aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/workqueue.c
blob: 880fb415a8f601ebb5fff636fee20b958fe71149 (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
/*
 * 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>

/*
 * The per-CPU workqueue (if single thread, we always use the first
 * possible cpu).
 *
 * The sequence counters are for flush_scheduled_work().  It wants to wait
 * until until all currently-scheduled works are completed, but it doesn't
 * want to be livelocked by new, incoming ones.  So it waits until
 * remove_sequence is >= the insert_sequence which pertained when
 * flush_scheduled_work() was called.
 */
struct cpu_workqueue_struct {

	spinlock_t lock;

	long remove_sequence;	/* Least-recently added (next to run) */
	long insert_sequence;	/* Next to add */

	struct list_head worklist;
	wait_queue_head_t more_work;
	wait_queue_head_t work_done;

	struct workqueue_struct *wq;
	task_t *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;
	const char *name;
	struct list_head list; 	/* Empty if single thread */
};

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

static int singlethread_cpu;

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

/* 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);
	work->wq_data = cwq;
	list_add_tail(&work->entry, &cwq->worklist);
	cwq->insert_sequence++;
	wake_up(&cwq->more_work);
	spin_unlock_irqrestore(&cwq->lock, flags);
}

/*
 * Queue work on a workqueue. Return non-zero if it was successfully
 * added.
 *
 * 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, cpu = get_cpu();

	if (!test_and_set_bit(0, &work->pending)) {
		if (unlikely(is_single_threaded(wq)))
			cpu = singlethread_cpu;
		BUG_ON(!list_empty(&work->entry));
		__queue_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
		ret = 1;
	}
	put_cpu();
	return ret;
}

static void delayed_work_timer_fn(unsigned long __data)
{
	struct work_struct *work = (struct work_struct *)__data;
	struct workqueue_struct *wq = work->wq_data;
	int cpu = smp_processor_id();

	if (unlikely(is_single_threaded(wq)))
		cpu = singlethread_cpu;

	__queue_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
}

int fastcall queue_delayed_work(struct workqueue_struct *wq,
			struct work_struct *work, unsigned long delay)
{
	int ret = 0;
	struct timer_list *timer = &work->timer;

	if (!test_and_set_bit(0, &work->pending)) {
		BUG_ON(timer_pending(timer));
		BUG_ON(!list_empty(&work->entry));

		/* This stores wq for the moment, for the timer_fn */
		work->wq_data = wq;
		timer->expires = jiffies + delay;
		timer->data = (unsigned long)work;
		timer->function = delayed_work_timer_fn;
		add_timer(timer);
		ret = 1;
	}
	return ret;
}

static void run_workqueue(struct cpu_workqueue_struct *cwq)
{
	unsigned long flags;

	/*
	 * Keep taking off work from the queue until
	 * done.
	 */
	spin_lock_irqsave(&cwq->lock, flags);
	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);
		void (*f) (void *) = work->func;
		void *data = work->data;

		list_del_init(cwq->worklist.next);
		spin_unlock_irqrestore(&cwq->lock, flags);

		BUG_ON(work->wq_data != cwq);
		clear_bit(0, &work->pending);
		f(data);

		spin_lock_irqsave(&cwq->lock, flags);
		cwq->remove_sequence++;
		wake_up(&cwq->work_done);
	}
	cwq->run_depth--;
	spin_unlock_irqrestore(&cwq->lock, flags);
}

static int worker_thread(void *__cwq)
{
	struct cpu_workqueue_struct *cwq = __cwq;
	DECLARE_WAITQUEUE(wait, current);
	struct k_sigaction sa;
	sigset_t blocked;

	current->flags |= PF_NOFREEZE;

	set_user_nice(current, -5);

	/* Block and flush all signals */
	sigfillset(&blocked);
	sigprocmask(SIG_BLOCK, &blocked, NULL);
	flush_signals(current);

	/* SIG_IGN makes children autoreap: see do_notify_parent(). */
	sa.sa.sa_handler = SIG_IGN;
	sa.sa.sa_flags = 0;
	siginitset(&sa.sa.sa_mask, sigmask(SIGCHLD));
	do_sigaction(SIGCHLD, &sa, (struct k_sigaction *)0);

	set_current_state(TASK_INTERRUPTIBLE);
	while (!kthread_should_stop()) {
		add_wait_queue(&cwq->more_work, &wait);
		if (list_empty(&cwq->worklist))
			schedule();
		else
			__set_current_state(TASK_RUNNING);
		remove_wait_queue(&cwq->more_work, &wait);

		if (!list_empty(&cwq->worklist))
			run_workqueue(cwq);
		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);
	return 0;
}

static void flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
{
	if (cwq->thread == current) {
		/*
		 * Probably keventd trying to flush its own queue. So simply run
		 * it by hand rather than deadlocking.
		 */
		run_workqueue(cwq);
	} else {
		DEFINE_WAIT(wait);
		long sequence_needed;

		spin_lock_irq(&cwq->lock);
		sequence_needed = cwq->insert_sequence;

		while (sequence_needed - cwq->remove_sequence > 0) {
			prepare_to_wait(&cwq->work_done, &wait,
					TASK_UNINTERRUPTIBLE);
			spin_unlock_irq(&cwq->lock);
			schedule();
			spin_lock_irq(&cwq->lock);
		}
		finish_wait(&cwq->work_done, &wait);
		spin_unlock_irq(&cwq->lock);
	}
}

