Cc: Christoph Lameter <clameter@...>, <heiko.carstens@...>, <horms@...>, Stefan Richter <stefanr@...>, Satyam Sharma <satyam@...>, Linux Kernel Mailing List <linux-kernel@...>, Paul E. McKenney <paulmck@...>, <netdev@...>, <ak@...>, <cfriesen@...>, <rpjday@...>, <jesper.juhl@...>, <linux-arch@...>, Andrew Morton <akpm@...>, <zlynx@...>, <schwidefsky@...>, Chris Snook <csnook@...>, Herbert Xu <herbert@...>, <davem@...>, Linus Torvalds <torvalds@...>, <wensong@...>, <wjiang@...>
>> A volatile default would disable optimizations for atomic_read.
An atomic_read() implemented as a "normal" C variable read would
allow that read to be combined with another "normal" read from
that variable. This could perhaps be marginally useful, although
I'd bet you cannot see it unless counting cycles on a simulator
or counting bits in the binary size.
With an asm() implementation, the compiler can not do this; with
a "volatile" implementation (either volatile variable or volatile-cast),
this invokes undefined behaviour (in both C and GCC).
Segher
-
