blob: fee45af2e5bdf7b3835c6fbec569018838e1676b (
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
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/kernel.h>
#include <linux/nmi.h>
#include <linux/percpu-defs.h>
static cpumask_t __read_mostly watchdog_cpus;
static unsigned int watchdog_next_cpu(unsigned int cpu)
{
cpumask_t cpus = watchdog_cpus;
unsigned int next_cpu;
next_cpu = cpumask_next(cpu, &cpus);
if (next_cpu >= nr_cpu_ids)
next_cpu = cpumask_first(&cpus);
if (next_cpu == cpu)
return nr_cpu_ids;
return next_cpu;
}
int __init watchdog_hardlockup_probe(void)
{
return 0;
}
void watchdog_hardlockup_enable(unsigned int cpu)
{
unsigned int next_cpu;
/*
* The new CPU will be marked online before the hrtimer interrupt
* gets a chance to run on it. If another CPU tests for a
* hardlockup on the new CPU before it has run its the hrtimer
* interrupt, it will get a false positive. Touch the watchdog on
* the new CPU to delay the check for at least 3 sampling periods
* to guarantee one hrtimer has run on the new CPU.
*/
watchdog_hardlockup_touch_cpu(cpu);
/*
* We are going to check the next CPU. Our watchdog_hrtimer
* need not be zero if the CPU has already been online earlier.
* Touch the watchdog on the next CPU to avoid false positive
* if we try to check it in less then 3 interrupts.
*/
next_cpu = watchdog_next_cpu(cpu);
if (next_cpu < nr_cpu_ids)
watchdog_hardlockup_touch_cpu(next_cpu);
cpumask_set_cpu(cpu, &watchdog_cpus);
}
void watchdog_hardlockup_disable(unsigned int cpu)
{
unsigned int next_cpu = watchdog_next_cpu(cpu);
/*
* Offlining this CPU will cause the CPU before this one to start
* checking the one after this one. If this CPU just finished checking
* the next CPU and updating hrtimer_interrupts_saved, and then the
* previous CPU checks it within one sample period, it will trigger a
* false positive. Touch the watchdog on the next CPU to prevent it.
*/
if (next_cpu < nr_cpu_ids)
watchdog_hardlockup_touch_cpu(next_cpu);
cpumask_clear_cpu(cpu, &watchdog_cpus);
}
void watchdog_buddy_check_hardlockup(unsigned long hrtimer_interrupts)
{
unsigned int next_cpu;
/*
* Test for hardlockups every 3 samples. The sample period is
* watchdog_thresh * 2 / 5, so 3 samples gets us back to slightly over
* watchdog_thresh (over by 20%).
*/
if (hrtimer_interrupts % 3 != 0)
return;
/* check for a hardlockup on the next CPU */
next_cpu = watchdog_next_cpu(smp_processor_id());
if (next_cpu >= nr_cpu_ids)
return;
watchdog_hardlockup_check(next_cpu, NULL);
}
|
