aboutsummaryrefslogtreecommitdiff
path: root/kernel/watchdog.c
blob: ecb0e8346e6534901bb6c94bec71e7e92baa104c (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Detect hard and soft lockups on a system
 *
 * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
 *
 * Note: Most of this code is borrowed heavily from the original softlockup
 * detector, so thanks to Ingo for the initial implementation.
 * Some chunks also taken from the old x86-specific nmi watchdog code, thanks
 * to those contributors as well.
 */

#define pr_fmt(fmt) "watchdog: " fmt

#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/tick.h>
#include <linux/sched/clock.h>
#include <linux/sched/debug.h>
#include <linux/sched/isolation.h>
#include <linux/stop_machine.h>

#include <asm/irq_regs.h>
#include <linux/kvm_para.h>

static DEFINE_MUTEX(watchdog_mutex);

#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED)
# define NMI_WATCHDOG_DEFAULT	1
#else
# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED)
# define NMI_WATCHDOG_DEFAULT	0
#endif

unsigned long __read_mostly watchdog_enabled;
int __read_mostly watchdog_user_enabled = 1;
int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT;
int __read_mostly soft_watchdog_user_enabled = 1;
int __read_mostly watchdog_thresh = 10;
static int __read_mostly nmi_watchdog_available;

struct cpumask watchdog_cpumask __read_mostly;
unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);

#ifdef CONFIG_HARDLOCKUP_DETECTOR

# ifdef CONFIG_SMP
int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
# endif /* CONFIG_SMP */

/*
 * Should we panic when a soft-lockup or hard-lockup occurs:
 */
unsigned int __read_mostly hardlockup_panic =
			IS_ENABLED(CONFIG_BOOTPARAM_HARDLOCKUP_PANIC);
/*
 * We may not want to enable hard lockup detection by default in all cases,
 * for example when running the kernel as a guest on a hypervisor. In these
 * cases this function can be called to disable hard lockup detection. This
 * function should only be executed once by the boot processor before the
 * kernel command line parameters are parsed, because otherwise it is not
 * possible to override this in hardlockup_panic_setup().
 */
void __init hardlockup_detector_disable(void)
{
	nmi_watchdog_user_enabled = 0;
}

static int __init hardlockup_panic_setup(char *str)
{
	if (!strncmp(str, "panic", 5))
		hardlockup_panic = 1;
	else if (!strncmp(str, "nopanic", 7))
		hardlockup_panic = 0;
	else if (!strncmp(str, "0", 1))
		nmi_watchdog_user_enabled = 0;
	else if (!strncmp(str, "1", 1))
		nmi_watchdog_user_enabled = 1;
	return 1;
}
__setup("nmi_watchdog=", hardlockup_panic_setup);

#endif /* CONFIG_HARDLOCKUP_DETECTOR */

/*
 * These functions can be overridden if an architecture implements its
 * own hardlockup detector.
 *
 * watchdog_nmi_enable/disable can be implemented to start and stop when
 * softlockup watchdog start and stop. The arch must select the
 * SOFTLOCKUP_DETECTOR Kconfig.
 */
int __weak watchdog_nmi_enable(unsigned int cpu)
{
	hardlockup_detector_perf_enable();
	return 0;
}

void __weak watchdog_nmi_disable(unsigned int cpu)
{
	hardlockup_detector_perf_disable();
}

/* Return 0, if a NMI watchdog is available. Error code otherwise */
int __weak __init watchdog_nmi_probe(void)
{
	return hardlockup_detector_perf_init();
}

/**
 * watchdog_nmi_stop - Stop the watchdog for reconfiguration
 *
 * The reconfiguration steps are:
 * watchdog_nmi_stop();
 * update_variables();
 * watchdog_nmi_start();
 */
void __weak watchdog_nmi_stop(void) { }

/**
 * watchdog_nmi_start - Start the watchdog after reconfiguration
 *
 * Counterpart to watchdog_nmi_stop().
 *
 * The following variables have been updated in update_variables() and
 * contain the currently valid configuration:
 * - watchdog_enabled
 * - watchdog_thresh
 * - watchdog_cpumask
 */
void __weak watchdog_nmi_start(void) { }

