On 4/9/19 10:10 AM, Nicholas Piggin wrote:
> Using a jiffies timer creates a dependency on the tick_do_timer_cpu
> incrementing jiffies. If that CPU has locked up and jiffies is not
> incrementing, the watchdog heartbeat timer for all CPUs stops and
> creates false positives and confusing warnings on local CPUs, and
> also causes the SMP detector to stop, so the root cause is never
> detected.
>
> Fix this by using hrtimer based timers for the watchdog heartbeat,
> like the generic kernel hardlockup detector.
>
> Cc: Gautham R. Shenoy <e...@linux.vnet.ibm.com>
> Reported-by: Ravikumar Bangoria <ravi.bango...@in.ibm.com>
> Signed-off-by: Nicholas Piggin <npig...@gmail.com>
This one is giving me a proper backtrace when hardlockup happens
with perf_fuzzer so,
Tested-by: Ravi Bangoria <ravi.bango...@linux.ibm.com>
Neat:
Reported-by: Ravi Bangoria <ravi.bango...@linux.ibm.com>
