summaryrefslogtreecommitdiffstats
path: root/kernel/workqueue.c
blob: 68e4dd808ec076b91bc9cfcd32625e5dea5f963d (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
/*
 * linux/kernel/workqueue.c
 *
 * Generic mechanism for defining kernel helper threads for running
 * arbitrary tasks in process context.
 *
 * Started by Ingo Molnar, Copyright (C) 2002
 *
 * Derived from the taskqueue/keventd code by:
 *
 *   David Woodhouse <dwmw2@infradead.org>
 *   Andrew Morton
 *   Kai Petzke <wpp@marie.physik.tu-berlin.de>
 *   Theodore Ts'o <tytso@mit.edu>
 *
 * Made to use alloc_percpu by Christoph Lameter.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/completion.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/kthread.h>
#include <linux/hardirq.h>
#include <linux/mempolicy.h>
#include <linux/freezer.h>
#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
#define CREATE_TRACE_POINTS
#include <trace/events/workqueue.h>

/*
 * Structure fields follow one of the following exclusion rules.
 *
 * I: Set during initialization and read-only afterwards.
 *
 * L: cwq->lock protected.  Access with cwq->lock held.
 *
 * W: workqueue_lock protected.
 */

/*
 * The per-CPU workqueue (if single thread, we always use the first
 * possible cpu).
 */
struct cpu_workqueue_struct {

	spinlock_t lock;

	struct list_head worklist;
	wait_queue_head_t more_work;
	struct work_struct *current_work;

	struct workqueue_struct *wq;		/* I: the owning workqueue */
	struct task_struct	*thread;
} ____cacheline_aligned;

/*
 * The externally visible workqueue abstraction is an array of
 * per-CPU workqueues:
 */
struct workqueue_struct {
	unsigned int		flags;		/* I: WQ_* flags */
	struct cpu_workqueue_struct *cpu_wq;	/* I: cwq's */
	struct list_head	list;		/* W: list of all workqueues */
	const char		*name;		/* I: workqueue name */
#ifdef CONFIG_LOCKDEP
	struct lockdep_map	lockdep_map;
#endif
};

#ifdef CONFIG_DEBUG_OBJECTS_WORK

static struct debug_obj_descr work_debug_descr;

/*
 * fixup_init is called when:
 * - an active object is initialized
 */
static int work_fixup_init(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		cancel_work_sync(work);
		debug_object_init(work, &work_debug_descr);
		return 1;
	default:
		return 0;
	}
}

/*
 * fixup_activate is called when:
 * - an active object is activated
 * - an unknown object is activated (might be a statically initialized object)
 */
static int work_fixup_activate(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {

	case ODEBUG_STATE_NOTAVAILABLE:
		/*
		 * This is not really a fixup. The work struct was
		 * statically initialized. We just make sure that it
		 * is tracked in the object tracker.
		 */
		if (test_bit(WORK_STRUCT_STATIC, work_data_bits(work))) {
			debug_object_init(work, &work_debug_descr);
			debug_object_activate(work, &work_debug_descr);
			return 0;
		}
		WARN_ON_ONCE(1);
		return 0;

	case ODEBUG_STATE_ACTIVE:
		WARN_ON(1);

	default:
		return 0;
	}
}

/*
 * fixup_free is called when:
 * - an active object is freed
 */
static int work_fixup_free(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		cancel_work_sync(work);
		debug_object_free(work, &work_debug_descr);
		return 1;
	default:
		return 0;
	}
}

static struct debug_obj_descr work_debug_descr = {
	.name		= "work_struct",
	.fixup_init	= work_fixup_init,
	.fixup_activate	= work_fixup_activate,
	.fixup_free	= work_fixup_free,
};

static inline void debug_work_activate(struct work_struct *work)
{
	debug_object_activate(work, &work_debug_descr);
}

static inline void debug_work_deactivate(struct work_struct *work)
{
	debug_object_deactivate(work, &work_debug_descr);
}

void __init_work(struct work_struct *work, int onstack)
{
	if (onstack)
		debug_object_init_on_stack(work, &work_debug_descr);
	else
		debug_object_init(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(__init_work);

void destroy_work_on_stack(struct work_struct *work)
{
	debug_object_free(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_work_on_stack);