/**
 * lockup_detector_update_enable - Update the sysctl enable bit
 *
 * Caller needs to make sure that the NMI/perf watchdogs are off, so this
 * can't race with watchdog_nmi_disable().
 */
static void lockup_detector_update_enable(void)
{
	watchdog_enabled = 0;
	if (!watchdog_user_enabled)
		return;
	if (nmi_watchdog_available && nmi_watchdog_user_enabled)
		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
	if (soft_watchdog_user_enabled)
		watchdog_enabled |= SOFT_WATCHDOG_ENABLED;
}

#ifdef CONFIG_SOFTLOCKUP_DETECTOR

/*
 * Delay the soflockup report when running a known slow code.
 * It does _not_ affect the timestamp of the last successdul reschedule.
 */
#define SOFTLOCKUP_DELAY_REPORT	ULONG_MAX

#ifdef CONFIG_SMP
int __read_mostly sysctl_softlockup_all_cpu_backtrace;
#endif

static struct cpumask watchdog_allowed_mask __read_mostly;

/* Global variables, exported for sysctl */
unsigned int __read_mostly softlockup_panic =
			IS_ENABLED(CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC);

static bool softlockup_initialized __read_mostly;
static u64 __read_mostly sample_period;

/* Timestamp taken after the last successful reschedule. */
static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
/* Timestamp of the last softlockup report. */
static DEFINE_PER_CPU(unsigned long, watchdog_report_ts);
static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
static DEFINE_PER_CPU(bool, softlockup_touch_sync);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
static unsigned long soft_lockup_nmi_warn;

static int __init nowatchdog_setup(char *str)
{
	watchdog_user_enabled = 0;
	return 1;
}
__setup("nowatchdog", nowatchdog_setup);

static int __init nosoftlockup_setup(char *str)
{
	soft_watchdog_user_enabled = 0;
	return 1;
}
__setup("nosoftlockup", nosoftlockup_setup);

static int __init watchdog_thresh_setup(char *str)
{
	get_option(&str, &watchdog_thresh);
	return 1;
}
__setup("watchdog_thresh=", watchdog_thresh_setup);

static void __lockup_detector_cleanup(void);

/*
 * Hard-lockup warnings should be triggered after just a few seconds. Soft-
 * lockups can have false positives under extreme conditions. So we generally
 * want a higher threshold for soft lockups than for hard lockups. So we couple
 * the thresholds with a factor: we make the soft threshold twice the amount of
 * time the hard threshold is.
 */
static int get_softlockup_thresh(void)
{
	return watchdog_thresh * 2;
}

/*
 * Returns seconds, approximately.  We don't need nanosecond
 * resolution, and we don't need to waste time with a big divide when
 * 2^30ns == 1.074s.
 */
static unsigned long get_timestamp(void)
{
	return running_clock() >> 30LL;  /* 2^30 ~= 10^9 */
}

static void set_sample_period(void)
{
	/*
	 * convert watchdog_thresh from seconds to ns
	 * the divide by 5 is to give hrtimer several chances (two
	 * or three with the current relation between the soft
	 * and hard thresholds) to increment before the
	 * hardlockup detector generates a warning
	 */
	sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5);
	watchdog_update_hrtimer_threshold(sample_period);
}

static void update_report_ts(void)
{
	__this_cpu_write(watchdog_report_ts, get_timestamp());
}

/* Commands for resetting the watchdog */
static void update_touch_ts(void)
{
	__this_cpu_write(watchdog_touch_ts, get_timestamp());
	update_report_ts();
}

