From: "Toke Høiland-Jørgensen" <toke@redhat.com>
To: "Jason A. Donenfeld" <Jason@zx2c4.com>, netdev@vger.kernel.org
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Subject: Re: [PATCH RFC v2] net: xdp: allow for layer 3 packets in generic skb handler
Date: Mon, 27 Apr 2020 13:16:22 +0200 [thread overview]
Message-ID: <87ftcpyy9l.fsf@toke.dk> (raw)
In-Reply-To: <20200427102229.414644-1-Jason@zx2c4.com>
"Jason A. Donenfeld" <Jason@zx2c4.com> writes:
> A user reported a few days ago that packets from wireguard were possibly
> ignored by XDP [1]. We haven't heard back from the original reporter to
> receive more info, so this here is mostly speculative. Successfully nerd
> sniped, Toke and I started poking around. Toke noticed that the generic
> skb xdp handler path seems to assume that packets will always have an
> ethernet header, which really isn't always the case for layer 3 packets,
> which are produced by multiple drivers. This patch is untested, but I
> wanted to gauge interest in this approach: if the mac_len is 0, then we
> assume that it's a layer 3 packet, and in that case prepend a pseudo
> ethhdr to the packet whose h_proto is copied from skb->protocol, which
> will have the appropriate v4 or v6 ethertype. This allows us to keep XDP
> programs' assumption correct about packets always having that ethernet
> header, so that existing code doesn't break, while still allowing layer
> 3 devices to use the generic XDP handler.
Seems to me like this would work; let's see if anyone else has any
comments :)
-Toke
next prev parent reply other threads:[~2020-04-27 11:16 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-27 1:10 [PATCH RFC v1] net: xdp: allow for layer 3 packets in generic skb handler Jason A. Donenfeld
2020-04-27 7:20 ` Toke Høiland-Jørgensen
2020-04-27 10:05 ` Jason A. Donenfeld
2020-04-27 10:22 ` [PATCH RFC v2] " Jason A. Donenfeld
2020-04-27 11:16 ` Toke Høiland-Jørgensen [this message]
2020-04-27 14:45 ` David Ahern
2020-04-27 19:58 ` Jason A. Donenfeld
2020-04-27 20:08 ` Toke Høiland-Jørgensen
2020-04-27 20:10 ` Jason A. Donenfeld
2020-04-27 20:42 ` [PATCH net v3] net: xdp: account " Jason A. Donenfeld
2020-04-27 20:52 ` Jakub Kicinski
2020-04-27 20:57 ` Jason A. Donenfeld
2020-04-27 21:00 ` Jakub Kicinski
2020-04-27 21:08 ` Jason A. Donenfeld
2020-04-27 21:19 ` Jakub Kicinski
2020-04-27 21:14 ` Toke Høiland-Jørgensen
2020-04-27 21:31 ` Jakub Kicinski
2020-04-27 23:00 ` Jason A. Donenfeld
2020-04-27 23:45 ` Jason A. Donenfeld
2020-04-28 0:15 ` Jakub Kicinski
2020-04-28 0:17 ` Jason A. Donenfeld
2020-04-28 0:40 ` Jakub Kicinski
2020-04-28 9:27 ` Toke Høiland-Jørgensen
2020-04-28 16:51 ` Jakub Kicinski
2020-04-28 17:03 ` Alexei Starovoitov
2020-04-27 21:00 ` Toke Høiland-Jørgensen
2020-04-27 10:30 ` [PATCH RFC v1] net: xdp: allow " Toke Høiland-Jørgensen
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=87ftcpyy9l.fsf@toke.dk \
--to=toke@redhat.com \
--cc=Jason@zx2c4.com \
--cc=netdev@vger.kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).