aboutsummaryrefslogtreecommitdiff
path: root/kernel/workqueue.c
blob: d1916fea710842719333d2fba32c4680a780c9f7 (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
/*
 * 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 <andrewm@uow.edu.au>
 *   Kai Petzke <wpp@marie.physik.tu-berlin.de>
 *   Theodore Ts'o <tytso@mit.edu>
 *
 * Made to use alloc_percpu by Christoph Lameter <clameter@sgi.com>.
 */

#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>

/*
 * 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;
	struct task_struct *thread;

	int run_depth;		/* Detect run_workqueue() recursion depth */
} ____cacheline_aligned;

/*
 * The externally visible workqueue abstraction is an array of
 * per-CPU workqueues:
 */
struct workqueue_struct {
	struct cpu_workqueue_struct *cpu_wq;
	struct list_head list;
	const char *name;
	int singlethread;
	int freezeable;		/* Freeze threads during suspend */
#ifdef CONFIG_LOCKDEP
	struct lockdep_map lockdep_map;
#endif
};

/* All the per-cpu workqueues on the system, for hotplug cpu to add/remove
   threads to each one as cpus come/go. */
static DEFINE_MUTEX(workqueue_mutex);
static LIST_HEAD(workqueues);

static int singlethread_cpu __read_mostly;
static cpumask_t 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_t cpu_populated_map __read_mostly;

/* If it's single threaded, it isn't in the list of workqueues. */
static inline int is_single_threaded(struct workqueue_struct *wq)
{
	return wq->singlethread;
}

static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq)
{
	return is_single_threaded(wq)
		? &cpu_singlethread_map : &cpu_populated_map;
}

static
struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu)
{
	if (unlikely(is_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 new;

	BUG_ON(!work_pending(work));

	new = (unsigned long) cwq | (1UL << WORK_STRUCT_PENDING);
	new |= WORK_STRUCT_FLAG_MASK & *work_data_bits(work);
	atomic_long_set(&work->data, new);
}

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);
}

static void insert_work(struct cpu_workqueue_struct *cwq,
				struct work_struct *work, int tail)
{
	set_wq_data(work, cwq);
	/*
	 * Ensure that we get the right work->data if we see the
	 * result of list_add() below, see try_to_grab_pending().
	 */
	smp_wmb();
	if (tail)
		list_add_tail(&work->entry, &cwq->worklist);
	else
		list_add(&work->entry, &cwq->worklist);
	wake_up(&cwq->more_work);
}

/* Preempt must be disabled. */
static void __queue_work(struct cpu_workqueue_struct *cwq,
			 struct work_struct *work)
{
	unsigned long flags;

	spin_lock_irqsave(&cwq->lock, flags);
	insert_work(cwq, work, 1);
	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 it was submitted, but there is no
 * guarantee that it will be processed by that CPU.
 */
int fastcall queue_work(struct workqueue_struct *wq, struct work_struct *work)
{
	int ret = 0;

	if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
		BUG_ON(!list_empty(&work->entry));
		__queue_work(wq_per_cpu(wq, get_cpu()), work);
		put_cpu();
		ret = 1;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(queue_work);

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);
	struct workqueue_struct *wq = cwq->wq;

	__queue_work(wq_per_cpu(wq, smp_processor_id()), &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 fastcall queue_delayed_work(struct workqueue_struct *wq,
			struct delayed_work *dwork, unsigned long delay)
{
	timer_stats_timer_set_start_info(&dwork->timer);
	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));

		/* This stores cwq for the moment, for the timer_fn */
		set_wq_data(work, wq_per_cpu(wq, raw_smp_processor_id()));
		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);
	cwq->run_depth++;
	if (cwq->run_depth > 3) {
		/* morton gets to eat his hat */
		printk("%s: recursion depth exceeded: %d\n",
			__FUNCTION__, cwq->run_depth);
		dump_stack();
	}
	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

		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_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
		lock_acquire(&lockdep_map, 0, 0, 0, 2, _THIS_IP_);
		f(work);
		lock_release(&lockdep_map, 1, _THIS_IP_);
		lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);

		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(),
				       	current->pid);
			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;
	}
	cwq->run_depth--;
	spin_unlock_irq(&cwq->lock);
}

static int worker_thread(void *__cwq)
{
	struct cpu_workqueue_struct *cwq = __cwq;
	DEFINE_WAIT(wait);

	if (cwq->wq->freezeable)
		set_freezable();

	set_user_nice(current, -5);

	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);
}

static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
					struct wq_barrier *barr, int tail)
{
	INIT_WORK(&barr->work, wq_barrier_func);
	__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));

	init_completion(&barr->done);

	insert_work(cwq, &barr->work, tail);
}

static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
{
	int active;

	if (cwq->thread == current) {
		/*
		 * Probably keventd trying to flush its own queue. So simply run
		 * it by hand rather than deadlocking.
		 */
		run_workqueue(cwq);
		active = 1;
	} else {
		struct wq_barrier barr;

		active = 0;
		spin_lock_irq(&cwq->lock);
		if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
			insert_wq_barrier(cwq, &barr, 1);
			active = 1;
		}
		spin_unlock_irq(&cwq->lock);

		if (active)
			wait_for_completion(&barr.done);
	}

	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.
 *
 * This function used to run the workqueues itself.  Now we just wait for the
 * helper threads to do it.
 */
void fastcall flush_workqueue(struct workqueue_struct *wq)
{
	const cpumask_t *cpu_map = wq_cpu_map(wq);
	int cpu;

	might_sleep();
	lock_acquire(&wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
	lock_release(&wq->lockdep_map, 1, _THIS_IP_);
	for_each_cpu_mask(cpu, *cpu_map)
		flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
}
EXPORT_SYMBOL_GPL(flush_workqueue);

