aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/smp.c
blob: 9910744f0856c5a084b4f9721dca09f376415645 (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
/*
 * Generic helpers for smp ipi calls
 *
 * (C) Jens Axboe <jens.axboe@oracle.com> 2008
 */
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/gfp.h>
#include <linux/smp.h>
#include <linux/cpu.h>

#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
static struct {
	struct list_head	queue;
	raw_spinlock_t		lock;
} call_function __cacheline_aligned_in_smp =
	{
		.queue		= LIST_HEAD_INIT(call_function.queue),
		.lock		= __RAW_SPIN_LOCK_UNLOCKED(call_function.lock),
	};

enum {
	CSD_FLAG_LOCK		= 0x01,
};

struct call_function_data {
	struct call_single_data	csd;
	atomic_t		refs;
	cpumask_var_t		cpumask;
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);

struct call_single_queue {
	struct list_head	list;
	raw_spinlock_t		lock;
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_queue, call_single_queue);

static int
hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	struct call_function_data *cfd = &per_cpu(cfd_data, cpu);

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
				cpu_to_node(cpu)))
			return notifier_from_errno(-ENOMEM);
		break;

#ifdef CONFIG_HOTPLUG_CPU
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:

	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		free_cpumask_var(cfd->cpumask);
		break;
#endif
	};

	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata hotplug_cfd_notifier = {
	.notifier_call		= hotplug_cfd,
};

static int __cpuinit init_call_single_data(void)
{
	void *cpu = (void *)(long)smp_processor_id();
	int i;

	for_each_possible_cpu(i) {
		struct call_single_queue *q = &per_cpu(call_single_queue, i);

		raw_spin_lock_init(&q->lock);
		INIT_LIST_HEAD(&q->list);
	}

	hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
	register_cpu_notifier(&hotplug_cfd_notifier);

	return 0;
}
early_initcall(init_call_single_data);

/*
 * csd_lock/csd_unlock used to serialize access to per-cpu csd resources
 *
 * For non-synchronous ipi calls the csd can still be in use by the
 * previous function call. For multi-cpu calls its even more interesting
 * as we'll have to ensure no other cpu is observing our csd.
 */
static void csd_lock_wait(struct call_single_data *data)
{
	while (data->flags & CSD_FLAG_LOCK)
		cpu_relax();
}

static void csd_lock(struct call_single_data *data)
{
	csd_lock_wait(data);
	data->flags = CSD_FLAG_LOCK;

	/*
	 * prevent CPU from reordering the above assignment
	 * to ->flags with any subsequent assignments to other
	 * fields of the specified call_single_data structure:
	 */
	smp_mb();
}

static void csd_unlock(struct call_single_data *data)
{
	WARN_ON(!(data->flags & CSD_FLAG_LOCK));

	/*
	 * ensure we're all done before releasing data:
	 */
	smp_mb();

	data->flags &= ~CSD_FLAG_LOCK;
}

/*
 * Insert a previously allocated call_single_data element
 * for execution on the given CPU. data must already have
 * ->func, ->info, and ->flags set.
 */
static
void generic_exec_single(int cpu, struct call_single_data *data, int wait)
{
	struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
	unsigned long flags;
	int ipi;

	raw_spin_lock_irqsave(&dst->lock, flags);
	ipi = list_empty(&dst->list);
	list_add_tail(&data->list, &dst->list);
	raw_spin_unlock_irqrestore(&dst->lock, flags);

	/*
	 * The list addition should be visible before sending the IPI
	 * handler locks the list to pull the entry off it because of
	 * normal cache coherency rules implied by spinlocks.
	 *
	 * If IPIs can go out of order to the cache coherency protocol
	 * in an architecture, sufficient synchronisation should be added
	 * to arch code to make it appear to obey cache coherency WRT
	 * locking and barrier primitives. Generic code isn't really
	 * equipped to do the right thing...
	 */
	if (ipi)
		arch_send_call_function_single_ipi(cpu);

	if (wait)
		csd_lock_wait(data);
}

/*
 * Invoked by arch to handle an IPI for call function. Must be called with
 * interrupts disabled.
 */
void generic_smp_call_function_interrupt(void)
{
	struct call_function_data *data;
	int cpu = smp_processor_id();

