On 10/29, Peter Zijlstra wrote:

On Tue, Oct 29, 2013 at 11:30:57AM +0100, Peter Zijlstra wrote:

quoted

@@ -154,9 +175,11 @@ int perf_output_begin(struct perf_output
 		 * 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_rmb();
+		smp_mb();
 		offset = head = local_read(&rb->head);
 		head += size;
 		if (unlikely(!perf_output_space(rb, tail, offset, head)))

That said; it would be very nice to be able to remove this barrier. This
is in every event write path :/

Yes.. And I'm afraid very much that I simply confused you. Perhaps Victor
is right and we do not need this mb(). So I am waiting for the end of
this story too.

And btw I do not understand why we need it (or smp_rmb) right after
ACCESS_ONCE(data_tail).

Oleg.