summaryrefslogtreecommitdiffstats
path: root/kernel/events
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2013-10-31 17:25:38 +0100
committerIngo Molnar <mingo@kernel.org>2013-11-06 12:34:20 +0100
commit85f59edf9684603026c64c902791748116d29478 (patch)
tree13da84a3f347a24a3929d7546a6d7e9addbdf857 /kernel/events
parentc72b42a3dde487132da80202756c101b371b2add (diff)
downloadlinux-85f59edf9684603026c64c902791748116d29478.tar.gz
linux-85f59edf9684603026c64c902791748116d29478.tar.bz2
linux-85f59edf9684603026c64c902791748116d29478.zip
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 <peterz@infradead.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: james.hogan@imgtec.com Cc: Vince Weaver <vince@deater.net> Cc: Victor Kaplansky <VICTORK@il.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Anton Blanchard <anton@samba.org> Link: http://lkml.kernel.org/n/tip-c19u6egfldyx86tpyc3zgkw9@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/events')
-rw-r--r--kernel/events/ring_buffer.c17
1 files 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);