/**
 * touch_softlockup_watchdog_sched - touch watchdog on scheduler stalls
 *
 * Call when the scheduler may have stalled for legitimate reasons
 * preventing the watchdog task from executing - e.g. the scheduler
 * entering idle state.  This should only be used for scheduler events.
 * Use touch_softlockup_watchdog() for everything else.
 */
notrace void touch_softlockup_watchdog_sched(void)
{
	/*
	 * Preemption can be enabled.  It doesn't matter which CPU's watchdog
	 * report period gets restarted here, so use the raw_ operation.
	 */
	raw_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT);
}

notrace void touch_softlockup_watchdog(void)
{
	touch_softlockup_watchdog_sched();
	wq_watchdog_touch(raw_smp_processor_id());
}
EXPORT_SYMBOL(touch_softlockup_watchdog);

void touch_all_softlockup_watchdogs(void)
{
	int cpu;

	/*
	 * watchdog_mutex cannpt be taken here, as this might be called
	 * from (soft)interrupt context, so the access to
	 * watchdog_allowed_cpumask might race with a concurrent update.
	 *
	 * The watchdog time stamp can race against a concurrent real
	 * update as well, the only side effect might be a cycle delay for
	 * the softlockup check.
	 */
	for_each_cpu(cpu, &watchdog_allowed_mask) {
		per_cpu(watchdog_report_ts, cpu) = SOFTLOCKUP_DELAY_REPORT;
		wq_watchdog_touch(cpu);
	}
}

void touch_softlockup_watchdog_sync(void)
{
	__this_cpu_write(softlockup_touch_sync, true);
	__this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT);
}

static int is_softlockup(unsigned long touch_ts,
			 unsigned long period_ts,
			 unsigned long now)
{
	if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){
		/* Warn about unreasonable delays. */
		if (time_after(now, period_ts + get_softlockup_thresh()))
			return now - touch_ts;
	}
	return 0;
}

/* watchdog detector functions */
bool is_hardlockup(void)
{
	unsigned long hrint = __this_cpu_read(hrtimer_interrupts);

	if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
		return true;

	__this_cpu_write(hrtimer_interrupts_saved, hrint);
	return false;
}

static void watchdog_interrupt_count(void)
{
	__this_cpu_inc(hrtimer_interrupts);
}

static DEFINE_PER_CPU(struct completion, softlockup_completion);
static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);

/*
 * The watchdog feed function - touches the timestamp.
 *
 * It only runs once every sample_period seconds (4 seconds by
 * default) to reset the softlockup timestamp. If this gets delayed
 * for more than 2*watchdog_thresh seconds then the debug-printout
 * triggers in watchdog_timer_fn().
 */
static int softlockup_fn(void *data)
{
	update_touch_ts();
	complete(this_cpu_ptr(&softlockup_completion));

	return 0;
}

/* watchdog kicker functions */
static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
{
	unsigned long touch_ts, period_ts, now;
	struct pt_regs *regs = get_irq_regs();
	int duration;
	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;

	if (!watchdog_enabled)
		return HRTIMER_NORESTART;

	/* kick the hardlockup detector */
	watchdog_interrupt_count();

	/* kick the softlockup detector */
	if (completion_done(this_cpu_ptr(&softlockup_completion))) {
		reinit_completion(this_cpu_ptr(&softlockup_completion));
		stop_one_cpu_nowait(smp_processor_id(),
				softlockup_fn, NULL,
				this_cpu_ptr(&softlockup_stop_work));
	}

	/* .. and repeat */
	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));

	/*
	 * Read the current timestamp first. It might become invalid anytime
	 * when a virtual machine is stopped by the host or when the watchog
	 * is touched from NMI.
	 */
	now = get_timestamp();
	/*
	 * If a virtual machine is stopped by the host it can look to
	 * the watchdog like a soft lockup. This function touches the watchdog.
	 */
	kvm_check_and_clear_guest_paused();
	/*
	 * The stored timestamp is comparable with @now only when not touched.
	 * It might get touched anytime from NMI. Make sure that is_softlockup()
	 * uses the same (valid) value.
	 */
	period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts));

