind;

	create_reader:
		if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress))
			continue;
		/* Create reader. */
		firsterr = torture_create_kthread(lock_torture_reader, &cxt.lrsa[j],
						  reader_tasks[j]);
		if (firsterr)
			goto unwind;
	}
	if (stat_interval > 0) {
		firsterr = torture_create_kthread(lock_torture_stats, NULL,
						  stats_task);
		if (firsterr)
			goto unwind;
	}
	torture_init_end();
	return 0;

unwind:
	torture_init_end();
	lock_torture_cleanup();
	return firsterr;
}

module_init(lock_torture_init);
module_exit(lock_torture_cleanup);