#else
static inline void debug_work_activate(struct work_struct *work) { }
static inline void debug_work_deactivate(struct work_struct *work) { }
#endif

/* Serializes the accesses to the list of workqueues. */
static DEFINE_SPINLOCK(workqueue_lock);
static LIST_HEAD(workqueues);

static int singlethread_cpu __read_mostly;
static const struct cpumask *cpu_singlethread_map __read_mostly;
/*
 * _cpu_down() first removes CPU from cpu_online_map, then CPU_DEAD
 * flushes cwq->worklist. This means that flush_workqueue/wait_on_work
 * which comes in between can't use for_each_online_cpu(). We could
 * use cpu_possible_map, the cpumask below is more a documentation
 * than optimization.
 */
static cpumask_var_t cpu_populated_map __read_mostly;

/* If it's single threaded, it isn't in the list of workqueues. */
static inline bool is_wq_single_threaded(struct workqueue_struct *wq)
{
	return wq->flags & WQ_SINGLE_THREAD;
}

static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq)
{
	return is_wq_single_threaded(wq)
		? cpu_singlethread_map : cpu_populated_map;
}

static struct cpu_workqueue_struct *get_cwq(unsigned int cpu,
					    struct workqueue_struct *wq)
{
	if (unlikely(is_wq_single_threaded(wq)))
		cpu = singlethread_cpu;
	return per_cpu_ptr(wq->cpu_wq, cpu);
}

/*
 * Set the workqueue on which a work item is to be run
 * - Must *only* be called if the pending flag is set
 */
static inline void set_wq_data(struct work_struct *work,
			       struct cpu_workqueue_struct *cwq,
			       unsigned long extra_flags)
{
	BUG_ON(!work_pending(work));

	atomic_long_set(&work->data, (unsigned long)cwq | work_static(work) |
			(1UL << WORK_STRUCT_PENDING) | extra_flags);
}

/*
 * Clear WORK_STRUCT_PENDING and the workqueue on which it was queued.
 */
static inline void clear_wq_data(struct work_struct *work)
{
	atomic_long_set(&work->data, work_static(work));
}

static inline
struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
{
	return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK);
}

/**
 * insert_work - insert a work into cwq
 * @cwq: cwq @work belongs to
 * @work: work to insert
 * @head: insertion point
 * @extra_flags: extra WORK_STRUCT_* flags to set
 *
 * Insert @work into @cwq after @head.
 *
 * CONTEXT:
 * spin_lock_irq(cwq->lock).
 */
static void insert_work(struct cpu_workqueue_struct *cwq,
			struct work_struct *work, struct list_head *head,
			unsigned int extra_flags)
{
	trace_workqueue_insertion(cwq->thread, work);

	/* we own @work, set data and link */
	set_wq_data(work, cwq, extra_flags);

	/*
	 * Ensure that we get the right work->data if we see the
	 * result of list_add() below, see try_to_grab_pending().
	 */
	smp_wmb();

	list_add_tail(&work->entry, head);
	wake_up(&cwq->more_work);
}

static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
			 struct work_struct *work)
{
	struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
	unsigned long flags;

	debug_work_activate(work);
	spin_lock_irqsave(&cwq->lock, flags);
	BUG_ON(!list_empty(&work->entry));
	insert_work(cwq, work, &cwq->worklist, 0);
	spin_unlock_irqrestore(&cwq->lock, flags);
}

/**
 * queue_work - queue work on a workqueue
 * @wq: workqueue to use
 * @work: work to queue
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 *
 * We queue the work to the CPU on which it was submitted, but if the CPU dies
 * it can be processed by another CPU.
 */
int queue_work(struct workqueue_struct *wq, struct work_struct *work)
{
	int ret;

	ret = queue_work_on(get_cpu(), wq, work);
	put_cpu();

	return ret;
}
EXPORT_SYMBOL_GPL(queue_work);

/**
 * queue_work_on - queue work on specific cpu
 * @cpu: CPU number to execute work on
 * @wq: workqueue to use
 * @work: work to queue
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 *
 * We queue the work to a specific CPU, the caller must ensure it
 * can't go away.
 */
int
queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work)
{
	int ret = 0;

	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
		__queue_work(cpu, wq, work);
		ret = 1;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(queue_work_on);

static void delayed_work_timer_fn(unsigned long __data)
{
	struct delayed_work *dwork = (struct delayed_work *)__data;
	struct cpu_workqueue_struct *cwq = get_wq_data(&dwork->work);