/*
 * flush_workqueue - ensure that any scheduled work has run to completion.
 *
 * Forces execution of the workqueue and blocks until its completion.
 * This is typically used in driver shutdown handlers.
 *
 * This function will sample each workqueue's current insert_sequence number and
 * will sleep until the head sequence is greater than or equal to that.  This
 * means that 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)
{
	might_sleep();

	if (is_single_threaded(wq)) {
		/* Always use first cpu's area. */
		flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, singlethread_cpu));
	} else {
		int cpu;

		lock_cpu_hotplug();
		for_each_online_cpu(cpu)
			flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
		unlock_cpu_hotplug();
	}
}

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

	spin_lock_init(&cwq->lock);
	cwq->wq = wq;
	cwq->thread = NULL;
	cwq->insert_sequence = 0;
	cwq->remove_sequence = 0;
	INIT_LIST_HEAD(&cwq->worklist);
	init_waitqueue_head(&cwq->more_work);
	init_waitqueue_head(&cwq->work_done);

	if (is_single_threaded(wq))
		p = kthread_create(worker_thread, cwq, "%s", wq->name);
	else
		p = kthread_create(worker_thread, cwq, "%s/%d", wq->name, cpu);
	if (IS_ERR(p))
		return NULL;
	cwq->thread = p;
	return p;
}

struct workqueue_struct *__create_workqueue(const char *name,
					    int singlethread)
{
	int cpu, destroy = 0;
	struct workqueue_struct *wq;
	struct task_struct *p;

	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;
	/* We don't need the distraction of CPUs appearing and vanishing. */
	lock_cpu_hotplug();
	if (singlethread) {
		INIT_LIST_HEAD(&wq->list);
		p = create_workqueue_thread(wq, singlethread_cpu);
		if (!p)
			destroy = 1;
		else
			wake_up_process(p);
	} else {
		spin_lock(&workqueue_lock);
		list_add(&wq->list, &workqueues);
		spin_unlock(&workqueue_lock);
		for_each_online_cpu(cpu) {
			p = create_workqueue_thread(wq, cpu);
			if (p) {
				kthread_bind(p, cpu);
				wake_up_process(p);
			} else
				destroy = 1;
		}
	}
	unlock_cpu_hotplug();

	/*
	 * Was there any error during startup? If yes then clean up:
	 */
	if (destroy) {
		destroy_workqueue(wq);
		wq = NULL;
	}
	return wq;
}

static void cleanup_workqueue_thread(struct workqueue_struct *wq, int cpu)
{
	struct cpu_workqueue_struct *cwq;
	unsigned long flags;
	struct task_struct *p;

	cwq = per_cpu_ptr(wq->cpu_wq, cpu);
	spin_lock_irqsave(&cwq->lock, flags);
	p = cwq->thread;
	cwq->thread = NULL;
	spin_unlock_irqrestore(&cwq->lock, flags);
	if (p)
		kthread_stop(p);
}

void destroy_workqueue(struct workqueue_struct *wq)
{
	int cpu;

	flush_workqueue(wq);

	/* We don't need the distraction of CPUs appearing and vanishing. */
	lock_cpu_hotplug();
	if (is_single_threaded(wq))
		cleanup_workqueue_thread(wq, singlethread_cpu);
	else {
		for_each_online_cpu(cpu)
			cleanup_workqueue_thread(wq, cpu);
		spin_lock(&workqueue_lock);
		list_del(&wq->list);
		spin_unlock(&workqueue_lock);
	}
	unlock_cpu_hotplug();
	free_percpu(wq->cpu_wq);
	kfree(wq);
}

static struct workqueue_struct *keventd_wq;

int fastcall schedule_work(struct work_struct *work)
{
	return queue_work(keventd_wq, work);
}

int fastcall schedule_delayed_work(struct work_struct *work, unsigned long delay)
{
	return queue_delayed_work(keventd_wq, work, delay);
}

int schedule_delayed_work_on(int cpu,
			struct work_struct *work, unsigned long delay)
{
	int ret = 0;
	struct timer_list *timer = &work->timer;

	if (!test_and_set_bit(0, &work->pending)) {
		BUG_ON(timer_pending(timer));
		BUG_ON(!list_empty(&work->entry));
		/* This stores keventd_wq for the moment, for the timer_fn */
		work->wq_data = keventd_wq;
		timer->expires = jiffies + delay;
		timer->data = (unsigned long)work;
		timer->function = delayed_work_timer_fn;
		add_timer_on(timer, cpu);
		ret = 1;
	}
	return ret;
}

