Netdev List
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <hawk@kernel.org>
To: netdev@vger.kernel.org, edumazet@google.com
Cc: Jesper Dangaard Brouer <hawk@kernel.org>,
	pabeni@redhat.com, kuba@kernel.org, davem@davemloft.net,
	lorenzo@kernel.org,
	Ilias Apalodimas <ilias.apalodimas@linaro.org>,
	mtahhan@redhat.com, huangjie.albert@bytedance.com,
	Yunsheng Lin <linyunsheng@huawei.com>,
	Liang Chen <liangchen.linux@gmail.com>
Subject: [PATCH net-next RFC v1 0/4] veth: reduce reallocations of SKBs when XDP bpf-prog is loaded
Date: Tue, 22 Aug 2023 19:59:00 +0200	[thread overview]
Message-ID: <169272709850.1975370.16698220879817216294.stgit@firesoul> (raw)

Loading an XDP bpf-prog on veth device driver results in a significant
performance degradation (for normal unrelated traffic) due to
veth_convert_skb_to_xdp_buff() in most cases fully reallocates an SKB and copy
data over, even when XDP prog does nothing (e.g. XDP_PASS).

This patchset reduce the cases that cause reallocation.
After patchset UDP and AF_XDP sending avoids reallocations.

Future work will investigate TCP.

---

Jesper Dangaard Brouer (4):
      veth: use same bpf_xdp_adjust_head check as generic-XDP
      veth: use generic-XDP functions when dealing with SKBs
      veth: lift skb_head_is_locked restriction for SKB based XDP
      veth: when XDP is loaded increase needed_headroom


 drivers/net/veth.c | 86 +++++++++++++++++++---------------------------
 net/core/dev.c     |  1 +
 net/core/filter.c  |  1 +
 3 files changed, 38 insertions(+), 50 deletions(-)

--
Jesper


             reply	other threads:[~2023-08-22 17:59 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-08-22 17:59 Jesper Dangaard Brouer [this message]
2023-08-22 17:59 ` [PATCH net-next RFC v1 1/4] veth: use same bpf_xdp_adjust_head check as generic-XDP Jesper Dangaard Brouer
2023-08-22 17:59 ` [PATCH net-next RFC v1 2/4] veth: use generic-XDP functions when dealing with SKBs Jesper Dangaard Brouer
2023-08-24 10:30   ` Toke Høiland-Jørgensen
2023-08-29 14:37     ` Jesper Dangaard Brouer
2023-09-01 13:32       ` Toke Høiland-Jørgensen
2023-08-22 17:59 ` [PATCH net-next RFC v1 3/4] veth: lift skb_head_is_locked restriction for SKB based XDP Jesper Dangaard Brouer
2023-08-22 17:59 ` [PATCH net-next RFC v1 4/4] veth: when XDP is loaded increase needed_headroom Jesper Dangaard Brouer
2023-08-24  4:27 ` [PATCH net-next RFC v1 0/4] veth: reduce reallocations of SKBs when XDP bpf-prog is loaded Liang Chen

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=169272709850.1975370.16698220879817216294.stgit@firesoul \
    --to=hawk@kernel.org \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=huangjie.albert@bytedance.com \
    --cc=ilias.apalodimas@linaro.org \
    --cc=kuba@kernel.org \
    --cc=liangchen.linux@gmail.com \
    --cc=linyunsheng@huawei.com \
    --cc=lorenzo@kernel.org \
    --cc=mtahhan@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.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