summaryrefslogtreecommitdiffstats
path: root/kernel/power/main.c
blob: 2a19f347bd8aa7414091d0ae4741158835fe6276 (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
/*
 * kernel/power/main.c - PM subsystem core functionality.
 *
 * Copyright (c) 2003 Patrick Mochel
 * Copyright (c) 2003 Open Source Development Lab
 * 
 * This file is released under the GPLv2
 *
 */

#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/kobject.h>
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/kmod.h>
#include <linux/init.h>
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/resume-trace.h>
#include <linux/freezer.h>
#include <linux/vmstat.h>
#include <linux/syscalls.h>

#include "power.h"

DEFINE_MUTEX(pm_mutex);

unsigned int pm_flags;
EXPORT_SYMBOL(pm_flags);

#ifdef CONFIG_PM_SLEEP

/* Routines for PM-transition notifications */

static BLOCKING_NOTIFIER_HEAD(pm_chain_head);

int register_pm_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&pm_chain_head, nb);
}
EXPORT_SYMBOL_GPL(register_pm_notifier);

int unregister_pm_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&pm_chain_head, nb);
}
EXPORT_SYMBOL_GPL(unregister_pm_notifier);

int pm_notifier_call_chain(unsigned long val)
{
	return (blocking_notifier_call_chain(&pm_chain_head, val, NULL)
			== NOTIFY_BAD) ? -EINVAL : 0;
}

#ifdef CONFIG_PM_DEBUG
int pm_test_level = TEST_NONE;

static const char * const pm_tests[__TEST_AFTER_LAST] = {
	[TEST_NONE] = "none",
	[TEST_CORE] = "core",
	[TEST_CPUS] = "processors",
	[TEST_PLATFORM] = "platform",
	[TEST_DEVICES] = "devices",
	[TEST_FREEZER] = "freezer",
};

static ssize_t pm_test_show(struct kobject *kobj, struct kobj_attribute *attr,
				char *buf)
{
	char *s = buf;
	int level;

	for (level = TEST_FIRST; level <= TEST_MAX; level++)
		if (pm_tests[level]) {
			if (level == pm_test_level)
				s += sprintf(s, "[%s] ", pm_tests[level]);
			else
				s += sprintf(s, "%s ", pm_tests[level]);
		}

	if (s != buf)
		/* convert the last space to a newline */
		*(s-1) = '\n';

	return (s - buf);
}

static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
				const char *buf, size_t n)
{
	const char * const *s;
	int level;
	char *p;
	int len;
	int error = -EINVAL;

	p = memchr(buf, '\n', n);
	len = p ? p - buf : n;

	mutex_lock(&pm_mutex);

	level = TEST_FIRST;
	for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++)
		if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) {
			pm_test_level = level;
			error = 0;
			break;
		}

	mutex_unlock(&pm_mutex);

	return error ? error : n;
}

power_attr(pm_test);
#endif /* CONFIG_PM_DEBUG */

#endif /* CONFIG_PM_SLEEP */

#ifdef CONFIG_SUSPEND

static int suspend_test(int level)
{
#ifdef CONFIG_PM_DEBUG
	if (pm_test_level == level) {
		printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
		mdelay(5000);
		return 1;
	}
#endif /* !CONFIG_PM_DEBUG */
	return 0;
}

#ifdef CONFIG_PM_TEST_SUSPEND

/*
 * We test the system suspend code by setting an RTC wakealarm a short
 * time in the future, then suspending.  Suspending the devices won't
 * normally take long ... some systems only need a few milliseconds.
 *
 * The time it takes is system-specific though, so when we test this
 * during system bootup we allow a LOT of time.
 */
#define TEST_SUSPEND_SECONDS	5

static unsigned long suspend_test_start_time;

static void suspend_test_start(void)
{
	/* FIXME Use better timebase than "jiffies", ideally a clocksource.
	 * What we want is a hardware counter that will work correctly even
	 * during the irqs-are-off stages of the suspend/resume cycle...
	 */
	suspend_test_start_time = jiffies;
}

static void suspend_test_finish(const char *label)
{
	long nj = jiffies - suspend_test_start_time;
	unsigned msec;

	msec = jiffies_to_msecs(abs(nj));
	pr_info("PM: %s took %d.%03d seconds\n", label,
			msec / 1000, msec % 1000);

	/* Warning on suspend means the RTC alarm period needs to be
	 * larger -- the system was sooo slooowwww to suspend that the
	 * alarm (should have) fired before the system went to sleep!
	 *
	 * Warning on either suspend or resume also means the system
	 * has some performance issues.  The stack dump of a WARN_ON
	 * is more likely to get the right attention than a printk...
	 */
	WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
}

