[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANn89iK4xS=Z7k7zH=ZyVjbFstkJ+b_cqTex9h2o===zwR1tPg@mail.gmail.com>
Date: Thu, 19 Oct 2023 21:18:51 +0200
From: Eric Dumazet <edumazet@...gle.com>
To: Dmitry Kravkov <dmitryk@...lt.com>
Cc: Shakeel Butt <shakeelb@...gle.com>, Abel Wu <wuyun.abel@...edance.com>,
"David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>,
Soheil Hassas Yeganeh <soheil@...gle.com>, Neal Cardwell <ncardwell@...gle.com>, netdev@...r.kernel.org,
eric.dumazet@...il.com
Subject: Re: [PATCH v2 net] net: do not leave an empty skb in write queue
On Thu, Oct 19, 2023 at 9:14 PM Dmitry Kravkov <dmitryk@...lt.com> wrote:
>
> On Thu, Oct 19, 2023 at 9:01 PM Shakeel Butt <shakeelb@...gle.com> wrote:
> >
> > +Abel Wu
> >
> > On Thu, Oct 19, 2023 at 4:24 AM Eric Dumazet <edumazet@...gle.com> wrote:
> > >
> > > Under memory stress conditions, tcp_sendmsg_locked()
> > > might call sk_stream_wait_memory(), thus releasing the socket lock.
> > >
> > > If a fresh skb has been allocated prior to this,
> > > we should not leave it in the write queue otherwise
> > > tcp_write_xmit() could panic.
>
> Eric, do you have a panic trace accidentally? Thanks
I have no panic yet. It would be a bit tricky to trigger I think,
but a bit of clever fault injection could do this.
Powered by blists - more mailing lists