	/* Reset the interval when touched by known problematic code. */
	if (period_ts == SOFTLOCKUP_DELAY_REPORT) {
		if (unlikely(__this_cpu_read(softlockup_touch_sync))) {
			/*
			 * If the time stamp was touched atomically
			 * make sure the scheduler tick is up to date.
			 */
			__this_cpu_write(softlockup_touch_sync, false);
			sched_clock_tick();
		}

		update_report_ts();
		return HRTIMER_RESTART;
	}

	/* Check for a softlockup. */
	touch_ts = __this_cpu_read(watchdog_touch_ts);
	duration = is_softlockup(touch_ts, period_ts, now);
	if (unlikely(duration)) {
		/*
		 * Prevent multiple soft-lockup reports if one cpu is already
		 * engaged in dumping all cpu back traces.
		 */
		if (softlockup_all_cpu_backtrace) {
			if (test_and_set_bit_lock(0, &soft_lockup_nmi_warn))
				return HRTIMER_RESTART;
		}

		/* Start period for the next softlockup warning. */
		update_report_ts();

		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
			smp_processor_id(), duration,
			current->comm, task_pid_nr(current));
		print_modules();
		print_irqtrace_events(current);
		if (regs)
			show_regs(regs);
		else
			dump_stack();

		if (softlockup_all_cpu_backtrace) {
			trigger_allbutself_cpu_backtrace();
			clear_bit_unlock(0, &soft_lockup_nmi_warn);
		}

		add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
		if (softlockup_panic)
			panic("softlockup: hung tasks");
	}

	return HRTIMER_RESTART;
}

static void watchdog_enable(unsigned int cpu)
{
	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
	struct completion *done = this_cpu_ptr(&softlockup_completion);

	WARN_ON_ONCE(cpu != smp_processor_id());

	init_completion(done);
	complete(done);

	/*
	 * Start the timer first to prevent the NMI watchdog triggering
	 * before the timer has a chance to fire.
	 */
	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
	hrtimer->function = watchdog_timer_fn;
	hrtimer_start(hrtimer, ns_to_ktime(sample_period),
		      HRTIMER_MODE_REL_PINNED_HARD);

	/* Initialize timestamp */
	update_touch_ts();
	/* Enable the perf event */
	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
		watchdog_nmi_enable(cpu);
}

static void watchdog_disable(unsigned int cpu)
{
	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);

	WARN_ON_ONCE(cpu != smp_processor_id());

	/*
	 * Disable the perf event first. That prevents that a large delay
	 * between disabling the timer and disabling the perf event causes
	 * the perf NMI to detect a false positive.
	 */
	watchdog_nmi_disable(cpu);
	hrtimer_cancel(hrtimer);
	wait_for_completion(this_cpu_ptr(&softlockup_completion));
}

static int softlockup_stop_fn(void *data)
{
	watchdog_disable(smp_processor_id());
	return 0;
}

static void softlockup_stop_all(void)
{
	int cpu;

	if (!softlockup_initialized)
		return;

	for_each_cpu(cpu, &watchdog_allowed_mask)
		smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false);

	cpumask_clear(&watchdog_allowed_mask);
}

static int softlockup_start_fn(void *data)
{
	watchdog_enable(smp_processor_id());
	return 0;
}

static void softlockup_start_all(void)
{
	int cpu;

	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
	for_each_cpu(cpu, &watchdog_allowed_mask)
		smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false);
}

int lockup_detector_online_cpu(unsigned int cpu)
{
	if (cpumask_test_cpu(cpu, &watchdog_allowed_mask))
		watchdog_enable(cpu);
	return 0;
}

int lockup_detector_offline_cpu(unsigned int cpu)
{
	if (cpumask_test_cpu(cpu, &watchdog_allowed_mask))
		watchdog_disable(cpu);
	return 0;
}

static void lockup_detector_reconfigure(void)
{
	cpus_read_lock();
	watchdog_nmi_stop();

	softlockup_stop_all();
	set_sample_period();
	lockup_detector_update_enable();
	if (watchdog_enabled && watchdog_thresh)
		softlockup_start_all();

	watchdog_nmi_start();
	cpus_read_unlock();
	/*
	 * Must be called outside the cpus locked section to prevent
	 * recursive locking in the perf code.
	 */
	__lockup_detector_cleanup();
}