	__queue_work(smp_processor_id(), cwq->wq, &dwork->work);
}

/**
 * queue_delayed_work - queue work on a workqueue after delay
 * @wq: workqueue to use
 * @dwork: delayable work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 */
int queue_delayed_work(struct workqueue_struct *wq,
			struct delayed_work *dwork, unsigned long delay)
{
	if (delay == 0)
		return queue_work(wq, &dwork->work);

	return queue_delayed_work_on(-1, wq, dwork, delay);
}
EXPORT_SYMBOL_GPL(queue_delayed_work);

/**
 * queue_delayed_work_on - queue work on specific CPU after delay
 * @cpu: CPU number to execute work on
 * @wq: workqueue to use
 * @dwork: work to queue
 * @delay: number of jiffies to wait before queueing
 *
 * Returns 0 if @work was already on a queue, non-zero otherwise.
 */
int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
			struct delayed_work *dwork, unsigned long delay)
{
	int ret = 0;
	struct timer_list *timer = &dwork->timer;
	struct work_struct *work = &dwork->work;

	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
		BUG_ON(timer_pending(timer));
		BUG_ON(!list_empty(&work->entry));

		timer_stats_timer_set_start_info(&dwork->timer);

		/* This stores cwq for the moment, for the timer_fn */
		set_wq_data(work, get_cwq(raw_smp_processor_id(), wq), 0);
		timer->expires = jiffies + delay;
		timer->data = (unsigned long)dwork;
		timer->function = delayed_work_timer_fn;

		if (unlikely(cpu >= 0))
			add_timer_on(timer, cpu);
		else
			add_timer(timer);
		ret = 1;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(queue_delayed_work_on);

static void run_workqueue(struct cpu_workqueue_struct *cwq)
{
	spin_lock_irq(&cwq->lock);
	while (!list_empty(&cwq->worklist)) {
		struct work_struct *work = list_entry(cwq->worklist.next,
						struct work_struct, entry);
		work_func_t f = work->func;
#ifdef CONFIG_LOCKDEP
		/*
		 * It is permissible to free the struct work_struct
		 * from inside the function that is called from it,
		 * this we need to take into account for lockdep too.
		 * To avoid bogus "held lock freed" warnings as well
		 * as problems when looking into work->lockdep_map,
		 * make a copy and use that here.
		 */
		struct lockdep_map lockdep_map = work->lockdep_map;
#endif
		trace_workqueue_execution(cwq->thread, work);
		debug_work_deactivate(work);
		cwq->current_work = work;
		list_del_init(cwq->worklist.next);
		spin_unlock_irq(&cwq->lock);

		BUG_ON(get_wq_data(work) != cwq);
		work_clear_pending(work);
		lock_map_acquire(&cwq->wq->lockdep_map);
		lock_map_acquire(&lockdep_map);
		f(work);
		lock_map_release(&lockdep_map);
		lock_map_release(&cwq->wq->lockdep_map);

		if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
			printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
					"%s/0x%08x/%d\n",
					current->comm, preempt_count(),
				       	task_pid_nr(current));
			printk(KERN_ERR "    last function: ");
			print_symbol("%s\n", (unsigned long)f);
			debug_show_held_locks(current);
			dump_stack();
		}

		spin_lock_irq(&cwq->lock);
		cwq->current_work = NULL;
	}
	spin_unlock_irq(&cwq->lock);
}

/**
 * worker_thread - the worker thread function
 * @__cwq: cwq to serve
 *
 * The cwq worker thread function.
 */
static int worker_thread(void *__cwq)
{
	struct cpu_workqueue_struct *cwq = __cwq;
	DEFINE_WAIT(wait);

	if (cwq->wq->flags & WQ_FREEZEABLE)
		set_freezable();

	for (;;) {
		prepare_to_wait(&cwq->more_work, &wait, TASK_INTERRUPTIBLE);
		if (!freezing(current) &&
		    !kthread_should_stop() &&
		    list_empty(&cwq->worklist))
			schedule();
		finish_wait(&cwq->more_work, &wait);

		try_to_freeze();

		if (kthread_should_stop())
			break;

		run_workqueue(cwq);
	}

	return 0;
}

struct wq_barrier {
	struct work_struct	work;
	struct completion	done;
};

static void wq_barrier_func(struct work_struct *work)
{
	struct wq_barrier *barr = container_of(work, struct wq_barrier, work);
	complete(&barr->done);
}

