From: "Alexei Starovoitov" <alexei.starovoitov@gmail.com>
To: "Jamal Hadi Salim" <jhs@mojatatu.com>, <netdev@vger.kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>,
"Eric Dumazet" <edumazet@kernel.org>,
"Jakub Kicinski" <kuba@kernel.org>,
"Paolo Abeni" <pabeni@redhat.com>,
"Simon Horman" <horms@kernel.org>, <bpf@vger.kernel.org>,
"Jiri Pirko" <jiri@resnulli.us>,
"Victor Nogueira" <victor@mojatatu.com>
Subject: Re: [PATCH net-next 1/1] net: neighbour: skip the stale dst lookup for a redirected skb
Date: Fri, 20 Nov 2026 19:06:40 +0000 [thread overview]
Message-ID: <DN09UU4NHKLV.29WR92GGDPBP5@gmail.com> (raw)
In-Reply-To: <CORE-J9UK.v1.r0.20261120103344-1@mojatatu.com>
On Fri, Nov 20, 2026 at 07:42 AM Jamal Hadi Salim <jhs@mojatatu.com> wrote:
> Skip the lookup when skb->dev is already neigh->dev; the parking neighbour
> is the top-level one in that case and can reinject the packet itself. A
> dst that is a route via another device, which is the sch_teql shape, still
> takes the lookup.
It doesn't. The check never reads dst->dev:
if (dst && skb->dev != neigh->dev &&
In the repro dst->dev is va, skb->dev and neigh->dev are vb.
The lookup is skipped. teql takes it, because skb->dev is the master.
That ends with 3/3 of your teql series:
https://lore.kernel.org/bpf/QDISC-6HS9.v6.r0.20261119070330@mojatatu.com/
Then 2/3 of it and the lookup itself can go. It can be a follow up.
Acked-by: Alexei Starovoitov <ast@kernel.org>
next prev parent reply other threads:[~2026-11-20 19:06 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-20 15:42 [PATCH net-next 0/1] net: neighbour: skip the stale dst lookup for a redirected skb Jamal Hadi Salim
2026-11-20 15:42 ` [PATCH net-next 1/1] " Jamal Hadi Salim
2026-11-20 19:06 ` Alexei Starovoitov [this message]
2026-11-20 15:47 ` [PATCH net-next 0/1] " netdev-bot+sinfo
2026-11-20 16:05 ` Jamal Hadi Salim
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=DN09UU4NHKLV.29WR92GGDPBP5@gmail.com \
--to=alexei.starovoitov@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=davem@davemloft.net \
--cc=edumazet@kernel.org \
--cc=horms@kernel.org \
--cc=jhs@mojatatu.com \
--cc=jiri@resnulli.us \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=victor@mojatatu.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox