Re: [PATCH 04/14] perf/x86: output side-band events overhead

[Mark Rutland <mark.rutland@arm.com>]

On Wed, Nov 23, 2016 at 04:44:42AM -0500, kan.liang@intel.com wrote:
> From: Kan Liang <kan.liang@intel.com>
> 
> Iterating all events which need to receive side-band events also bring
> some overhead.
> Save the overhead information in task context or CPU context, whichever
> context is available.

Do we really want to expose this concept to userspace?

What if the implementation changes?

Thanks,
Mark.

> Signed-off-by: Kan Liang <kan.liang@intel.com>
> ---
>  include/linux/perf_event.h      |  2 ++
>  include/uapi/linux/perf_event.h |  1 +
>  kernel/events/core.c            | 32 ++++++++++++++++++++++++++++----
>  3 files changed, 31 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index f72b97a..ec3cb7f 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -764,6 +764,8 @@ struct perf_event_context {
>  #endif
>  	void				*task_ctx_data; /* pmu specific data */
>  	struct rcu_head			rcu_head;
> +
> +	struct perf_overhead_entry	sb_overhead;
>  };
>  
>  /*
> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
> index 9124c7c..5e7c522 100644
> --- a/include/uapi/linux/perf_event.h
> +++ b/include/uapi/linux/perf_event.h
> @@ -994,6 +994,7 @@ struct perf_branch_entry {
>  enum perf_record_overhead_type {
>  	PERF_NMI_OVERHEAD	= 0,
>  	PERF_MUX_OVERHEAD,
> +	PERF_SB_OVERHEAD,
>  
>  	PERF_OVERHEAD_MAX,
>  };
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 9934059..51e9df7 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -1829,9 +1829,15 @@ event_sched_out(struct perf_event *event,
>  	if (event->attr.exclusive || !cpuctx->active_oncpu)
>  		cpuctx->exclusive = 0;
>  
> -	if (log_overhead && cpuctx->mux_overhead.nr) {
> -		cpuctx->mux_overhead.cpu = smp_processor_id();
> -		perf_log_overhead(event, PERF_MUX_OVERHEAD, &cpuctx->mux_overhead);
> +	if (log_overhead) {
> +		if (cpuctx->mux_overhead.nr) {
> +			cpuctx->mux_overhead.cpu = smp_processor_id();
> +			perf_log_overhead(event, PERF_MUX_OVERHEAD, &cpuctx->mux_overhead);
> +		}
> +		if (ctx->sb_overhead.nr) {
> +			ctx->sb_overhead.cpu = smp_processor_id();
> +			perf_log_overhead(event, PERF_SB_OVERHEAD, &ctx->sb_overhead);
> +		}
>  	}
>  
>  	perf_pmu_enable(event->pmu);
> @@ -6133,6 +6139,14 @@ static void perf_iterate_sb_cpu(perf_iterate_f output, void *data)
>  	}
>  }
>  
> +static void
> +perf_caculate_sb_overhead(struct perf_event_context *ctx,
> +			  u64 time)
> +{
> +	ctx->sb_overhead.nr++;
> +	ctx->sb_overhead.time += time;
> +}
> +
>  /*
>   * Iterate all events that need to receive side-band events.
>   *
> @@ -6143,9 +6157,12 @@ static void
>  perf_iterate_sb(perf_iterate_f output, void *data,
>  	       struct perf_event_context *task_ctx)
>  {
> +	struct perf_event_context *overhead_ctx = task_ctx;
>  	struct perf_event_context *ctx;
> +	u64 start_clock, end_clock;
>  	int ctxn;
>  
> +	start_clock = perf_clock();
>  	rcu_read_lock();
>  	preempt_disable();
>  
> @@ -6163,12 +6180,19 @@ perf_iterate_sb(perf_iterate_f output, void *data,
>  
>  	for_each_task_context_nr(ctxn) {
>  		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
> -		if (ctx)
> +		if (ctx) {
>  			perf_iterate_ctx(ctx, output, data, false);
> +			if (!overhead_ctx)
> +				overhead_ctx = ctx;
> +		}
>  	}
>  done:
>  	preempt_enable();
>  	rcu_read_unlock();
> +
> +	end_clock = perf_clock();
> +	if (overhead_ctx)
> +		perf_caculate_sb_overhead(overhead_ctx, end_clock - start_clock);
>  }
>  
>  /*
> -- 
> 2.5.5
>