/**
 * insert_wq_barrier - insert a barrier work
 * @cwq: cwq to insert barrier into
 * @barr: wq_barrier to insert
 * @head: insertion point
 *
 * Insert barrier @barr into @cwq before @head.
 *
 * CONTEXT:
 * spin_lock_irq(cwq->lock).
 */
static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
			struct wq_barrier *barr, struct list_head *head)
{
	/*
	 * debugobject calls are safe here even with cwq->lock locked
	 * as we know for sure that this will not trigger any of the
	 * checks and call back into the fixup functions where we
	 * might deadlock.
	 */
	INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
	__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
	init_completion(&barr->done);

	debug_work_activate(&barr->work);
	insert_work(cwq, &barr->work, head, 0);
}

static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
{
	int active = 0;
	struct wq_barrier barr;

	WARN_ON(cwq->thread == current);

	spin_lock_irq(&cwq->lock);
	if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
		insert_wq_barrier(cwq, &barr, &cwq->worklist);
		active = 1;
	}
	spin_unlock_irq(&cwq->lock);

	if (active) {
		wait_for_completion(&barr.done);
		destroy_work_on_stack(&barr.work);
	}

	return active;
}

/**
 * flush_workqueue - ensure that any scheduled work has run to completion.
 * @wq: workqueue to flush
 *
 * Forces execution of the workqueue and blocks until its completion.
 * This is typically used in driver shutdown handlers.
 *
 * We sleep until all works which were queued on entry have been handled,
 * but we are not livelocked by new incoming ones.
 */
void flush_workqueue(struct workqueue_struct *wq)
{
	const struct cpumask *cpu_map = wq_cpu_map(wq);
	int cpu;

	might_sleep();
	lock_map_acquire(&wq->lockdep_map);
	lock_map_release(&wq->lockdep_map);
	for_each_cpu(cpu, cpu_map)
		flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
}
EXPORT_SYMBOL_GPL(flush_workqueue);

/**
 * flush_work - block until a work_struct's callback has terminated
 * @work: the work which is to be flushed
 *
 * Returns false if @work has already terminated.
 *
 * It is expected that, prior to calling flush_work(), the caller has
 * arranged for the work to not be requeued, otherwise it doesn't make
 * sense to use this function.
 */
int flush_work(struct work_struct *work)
{
	struct cpu_workqueue_struct *cwq;
	struct list_head *prev;
	struct wq_barrier barr;

	might_sleep();
	cwq = get_wq_data(work);
	if (!cwq)
		return 0;

	lock_map_acquire(&cwq->wq->lockdep_map);
	lock_map_release(&cwq->wq->lockdep_map);

	spin_lock_irq(&cwq->lock);
	if (!list_empty(&work->entry)) {
		/*
		 * See the comment near try_to_grab_pending()->smp_rmb().
		 * If it was re-queued under us we are not going to wait.
		 */
		smp_rmb();
		if (unlikely(cwq != get_wq_data(work)))
			goto already_gone;
		prev = &work->entry;
	} else {
		if (cwq->current_work != work)
			goto already_gone;
		prev = &cwq->worklist;
	}
	insert_wq_barrier(cwq, &barr, prev->next);

	spin_unlock_irq(&cwq->lock);
	wait_for_completion(&barr.done);
	destroy_work_on_stack(&barr.work);
	return 1;
already_gone:
	spin_unlock_irq(&cwq->lock);
	return 0;
}
EXPORT_SYMBOL_GPL(flush_work);

/*
 * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
 * so this work can't be re-armed in any way.
 */
static int try_to_grab_pending(struct work_struct *work)
{
	struct cpu_workqueue_struct *cwq;
	int ret = -1;

	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work)))
		return 0;

