aboutsummaryrefslogtreecommitdiff
path: root/kernel/stop_machine.c
blob: 1eb82661ecdb1257adcbf1c377804a4fc446c93b (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
/*
 * kernel/stop_machine.c
 *
 * Copyright (C) 2008, 2005	IBM Corporation.
 * Copyright (C) 2008, 2005	Rusty Russell rusty@rustcorp.com.au
 * Copyright (C) 2010		SUSE Linux Products GmbH
 * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
 *
 * This file is released under the GPLv2 and any later version.
 */
#include <linux/completion.h>
#include <linux/cpu.h>
#include <linux/init.h>
#include <linux/kthread.h>
#include <linux/export.h>
#include <linux/percpu.h>
#include <linux/sched.h>
#include <linux/stop_machine.h>
#include <linux/interrupt.h>
#include <linux/kallsyms.h>
#include <linux/smpboot.h>
#include <linux/atomic.h>
#include <linux/nmi.h>

/*
 * Structure to determine completion condition and record errors.  May
 * be shared by works on different cpus.
 */
struct cpu_stop_done {
	atomic_t		nr_todo;	/* nr left to execute */
	int			ret;		/* collected return value */
	struct completion	completion;	/* fired if nr_todo reaches 0 */
};

/* the actual stopper, one per every possible cpu, enabled on online cpus */
struct cpu_stopper {
	struct task_struct	*thread;

	spinlock_t		lock;
	bool			enabled;	/* is this stopper enabled? */
	struct list_head	works;		/* list of pending works */

	struct cpu_stop_work	stop_work;	/* for stop_cpus */
};

static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
static bool stop_machine_initialized = false;

/* static data for stop_cpus */
static DEFINE_MUTEX(stop_cpus_mutex);
static bool stop_cpus_in_progress;

static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
{
	memset(done, 0, sizeof(*done));
	atomic_set(&done->nr_todo, nr_todo);
	init_completion(&done->completion);
}

/* signal completion unless @done is NULL */
static void cpu_stop_signal_done(struct cpu_stop_done *done)
{
	if (atomic_dec_and_test(&done->nr_todo))
		complete(&done->completion);
}

static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
					struct cpu_stop_work *work)
{
	list_add_tail(&work->list, &stopper->works);
	wake_up_process(stopper->thread);
}

/* queue @work to @stopper.  if offline, @work is completed immediately */
static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
{
	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
	unsigned long flags;
	bool enabled;

	spin_lock_irqsave(&stopper->lock, flags);
	enabled = stopper->enabled;
	if (enabled)
		__cpu_stop_queue_work(stopper, work);
	else if (work->done)
		cpu_stop_signal_done(work->done);
	spin_unlock_irqrestore(&stopper->lock, flags);

	return enabled;
}

/**
 * stop_one_cpu - stop a cpu
 * @cpu: cpu to stop
 * @fn: function to execute
 * @arg: argument to @fn
 *
 * Execute @fn(@arg) on @cpu.  @fn is run in a process context with
 * the highest priority preempting any task on the cpu and
 * monopolizing it.  This function returns after the execution is
 * complete.
 *
 * This function doesn't guarantee @cpu stays online till @fn
 * completes.  If @cpu goes down in the middle, execution may happen
 * partially or fully on different cpus.  @fn should either be ready
 * for that or the caller should ensure that @cpu stays online until
 * this function completes.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * -ENOENT if @fn(@arg) was not executed because @cpu was offline;
 * otherwise, the return value of @fn.
 */
int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
{
	struct cpu_stop_done done;
	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };

	cpu_stop_init_done(&done, 1);
	if (!cpu_stop_queue_work(cpu, &work))
		return -ENOENT;
	/*
	 * In case @cpu == smp_proccessor_id() we can avoid a sleep+wakeup
	 * cycle by doing a preemption:
	 */
	cond_resched();
	wait_for_completion(&done.completion);
	return done.ret;
}

/* This controls the threads on each CPU. */
enum multi_stop_state {
	/* Dummy starting state for thread. */
	MULTI_STOP_NONE,
	/* Awaiting everyone to be scheduled. */
	MULTI_STOP_PREPARE,
	/* Disable interrupts. */
	MULTI_STOP_DISABLE_IRQ,
	/* Run the function */
	MULTI_STOP_RUN,
	/* Exit */
	MULTI_STOP_EXIT,
};

struct multi_stop_data {
	cpu_stop_fn_t		fn;
	void			*data;
	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
	unsigned int		num_threads;
	const struct cpumask	*active_cpus;

	enum multi_stop_state	state;
	atomic_t		thread_ack;
};

static void set_state(struct multi_stop_data *msdata,
		      enum multi_stop_state newstate)
{
	/* Reset ack counter. */
	atomic_set(&msdata->thread_ack, msdata->num_threads);
	smp_wmb();
	msdata->state = newstate;
}

