Re: [PATCH 03/10] perf: Make sure we read only scheduled events

[Peter Zijlstra]

On Thu, Aug 24, 2017 at 06:27:30PM +0200, Jiri Olsa wrote:
> Adding leader's state check into perf_output_read_group
> to ensure we read only leader, which is scheduled in.
> 
> Similar check is already there for siblings.
> 
> Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
> ---
>  kernel/events/core.c | 10 +++++++---
>  1 file changed, 7 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 30e30e94ea32..9a2791afe051 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -5760,6 +5760,11 @@ void perf_event__output_id_sample(struct perf_event *event,
>  		__perf_event__output_id_sample(handle, sample);
>  }
>  
> +static bool can_read(struct perf_event *event)
> +{
> +	return event->state == PERF_EVENT_STATE_ACTIVE;
> +}
> +
>  static void perf_output_read_one(struct perf_output_handle *handle,
>  				 struct perf_event *event,
>  				 u64 enabled, u64 running)
> @@ -5800,7 +5805,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
>  	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
>  		values[n++] = running;
>  
> -	if (leader != event)
> +	if ((leader != event) && can_read(leader))
>  		leader->pmu->read(leader);
>  
>  	values[n++] = perf_event_count(leader);
> @@ -5812,8 +5817,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
>  	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
>  		n = 0;
>  
> -		if ((sub != event) &&
> -		    (sub->state == PERF_EVENT_STATE_ACTIVE))
> +		if ((sub != event) && can_read(sub))
>  			sub->pmu->read(sub);
>  
>  		values[n++] = perf_event_count(sub);

I'm not seeing how this makes sense. Groups should either _all_ be
scheduled or not at all. Please explain.