Re: [PATCH v6 3/4] bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter

On Wed, Aug 05, 2015 at 09:08:32AM -0700, Alexei Starovoitov wrote:

On 8/5/15 6:53 AM, Peter Zijlstra wrote:

quoted

+	/*
+	 * If the event is currently on this CPU, its either a per-task event,
+	 * or local to this CPU. Furthermore it means its ACTIVE (otherwise
+	 * oncpu == -1).
+	 */
+	if (event->oncpu == smp_processor_id())
+		event->pmu->read(event);
+
+	val = local64_read(&event->count);
+	local_irq_restore(flags);
+

nice! cleaner and faster.
so raw_spin_lock(&ctx->lock) is not needed, because
update_*(event) methods are not called, right?

Indeed, and by ensuring the event is indeed local (by force of WARN_ON)
disabling IRQs will avoid counter scheduling and result in a stable
event state.