/* Last one to ack a state moves to the next state. */
static void ack_state(struct multi_stop_data *msdata)
{
	if (atomic_dec_and_test(&msdata->thread_ack))
		set_state(msdata, msdata->state + 1);
}

/* This is the cpu_stop function which stops the CPU. */
static int multi_cpu_stop(void *data)
{
	struct multi_stop_data *msdata = data;
	enum multi_stop_state curstate = MULTI_STOP_NONE;
	int cpu = smp_processor_id(), err = 0;
	unsigned long flags;
	bool is_active;

	/*
	 * When called from stop_machine_from_inactive_cpu(), irq might
	 * already be disabled.  Save the state and restore it on exit.
	 */
	local_save_flags(flags);

	if (!msdata->active_cpus)
		is_active = cpu == cpumask_first(cpu_online_mask);
	else
		is_active = cpumask_test_cpu(cpu, msdata->active_cpus);

	/* Simple state machine */
	do {
		/* Chill out and ensure we re-read multi_stop_state. */
		cpu_relax_yield();
		if (msdata->state != curstate) {
			curstate = msdata->state;
			switch (curstate) {
			case MULTI_STOP_DISABLE_IRQ:
				local_irq_disable();
				hard_irq_disable();
				break;
			case MULTI_STOP_RUN:
				if (is_active)
					err = msdata->fn(msdata->data);
				break;
			default:
				break;
			}
			ack_state(msdata);
		} else if (curstate > MULTI_STOP_PREPARE) {
			/*
			 * At this stage all other CPUs we depend on must spin
			 * in the same loop. Any reason for hard-lockup should
			 * be detected and reported on their side.
			 */
			touch_nmi_watchdog();
		}
	} while (curstate != MULTI_STOP_EXIT);

	local_irq_restore(flags);
	return err;
}

static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
				    int cpu2, struct cpu_stop_work *work2)
{
	struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
	int err;
retry:
	spin_lock_irq(&stopper1->lock);
	spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);

	err = -ENOENT;
	if (!stopper1->enabled || !stopper2->enabled)
		goto unlock;
	/*
	 * Ensure that if we race with __stop_cpus() the stoppers won't get
	 * queued up in reverse order leading to system deadlock.
	 *
	 * We can't miss stop_cpus_in_progress if queue_stop_cpus_work() has
	 * queued a work on cpu1 but not on cpu2, we hold both locks.
	 *
	 * It can be falsely true but it is safe to spin until it is cleared,
	 * queue_stop_cpus_work() does everything under preempt_disable().
	 */
	err = -EDEADLK;
	if (unlikely(stop_cpus_in_progress))
			goto unlock;

	err = 0;
	__cpu_stop_queue_work(stopper1, work1);
	__cpu_stop_queue_work(stopper2, work2);
unlock:
	spin_unlock(&stopper2->lock);
	spin_unlock_irq(&stopper1->lock);

	if (unlikely(err == -EDEADLK)) {
		while (stop_cpus_in_progress)
			cpu_relax();
		goto retry;
	}
	return err;
}
/**
 * stop_two_cpus - stops two cpus
 * @cpu1: the cpu to stop
 * @cpu2: the other cpu to stop
 * @fn: function to execute
 * @arg: argument to @fn
 *
 * Stops both the current and specified CPU and runs @fn on one of them.
 *
 * returns when both are completed.
 */
int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg)
{
	struct cpu_stop_done done;
	struct cpu_stop_work work1, work2;
	struct multi_stop_data msdata;

	msdata = (struct multi_stop_data){
		.fn = fn,
		.data = arg,
		.num_threads = 2,
		.active_cpus = cpumask_of(cpu1),
	};

	work1 = work2 = (struct cpu_stop_work){
		.fn = multi_cpu_stop,
		.arg = &msdata,
		.done = &done
	};

	cpu_stop_init_done(&done, 2);
	set_state(&msdata, MULTI_STOP_PREPARE);

	if (cpu1 > cpu2)
		swap(cpu1, cpu2);
	if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2))
		return -ENOENT;

	wait_for_completion(&done.completion);
	return done.ret;
}

/**
 * stop_one_cpu_nowait - stop a cpu but don't wait for completion
 * @cpu: cpu to stop
 * @fn: function to execute
 * @arg: argument to @fn
 * @work_buf: pointer to cpu_stop_work structure
 *
 * Similar to stop_one_cpu() but doesn't wait for completion.  The
 * caller is responsible for ensuring @work_buf is currently unused
 * and will remain untouched until stopper starts executing @fn.
 *
 * CONTEXT:
 * Don't care.
 *
 * RETURNS:
 * true if cpu_stop_work was queued successfully and @fn will be called,
 * false otherwise.
 */
bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
			struct cpu_stop_work *work_buf)
{
	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
	return cpu_stop_queue_work(cpu, work_buf);
}

static bool queue_stop_cpus_work(const struct cpumask *cpumask,
				 cpu_stop_fn_t fn, void *arg,
				 struct cpu_stop_done *done)
{
	struct cpu_stop_work *work;
	unsigned int cpu;
	bool queued = false;

