]> pilppa.com Git - linux-2.6-omap-h63xx.git/commit
[NET]: Memory barrier cleanups
authorRalf Baechle <ralf@linux-mips.org>
Thu, 7 Dec 2006 08:11:33 +0000 (00:11 -0800)
committerDavid S. Miller <davem@davemloft.net>
Thu, 7 Dec 2006 08:11:33 +0000 (00:11 -0800)
commite16aa207ccb61c5111525c462eeeba1f3f5fd370
tree8a0a344fe7a3a10567075c9d63438ff6d79a1ca6
parent26db167702756d0022f8ea5f1f30cad3018cfe31
[NET]: Memory barrier cleanups

I believe all the below memory barriers only matter on SMP so
therefore the smp_* variant of the barrier should be used.

I'm wondering if the barrier in net/ipv4/inet_timewait_sock.c should be
dropped entirely.  schedule_work's implementation currently implies a
memory barrier and I think sane semantics of schedule_work() should imply
a memory barrier, as needed so the caller shouldn't have to worry.
It's not quite obvious why the barrier in net/packet/af_packet.c is
needed; maybe it should be implied through flush_dcache_page?

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
net/core/wireless.c
net/ipv4/inet_timewait_sock.c
net/ipv4/tcp_input.c
net/packet/af_packet.c