From: Martin KaFai Lau <martin.lau@linux•dev>
To: Jesper Dangaard Brouer <hawk@kernel•org>
Cc: Jakub Kicinski <kuba@kernel•org>,
Lorenzo Bianconi <lorenzo@kernel•org>,
Stanislav Fomichev <stfomichev@gmail•com>,
bpf@vger•kernel.org, netdev@vger•kernel.org,
Alexei Starovoitov <ast@kernel•org>,
Daniel Borkmann <borkmann@iogearbox•net>,
Eric Dumazet <eric.dumazet@gmail•com>,
"David S. Miller" <davem@davemloft•net>,
Paolo Abeni <pabeni@redhat•com>,
sdf@fomichev•me, kernel-team@cloudflare•com,
arthur@arthurfabre•com, jakub@cloudflare•com,
Jesse Brandeburg <jbrandeburg@cloudflare•com>,
Andrew Rzeznik <arzeznik@cloudflare•com>
Subject: Re: [PATCH bpf-next V2 0/7] xdp: Allow BPF to set RX hints for XDP_REDIRECTed packets
Date: Tue, 5 Aug 2025 18:24:18 -0700 [thread overview]
Message-ID: <baa409d6-e571-4380-b046-5ea54c0e613d@linux.dev> (raw)
In-Reply-To: <de68b1d7-86cd-4280-af6a-13f0751228c4@kernel.org>
On 8/4/25 6:18 AM, Jesper Dangaard Brouer wrote:
> Do keep-in-mind that "moving skb allocation out of the driver" is not
> part of this patchset and a moonshot goal that will take a long time
> (but we are already "simulation" this via XDP-redirect for years now).
The XDP_PASS was first done in the very early days of BPF in 2016. The
XDP-redirect then followed a similar setup. A lot has improved since then. A
moonshot in 2016 does not necessarily mean it is still hard to do now. e.g. Loop
is feasible. Directly reading/writing skb is also easier.
Let’s first quantify what the performance loss would be if the skb is allocated
and field-set by the xdp prog (for the general XDP_PASS case and the
redirect+cpumap case). If it’s really worth it, let’s see what it would take for
the XDP program to achieve similar optimizations.
> Drivers should obviously not unconditionally populate the xdp_frame's
> rx_meta area. It is first time to populate rx_meta, once driver reach
afaict, the rx_meta is reserved regardless though. The xdp prog cannot use that
space for data_meta. The rx_meta will grow in time.
My preference is to allow xdp prog to decide what needs to write in data_meta
and decides what needs to set in the skb directly. This is the general case it
should support first and then optimize.
next prev parent reply other threads:[~2025-08-06 1:24 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-02 14:58 [PATCH bpf-next V2 0/7] xdp: Allow BPF to set RX hints for XDP_REDIRECTed packets Jesper Dangaard Brouer
2025-07-02 14:58 ` [PATCH bpf-next V2 1/7] net: xdp: Add xdp_rx_meta structure Jesper Dangaard Brouer
2025-07-17 9:19 ` Jakub Sitnicki
2025-07-17 14:40 ` Jesper Dangaard Brouer
2025-07-18 10:33 ` Jakub Sitnicki
2025-07-02 14:58 ` [PATCH bpf-next V2 2/7] selftests/bpf: Adjust test for maximum packet size in xdp_do_redirect Jesper Dangaard Brouer
2025-07-02 14:58 ` [PATCH bpf-next V2 3/7] net: xdp: Add kfuncs to store hw metadata in xdp_buff Jesper Dangaard Brouer
2025-07-03 11:41 ` Jesper Dangaard Brouer
2025-07-03 12:26 ` Lorenzo Bianconi
2025-07-02 14:58 ` [PATCH bpf-next V2 4/7] net: xdp: Set skb hw metadata from xdp_frame Jesper Dangaard Brouer
2025-07-02 14:58 ` [PATCH bpf-next V2 5/7] net: veth: Read xdp metadata from rx_meta struct if available Jesper Dangaard Brouer
2025-07-17 12:11 ` Jakub Sitnicki
2025-07-02 14:58 ` [PATCH bpf-next V2 6/7] bpf: selftests: Add rx_meta store kfuncs selftest Jesper Dangaard Brouer
2025-07-23 9:24 ` Bouska, Zdenek
2025-07-02 14:58 ` [PATCH bpf-next V2 7/7] net: xdp: update documentation for xdp-rx-metadata.rst Jesper Dangaard Brouer
2025-07-02 16:05 ` [PATCH bpf-next V2 0/7] xdp: Allow BPF to set RX hints for XDP_REDIRECTed packets Stanislav Fomichev
2025-07-03 11:17 ` Jesper Dangaard Brouer
2025-07-07 14:40 ` Stanislav Fomichev
2025-07-09 9:31 ` Lorenzo Bianconi
2025-07-11 16:04 ` Stanislav Fomichev
2025-07-16 11:17 ` Lorenzo Bianconi
2025-07-16 21:20 ` Jakub Kicinski
2025-07-17 13:08 ` Jesper Dangaard Brouer
2025-07-18 1:25 ` Jakub Kicinski
2025-07-18 10:56 ` Jesper Dangaard Brouer
2025-07-22 1:13 ` Jakub Kicinski
2025-07-28 10:53 ` Lorenzo Bianconi
2025-07-28 16:29 ` Jakub Kicinski
2025-07-29 11:15 ` Jesper Dangaard Brouer
2025-07-29 19:47 ` Martin KaFai Lau
2025-07-31 16:27 ` Jesper Dangaard Brouer
2025-08-01 20:38 ` Jakub Kicinski
2025-08-04 13:18 ` Jesper Dangaard Brouer
2025-08-06 0:28 ` Jakub Kicinski
2025-08-07 18:26 ` Jesper Dangaard Brouer
2025-08-06 1:24 ` Martin KaFai Lau [this message]
2025-08-07 19:07 ` Jesper Dangaard Brouer
2025-08-13 2:59 ` Martin KaFai Lau
2025-07-31 21:18 ` Lorenzo Bianconi
2025-08-01 20:40 ` Jakub Kicinski
2025-08-05 13:18 ` Lorenzo Bianconi
2025-08-05 23:54 ` Jakub Kicinski
2025-07-18 9:55 ` Lorenzo Bianconi
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=baa409d6-e571-4380-b046-5ea54c0e613d@linux.dev \
--to=martin.lau@linux$(echo .)dev \
--cc=arthur@arthurfabre$(echo .)com \
--cc=arzeznik@cloudflare$(echo .)com \
--cc=ast@kernel$(echo .)org \
--cc=borkmann@iogearbox$(echo .)net \
--cc=bpf@vger$(echo .)kernel.org \
--cc=davem@davemloft$(echo .)net \
--cc=eric.dumazet@gmail$(echo .)com \
--cc=hawk@kernel$(echo .)org \
--cc=jakub@cloudflare$(echo .)com \
--cc=jbrandeburg@cloudflare$(echo .)com \
--cc=kernel-team@cloudflare$(echo .)com \
--cc=kuba@kernel$(echo .)org \
--cc=lorenzo@kernel$(echo .)org \
--cc=netdev@vger$(echo .)kernel.org \
--cc=pabeni@redhat$(echo .)com \
--cc=sdf@fomichev$(echo .)me \
--cc=stfomichev@gmail$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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