From c72b42a3dde487132da80202756c101b371b2add Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 31 Oct 2013 17:20:25 +0100 Subject: [PATCH] perf: Add unlikely() to the ring-buffer code Add unlikely() annotations to 'slow' paths: When having a sampling event but no output buffer; you have bigger issues -- also the bail is still faster than actually doing the work. When having a sampling event but a control page only buffer, you have bigger issues -- again the bail is still faster than actually doing work. Optimize for the case where you're not loosing events -- again, not doing the work is still faster but make sure that when you have to actually do work its as fast as possible. The typical watermark is 1/2 the buffer size, so most events will not take this path. Shrinks perf_output_begin() by 16 bytes on x86_64-defconfig. 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-wlg3jew3qnutm8opd0hyeuwn@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 6929c5848d4f..383cde476176 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -121,17 +121,17 @@ int perf_output_begin(struct perf_output_handle *handle, event = event->parent; rb = rcu_dereference(event->rb); - if (!rb) + if (unlikely(!rb)) goto out; - handle->rb = rb; - handle->event = event; - - if (!rb->nr_pages) + if (unlikely(!rb->nr_pages)) goto out; + handle->rb = rb; + handle->event = event; + have_lost = local_read(&rb->lost); - if (have_lost) { + if (unlikely(have_lost)) { lost_event.header.size = sizeof(lost_event); perf_event_header__init_id(&lost_event.header, &sample_data, event); @@ -157,7 +157,7 @@ int perf_output_begin(struct perf_output_handle *handle, head += size; } while (local_cmpxchg(&rb->head, offset, head) != offset); - if (head - local_read(&rb->wakeup) > rb->watermark) + if (unlikely(head - local_read(&rb->wakeup) > rb->watermark)) local_add(rb->watermark, &rb->wakeup); handle->page = offset >> (PAGE_SHIFT + page_order(rb)); @@ -167,7 +167,7 @@ int perf_output_begin(struct perf_output_handle *handle, handle->addr += handle->size; handle->size = (PAGE_SIZE << page_order(rb)) - handle->size; - if (have_lost) { + if (unlikely(have_lost)) { lost_event.header.type = PERF_RECORD_LOST; lost_event.header.misc = 0; lost_event.id = event->id;