From 85f59edf9684603026c64c902791748116d29478 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 31 Oct 2013 17:25:38 +0100 Subject: [PATCH] perf: Optimize perf_output_begin() There's no point in re-doing the memory-barrier when we fail the cmpxchg(). Also placing it after the space reservation loop makes it clearer it only separates the userpage->tail read from the data stores. Signed-off-by: Peter Zijlstra Cc: Benjamin Herrenschmidt Cc: Frederic Weisbecker Cc: Mathieu Desnoyers Cc: Michael Ellerman Cc: Michael Neuling Cc: "Paul E. McKenney" Cc: james.hogan@imgtec.com Cc: Vince Weaver Cc: Victor Kaplansky Cc: Oleg Nesterov Cc: Anton Blanchard Link: http://lkml.kernel.org/n/tip-c19u6egfldyx86tpyc3zgkw9@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 383cde476176..6ed16ecfd0a3 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -141,15 +141,7 @@ int perf_output_begin(struct perf_output_handle *handle, perf_output_get_handle(handle); do { - /* - * Userspace could choose to issue a mb() before updating the - * tail pointer. So that all reads will be completed before the - * write is issued. - * - * See perf_output_put_handle(). - */ tail = ACCESS_ONCE(rb->user_page->data_tail); - smp_mb(); offset = head = local_read(&rb->head); if (!rb->overwrite && unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size)) @@ -157,6 +149,15 @@ int perf_output_begin(struct perf_output_handle *handle, head += size; } while (local_cmpxchg(&rb->head, offset, head) != offset); + /* + * Separate the userpage->tail read from the data stores below. + * Matches the MB userspace SHOULD issue after reading the data + * and before storing the new tail position. + * + * See perf_output_put_handle(). + */ + smp_mb(); + if (unlikely(head - local_read(&rb->wakeup) > rb->watermark)) local_add(rb->watermark, &rb->wakeup); -- 2.20.1