Cc: Paul Mackerras <paulus@...>, <heiko.carstens@...>, <horms@...>, Stefan Richter <stefanr@...>, Satyam Sharma <satyam@...>, Linux Kernel Mailing List <linux-kernel@...>, David Miller <davem@...>, Paul E. McKenney <paulmck@...>, Ilpo Järvinen <ilpo.jarvinen@...>, <ak@...>, <cfriesen@...>, <rpjday@...>, Netdev <netdev@...>, <jesper.juhl@...>, <linux-arch@...>, Andrew Morton <akpm@...>, <zlynx@...>, <schwidefsky@...>, Chris Snook <csnook@...>, Herbert Xu <herbert@...>, Linus Torvalds <torvalds@...>, <wensong@...>, <wjiang@...>
>> atomic_dec() already has volatile behavior everywhere, so this is
"volatile" has nothing to do with reordering. atomic_dec() writes
to memory, so it _does_ have "volatile semantics", implicitly, as
long as the compiler cannot optimise the atomic variable away
completely -- any store counts as a side effect.
Segher
-