	/*
	 * Shouldn't receive this interrupt on a cpu that is not yet online.
	 */
	WARN_ON_ONCE(!cpu_online(cpu));

	/*
	 * Ensure entry is visible on call_function_queue after we have
	 * entered the IPI. See comment in smp_call_function_many.
	 * If we don't have this, then we may miss an entry on the list
	 * and never get another IPI to process it.
	 */
	smp_mb();

	/*
	 * It's ok to use list_for_each_rcu() here even though we may
	 * delete 'pos', since list_del_rcu() doesn't clear ->next
	 */
	list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
		int refs;
		void (*func) (void *info);

		/*
		 * Since we walk the list without any locks, we might
		 * see an entry that was completed, removed from the
		 * list and is in the process of being reused.
		 *
		 * We must check that the cpu is in the cpumask before
		 * checking the refs, and both must be set before
		 * executing the callback on this cpu.
		 */

		if (!cpumask_test_cpu(cpu, data->cpumask))
			continue;

		smp_rmb();

		if (atomic_read(&data->refs) == 0)
			continue;

		func = data->csd.func;			/* for later warn */
		data->csd.func(data->csd.info);

		/*
		 * If the cpu mask is not still set then it enabled interrupts,
		 * we took another smp interrupt, and executed the function
		 * twice on this cpu.  In theory that copy decremented refs.
		 */
		if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) {
			WARN(1, "%pS enabled interrupts and double executed\n",
			     func);
			continue;
		}

		refs = atomic_dec_return(&data->refs);
		WARN_ON(refs < 0);

		if (refs)
			continue;

		WARN_ON(!cpumask_empty(data->cpumask));

		raw_spin_lock(&call_function.lock);
		list_del_rcu(&data->csd.list);
		raw_spin_unlock(&call_function.lock);

		csd_unlock(&data->csd);
	}

}

/*
 * Invoked by arch to handle an IPI for call function single. Must be
 * called from the arch with interrupts disabled.
 */
void generic_smp_call_function_single_interrupt(void)
{
	struct call_single_queue *q = &__get_cpu_var(call_single_queue);
	unsigned int data_flags;
	LIST_HEAD(list);

	/*
	 * Shouldn't receive this interrupt on a cpu that is not yet online.
	 */
	WARN_ON_ONCE(!cpu_online(smp_processor_id()));

	raw_spin_lock(&q->lock);
	list_replace_init(&q->list, &list);
	raw_spin_unlock(&q->lock);

	while (!list_empty(&list)) {
		struct call_single_data *data;

		data = list_entry(list.next, struct call_single_data, list);
		list_del(&data->list);

		/*
		 * 'data' can be invalid after this call if flags == 0
		 * (when called through generic_exec_single()),
		 * so save them away before making the call:
		 */
		data_flags = data->flags;

		data->func(data->info);

		/*
		 * Unlocked CSDs are valid through generic_exec_single():
		 */
		if (data_flags & CSD_FLAG_LOCK)
			csd_unlock(data);
	}
}

static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);

/*
 * smp_call_function_single - Run a function on a specific CPU
 * @func: The function to run. This must be fast and non-blocking.
 * @info: An arbitrary pointer to pass to the function.
 * @wait: If true, wait until function has completed on other CPUs.
 *
 * Returns 0 on success, else a negative status code.
 */
int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
			     int wait)
{
	struct call_single_data d = {
		.flags = 0,
	};
	unsigned long flags;
	int this_cpu;
	int err = 0;

	/*
	 * prevent preemption and reschedule on another processor,
	 * as well as CPU removal
	 */
	this_cpu = get_cpu();