	/*
	 * The queueing is in progress, or it is already queued. Try to
	 * steal it from ->worklist without clearing WORK_STRUCT_PENDING.
	 */

	cwq = get_wq_data(work);
	if (!cwq)
		return ret;

	spin_lock_irq(&cwq->lock);
	if (!list_empty(&work->entry)) {
		/*
		 * This work is queued, but perhaps we locked the wrong cwq.
		 * In that case we must see the new value after rmb(), see
		 * insert_work()->wmb().
		 */
		smp_rmb();
		if (cwq == get_wq_data(work)) {
			debug_work_deactivate(work);
			list_del_init(&work->entry);
			ret = 1;
		}
	}
	spin_unlock_irq(&cwq->lock);

	return ret;
}

static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
				struct work_struct *work)
{
	struct wq_barrier barr;
	int running = 0;

	spin_lock_irq(&cwq->lock);
	if (unlikely(cwq->current_work == work)) {
		insert_wq_barrier(cwq, &barr, cwq->worklist.next);
		running = 1;
	}
	spin_unlock_irq(&cwq->lock);

	if (unlikely(running)) {
		wait_for_completion(&barr.done);
		destroy_work_on_stack(&barr.work);
	}
}

static void wait_on_work(struct work_struct *work)
{
	struct cpu_workqueue_struct *cwq;
	struct workqueue_struct *wq;
	const struct cpumask *cpu_map;
	int cpu;

	might_sleep();

	lock_map_acquire(&work->lockdep_map);
	lock_map_release(&work->lockdep_map);

	cwq = get_wq_data(work);
	if (!cwq)
		return;

	wq = cwq->wq;
	cpu_map = wq_cpu_map(wq);

	for_each_cpu(cpu, cpu_map)
		wait_on_cpu_work(get_cwq(cpu, wq), work);
}

static int __cancel_work_timer(struct work_struct *work,
				struct timer_list* timer)
{
	int ret;

	do {
		ret = (timer && likely(del_timer(timer)));
		if (!ret)
			ret = try_to_grab_pending(work);
		wait_on_work(work);
	} while (unlikely(ret < 0));

	clear_wq_data(work);
	return ret;
}

/**
 * cancel_work_sync - block until a work_struct's callback has terminated
 * @work: the work which is to be flushed
 *
 * Returns true if @work was pending.
 *
 * cancel_work_sync() will cancel the work if it is queued. If the work's
 * callback appears to be running, cancel_work_sync() will block until it
 * has completed.
 *
 * It is possible to use this function if the work re-queues itself. It can
 * cancel the work even if it migrates to another workqueue, however in that
 * case it only guarantees that work->func() has completed on the last queued
 * workqueue.
 *
 * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not
 * pending, otherwise it goes into a busy-wait loop until the timer expires.
 *
 * The caller must ensure that workqueue_struct on which this work was last
 * queued can't be destroyed before this function returns.
 */
int cancel_work_sync(struct work_struct *work)
{
	return __cancel_work_timer(work, NULL);
}
EXPORT_SYMBOL_GPL(cancel_work_sync);

/**
 * cancel_delayed_work_sync - reliably kill off a delayed work.
 * @dwork: the delayed work struct
 *
 * Returns true if @dwork was pending.
 *
 * It is possible to use this function if @dwork rearms itself via queue_work()
 * or queue_delayed_work(). See also the comment for cancel_work_sync().
 */
int cancel_delayed_work_sync(struct delayed_work *dwork)
{
	return __cancel_work_timer(&dwork->work, &dwork->timer);
}
EXPORT_SYMBOL(cancel_delayed_work_sync);

static struct workqueue_struct *keventd_wq __read_mostly;

/**
 * schedule_work - put work task in global workqueue
 * @work: job to be done
 *
 * Returns zero if @work was already on the kernel-global workqueue and
 * non-zero otherwise.
 *
 * This puts a job in the kernel-global workqueue if it was not already
 * queued and leaves it in the same position on the kernel-global
 * workqueue otherwise.
 */
int schedule_work(struct work_struct *work)
{
	return queue_work(keventd_wq, work);
}
EXPORT_SYMBOL(schedule_work);

/*
 * schedule_work_on - put work task on a specific cpu
 * @cpu: cpu to put the work task on
 * @work: job to be done
 *
 * This puts a job on a specific cpu
 */
int schedule_work_on(int cpu, struct work_struct *work)
{
	return queue_work_on(cpu, keventd_wq, work);
}
EXPORT_SYMBOL(schedule_work_on);

