Messages in this thread |  | | Subject | RE: perf events ring buffer memory barrier on powerpc | From | Victor Kaplansky <> | Date | Thu, 31 Oct 2013 14:55:25 +0200 |
| |
"David Laight" <David.Laight@aculab.com> wrote on 10/31/2013 02:28:56 PM:
> So even though the wmb() in the writer ensures the writes are correctly > ordered, the reader can read the old value from the second location from > its local cache.
In case of circular buffer, the only thing that producer reads is @tail, and nothing wrong will happen if producer reads old value of @tail. Moreover, adherents of smp_mb() insert it *after* the read of @tail, so it cannot prevent reading of old value anyway. -- Victor
|  |