On Mon, Nov 23, 2020 at 10:05 PM Peter Zijlstra wrote:
>
> On Mon, Nov 23, 2020 at 01:37:25PM +0800, Pingfan Liu wrote:
>
> > +/* When crashed, other cpus hang in idle loop, so here do an emergency job
> > under no lock */
>
> -ENOPARSE, -ETOOLONG
>
> > +void perf_pmu_disable_all(void)
> > +{
>
On Mon, Nov 23, 2020 at 01:37:25PM +0800, Pingfan Liu wrote:
> +/* When crashed, other cpus hang in idle loop, so here do an emergency job
> under no lock */
-ENOPARSE, -ETOOLONG
> +void perf_pmu_disable_all(void)
> +{
> + struct pmu *pmu;
> +
> + list_for_each_entry(pmu, , entry)
> +
In crash context, NMI should be suppressed before jump to a new kernel.
Naturally as the source of NMI on some arches, PMU should be turned off at
that time.
Introduce perf_pmu_disable_all() to achieve the goal.
Signed-off-by: Pingfan Liu
Cc: Peter Zijlstra
Cc: Ingo Molnar
Cc: Arnaldo
3 matches
Mail list logo