From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To: netdev@vger.kernel.org
Cc: ast@kernel.org, daniel@iogearbox.net, sdf@google.com,
posk@google.com, Willem de Bruijn <willemb@google.com>
Subject: [PATCH bpf-next 01/13] bpf: in bpf_skb_adjust_room avoid copy in tx fast path
Date: Wed, 20 Mar 2019 10:49:32 -0400 [thread overview]
Message-ID: <20190320144944.147862-2-willemdebruijn.kernel@gmail.com> (raw)
In-Reply-To: <20190320144944.147862-1-willemdebruijn.kernel@gmail.com>
From: Willem de Bruijn <willemb@google.com>
bpf_skb_adjust_room calls skb_cow on grow.
This expensive operation can be avoided in the fast path when the only
other clone has released the header. This is the common case for TCP,
where one headerless clone is kept on the retransmit queue.
It is safe to do so even when touching the gso fields in skb_shinfo.
Regular tunnel encap with iptunnel_handle_offloads takes the same
optimization.
The tcp stack unclones in the unlikely case that it accesses these
fields through headerless clones packets on the retransmit queue (see
__tcp_retransmit_skb).
If any other clones are present, e.g., from packet sockets,
skb_cow_head returns the same value as skb_cow().
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
net/core/filter.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index 647c63a7b25b6..8e15fb919b574 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2971,7 +2971,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff)
if (skb_is_gso(skb) && !skb_is_gso_tcp(skb))
return -ENOTSUPP;
- ret = skb_cow(skb, len_diff);
+ ret = skb_cow_head(skb, len_diff);
if (unlikely(ret < 0))
return ret;
--
2.21.0.225.g810b269d1ac-goog
next prev parent reply other threads:[~2019-03-20 14:49 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-20 14:49 [PATCH bpf-next 00/13] bpf tc tunneling Willem de Bruijn
2019-03-20 14:49 ` Willem de Bruijn [this message]
2019-03-20 14:49 ` [PATCH bpf-next 02/13] selftests/bpf: bpf tunnel encap test Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 03/13] selftests/bpf: expand bpf tunnel test with decap Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 04/13] selftests/bpf: expand bpf tunnel test to ipv6 Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 05/13] selftests/bpf: extend bpf tunnel test with gre Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 06/13] selftests/bpf: extend bpf tunnel test with tso Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 07/13] bpf: add bpf_skb_adjust_room mode BPF_ADJ_ROOM_MAC Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 08/13] bpf: add bpf_skb_adjust_room flag BPF_F_ADJ_ROOM_FIXED_GSO Willem de Bruijn
2019-03-21 13:42 ` Alan Maguire
2019-03-21 14:00 ` Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 09/13] bpf: add bpf_skb_adjust_room encap flags Willem de Bruijn
2019-03-20 15:51 ` Alan Maguire
2019-03-20 18:10 ` Willem de Bruijn
2019-03-21 3:13 ` Alexei Starovoitov
2019-03-21 13:25 ` Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 10/13] bpf: Sync bpf.h to tools Willem de Bruijn
2019-03-20 14:56 ` Soheil Hassas Yeganeh
2019-03-20 14:49 ` [PATCH bpf-next 11/13] selftests/bpf: convert bpf tunnel test to BPF_ADJ_ROOM_MAC Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 12/13] selftests/bpf: convert bpf tunnel test to BPF_F_ADJ_ROOM_FIXED_GSO Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 13/13] selftests/bpf: convert bpf tunnel test to encap modes Willem de Bruijn
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=20190320144944.147862-2-willemdebruijn.kernel@gmail.com \
--to=willemdebruijn.kernel@gmail.com \
--cc=ast@kernel.org \
--cc=daniel@iogearbox.net \
--cc=netdev@vger.kernel.org \
--cc=posk@google.com \
--cc=sdf@google.com \
--cc=willemb@google.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).