	/*
	 * Disable preemption while queueing to avoid getting
	 * preempted by a stopper which might wait for other stoppers
	 * to enter @fn which can lead to deadlock.
	 */
	preempt_disable();
	stop_cpus_in_progress = true;
	for_each_cpu(cpu, cpumask) {
		work = &per_cpu(cpu_stopper.stop_work, cpu);
		work->fn = fn;
		work->arg = arg;
		work->done = done;
		if (cpu_stop_queue_work(cpu, work))
			queued = true;
	}
	stop_cpus_in_progress = false;
	preempt_enable();

	return queued;
}

static int __stop_cpus(const struct cpumask *cpumask,
		       cpu_stop_fn_t fn, void *arg)
{
	struct cpu_stop_done done;

	cpu_stop_init_done(&done, cpumask_weight(cpumask));
	if (!queue_stop_cpus_work(cpumask, fn, arg, &done))
		return -ENOENT;
	wait_for_completion(&done.completion);
	return done.ret;
}

/**
 * stop_cpus - stop multiple cpus
 * @cpumask: cpus to stop
 * @fn: function to execute
 * @arg: argument to @fn
 *
 * Execute @fn(@arg) on online cpus in @cpumask.  On each target cpu,
 * @fn is run in a process context with the highest priority
 * preempting any task on the cpu and monopolizing it.  This function
 * returns after all executions are complete.
 *
 * This function doesn't guarantee the cpus in @cpumask stay online
 * till @fn completes.  If some cpus go down in the middle, execution
 * on the cpu may happen partially or fully on different cpus.  @fn
 * should either be ready for that or the caller should ensure that
 * the cpus stay online until this function completes.
 *
 * All stop_cpus() calls are serialized making it safe for @fn to wait
 * for all cpus to start executing it.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * -ENOENT if @fn(@arg) was not executed at all because all cpus in
 * @cpumask were offline; otherwise, 0 if all executions of @fn
 * returned 0, any non zero return value if any returned non zero.
 */
int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
{
	int ret;

	/* static works are used, process one request at a time */
	mutex_lock(&stop_cpus_mutex);
	ret = __stop_cpus(cpumask, fn, arg);
	mutex_unlock(&stop_cpus_mutex);
	return ret;
}

/**
 * try_stop_cpus - try to stop multiple cpus
 * @cpumask: cpus to stop
 * @fn: function to execute
 * @arg: argument to @fn
 *
 * Identical to stop_cpus() except that it fails with -EAGAIN if
 * someone else is already using the facility.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * -EAGAIN if someone else is already stopping cpus, -ENOENT if
 * @fn(@arg) was not executed at all because all cpus in @cpumask were
 * offline; otherwise, 0 if all executions of @fn returned 0, any non
 * zero return value if any returned non zero.
 */
int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
{
	int ret;

	/* static works are used, process one request at a time */
	if (!mutex_trylock(&stop_cpus_mutex))
		return -EAGAIN;
	ret = __stop_cpus(cpumask, fn, arg);
	mutex_unlock(&stop_cpus_mutex);
	return ret;
}

static int cpu_stop_should_run(unsigned int cpu)
{
	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
	unsigned long flags;
	int run;

	spin_lock_irqsave(&stopper->lock, flags);
	run = !list_empty(&stopper->works);
	spin_unlock_irqrestore(&stopper->lock, flags);
	return run;
}

static void cpu_stopper_thread(unsigned int cpu)
{
	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
	struct cpu_stop_work *work;

repeat:
	work = NULL;
	spin_lock_irq(&stopper->lock);
	if (!list_empty(&stopper->works)) {
		work = list_first_entry(&stopper->works,
					struct cpu_stop_work, list);
		list_del_init(&work->list);
	}
	spin_unlock_irq(&stopper->lock);

	if (work) {
		cpu_stop_fn_t fn = work->fn;
		void *arg = work->arg;
		struct cpu_stop_done *done = work->done;
		int ret;

