github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-12 16:18:45 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

watchdog/hardlockup: improve buddy system detection timeliness

Browse Source 
Currently, the buddy system only performs checks every 3rd sample.  With a
4-second interval.  If a check window is missed, the next check occurs 12
seconds later, potentially delaying hard lockup detection for up to 24
seconds.

Modify the buddy system to perform checks at every interval (4s). 
Introduce a missed-interrupt threshold to maintain the existing grace
period while reducing the detection window to 8-12 seconds.

Best and worst case detection scenarios:

Before (12s check window):
- Best case: Lockup occurs after first check but just before heartbeat
  interval. Detected in ~8s (8s till next check).
- Worst case: Lockup occurs just after a check.
  Detected in ~24s (missed check + 12s till next check + 12s logic).

After (4s check window with threshold of 3):
- Best case: Lockup occurs just before a check.
  Detected in ~8s (0s till 1st check + 4s till 2nd + 4s till 3rd).
- Worst case: Lockup occurs just after a check.
  Detected in ~12s (4s till 1st check + 4s till 2nd + 4s till 3rd).

Link: https://lkml.kernel.org/r/20260312-hardlockup-watchdog-fixes-v2-4-45bd8a0cc7ed@google.com
Signed-off-by: Mayank Rungta <mrungta@google.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Li Huafei <lihuafei1@huawei.com>
Cc: Max Kellermann <max.kellermann@ionos.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Stephane Erainan <eranian@google.com>
Cc: Wang Jinchao <wangjinchao600@gmail.com>
Cc: Yunhui Cui <cuiyunhui@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Mayank Rungta 2026-03-12 16:22:05 -07:00 committed by Andrew Morton
parent de83258343
commit 077ba03600
3 changed files with 18 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
include/linux/nmi.h
View File

@ -21,6 +21,7 @@ void lockup_detector_soft_poweroff(void);
extern int watchdog_user_enabled;
extern int watchdog_thresh;
extern unsigned long watchdog_enabled;
extern int watchdog_hardlockup_miss_thresh;
extern struct cpumask watchdog_cpumask;
extern unsigned long *watchdog_cpumask_bits;

19
kernel/watchdog.c
View File

@ -60,6 +60,13 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
# endif /* CONFIG_SMP */
/*
* Number of consecutive missed interrupts before declaring a lockup.
* Default to 1 (immediate) for NMI/Perf. Buddy will overwrite this to 3.
*/
int __read_mostly watchdog_hardlockup_miss_thresh = 1;
EXPORT_SYMBOL_GPL(watchdog_hardlockup_miss_thresh);
/*
* Should we panic when a soft-lockup or hard-lockup occurs:
*/
@ -137,6 +144,7 @@ __setup("nmi_watchdog=", hardlockup_panic_setup);
static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts);
static DEFINE_PER_CPU(int, hrtimer_interrupts_saved);
static DEFINE_PER_CPU(int, hrtimer_interrupts_missed);
static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned);
static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched);
static unsigned long hard_lockup_nmi_warn;
@ -159,7 +167,7 @@ void watchdog_hardlockup_touch_cpu(unsigned int cpu)
per_cpu(watchdog_hardlockup_touched, cpu) = true;
}
static void watchdog_hardlockup_update(unsigned int cpu)
static void watchdog_hardlockup_update_reset(unsigned int cpu)
{
int hrint = atomic_read(&per_cpu(hrtimer_interrupts, cpu));
@ -169,6 +177,7 @@ static void watchdog_hardlockup_update(unsigned int cpu)
* written/read by a single CPU.
*/
per_cpu(hrtimer_interrupts_saved, cpu) = hrint;
per_cpu(hrtimer_interrupts_missed, cpu) = 0;
}
static bool is_hardlockup(unsigned int cpu)
@ -176,10 +185,14 @@ static bool is_hardlockup(unsigned int cpu)
int hrint = atomic_read(&per_cpu(hrtimer_interrupts, cpu));
if (per_cpu(hrtimer_interrupts_saved, cpu) != hrint) {
watchdog_hardlockup_update(cpu);
watchdog_hardlockup_update_reset(cpu);
return false;
}
per_cpu(hrtimer_interrupts_missed, cpu)++;
if (per_cpu(hrtimer_interrupts_missed, cpu) % watchdog_hardlockup_miss_thresh)
return false;
return true;
}
@ -198,7 +211,7 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
unsigned long flags;
if (per_cpu(watchdog_hardlockup_touched, cpu)) {
watchdog_hardlockup_update(cpu);
watchdog_hardlockup_update_reset(cpu);
per_cpu(watchdog_hardlockup_touched, cpu) = false;
return;
}

9
kernel/watchdog_buddy.c
View File

@ -21,6 +21,7 @@ static unsigned int watchdog_next_cpu(unsigned int cpu)
int __init watchdog_hardlockup_probe(void)
{
watchdog_hardlockup_miss_thresh = 3;
return 0;
}
@ -86,14 +87,6 @@ void watchdog_buddy_check_hardlockup(int 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)