[PATCH] hardlockup: detect hard lockups without NMIs using secondary cpus

[Colin Cross]

On Thu, Jan 10, 2013 at 12:38 PM, Tony Lindgren <tony at atomide.com> wrote:
>
> * Colin Cross <ccross at android.com> [130109 18:05]:
> > +static void watchdog_check_hardlockup_other_cpu(void)
> > +{
> > +     int cpu;
> > +     cpumask_t cpus = watchdog_cpus;
> > +
> > +     /*
> > +      * 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 (__this_cpu_read(hrtimer_interrupts) % 3 != 0)
> > +             return;
> > +
> > +     /* check for a hardlockup on the next cpu */
> > +     cpu = cpumask_next(smp_processor_id(), &cpus);
>
> Hmm don't you want to check cpu_oneline_mask here and
> return if the other CPU is offline?

watchdog_cpus is effectively a local copy of cpu_online_mask, but
updated after the watchdog_nmi_touch in watchdog_nmi_enable.  This
avoids a false positive after hotplugging in a cpu when
cpu_online_mask is true but that cpu hasn't yet run it's first
hrtimer.

> > +     if (cpu >= nr_cpu_ids)
> > +             cpu = cpumask_first(&cpus);
> > +     if (cpu == smp_processor_id())
> > +             return;
>
> Regards,
>
> Tony