		/* cpu stop callbacks must not sleep, make in_atomic() == T */
		preempt_count_inc();
		ret = fn(arg);
		if (done) {
			if (ret)
				done->ret = ret;
			cpu_stop_signal_done(done);
		}
		preempt_count_dec();
		WARN_ONCE(preempt_count(),
			  "cpu_stop: %pf(%p) leaked preempt count\n", fn, arg);
		goto repeat;
	}
}

void stop_machine_park(int cpu)
{
	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
	/*
	 * Lockless. cpu_stopper_thread() will take stopper->lock and flush
	 * the pending works before it parks, until then it is fine to queue
	 * the new works.
	 */
	stopper->enabled = false;
	kthread_park(stopper->thread);
}

extern void sched_set_stop_task(int cpu, struct task_struct *stop);

static void cpu_stop_create(unsigned int cpu)
{
	sched_set_stop_task(cpu, per_cpu(cpu_stopper.thread, cpu));
}

static void cpu_stop_park(unsigned int cpu)
{
	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);

	WARN_ON(!list_empty(&stopper->works));
}

void stop_machine_unpark(int cpu)
{
	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);

	stopper->enabled = true;
	kthread_unpark(stopper->thread);
}

static struct smp_hotplug_thread cpu_stop_threads = {
	.store			= &cpu_stopper.thread,
	.thread_should_run	= cpu_stop_should_run,
	.thread_fn		= cpu_stopper_thread,
	.thread_comm		= "migration/%u",
	.create			= cpu_stop_create,
	.park			= cpu_stop_park,
	.selfparking		= true,
};

static int __init cpu_stop_init(void)
{
	unsigned int cpu;

	for_each_possible_cpu(cpu) {
		struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);

		spin_lock_init(&stopper->lock);
		INIT_LIST_HEAD(&stopper->works);
	}

	BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads));
	stop_machine_unpark(raw_smp_processor_id());
	stop_machine_initialized = true;
	return 0;
}
early_initcall(cpu_stop_init);

static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
{
	struct multi_stop_data msdata = {
		.fn = fn,
		.data = data,
		.num_threads = num_online_cpus(),
		.active_cpus = cpus,
	};

	if (!stop_machine_initialized) {
		/*
		 * Handle the case where stop_machine() is called
		 * early in boot before stop_machine() has been
		 * initialized.
		 */
		unsigned long flags;
		int ret;

		WARN_ON_ONCE(msdata.num_threads != 1);

		local_irq_save(flags);
		hard_irq_disable();
		ret = (*fn)(data);
		local_irq_restore(flags);

		return ret;
	}

	/* Set the initial state and stop all online cpus. */
	set_state(&msdata, MULTI_STOP_PREPARE);
	return stop_cpus(cpu_online_mask, multi_cpu_stop, &msdata);
}

int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
{
	int ret;

	/* No CPUs can come up or down during this. */
	get_online_cpus();
	ret = __stop_machine(fn, data, cpus);
	put_online_cpus();
	return ret;
}
EXPORT_SYMBOL_GPL(stop_machine);

/**
 * stop_machine_from_inactive_cpu - stop_machine() from inactive CPU
 * @fn: the function to run
 * @data: the data ptr for the @fn()
 * @cpus: the cpus to run the @fn() on (NULL = any online cpu)
 *
 * This is identical to stop_machine() but can be called from a CPU which
 * is not active.  The local CPU is in the process of hotplug (so no other
 * CPU hotplug can start) and not marked active and doesn't have enough
 * context to sleep.
 *
 * This function provides stop_machine() functionality for such state by
 * using busy-wait for synchronization and executing @fn directly for local
 * CPU.
 *
 * CONTEXT:
 * Local CPU is inactive.  Temporarily stops all active CPUs.
 *
 * RETURNS:
 * 0 if all executions of @fn returned 0, any non zero return value if any
 * returned non zero.
 */
int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
				  const struct cpumask *cpus)
{
	struct multi_stop_data msdata = { .fn = fn, .data = data,
					    .active_cpus = cpus };
	struct cpu_stop_done done;
	int ret;

	/* Local CPU must be inactive and CPU hotplug in progress. */
	BUG_ON(cpu_active(raw_smp_processor_id()));
	msdata.num_threads = num_active_cpus() + 1;	/* +1 for local */

	/* No proper task established and can't sleep - busy wait for lock. */
	while (!mutex_trylock(&stop_cpus_mutex))
		cpu_relax();

	/* Schedule work on other CPUs and execute directly for local CPU */
	set_state(&msdata, MULTI_STOP_PREPARE);
	cpu_stop_init_done(&done, num_active_cpus());
	queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata,
			     &done);
	ret = multi_cpu_stop(&msdata);

	/* Busy wait for completion. */
	while (!completion_done(&done.completion))
		cpu_relax();

	mutex_unlock(&stop_cpus_mutex);
	return ret ?: done.ret;
}