#else

static void suspend_test_start(void)
{
}

static void suspend_test_finish(const char *label)
{
}

#endif

static struct platform_suspend_ops *suspend_ops;

/**
 *	suspend_set_ops - Set the global suspend method table.
 *	@ops:	Pointer to ops structure.
 */

void suspend_set_ops(struct platform_suspend_ops *ops)
{
	mutex_lock(&pm_mutex);
	suspend_ops = ops;
	mutex_unlock(&pm_mutex);
}

/**
 * suspend_valid_only_mem - generic memory-only valid callback
 *
 * Platform drivers that implement mem suspend only and only need
 * to check for that in their .valid callback can use this instead
 * of rolling their own .valid callback.
 */
int suspend_valid_only_mem(suspend_state_t state)
{
	return state == PM_SUSPEND_MEM;
}

/**
 *	suspend_prepare - Do prep work before entering low-power state.
 *
 *	This is common code that is called for each state that we're entering.
 *	Run suspend notifiers, allocate a console and stop all processes.
 */
static int suspend_prepare(void)
{
	int error;

	if (!suspend_ops || !suspend_ops->enter)
		return -EPERM;

	pm_prepare_console();

	error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
	if (error)
		goto Finish;

	error = usermodehelper_disable();
	if (error)
		goto Finish;

	error = suspend_freeze_processes();
	if (!error)
		return 0;

	suspend_thaw_processes();
	usermodehelper_enable();
 Finish:
	pm_notifier_call_chain(PM_POST_SUSPEND);
	pm_restore_console();
	return error;
}

/* default implementation */
void __attribute__ ((weak)) arch_suspend_disable_irqs(void)
{
	local_irq_disable();
}

/* default implementation */
void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
{
	local_irq_enable();
}

/**
 *	suspend_enter - enter the desired system sleep state.
 *	@state:		state to enter
 *
 *	This function should be called after devices have been suspended.
 */
static int suspend_enter(suspend_state_t state)
{
	int error;

	if (suspend_ops->prepare) {
		error = suspend_ops->prepare();
		if (error)
			return error;
	}

	error = dpm_suspend_noirq(PMSG_SUSPEND);
	if (error) {
		printk(KERN_ERR "PM: Some devices failed to power down\n");
		goto Platfrom_finish;
	}

	if (suspend_ops->prepare_late) {
		error = suspend_ops->prepare_late();
		if (error)
			goto Power_up_devices;
	}

	if (suspend_test(TEST_PLATFORM))
		goto Platform_wake;

	error = disable_nonboot_cpus();
	if (error || suspend_test(TEST_CPUS))
		goto Enable_cpus;

	arch_suspend_disable_irqs();
	BUG_ON(!irqs_disabled());

	error = sysdev_suspend(PMSG_SUSPEND);
	if (!error) {
		if (!suspend_test(TEST_CORE))
			error = suspend_ops->enter(state);
		sysdev_resume();
	}

	arch_suspend_enable_irqs();
	BUG_ON(irqs_disabled());

 Enable_cpus:
	enable_nonboot_cpus();

 Platform_wake:
	if (suspend_ops->wake)
		suspend_ops->wake();

 Power_up_devices:
	dpm_resume_noirq(PMSG_RESUME);

 Platfrom_finish:
	if (suspend_ops->finish)
		suspend_ops->finish();

	return error;
}

/**
 *	suspend_devices_and_enter - suspend devices and enter the desired system
 *				    sleep state.
 *	@state:		  state to enter
 */
int suspend_devices_and_enter(suspend_state_t state)
{
	int error;

	if (!suspend_ops)
		return -ENOSYS;

	if (suspend_ops->begin) {
		error = suspend_ops->begin(state);
		if (error)
			goto Close;
	}
	suspend_console();
	suspend_test_start();
	error = dpm_suspend_start(PMSG_SUSPEND);
	if (error) {
		printk(KERN_ERR "PM: Some devices failed to suspend\n");
		goto Recover_platform;
	}
	suspend_test_finish("suspend devices");
	if (suspend_test(TEST_DEVICES))
		goto Recover_platform;

	suspend_enter(state);

 Resume_devices:
	suspend_test_start();
	dpm_resume_end(PMSG_RESUME);
	suspend_test_finish("resume devices");
	resume_console();
 Close:
	if (suspend_ops->end)
		suspend_ops->end();
	return error;

 Recover_platform:
	if (suspend_ops->recover)
		suspend_ops->recover();
	goto Resume_devices;
}

