[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <m2ed9ecrj4.fsf@gmail.com>
Date: Mon, 03 Jun 2024 10:19:27 +0100
From: Donald Hunter <donald.hunter@...il.com>
To: Simon Horman <horms@...nel.org>
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
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.
Powered by blists - more mailing lists