On Mon, Jun 30, 2014 at 04:50:44PM +0800, Yan, Zheng wrote:
> +static inline bool branch_user_callstack(unsigned br_sel)
> +{
> +	return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK);
> +}
> +
>  void intel_pmu_lbr_enable(struct perf_event *event)
>  {
>  	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
> +	struct x86_perf_task_context *task_ctx;
>  
>  	if (!x86_pmu.lbr_nr)
>  		return;
> @@ -214,6 +220,10 @@ void intel_pmu_lbr_enable(struct perf_event *event)
>  	}
>  	cpuc->br_sel = event->hw.branch_reg.reg;
>  
> +	task_ctx = event->ctx ? event->ctx->task_ctx_data : NULL;
> +	if (branch_user_callstack(cpuc->br_sel))
> +		task_ctx->lbr_callstack_users++;
> +

So what happens if we make a per-cpu event which satisfies
branch_user_callstack() ?