[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20240603120917.GY491852@kernel.org>
Date: Mon, 3 Jun 2024 13:09:17 +0100
From: Simon Horman <horms@...nel.org>
To: Donald Hunter <donald.hunter@...il.com>
Cc: netdev@...r.kernel.org, Jakub Kicinski <kuba@...nel.org>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>, Paolo Abeni <pabeni@...hat.com>,
Pablo Neira Ayuso <pablo@...filter.org>,
Jozsef Kadlecsik <kadlec@...filter.org>,
netfilter-devel@...r.kernel.org, donald.hunter@...hat.com
Subject: Re: [PATCH net-next v1] netfilter: nfnetlink: convert kfree_skb to
consume_skb
On Mon, Jun 03, 2024 at 10:19:27AM +0100, Donald Hunter wrote:
> Simon Horman <horms@...nel.org> writes:
>
> > On Tue, May 28, 2024 at 11:37:54AM +0100, Donald Hunter wrote:
> >> Use consume_skb in the batch code path to avoid generating spurious
> >> NOT_SPECIFIED skb drop reasons.
> >>
> >> Signed-off-by: Donald Hunter <donald.hunter@...il.com>
> >
> > Hi Donald,
> >
> > I do wonder if this is the correct approach. I'm happy to stand corrected,
> > but my understanding is that consume_skb() is for situations where the skb
> > is no longer needed for reasons other than errors. But some of these
> > call-sites do appear to be error paths of sorts.
> >
> > ...
>
> Hi Simon,
>
> They all look to be application layer errors which are either
> communicated back to the client or cause a replay. My understanding is
> that consume_skb() should be used here since kfree_skb() now implies a
> (transport?) drop.
Hi Donald,
Thanks, that makes sense to me.
Powered by blists - more mailing lists