On Sat, Feb 04, 2017 at 07:19:37AM -0800, Eric Dumazet wrote:
>
> > The comment says that it's pairing with an mb in tcp_poll, but
> > tcp_poll doesn't touch QUEUE_SHRUNK at all. So what exactly is
> > this barrier for?
>
> Do not focus on QUEUE_SHRUNK flag, which is locally used by this thread
>
On Sat, 2017-02-04 at 17:59 +0800, Herbert Xu wrote:
> Jason Baron wrote:
> > From: Jason Baron
> >
> > sock_reset_flag() maps to __clear_bit() not the atomic version clear_bit().
> > Thus, we need smp_mb(), smp_mb__after_atomic() is not sufficient.
> >
> > Fixes: 3c7151275c0c ("tcp: add memory
Jason Baron wrote:
> From: Jason Baron
>
> sock_reset_flag() maps to __clear_bit() not the atomic version clear_bit().
> Thus, we need smp_mb(), smp_mb__after_atomic() is not sufficient.
>
> Fixes: 3c7151275c0c ("tcp: add memory barriers to write space paths")
> Cc: Eric Dumazet
> Cc: Oleg Nes
From: Eric Dumazet
Date: Tue, 24 Jan 2017 20:53:37 -0800
> On Tue, 2017-01-24 at 21:49 -0500, Jason Baron wrote:
>> From: Jason Baron
>>
>> sock_reset_flag() maps to __clear_bit() not the atomic version clear_bit().
>> Thus, we need smp_mb(), smp_mb__after_atomic() is not sufficient.
>>
>> Fix
On Tue, 2017-01-24 at 21:49 -0500, Jason Baron wrote:
> From: Jason Baron
>
> sock_reset_flag() maps to __clear_bit() not the atomic version clear_bit().
> Thus, we need smp_mb(), smp_mb__after_atomic() is not sufficient.
>
> Fixes: 3c7151275c0c ("tcp: add memory barriers to write space paths")
From: Jason Baron
sock_reset_flag() maps to __clear_bit() not the atomic version clear_bit().
Thus, we need smp_mb(), smp_mb__after_atomic() is not sufficient.
Fixes: 3c7151275c0c ("tcp: add memory barriers to write space paths")
Cc: Eric Dumazet
Cc: Oleg Nesterov
Signed-off-by: Jason Baron
-
