Just one clarification ...
On 8/10/2018 9:25 AM, Reinette Chatre wrote:
> static inline int x86_perf_event_error_state(struct perf_event *event)
> {
> int ret = 0;
> u64 tmp;
>
> ret = perf_event_read_local(event, &tmp, NULL, NULL);
> if (ret < 0)
> return ret;
>
> if (event->attr.pinned && event->oncpu != smp_processor_id())
> return -EBUSY;
I am preparing a patch series and in that the above extra test will be
included as the last sanity check in perf_event_read_local() as you
suggested. This inline function will thus go away and the only error
state check would be a call to perf_event_read_local().
Reinette