/**
 *	suspend_finish - Do final work before exiting suspend sequence.
 *
 *	Call platform code to clean up, restart processes, and free the 
 *	console that we've allocated. This is not called for suspend-to-disk.
 */
static void suspend_finish(void)
{
	suspend_thaw_processes();
	usermodehelper_enable();
	pm_notifier_call_chain(PM_POST_SUSPEND);
	pm_restore_console();
}




static const char * const pm_states[PM_SUSPEND_MAX] = {
	[PM_SUSPEND_STANDBY]	= "standby",
	[PM_SUSPEND_MEM]	= "mem",
};

static inline int valid_state(suspend_state_t state)
{
	/* All states need lowlevel support and need to be valid
	 * to the lowlevel implementation, no valid callback
	 * implies that none are valid. */
	if (!suspend_ops || !suspend_ops->valid || !suspend_ops->valid(state))
		return 0;
	return 1;
}


/**
 *	enter_state - Do common work of entering low-power state.
 *	@state:		pm_state structure for state we're entering.
 *
 *	Make sure we're the only ones trying to enter a sleep state. Fail
 *	if someone has beat us to it, since we don't want anything weird to
 *	happen when we wake up.
 *	Then, do the setup for suspend, enter the state, and cleaup (after
 *	we've woken up).
 */
static int enter_state(suspend_state_t state)
{
	int error;

	if (!valid_state(state))
		return -ENODEV;

	if (!mutex_trylock(&pm_mutex))
		return -EBUSY;

	printk(KERN_INFO "PM: Syncing filesystems ... ");
	sys_sync();
	printk("done.\n");

	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
	error = suspend_prepare();
	if (error)
		goto Unlock;

	if (suspend_test(TEST_FREEZER))
		goto Finish;

	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
	error = suspend_devices_and_enter(state);

 Finish:
	pr_debug("PM: Finishing wakeup.\n");
	suspend_finish();
 Unlock:
	mutex_unlock(&pm_mutex);
	return error;
}


/**
 *	pm_suspend - Externally visible function for suspending system.
 *	@state:		Enumerated value of state to enter.
 *
 *	Determine whether or not value is within range, get state 
 *	structure, and enter (above).
 */

int pm_suspend(suspend_state_t state)
{
	if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
		return enter_state(state);
	return -EINVAL;
}

EXPORT_SYMBOL(pm_suspend);

#endif /* CONFIG_SUSPEND */

struct kobject *power_kobj;

/**
 *	state - control system power state.
 *
 *	show() returns what states are supported, which is hard-coded to
 *	'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and
 *	'disk' (Suspend-to-Disk).
 *
 *	store() accepts one of those strings, translates it into the 
 *	proper enumerated value, and initiates a suspend transition.
 */

static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
			  char *buf)
{
	char *s = buf;
#ifdef CONFIG_SUSPEND
	int i;

	for (i = 0; i < PM_SUSPEND_MAX; i++) {
		if (pm_states[i] && valid_state(i))
			s += sprintf(s,"%s ", pm_states[i]);
	}
#endif
#ifdef CONFIG_HIBERNATION
	s += sprintf(s, "%s\n", "disk");
#else
	if (s != buf)
		/* convert the last space to a newline */
		*(s-1) = '\n';
#endif
	return (s - buf);
}

static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
			   const char *buf, size_t n)
{
#ifdef CONFIG_SUSPEND
	suspend_state_t state = PM_SUSPEND_STANDBY;
	const char * const *s;
#endif
	char *p;
	int len;
	int error = -EINVAL;

	p = memchr(buf, '\n', n);
	len = p ? p - buf : n;

	/* First, check if we are requested to hibernate */
	if (len == 4 && !strncmp(buf, "disk", len)) {
		error = hibernate();
  goto Exit;
	}

#ifdef CONFIG_SUSPEND
	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) {
		if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
			break;
	}
	if (state < PM_SUSPEND_MAX && *s)
		error = enter_state(state);
#endif

 Exit:
	return error ? error : n;
}

power_attr(state);

#ifdef CONFIG_PM_TRACE
int pm_trace_enabled;

static ssize_t pm_trace_show(struct kobject *kobj, struct kobj_attribute *attr,
			     char *buf)
{
	return sprintf(buf, "%d\n", pm_trace_enabled);
}

static ssize_t
pm_trace_store(struct kobject *kobj, struct kobj_attribute *attr,
	       const char *buf, size_t n)
{
	int val;

	if (sscanf(buf, "%d", &val) == 1) {
		pm_trace_enabled = !!val;
		return n;
	}
	return -EINVAL;
}

power_attr(pm_trace);
#endif /* CONFIG_PM_TRACE */

static struct attribute * g[] = {
	&state_attr.attr,
#ifdef CONFIG_PM_TRACE
	&pm_trace_attr.attr,
#endif
#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_PM_DEBUG)
	&pm_test_attr.attr,
#endif
	NULL,
};

static struct attribute_group attr_group = {
	.attrs = g,
};


static int __init pm_init(void)
{
	power_kobj = kobject_create_and_add("power", NULL);
	if (!power_kobj)
		return -ENOMEM;
	return sysfs_create_group(power_kobj, &attr_group);
}

core_initcall(pm_init);


