[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240118084020.2326c3ac@kernel.org>
Date: Thu, 18 Jan 2024 08:40:20 -0800
From: Jakub Kicinski <kuba@...nel.org>
To: Eric Dumazet <edumazet@...gle.com>
Cc: Paolo Abeni <pabeni@...hat.com>, Salvatore Dipietro
<dipiets@...zon.com>, alisaidi@...zon.com, benh@...zon.com,
blakgeof@...zon.com, davem@...emloft.net, dipietro.salvatore@...il.com,
dsahern@...nel.org, netdev@...r.kernel.org
Subject: Re: [PATCH v3] tcp: Add memory barrier to tcp_push()
On Thu, 18 Jan 2024 11:42:40 +0100 Eric Dumazet wrote:
> > > diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> > > index ff6838ca2e58..ab9e3922393c 100644
> > > --- a/net/ipv4/tcp.c
> > > +++ b/net/ipv4/tcp.c
> > > @@ -726,6 +726,7 @@ void tcp_push(struct sock *sk, int flags, int mss_now,
> > > /* It is possible TX completion already happened
> > > * before we set TSQ_THROTTLED.
> > > */
> > > + smp_mb__after_atomic();
> >
> > Out of sheer ignorance I'm wondering if moving such barrier inside the
> > above 'if' just after 'set_bit' would suffice?
>
> I think this would work just fine.
Sorry, "this" as in Paolo's suggestion or "this" as in the v3 patch
as posted? :)
Powered by blists - more mailing lists