	/*
	 * Can deadlock when called with interrupts disabled.
	 * We allow cpu's that are not yet online though, as no one else can
	 * send smp call function interrupt to this cpu and as such deadlocks
	 * can't happen.
	 */
	WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
		     && !oops_in_progress);

	if (cpu == this_cpu) {
		local_irq_save(flags);
		func(info);
		local_irq_restore(flags);
	} else {
		if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
			struct call_single_data *data = &d;

			if (!wait)
				data = &__get_cpu_var(csd_data);

			csd_lock(data);

			data->func = func;
			data->info = info;
			generic_exec_single(cpu, data, wait);
		} else {
			err = -ENXIO;	/* CPU not online */
		}
	}

	put_cpu();

	return err;
}
EXPORT_SYMBOL(smp_call_function_single);

/*
 * smp_call_function_any - Run a function on any of the given cpus
 * @mask: The mask of cpus it can run on.
 * @func: The function to run. This must be fast and non-blocking.
 * @info: An arbitrary pointer to pass to the function.
 * @wait: If true, wait until function has completed.
 *
 * Returns 0 on success, else a negative status code (if no cpus were online).
 * Note that @wait will be implicitly turned on in case of allocation failures,
 * since we fall back to on-stack allocation.
 *
 * Selection preference:
 *	1) current cpu if in @mask
 *	2) any cpu of current node if in @mask
 *	3) any other online cpu in @mask
 */
int smp_call_function_any(const struct cpumask *mask,
			  smp_call_func_t func, void *info, int wait)
{
	unsigned int cpu;
	const struct cpumask *nodemask;
	int ret;

	/* Try for same CPU (cheapest) */
	cpu = get_cpu();
	if (cpumask_test_cpu(cpu, mask))
		goto call;

	/* Try for same node. */
	nodemask = cpumask_of_node(cpu_to_node(cpu));
	for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids;
	     cpu = cpumask_next_and(cpu, nodemask, mask)) {
		if (cpu_online(cpu))
			goto call;
	}

	/* Any online will do: smp_call_function_single handles nr_cpu_ids. */
	cpu = cpumask_any_and(mask, cpu_online_mask);
call:
	ret = smp_call_function_single(cpu, func, info, wait);
	put_cpu();
	return ret;
}
EXPORT_SYMBOL_GPL(smp_call_function_any);

/**
 * __smp_call_function_single(): Run a function on a specific CPU
 * @cpu: The CPU to run on.
 * @data: Pre-allocated and setup data structure
 * @wait: If true, wait until function has completed on specified CPU.
 *
 * Like smp_call_function_single(), but allow caller to pass in a
 * pre-allocated data structure. Useful for embedding @data inside
 * other structures, for instance.
 */
void __smp_call_function_single(int cpu, struct call_single_data *data,
				int wait)
{
	unsigned int this_cpu;
	unsigned long flags;

	this_cpu = get_cpu();
	/*
	 * Can deadlock when called with interrupts disabled.
	 * We allow cpu's that are not yet online though, as no one else can
	 * send smp call function interrupt to this cpu and as such deadlocks
	 * can't happen.
	 */
	WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
		     && !oops_in_progress);

	if (cpu == this_cpu) {
		local_irq_save(flags);
		data->func(data->info);
		local_irq_restore(flags);
	} else {
		csd_lock(data);
		generic_exec_single(cpu, data, wait);
	}
	put_cpu();
}

/**
 * smp_call_function_many(): Run a function on a set of other CPUs.
 * @mask: The set of cpus to run on (only runs on online subset).
 * @func: The function to run. This must be fast and non-blocking.
 * @info: An arbitrary pointer to pass to the function.
 * @wait: If true, wait (atomically) until function has completed
 *        on other CPUs.
 *
 * If @wait is true, then returns once @func has returned.
 *
 * You must not call this function with disabled interrupts or from a
 * hardware interrupt handler or from a bottom half handler. Preemption
 * must be disabled when calling this function.
 */
void smp_call_function_many(const struct cpumask *mask,
			    smp_call_func_t func, void *info, bool wait)
{
	struct call_function_data *data;
	unsigned long flags;
	int cpu, next_cpu, this_cpu = smp_processor_id();

	/*
	 * Can deadlock when called with interrupts disabled.
	 * We allow cpu's that are not yet online though, as no one else can
	 * send smp call function interrupt to this cpu and as such deadlocks
	 * can't happen.
	 */
	WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
		     && !oops_in_progress && !early_boot_irqs_disabled);

