From: Paolo Abeni <pabeni@redhat.com>
To: netdev@vger.kernel.org
Cc: Jamal Hadi Salim <jhs@mojatatu.com>,
Cong Wang <xiyou.wangcong@gmail.com>,
Jiri Pirko <jiri@resnulli.us>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Subject: [PATCH net-next 0/4] TC: refactor TC_ACT_REDIRECT action
Date: Fri, 13 Jul 2018 11:54:58 +0200 [thread overview]
Message-ID: <cover.1531473946.git.pabeni@redhat.com> (raw)
This series is aimed at improving the act_mirred redirect performances.
Such action is used by OVS to represent TC S/W flows, and it's current largest
bottle-neck is the need for a skb_clone() for each packet.
The first 2 patches introduce some cleanup and safeguards to allow changing the
TC_ACT_REDIRECT handling: currently the action context is stored in per CPU
variables, and we allow also to use the tcf_result. Finally we use this extended
infrastructure in act_mirred to implement redirect via TC_ACT_REDIRECT, when
possible.
Overall this the above gives a ~10% performance improvement in forwarding tput,
when using the TC S/W datapath.
Paolo Abeni (4):
tc/act: user space can't use TC_ACT_REDIRECT directly
tc/act: remove unneeded RCU lock in action callback
net/sched: refactor TC_ACT_REDIRECT handling
act_mirred: use ACT_REDIRECT when possible
include/net/act_api.h | 2 +-
include/net/sch_generic.h | 17 ++++++++++++++++-
include/uapi/linux/pkt_cls.h | 1 +
net/core/dev.c | 4 ++--
net/core/filter.c | 29 +++++++++++++++++++++++------
net/core/lwt_bpf.c | 5 ++++-
net/sched/act_api.c | 5 +++++
net/sched/act_bpf.c | 8 ++++----
net/sched/act_csum.c | 12 +++---------
net/sched/act_ife.c | 5 +----
net/sched/act_mirred.c | 19 ++++++++++++++-----
net/sched/act_sample.c | 4 +---
net/sched/act_skbedit.c | 10 +++-------
net/sched/act_skbmod.c | 21 +++++++++------------
net/sched/act_tunnel_key.c | 6 +-----
net/sched/act_vlan.c | 19 +++++++------------
net/sched/cls_bpf.c | 8 +++++---
17 files changed, 100 insertions(+), 75 deletions(-)
--
2.17.1
next reply other threads:[~2018-07-13 10:09 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-13 9:54 Paolo Abeni [this message]
2018-07-13 9:54 ` [PATCH net-next 1/4] tc/act: user space can't use TC_ACT_REDIRECT directly Paolo Abeni
2018-07-13 9:55 ` [PATCH net-next 2/4] tc/act: remove unneeded RCU lock in action callback Paolo Abeni
2018-07-13 14:08 ` Daniel Borkmann
2018-07-13 14:26 ` Paolo Abeni
2018-07-13 14:41 ` Daniel Borkmann
2018-07-13 15:00 ` Paolo Abeni
2018-07-13 9:55 ` [PATCH net-next 3/4] net/sched: refactor TC_ACT_REDIRECT handling Paolo Abeni
2018-07-13 14:13 ` Daniel Borkmann
2018-07-13 14:37 ` Paolo Abeni
2018-07-13 16:32 ` Daniel Borkmann
2018-07-13 9:55 ` [PATCH net-next 4/4] act_mirred: use ACT_REDIRECT when possible Paolo Abeni
2018-07-16 23:39 ` Cong Wang
2018-07-17 7:01 ` Eyal Birger
2018-07-17 9:15 ` Paolo Abeni
2018-07-17 9:38 ` Dave Taht
2018-07-17 17:24 ` Cong Wang
2018-07-18 10:05 ` Paolo Abeni
2018-07-19 17:56 ` Cong Wang
2018-07-20 10:16 ` Paolo Abeni
2018-07-19 17:16 ` kbuild test robot
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=cover.1531473946.git.pabeni@redhat.com \
--to=pabeni@redhat.com \
--cc=ast@kernel.org \
--cc=daniel@iogearbox.net \
--cc=jhs@mojatatu.com \
--cc=jiri@resnulli.us \
--cc=marcelo.leitner@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=xiyou.wangcong@gmail.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).