From: Jakub Kicinski <kuba@kernel.org>
To: "Toke Høiland-Jørgensen" <toke@redhat.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>,
Zvi Effron <zeffron@riotgames.com>,
Lorenz Bauer <lmb@cloudflare.com>,
Lorenzo Bianconi <lbianconi@redhat.com>,
Daniel Borkmann <daniel@iogearbox.net>,
John Fastabend <john.fastabend@gmail.com>,
Network Development <netdev@vger.kernel.org>,
bpf <bpf@vger.kernel.org>
Subject: Re: Redux: Backwards compatibility for XDP multi-buff
Date: Tue, 21 Sep 2021 15:51:18 -0700 [thread overview]
Message-ID: <20210921155118.439c0aa9@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com> (raw)
In-Reply-To: <87czp13718.fsf@toke.dk>
On Wed, 22 Sep 2021 00:20:19 +0200 Toke Høiland-Jørgensen wrote:
> >> Neither of those are desirable outcomes, I think; and if we add a
> >> separate "XDP multi-buff" switch, we might as well make it system-wide?
> >
> > If we have an internal flag 'this driver supports multi-buf xdp' cannot we
> > make xdp_redirect to linearize in case the packet is being redirected
> > to non multi-buf aware driver (potentially with corresponding non mb aware xdp
> > progs attached) from mb aware driver?
>
> Hmm, the assumption that XDP frames take up at most one page has been
> fundamental from the start of XDP. So what does linearise mean in this
> context? If we get a 9k packet, should we dynamically allocate a
> multi-page chunk of contiguous memory and copy the frame into that, or
> were you thinking something else?
My $.02 would be to not care about redirect at all.
It's not like the user experience with redirect is anywhere close
to amazing right now. Besides (with the exception of SW devices which
will likely gain mb support quickly) mixed-HW setups are very rare.
If the source of the redirect supports mb so will likely the target.
next prev parent reply other threads:[~2021-09-21 22:51 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-21 16:06 Redux: Backwards compatibility for XDP multi-buff Toke Høiland-Jørgensen
2021-09-21 17:31 ` Zvi Effron
2021-09-21 18:22 ` Toke Høiland-Jørgensen
2021-09-21 19:17 ` Zvi Effron
2021-09-21 22:14 ` Toke Høiland-Jørgensen
2021-09-21 23:10 ` Zvi Effron
2021-09-22 20:13 ` Toke Høiland-Jørgensen
2021-09-21 20:12 ` Alexei Starovoitov
2021-09-21 22:20 ` Toke Høiland-Jørgensen
2021-09-21 22:51 ` Jakub Kicinski [this message]
2021-09-22 20:01 ` Toke Høiland-Jørgensen
2021-09-22 21:23 ` Zvi Effron
2021-09-23 18:45 ` Toke Høiland-Jørgensen
2021-09-23 13:46 ` Jakub Kicinski
2021-09-27 12:43 ` Jesper Dangaard Brouer
2021-09-21 22:54 ` Jakub Kicinski
2021-09-22 20:02 ` Toke Høiland-Jørgensen
2021-09-22 21:11 ` Zvi Effron
2021-09-23 19:00 ` Toke Høiland-Jørgensen
2021-09-23 10:33 ` Lorenz Bauer
2021-09-23 12:59 ` Toke Høiland-Jørgensen
2021-09-24 10:18 ` Lorenz Bauer
2021-09-24 17:55 ` Zvi Effron
2021-09-24 19:38 ` Toke Høiland-Jørgensen
2021-09-28 8:47 ` Lorenz Bauer
2021-09-28 13:43 ` 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=20210921155118.439c0aa9@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com \
--to=kuba@kernel.org \
--cc=alexei.starovoitov@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=john.fastabend@gmail.com \
--cc=lbianconi@redhat.com \
--cc=lmb@cloudflare.com \
--cc=netdev@vger.kernel.org \
--cc=toke@redhat.com \
--cc=zeffron@riotgames.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;
as well as URLs for NNTP newsgroup(s).