Re: [RFC] tcp: race in receive part
From: Oleg Nesterov <oleg@redhat.com>
Date: 2009-06-23 22:59:43
Also in:
lkml
(Off-topic) On 06/23, Eric Dumazet wrote:
The optimization we could do, defining a smp_mb_after_read_lock() that could be a nop on x86
Imho it would be nice to have smp_mb__before/after_lock. insert_work(), __pte_alloc(), try_to_wake_up() could use it. Probably something else. Oleg.