/**
 * schedule_delayed_work - put work task in global workqueue after delay
 * @dwork: job to be done
 * @delay: number of jiffies to wait or 0 for immediate execution
 *
 * After waiting for a given time this puts a job in the kernel-global
 * workqueue.
 */
int schedule_delayed_work(struct delayed_work *dwork,
					unsigned long delay)
{
	return queue_delayed_work(keventd_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work);

/**
 * flush_delayed_work - block until a dwork_struct's callback has terminated
 * @dwork: the delayed work which is to be flushed
 *
 * Any timeout is cancelled, and any pending work is run immediately.
 */
void flush_delayed_work(struct delayed_work *dwork)
{
	if (del_timer_sync(&dwork->timer)) {
		__queue_work(get_cpu(), get_wq_data(&dwork->work)->wq,
			     &dwork->work);
		put_cpu();
	}
	flush_work(&dwork->work);
}
EXPORT_SYMBOL(flush_delayed_work);

/**
 * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
 * @cpu: cpu to use
 * @dwork: job to be done
 * @delay: number of jiffies to wait
 *
 * After waiting for a given time this puts a job in the kernel-global
 * workqueue on the specified CPU.
 */
int schedule_delayed_work_on(int cpu,
			struct delayed_work *dwork, unsigned long delay)
{
	return queue_delayed_work_on(cpu, keventd_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work_on);

/**
 * schedule_on_each_cpu - call a function on each online CPU from keventd
 * @func: the function to call
 *
 * Returns zero on success.
 * Returns -ve errno on failure.
 *
 * schedule_on_each_cpu() is very slow.
 */
int schedule_on_each_cpu(work_func_t func)
{
	int cpu;
	int orig = -1;
	struct work_struct *works;

	works = alloc_percpu(struct work_struct);
	if (!works)
		return -ENOMEM;

	get_online_cpus();

	/*
	 * When running in keventd don't schedule a work item on
	 * itself.  Can just call directly because the work queue is
	 * already bound.  This also is faster.
	 */
	if (current_is_keventd())
		orig = raw_smp_processor_id();

	for_each_online_cpu(cpu) {
		struct work_struct *work = per_cpu_ptr(works, cpu);

		INIT_WORK(work, func);
		if (cpu != orig)
			schedule_work_on(cpu, work);
	}
	if (orig >= 0)
		func(per_cpu_ptr(works, orig));

	for_each_online_cpu(cpu)
		flush_work(per_cpu_ptr(works, cpu));

	put_online_cpus();
	free_percpu(works);
	return 0;
}

/**
 * flush_scheduled_work - ensure that any scheduled work has run to completion.
 *
 * Forces execution of the kernel-global workqueue and blocks until its
 * completion.
 *
 * Think twice before calling this function!  It's very easy to get into
 * trouble if you don't take great care.  Either of the following situations
 * will lead to deadlock:
 *
 *	One of the work items currently on the workqueue needs to acquire
 *	a lock held by your code or its caller.
 *
 *	Your code is running in the context of a work routine.
 *
 * They will be detected by lockdep when they occur, but the first might not
 * occur very often.  It depends on what work items are on the workqueue and
 * what locks they need, which you have no control over.
 *
 * In most situations flushing the entire workqueue is overkill; you merely
 * need to know that a particular work item isn't queued and isn't running.
 * In such cases you should use cancel_delayed_work_sync() or
 * cancel_work_sync() instead.
 */
void flush_scheduled_work(void)
{
	flush_workqueue(keventd_wq);
}
EXPORT_SYMBOL(flush_scheduled_work);

/**
 * execute_in_process_context - reliably execute the routine with user context
 * @fn:		the function to execute
 * @ew:		guaranteed storage for the execute work structure (must
 *		be available when the work executes)
 *
 * Executes the function immediately if process context is available,
 * otherwise schedules the function for delayed execution.
 *
 * Returns:	0 - function was executed
 *		1 - function was scheduled for execution
 */
int execute_in_process_context(work_func_t fn, struct execute_work *ew)
{
	if (!in_interrupt()) {
		fn(&ew->work);
		return 0;
	}