/*
 * Create the watchdog infrastructure and configure the detector(s).
 */
static __init void lockup_detector_setup(void)
{
	/*
	 * If sysctl is off and watchdog got disabled on the command line,
	 * nothing to do here.
	 */
	lockup_detector_update_enable();

	if (!IS_ENABLED(CONFIG_SYSCTL) &&
	    !(watchdog_enabled && watchdog_thresh))
		return;

	mutex_lock(&watchdog_mutex);
	lockup_detector_reconfigure();
	softlockup_initialized = true;
	mutex_unlock(&watchdog_mutex);
}

#else /* CONFIG_SOFTLOCKUP_DETECTOR */
static void lockup_detector_reconfigure(void)
{
	cpus_read_lock();
	watchdog_nmi_stop();
	lockup_detector_update_enable();
	watchdog_nmi_start();
	cpus_read_unlock();
}
static inline void lockup_detector_setup(void)
{
	lockup_detector_reconfigure();
}
#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */

static void __lockup_detector_cleanup(void)
{
	lockdep_assert_held(&watchdog_mutex);
	hardlockup_detector_perf_cleanup();
}

/**
 * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes
 *
 * Caller must not hold the cpu hotplug rwsem.
 */
void lockup_detector_cleanup(void)
{
	mutex_lock(&watchdog_mutex);
	__lockup_detector_cleanup();
	mutex_unlock(&watchdog_mutex);
}

/**
 * lockup_detector_soft_poweroff - Interface to stop lockup detector(s)
 *
 * Special interface for parisc. It prevents lockup detector warnings from
 * the default pm_poweroff() function which busy loops forever.
 */
void lockup_detector_soft_poweroff(void)
{
	watchdog_enabled = 0;
}

#ifdef CONFIG_SYSCTL

/* Propagate any changes to the watchdog infrastructure */
static void proc_watchdog_update(void)
{
	/* Remove impossible cpus to keep sysctl output clean. */
	cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
	lockup_detector_reconfigure();
}

/*
 * common function for watchdog, nmi_watchdog and soft_watchdog parameter
 *
 * caller             | table->data points to      | 'which'
 * -------------------|----------------------------|--------------------------
 * proc_watchdog      | watchdog_user_enabled      | NMI_WATCHDOG_ENABLED |
 *                    |                            | SOFT_WATCHDOG_ENABLED
 * -------------------|----------------------------|--------------------------
 * proc_nmi_watchdog  | nmi_watchdog_user_enabled  | NMI_WATCHDOG_ENABLED
 * -------------------|----------------------------|--------------------------
 * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED
 */
static int proc_watchdog_common(int which, struct ctl_table *table, int write,
				void *buffer, size_t *lenp, loff_t *ppos)
{
	int err, old, *param = table->data;

	mutex_lock(&watchdog_mutex);

	if (!write) {
		/*
		 * On read synchronize the userspace interface. This is a
		 * racy snapshot.
		 */
		*param = (watchdog_enabled & which) != 0;
		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
	} else {
		old = READ_ONCE(*param);
		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
		if (!err && old != READ_ONCE(*param))
			proc_watchdog_update();
	}
	mutex_unlock(&watchdog_mutex);
	return err;
}

/*
 * /proc/sys/kernel/watchdog
 */
int proc_watchdog(struct ctl_table *table, int write,
		  void *buffer, size_t *lenp, loff_t *ppos)
{
	return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED,
				    table, write, buffer, lenp, ppos);
}

/*
 * /proc/sys/kernel/nmi_watchdog
 */
int proc_nmi_watchdog(struct ctl_table *table, int write,
		      void *buffer, size_t *lenp, loff_t *ppos)
{
	if (!nmi_watchdog_available && write)
		return -ENOTSUPP;
	return proc_watchdog_common(NMI_WATCHDOG_ENABLED,
				    table, write, buffer, lenp, ppos);
}