	/* So, what's a CPU they want? Ignoring this one. */
	cpu = cpumask_first_and(mask, cpu_online_mask);
	if (cpu == this_cpu)
		cpu = cpumask_next_and(cpu, mask, cpu_online_mask);

	/* No online cpus?  We're done. */
	if (cpu >= nr_cpu_ids)
		return;

	/* Do we have another CPU which isn't us? */
	next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
	if (next_cpu == this_cpu)
		next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);

	/* Fastpath: do that cpu by itself. */
	if (next_cpu >= nr_cpu_ids) {
		smp_call_function_single(cpu, func, info, wait);
		return;
	}

	data = &__get_cpu_var(cfd_data);
	csd_lock(&data->csd);
	BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask));

	data->csd.func = func;
	data->csd.info = info;
	cpumask_and(data->cpumask, mask, cpu_online_mask);
	cpumask_clear_cpu(this_cpu, data->cpumask);

	/*
	 * To ensure the interrupt handler gets an complete view
	 * we order the cpumask and refs writes and order the read
	 * of them in the interrupt handler.  In addition we may
	 * only clear our own cpu bit from the mask.
	 */
	smp_wmb();

	atomic_set(&data->refs, cpumask_weight(data->cpumask));

	raw_spin_lock_irqsave(&call_function.lock, flags);
	/*
	 * Place entry at the _HEAD_ of the list, so that any cpu still
	 * observing the entry in generic_smp_call_function_interrupt()
	 * will not miss any other list entries:
	 */
	list_add_rcu(&data->csd.list, &call_function.queue);
	raw_spin_unlock_irqrestore(&call_function.lock, flags);

	/*
	 * Make the list addition visible before sending the ipi.
	 * (IPIs must obey or appear to obey normal Linux cache
	 * coherency rules -- see comment in generic_exec_single).
	 */
	smp_mb();

	/* Send a message to all CPUs in the map */
	arch_send_call_function_ipi_mask(data->cpumask);

	/* Optionally wait for the CPUs to complete */
	if (wait)
		csd_lock_wait(&data->csd);
}
EXPORT_SYMBOL(smp_call_function_many);

/**
 * smp_call_function(): Run a function on all other CPUs.
 * @func: The function to run. This must be fast and non-blocking.
 * @info: An arbitrary pointer to pass to the function.
 * @wait: If true, wait (atomically) until function has completed
 *        on other CPUs.
 *
 * Returns 0.
 *
 * If @wait is true, then returns once @func has returned; otherwise
 * it returns just before the target cpu calls @func.
 *
 * You must not call this function with disabled interrupts or from a
 * hardware interrupt handler or from a bottom half handler.
 */
int smp_call_function(smp_call_func_t func, void *info, int wait)
{
	preempt_disable();
	smp_call_function_many(cpu_online_mask, func, info, wait);
	preempt_enable();

	return 0;
}
EXPORT_SYMBOL(smp_call_function);

void ipi_call_lock(void)
{
	raw_spin_lock(&call_function.lock);
}

void ipi_call_unlock(void)
{
	raw_spin_unlock(&call_function.lock);
}

void ipi_call_lock_irq(void)
{
	raw_spin_lock_irq(&call_function.lock);
}

void ipi_call_unlock_irq(void)
{
	raw_spin_unlock_irq(&call_function.lock);
}
#endif /* USE_GENERIC_SMP_HELPERS */

/*
 * Call a function on all processors.  May be used during early boot while
 * early_boot_irqs_disabled is set.  Use local_irq_save/restore() instead
 * of local_irq_disable/enable().
 */
int on_each_cpu(void (*func) (void *info), void *info, int wait)
{
	unsigned long flags;
	int ret = 0;

	preempt_disable();
	ret = smp_call_function(func, info, wait);
	local_irq_save(flags);
	func(info);
	local_irq_restore(flags);
	preempt_enable();
	return ret;
}
EXPORT_SYMBOL(on_each_cpu);