	INIT_WORK(&ew->work, fn);
	schedule_work(&ew->work);

	return 1;
}
EXPORT_SYMBOL_GPL(execute_in_process_context);

int keventd_up(void)
{
	return keventd_wq != NULL;
}

int current_is_keventd(void)
{
	struct cpu_workqueue_struct *cwq;
	int cpu = raw_smp_processor_id(); /* preempt-safe: keventd is per-cpu */
	int ret = 0;

	BUG_ON(!keventd_wq);

	cwq = per_cpu_ptr(keventd_wq->cpu_wq, cpu);
	if (current == cwq->thread)
		ret = 1;

	return ret;

}

static struct cpu_workqueue_struct *
init_cpu_workqueue(struct workqueue_struct *wq, int cpu)
{
	struct cpu_workqueue_struct *cwq = per_cpu_ptr(wq->cpu_wq, cpu);

	cwq->wq = wq;
	spin_lock_init(&cwq->lock);
	INIT_LIST_HEAD(&cwq->worklist);
	init_waitqueue_head(&cwq->more_work);

	return cwq;
}

static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
{
	struct workqueue_struct *wq = cwq->wq;
	const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d";
	struct task_struct *p;

	p = kthread_create(worker_thread, cwq, fmt, wq->name, cpu);
	/*
	 * Nobody can add the work_struct to this cwq,
	 *	if (caller is __create_workqueue)
	 *		nobody should see this wq
	 *	else // caller is CPU_UP_PREPARE
	 *		cpu is not on cpu_online_map
	 * so we can abort safely.
	 */
	if (IS_ERR(p))
		return PTR_ERR(p);
	cwq->thread = p;

	trace_workqueue_creation(cwq->thread, cpu);

	return 0;
}

static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
{
	struct task_struct *p = cwq->thread;

	if (p != NULL) {
		if (cpu >= 0)
			kthread_bind(p, cpu);
		wake_up_process(p);
	}
}

struct workqueue_struct *__create_workqueue_key(const char *name,
						unsigned int flags,
						struct lock_class_key *key,
						const char *lock_name)
{
	struct workqueue_struct *wq;
	struct cpu_workqueue_struct *cwq;
	int err = 0, cpu;

	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
	if (!wq)
		goto err;

	wq->cpu_wq = alloc_percpu(struct cpu_workqueue_struct);
	if (!wq->cpu_wq)
		goto err;

	wq->flags = flags;
	wq->name = name;
	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
	INIT_LIST_HEAD(&wq->list);

	if (flags & WQ_SINGLE_THREAD) {
		cwq = init_cpu_workqueue(wq, singlethread_cpu);
		err = create_workqueue_thread(cwq, singlethread_cpu);
		start_workqueue_thread(cwq, -1);
	} else {
		cpu_maps_update_begin();
		/*
		 * We must place this wq on list even if the code below fails.
		 * cpu_down(cpu) can remove cpu from cpu_populated_map before
		 * destroy_workqueue() takes the lock, in that case we leak
		 * cwq[cpu]->thread.
		 */
		spin_lock(&workqueue_lock);
		list_add(&wq->list, &workqueues);
		spin_unlock(&workqueue_lock);
		/*
		 * We must initialize cwqs for each possible cpu even if we
		 * are going to call destroy_workqueue() finally. Otherwise
		 * cpu_up() can hit the uninitialized cwq once we drop the
		 * lock.
		 */
		for_each_possible_cpu(cpu) {
			cwq = init_cpu_workqueue(wq, cpu);
			if (err || !cpu_online(cpu))
				continue;
			err = create_workqueue_thread(cwq, cpu);
			start_workqueue_thread(cwq, cpu);
		}
		cpu_maps_update_done();
	}

	if (err) {
		destroy_workqueue(wq);
		wq = NULL;
	}
	return wq;
err:
	if (wq) {
		free_percpu(wq->cpu_wq);
		kfree(wq);
	}
	return NULL;
}
EXPORT_SYMBOL_GPL(__create_workqueue_key);

static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
{
	/*
	 * Our caller is either destroy_workqueue() or CPU_POST_DEAD,
	 * cpu_add_remove_lock protects cwq->thread.
	 */
	if (cwq->thread == NULL)
		return;

	lock_map_acquire(&cwq->wq->lockdep_map);
	lock_map_release(&cwq->wq->lockdep_map);

	flush_cpu_workqueue(cwq);
	/*
	 * If the caller is CPU_POST_DEAD and cwq->worklist was not empty,
	 * a concurrent flush_workqueue() can insert a barrier after us.
	 * However, in that case run_workqueue() won't return and check
	 * kthread_should_stop() until it flushes all work_struct's.
	 * When ->worklist becomes empty it is safe to exit because no
	 * more work_structs can be queued on this cwq: flush_workqueue
	 * checks list_empty(), and a "normal" queue_work() can't use
	 * a dead CPU.
	 */
	trace_workqueue_destruction(cwq->thread);
	kthread_stop(cwq->thread);
	cwq->thread = NULL;
}

