Re: [tip:perf/urgent] perf/x86/intel: Fix PMI handling for Intel PT

[Peter Zijlstra <peterz@infradead.org>]

On Fri, Jun 19, 2015 at 10:58:36AM -0700, tip-bot for Alexander Shishkin wrote:
> @@ -371,12 +373,24 @@ int x86_add_exclusive(unsigned int what)
>  
>  out:
>  	mutex_unlock(&pmc_reserve_mutex);
> +
> +	/*
> +	 * Assuming that all exclusive events will share the PMI handler
> +	 * (which checks active_events for whether there is work to do),
> +	 * we can bump active_events counter right here, except for
> +	 * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init()
> +	 * path, which already bumps active_events for them.
> +	 */
> +	if (!ret && what != x86_lbr_exclusive_lbr)
> +		atomic_inc(&active_events);
> +
>  	return ret;
>  }
>  
>  void x86_del_exclusive(unsigned int what)
>  {
>  	atomic_dec(&x86_pmu.lbr_exclusive[what]);
> +	atomic_dec(&active_events);
>  }
>  

This, conditional inc, unconditional dec.

This leads to active_events == 0 even though there's still the NMI
watchdog active generating NMIs.

I would say, drop the condition on inc, double inc isn't a problem as
long as we match with a double dec and that results in simpler code too.