summaryrefslogtreecommitdiffstats
path: root/kernel/watchdog.c
diff options
context:
space:
mode:
authorPetr Mladek <pmladek@suse.com>2021-04-30 07:54:30 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2021-04-30 20:20:36 +0200
commit1bc503cb4a2638fb1c57801a7796aca57845ce63 (patch)
treea115a325f8e5655f2830906c7520939ab6c73171 /kernel/watchdog.c
parentwatchdog/softlockup: report the overall time of softlockups (diff)
downloadlinux-1bc503cb4a2638fb1c57801a7796aca57845ce63.tar.xz
linux-1bc503cb4a2638fb1c57801a7796aca57845ce63.zip
watchdog/softlockup: remove logic that tried to prevent repeated reports
The softlockup detector does some gymnastic with the variable soft_watchdog_warn. It was added by the commit 58687acba59266735ad ("lockup_detector: Combine nmi_watchdog and softlockup detector"). The purpose is not completely clear. There are the following clues. They describe the situation how it looked after the above mentioned commit: 1. The variable was checked with a comment "only warn once". 2. The variable was set when softlockup was reported. It was cleared only when the CPU was not longer in the softlockup state. 3. watchdog_touch_ts was not explicitly updated when the softlockup was reported. Without this variable, the report would normally be printed again during every following watchdog_timer_fn() invocation. The logic has got even more tangled up by the commit ed235875e2ca98 ("kernel/watchdog.c: print traces for all cpus on lockup detection"). After this commit, soft_watchdog_warn is set only when softlockup_all_cpu_backtrace is enabled. But multiple reports from all CPUs are prevented by a new variable soft_lockup_nmi_warn. Conclusion: The variable probably never worked as intended. In each case, it has not worked last many years because the softlockup was reported repeatedly after the full period defined by watchdog_thresh. The reason is that watchdog gets touched in many known slow paths, for example, in printk_stack_address(). This code is called also when printing the softlockup report. It means that the watchdog timestamp gets updated after each report. Solution: Simply remove the logic. People want the periodic report anyway. Link: https://lkml.kernel.org/r/20210311122130.6788-5-pmladek@suse.com Signed-off-by: Petr Mladek <pmladek@suse.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Laurence Oberman <loberman@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vincent Whitchurch <vincent.whitchurch@axis.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'kernel/watchdog.c')
-rw-r--r--kernel/watchdog.c14
1 files changed, 2 insertions, 12 deletions
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6bc5113d3d74..b8d4182d14cc 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -179,7 +179,6 @@ static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
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(bool, soft_watchdog_warn);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
static unsigned long soft_lockup_nmi_warn;
@@ -411,19 +410,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
if (kvm_check_and_clear_guest_paused())
return HRTIMER_RESTART;
- /* only warn once */
- if (__this_cpu_read(soft_watchdog_warn) == true)
- return HRTIMER_RESTART;
-
if (softlockup_all_cpu_backtrace) {
/* Prevent multiple soft-lockup reports if one cpu is already
* engaged in dumping cpu back traces
*/
- if (test_and_set_bit(0, &soft_lockup_nmi_warn)) {
- /* Someone else will report us. Let's give up */
- __this_cpu_write(soft_watchdog_warn, true);
+ if (test_and_set_bit(0, &soft_lockup_nmi_warn))
return HRTIMER_RESTART;
- }
}
/* Start period for the next softlockup warning. */
@@ -453,9 +445,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
if (softlockup_panic)
panic("softlockup: hung tasks");
- __this_cpu_write(soft_watchdog_warn, true);
- } else
- __this_cpu_write(soft_watchdog_warn, false);
+ }
return HRTIMER_RESTART;
}