int schedule_on_each_cpu(void (*func) (void *info), void *info)
{
	int cpu;
	struct work_struct *work;

	work = kmalloc(NR_CPUS * sizeof(struct work_struct), GFP_KERNEL);

	if (!work)
		return -ENOMEM;
	for_each_online_cpu(cpu) {
		INIT_WORK(work + cpu, func, info);
		__queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu),
				work + cpu);
	}
	flush_workqueue(keventd_wq);
	kfree(work);
	return 0;
}

void flush_scheduled_work(void)
{
	flush_workqueue(keventd_wq);
}

/**
 * cancel_rearming_delayed_workqueue - reliably kill off a delayed
 *			work whose handler rearms the delayed work.
 * @wq:   the controlling workqueue structure
 * @work: the delayed work struct
 */
void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq,
				       struct work_struct *work)
{
	while (!cancel_delayed_work(work))
		flush_workqueue(wq);
}
EXPORT_SYMBOL(cancel_rearming_delayed_workqueue);

/**
 * cancel_rearming_delayed_work - reliably kill off a delayed keventd
 *			work whose handler rearms the delayed work.
 * @work: the delayed work struct
 */
void cancel_rearming_delayed_work(struct work_struct *work)
{
	cancel_rearming_delayed_workqueue(keventd_wq, work);
}
EXPORT_SYMBOL(cancel_rearming_delayed_work);

/**
 * execute_in_process_context - reliably execute the routine with user context
 * @fn:		the function to execute
 * @data:	data to pass to the function
 * @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(void (*fn)(void *data), void *data,
			       struct execute_work *ew)
{
	if (!in_interrupt()) {
		fn(data);
		return 0;
	}

	INIT_WORK(&ew->work, fn, data);
	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 = 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;

}

#ifdef CONFIG_HOTPLUG_CPU
/* Take the work from this (downed) CPU. */
static void take_over_work(struct workqueue_struct *wq, unsigned int cpu)
{
	struct cpu_workqueue_struct *cwq = per_cpu_ptr(wq->cpu_wq, cpu);
	LIST_HEAD(list);
	struct work_struct *work;

	spin_lock_irq(&cwq->lock);
	list_splice_init(&cwq->worklist, &list);

	while (!list_empty(&list)) {
		printk("Taking work for %s\n", wq->name);
		work = list_entry(list.next,struct work_struct,entry);
		list_del(&work->entry);
		__queue_work(per_cpu_ptr(wq->cpu_wq, smp_processor_id()), work);
	}
	spin_unlock_irq(&cwq->lock);
}

/* We're holding the cpucontrol mutex here */
static int workqueue_cpu_callback(struct notifier_block *nfb,
				  unsigned long action,
				  void *hcpu)
{
	unsigned int hotcpu = (unsigned long)hcpu;
	struct workqueue_struct *wq;

	switch (action) {
	case CPU_UP_PREPARE:
		/* Create a new workqueue thread for it. */
		list_for_each_entry(wq, &workqueues, list) {
			if (!create_workqueue_thread(wq, hotcpu)) {
				printk("workqueue for %i failed\n", hotcpu);
				return NOTIFY_BAD;
			}
		}
		break;

	case CPU_ONLINE:
		/* Kick off worker threads. */
		list_for_each_entry(wq, &workqueues, list) {
			struct cpu_workqueue_struct *cwq;

			cwq = per_cpu_ptr(wq->cpu_wq, hotcpu);
			kthread_bind(cwq->thread, hotcpu);
			wake_up_process(cwq->thread);
		}
		break;

	case CPU_UP_CANCELED:
		list_for_each_entry(wq, &workqueues, list) {
			/* Unbind so it can run. */
			kthread_bind(per_cpu_ptr(wq->cpu_wq, hotcpu)->thread,
				     any_online_cpu(cpu_online_map));
			cleanup_workqueue_thread(wq, hotcpu);
		}
		break;

	case CPU_DEAD:
		list_for_each_entry(wq, &workqueues, list)
			cleanup_workqueue_thread(wq, hotcpu);
		list_for_each_entry(wq, &workqueues, list)
			take_over_work(wq, hotcpu);
		break;
	}

	return NOTIFY_OK;
}
#endif

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

EXPORT_SYMBOL_GPL(__create_workqueue);
EXPORT_SYMBOL_GPL(queue_work);
EXPORT_SYMBOL_GPL(queue_delayed_work);
EXPORT_SYMBOL_GPL(flush_workqueue);
EXPORT_SYMBOL_GPL(destroy_workqueue);

EXPORT_SYMBOL(schedule_work);
EXPORT_SYMBOL(schedule_delayed_work);
EXPORT_SYMBOL(schedule_delayed_work_on);
EXPORT_SYMBOL(flush_scheduled_work);