Re: [PATCH v9] perf: Sharing PMU counters across compatible events

[Song Liu <songliubraving@fb.com>]

Hi Peter, 

> On Jan 10, 2020, at 9:37 AM, Song Liu <songliubraving@fb.com> wrote:
> 
>>> 
>>> @@ -2242,9 +2494,9 @@ static void __perf_event_disable(struct perf_event *event,
>>> 	}
>>> 
>>> 	if (event == event->group_leader)
>>> -		group_sched_out(event, cpuctx, ctx);
>>> +		group_sched_out(event, cpuctx, ctx, true);
>>> 	else
>>> -		event_sched_out(event, cpuctx, ctx);
>>> +		event_sched_out(event, cpuctx, ctx, true);
>>> 
>>> 	perf_event_set_state(event, PERF_EVENT_STATE_OFF);
>>> }
>> 
>> So the above event_sched_out(.remove_dup) is very inconsistent with the
>> below ctx_resched(.event_add_dup).
> 
> [...]
> 
>>> @@ -2810,7 +3069,7 @@ static void __perf_event_enable(struct perf_event *event,
>>> 	if (ctx->task)
>>> 		WARN_ON_ONCE(task_ctx != ctx);
>>> 
>>> -	ctx_resched(cpuctx, task_ctx, get_event_type(event));
>>> +	ctx_resched(cpuctx, task_ctx, get_event_type(event), event);
>>> }
>>> 
>>> /*
>> 
>> We basically need:
>> 
>> * perf_event_setup_dup() after add_event_to_ctx(), but before *sched_in()
>>  - perf_install_in_context()
>>  - perf_event_enable()
>>  - inherit_event()
>> 
>> * perf_event_remove_dup() after *sched_out(), but before list_del_event()
>>  - perf_remove_from_context()
>>  - perf_event_disable()

Quick question:

For the remove_dup() path, if we do it after *_sched_out(), we will need to 
disable-then-enable the pmu for one extra time. In current version, we only
call perf_event_remove_dup() in event_sched_out(), where extra disable/enable
is not necessary. Is it a good tradeoff to add one extra disable-enable for 
cleaner code?

Thanks,
Song