/**
 * destroy_workqueue - safely terminate a workqueue
 * @wq: target workqueue
 *
 * Safely destroy a workqueue. All work currently pending will be done first.
 */
void destroy_workqueue(struct workqueue_struct *wq)
{
	const struct cpumask *cpu_map = wq_cpu_map(wq);
	int cpu;

	cpu_maps_update_begin();
	spin_lock(&workqueue_lock);
	list_del(&wq->list);
	spin_unlock(&workqueue_lock);

	for_each_cpu(cpu, cpu_map)
		cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
 	cpu_maps_update_done();

	free_percpu(wq->cpu_wq);
	kfree(wq);
}
EXPORT_SYMBOL_GPL(destroy_workqueue);

static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
						unsigned long action,
						void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;
	struct cpu_workqueue_struct *cwq;
	struct workqueue_struct *wq;
	int err = 0;

	action &= ~CPU_TASKS_FROZEN;

	switch (action) {
	case CPU_UP_PREPARE:
		cpumask_set_cpu(cpu, cpu_populated_map);
	}
undo:
	list_for_each_entry(wq, &workqueues, list) {
		cwq = per_cpu_ptr(wq->cpu_wq, cpu);

		switch (action) {
		case CPU_UP_PREPARE:
			err = create_workqueue_thread(cwq, cpu);
			if (!err)
				break;
			printk(KERN_ERR "workqueue [%s] for %i failed\n",
				wq->name, cpu);
			action = CPU_UP_CANCELED;
			err = -ENOMEM;
			goto undo;

		case CPU_ONLINE:
			start_workqueue_thread(cwq, cpu);
			break;

		case CPU_UP_CANCELED:
			start_workqueue_thread(cwq, -1);
		case CPU_POST_DEAD:
			cleanup_workqueue_thread(cwq);
			break;
		}
	}

	switch (action) {
	case CPU_UP_CANCELED:
	case CPU_POST_DEAD:
		cpumask_clear_cpu(cpu, cpu_populated_map);
	}

	return notifier_from_errno(err);
}

#ifdef CONFIG_SMP

struct work_for_cpu {
	struct completion completion;
	long (*fn)(void *);
	void *arg;
	long ret;
};

static int do_work_for_cpu(void *_wfc)
{
	struct work_for_cpu *wfc = _wfc;
	wfc->ret = wfc->fn(wfc->arg);
	complete(&wfc->completion);
	return 0;
}

/**
 * work_on_cpu - run a function in user context on a particular cpu
 * @cpu: the cpu to run on
 * @fn: the function to run
 * @arg: the function arg
 *
 * This will return the value @fn returns.
 * It is up to the caller to ensure that the cpu doesn't go offline.
 * The caller must not hold any locks which would prevent @fn from completing.
 */
long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
{
	struct task_struct *sub_thread;
	struct work_for_cpu wfc = {
		.completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
		.fn = fn,
		.arg = arg,
	};

	sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
	if (IS_ERR(sub_thread))
		return PTR_ERR(sub_thread);
	kthread_bind(sub_thread, cpu);
	wake_up_process(sub_thread);
	wait_for_completion(&wfc.completion);
	return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);
#endif /* CONFIG_SMP */

void __init init_workqueues(void)
{
	alloc_cpumask_var(&cpu_populated_map, GFP_KERNEL);

	cpumask_copy(cpu_populated_map, cpu_online_mask);
	singlethread_cpu = cpumask_first(cpu_possible_mask);
	cpu_singlethread_map = cpumask_of(singlethread_cpu);
	hotcpu_notifier(workqueue_cpu_callback, 0);
	keventd_wq = create_workqueue("events");
	BUG_ON(!keventd_wq);
}
OpenPOWER on IntegriCloud