/*
 * 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)) {
			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, 0);
		running = 1;
	}
	spin_unlock_irq(&cwq->lock);

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

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

	might_sleep();

	lock_acquire(&work->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
	lock_release(&work->lockdep_map, 1, _THIS_IP_);

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

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

	for_each_cpu_mask(cpu, *cpu_map)
		wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), 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));

	work_clear_pending(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
 *
 * This puts a job in the kernel-global workqueue.
 */
int fastcall schedule_work(struct work_struct *work)
{
	return queue_work(keventd_wq, work);
}
EXPORT_SYMBOL(schedule_work);

/**
 * 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 fastcall schedule_delayed_work(struct delayed_work *dwork,
					unsigned long delay)
{
	timer_stats_timer_set_start_info(&dwork->timer);
	return queue_delayed_work(keventd_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_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.
 *
 * Appears to be racy against CPU hotplug.
 *
 * schedule_on_each_cpu() is very slow.
 */
int schedule_on_each_cpu(work_func_t func)
{
	int cpu;
	struct work_struct *works;

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

	preempt_disable();		/* CPU hotplug */
	for_each_online_cpu(cpu) {
		struct work_struct *work = per_cpu_ptr(works, cpu);

		INIT_WORK(work, func);
		set_bit(WORK_STRUCT_PENDING, work_data_bits(work));
		__queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu), work);
	}
	preempt_enable();
	flush_workqueue(keventd_wq);
	free_percpu(works);
	return 0;
}

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_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;

	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,
						int singlethread,
						int freezeable,
						struct lock_class_key *key)
{
	struct workqueue_struct *wq;
	struct cpu_workqueue_struct *cwq;
	int err = 0, cpu;

	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
	if (!wq)
		return NULL;

	wq->cpu_wq = alloc_percpu(struct cpu_workqueue_struct);
	if (!wq->cpu_wq) {
		kfree(wq);
		return NULL;
	}

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

	if (singlethread) {
		cwq = init_cpu_workqueue(wq, singlethread_cpu);
		err = create_workqueue_thread(cwq, singlethread_cpu);
		start_workqueue_thread(cwq, -1);
	} else {
		mutex_lock(&workqueue_mutex);
		list_add(&wq->list, &workqueues);

		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);
		}
		mutex_unlock(&workqueue_mutex);
	}

	if (err) {
		destroy_workqueue(wq);
		wq = NULL;
	}
	return wq;
}
EXPORT_SYMBOL_GPL(__create_workqueue_key);

static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
{
	/*
	 * Our caller is either destroy_workqueue() or CPU_DEAD,
	 * workqueue_mutex protects cwq->thread
	 */
	if (cwq->thread == NULL)
		return;

	lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
	lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);

	flush_cpu_workqueue(cwq);
	/*
	 * If the caller is CPU_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.
	 */
	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 cpumask_t *cpu_map = wq_cpu_map(wq);
	struct cpu_workqueue_struct *cwq;
	int cpu;

	mutex_lock(&workqueue_mutex);
	list_del(&wq->list);
	mutex_unlock(&workqueue_mutex);

	for_each_cpu_mask(cpu, *cpu_map) {
		cwq = per_cpu_ptr(wq->cpu_wq, cpu);
		cleanup_workqueue_thread(cwq, cpu);
	}

	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;

	action &= ~CPU_TASKS_FROZEN;

	switch (action) {
	case CPU_LOCK_ACQUIRE:
		mutex_lock(&workqueue_mutex);
		return NOTIFY_OK;

	case CPU_LOCK_RELEASE:
		mutex_unlock(&workqueue_mutex);
		return NOTIFY_OK;

	case CPU_UP_PREPARE:
		cpu_set(cpu, cpu_populated_map);
	}

	list_for_each_entry(wq, &workqueues, list) {
		cwq = per_cpu_ptr(wq->cpu_wq, cpu);

		switch (action) {
		case CPU_UP_PREPARE:
			if (!create_workqueue_thread(cwq, cpu))
				break;
			printk(KERN_ERR "workqueue for %i failed\n", cpu);
			return NOTIFY_BAD;

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

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

	return NOTIFY_OK;
}

void __init init_workqueues(void)
{
	cpu_populated_map = cpu_online_map;
	singlethread_cpu = first_cpu(cpu_possible_map);
	cpu_singlethread_map = cpumask_of_cpu(singlethread_cpu);
	hotcpu_notifier(workqueue_cpu_callback, 0);
	keventd_wq = create_workqueue("events");
	BUG_ON(!keventd_wq);
}