#ifdef CONFIG_PM_TEST_SUSPEND

#include <linux/rtc.h>

/*
 * To test system suspend, we need a hands-off mechanism to resume the
 * system.  RTCs wake alarms are a common self-contained mechanism.
 */

static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
{
	static char err_readtime[] __initdata =
		KERN_ERR "PM: can't read %s time, err %d\n";
	static char err_wakealarm [] __initdata =
		KERN_ERR "PM: can't set %s wakealarm, err %d\n";
	static char err_suspend[] __initdata =
		KERN_ERR "PM: suspend test failed, error %d\n";
	static char info_test[] __initdata =
		KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";

	unsigned long		now;
	struct rtc_wkalrm	alm;
	int			status;

	/* this may fail if the RTC hasn't been initialized */
	status = rtc_read_time(rtc, &alm.time);
	if (status < 0) {
		printk(err_readtime, dev_name(&rtc->dev), status);
		return;
	}
	rtc_tm_to_time(&alm.time, &now);

	memset(&alm, 0, sizeof alm);
	rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
	alm.enabled = true;

	status = rtc_set_alarm(rtc, &alm);
	if (status < 0) {
		printk(err_wakealarm, dev_name(&rtc->dev), status);
		return;
	}

	if (state == PM_SUSPEND_MEM) {
		printk(info_test, pm_states[state]);
		status = pm_suspend(state);
		if (status == -ENODEV)
			state = PM_SUSPEND_STANDBY;
	}
	if (state == PM_SUSPEND_STANDBY) {
		printk(info_test, pm_states[state]);
		status = pm_suspend(state);
	}
	if (status < 0)
		printk(err_suspend, status);

	/* Some platforms can't detect that the alarm triggered the
	 * wakeup, or (accordingly) disable it after it afterwards.
	 * It's supposed to give oneshot behavior; cope.
	 */
	alm.enabled = false;
	rtc_set_alarm(rtc, &alm);
}

static int __init has_wakealarm(struct device *dev, void *name_ptr)
{
	struct rtc_device *candidate = to_rtc_device(dev);

	if (!candidate->ops->set_alarm)
		return 0;
	if (!device_may_wakeup(candidate->dev.parent))
		return 0;

	*(const char **)name_ptr = dev_name(dev);
	return 1;
}

/*
 * Kernel options like "test_suspend=mem" force suspend/resume sanity tests
 * at startup time.  They're normally disabled, for faster boot and because
 * we can't know which states really work on this particular system.
 */
static suspend_state_t test_state __initdata = PM_SUSPEND_ON;

static char warn_bad_state[] __initdata =
	KERN_WARNING "PM: can't test '%s' suspend state\n";

static int __init setup_test_suspend(char *value)
{
	unsigned i;

	/* "=mem" ==> "mem" */
	value++;
	for (i = 0; i < PM_SUSPEND_MAX; i++) {
		if (!pm_states[i])
			continue;
		if (strcmp(pm_states[i], value) != 0)
			continue;
		test_state = (__force suspend_state_t) i;
		return 0;
	}
	printk(warn_bad_state, value);
	return 0;
}
__setup("test_suspend", setup_test_suspend);

static int __init test_suspend(void)
{
	static char		warn_no_rtc[] __initdata =
		KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";

	char			*pony = NULL;
	struct rtc_device	*rtc = NULL;

	/* PM is initialized by now; is that state testable? */
	if (test_state == PM_SUSPEND_ON)
		goto done;
	if (!valid_state(test_state)) {
		printk(warn_bad_state, pm_states[test_state]);
		goto done;
	}

	/* RTCs have initialized by now too ... can we use one? */
	class_find_device(rtc_class, NULL, &pony, has_wakealarm);
	if (pony)
		rtc = rtc_class_open(pony);
	if (!rtc) {
		printk(warn_no_rtc);
		goto done;
	}

	/* go for it */
	test_wakealarm(rtc, test_state);
	rtc_class_close(rtc);
done:
	return 0;
}
late_initcall(test_suspend);

#endif /* CONFIG_PM_TEST_SUSPEND */
OpenPOWER on IntegriCloud