/*
 * /proc/sys/kernel/soft_watchdog
 */
int proc_soft_watchdog(struct ctl_table *table, int write,
			void *buffer, size_t *lenp, loff_t *ppos)
{
	return proc_watchdog_common(SOFT_WATCHDOG_ENABLED,
				    table, write, buffer, lenp, ppos);
}

/*
 * /proc/sys/kernel/watchdog_thresh
 */
int proc_watchdog_thresh(struct ctl_table *table, int write,
			 void *buffer, size_t *lenp, loff_t *ppos)
{
	int err, old;

	mutex_lock(&watchdog_mutex);

	old = READ_ONCE(watchdog_thresh);
	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);

	if (!err && write && old != READ_ONCE(watchdog_thresh))
		proc_watchdog_update();

	mutex_unlock(&watchdog_mutex);
	return err;
}

/*
 * The cpumask is the mask of possible cpus that the watchdog can run
 * on, not the mask of cpus it is actually running on.  This allows the
 * user to specify a mask that will include cpus that have not yet
 * been brought online, if desired.
 */
int proc_watchdog_cpumask(struct ctl_table *table, int write,
			  void *buffer, size_t *lenp, loff_t *ppos)
{
	int err;

	mutex_lock(&watchdog_mutex);

	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
	if (!err && write)
		proc_watchdog_update();

	mutex_unlock(&watchdog_mutex);
	return err;
}

static const int sixty = 60;

static struct ctl_table watchdog_sysctls[] = {
	{
		.procname       = "watchdog",
		.data		= &watchdog_user_enabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler   = proc_watchdog,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
	{
		.procname	= "watchdog_thresh",
		.data		= &watchdog_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_watchdog_thresh,
		.extra1		= SYSCTL_ZERO,
		.extra2		= (void *)&sixty,
	},
	{
		.procname       = "nmi_watchdog",
		.data		= &nmi_watchdog_user_enabled,
		.maxlen		= sizeof(int),
		.mode		= NMI_WATCHDOG_SYSCTL_PERM,
		.proc_handler   = proc_nmi_watchdog,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
	{
		.procname	= "watchdog_cpumask",
		.data		= &watchdog_cpumask_bits,
		.maxlen		= NR_CPUS,
		.mode		= 0644,
		.proc_handler	= proc_watchdog_cpumask,
	},
#ifdef CONFIG_SOFTLOCKUP_DETECTOR
	{
		.procname       = "soft_watchdog",
		.data		= &soft_watchdog_user_enabled,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler   = proc_soft_watchdog,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
	{
		.procname	= "softlockup_panic",
		.data		= &softlockup_panic,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
#ifdef CONFIG_SMP
	{
		.procname	= "softlockup_all_cpu_backtrace",
		.data		= &sysctl_softlockup_all_cpu_backtrace,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
#endif /* CONFIG_SMP */
#endif
#ifdef CONFIG_HARDLOCKUP_DETECTOR
	{
		.procname	= "hardlockup_panic",
		.data		= &hardlockup_panic,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
#ifdef CONFIG_SMP
	{
		.procname	= "hardlockup_all_cpu_backtrace",
		.data		= &sysctl_hardlockup_all_cpu_backtrace,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
#endif /* CONFIG_SMP */
#endif
	{}
};

static void __init watchdog_sysctl_init(void)
{
	register_sysctl_init("kernel", watchdog_sysctls);
}
#else
#define watchdog_sysctl_init() do { } while (0)
#endif /* CONFIG_SYSCTL */

void __init lockup_detector_init(void)
{
	if (tick_nohz_full_enabled())
		pr_info("Disabling watchdog on nohz_full cores by default\n");

	cpumask_copy(&watchdog_cpumask,
		     housekeeping_cpumask(HK_TYPE_TIMER));

	if (!watchdog_nmi_probe())
		nmi_watchdog_available = true;
	lockup_detector_setup();
	watchdog_sysctl_init();
}