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
|
/*
* Detect hard and soft lockups on a system
*
* started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
*
* this code detects hard lockups: incidents in where on a CPU
* the kernel does not respond to anything except NMI.
*
* Note: Most of this code is borrowed heavily from softlockup.c,
* so thanks to Ingo for the initial implementation.
* Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks
* to those contributors as well.
*/
#include <linux/mm.h>
#include <linux/cpu.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/lockdep.h>
#include <linux/notifier.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <asm/irq_regs.h>
#include <linux/perf_event.h>
int watchdog_enabled;
int __read_mostly softlockup_thresh = 60;
static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
static DEFINE_PER_CPU(bool, softlockup_touch_sync);
static DEFINE_PER_CPU(bool, soft_watchdog_warn);
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
#endif
static int no_watchdog;
/* boot commands */
/*
* Should we panic when a soft-lockup or hard-lockup occurs:
*/
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static int hardlockup_panic;
static int __init hardlockup_panic_setup(char *str)
{
if (!strncmp(str, "panic", 5))
hardlockup_panic = 1;
else if (!strncmp(str, "0", 1))
no_watchdog = 1;
return 1;
}
__setup("nmi_watchdog=", hardlockup_panic_setup);
#endif
unsigned int __read_mostly softlockup_panic =
CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
static int __init softlockup_panic_setup(char *str)
{
softlockup_panic = simple_strtoul(str, NULL, 0);
return 1;
}
__setup("softlockup_panic=", softlockup_panic_setup);
static int __init nowatchdog_setup(char *str)
{
no_watchdog = 1;
return 1;
}
__setup("nowatchdog", nowatchdog_setup);
/* deprecated */
static int __init nosoftlockup_setup(char *str)
{
no_watchdog = 1;
return 1;
}
__setup("nosoftlockup", nosoftlockup_setup);
/* */
/*
* 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(int this_cpu)
{
return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */
}
static unsigned long get_sample_period(void)
{
/*
* convert softlockup_thresh from seconds to ns
* the divide by 5 is to give hrtimer 5 chances to
* increment before the hardlockup detector generates
* a warning
*/
return softlockup_thresh / 5 * NSEC_PER_SEC;
}
/* Commands for resetting the watchdog */
static void __touch_watchdog(void)
{
int this_cpu = smp_processor_id();
__get_cpu_var(watchdog_touch_ts) = get_timestamp(this_cpu);
}
void touch_softlockup_watchdog(void)
{
__raw_get_cpu_var(watchdog_touch_ts) = 0;
}
EXPORT_SYMBOL(touch_softlockup_watchdog);
void touch_all_softlockup_watchdogs(void)
{
int cpu;
/*
* this is done lockless
* do we care if a 0 races with a timestamp?
* all it means is the softlock check starts one cycle later
*/
for_each_online_cpu(cpu)
per_cpu(watchdog_touch_ts, cpu) = 0;
}
#ifdef CONFIG_HARDLOCKUP_DETECTOR
void touch_nmi_watchdog(void)
{
if (watchdog_enabled) {
unsigned cpu;
for_each_present_cpu(cpu) {
if (per_cpu(watchdog_nmi_touch, cpu) != true)
per_cpu(watchdog_nmi_touch, cpu) = true;
}
}
touch_softlockup_watchdog();
}
EXPORT_SYMBOL(touch_nmi_watchdog);
#endif
void touch_softlockup_watchdog_sync(void)
{
__raw_get_cpu_var(softlockup_touch_sync) = true;
__raw_get_cpu_var(watchdog_touch_ts) = 0;
}
#ifdef CONFIG_HARDLOCKUP_DETECTOR
/* watchdog detector functions */
static int is_hardlockup(void)
{
unsigned long hrint = __get_cpu_var(hrtimer_interrupts);
if (__get_cpu_var(hrtimer_interrupts_saved) == hrint)
return 1;
__get_cpu_var(hrtimer_interrupts_saved) = hrint;
return 0;
}
#endif
static int is_softlockup(unsigned long touch_ts)
{
unsigned long now = get_timestamp(smp_processor_id());
/* Warn about unreasonable delays: */
if (time_after(now, touch_ts + softlockup_thresh))
return now - touch_ts;
return 0;
}
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static struct perf_event_attr wd_hw_attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES,
.size = sizeof(struct perf_event_attr),
.pinned = 1,
.disabled = 1,
};
/* Callback function for perf event subsystem */
static void watchdog_overflow_callback(struct perf_event *event, int nmi,
struct perf_sample_data *data,
struct pt_regs *regs)
{
/* Ensure the watchdog never gets throttled */
event->hw.interrupts = 0;
if (__get_cpu_var(watchdog_nmi_touch) == true) {
__get_cpu_var(watchdog_nmi_touch) = false;
return;
}
/* check for a hardlockup
* This is done by making sure our timer interrupt
* is incrementing. The timer interrupt should have
* fired multiple times before we overflow'd. If it hasn't
* then this is a good indication the cpu is stuck
*/
if (is_hardlockup()) {
int this_cpu = smp_processor_id();
/* only print hardlockups once */
if (__get_cpu_var(hard_watchdog_warn) == true)
return;
if (hardlockup_panic)
panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
else
WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu);
__get_cpu_var(hard_watchdog_warn) = true;
return;
}
__get_cpu_var(hard_watchdog_warn) = false;
return;
}
static void watchdog_interrupt_count(void)
{
__get_cpu_var(hrtimer_interrupts)++;
}
#else
static inline void watchdog_interrupt_count(void) { return; }
#endif /* CONFIG_HARDLOCKUP_DETECTOR */
/* watchdog kicker functions */
static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
{
unsigned long touch_ts = __get_cpu_var(watchdog_touch_ts);
struct pt_regs *regs = get_irq_regs();
int duration;
/* kick the hardlockup detector */
watchdog_interrupt_count();
/* kick the softlockup detector */
wake_up_process(__get_cpu_var(softlockup_watchdog));
/* .. and repeat */
hrtimer_forward_now(hrtimer, ns_to_ktime(get_sample_period()));
if (touch_ts == 0) {
if (unlikely(__get_cpu_var(softlockup_touch_sync))) {
/*
* If the time stamp was touched atomically
* make sure the scheduler tick is up to date.
*/
__get_cpu_var(softlockup_touch_sync) = false;
sched_clock_tick();
}
__touch_watchdog();
return HRTIMER_RESTART;
}
/* check for a softlockup
* This is done by making sure a high priority task is
* being scheduled. The task touches the watchdog to
* indicate it is getting cpu time. If it hasn't then
* this is a good indication some task is hogging the cpu
*/
duration = is_softlockup(touch_ts);
if (unlikely(duration)) {
/* only warn once */
if (__get_cpu_var(soft_watchdog_warn) == true)
return HRTIMER_RESTART;
printk(KERN_ERR "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_panic)
panic("softlockup: hung tasks");
__get_cpu_var(soft_watchdog_warn) = true;
} else
__get_cpu_var(soft_watchdog_warn) = false;
return HRTIMER_RESTART;
}
/*
* Th
|