All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jiri Pirko <jiri@resnulli.us>
To: Paolo Abeni <pabeni@redhat.com>
Cc: netdev@vger.kernel.org, Jamal Hadi Salim <jhs@mojatatu.com>,
	Cong Wang <xiyou.wangcong@gmail.com>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>,
	Eyal Birger <eyal.birger@gmail.com>,
	"David S. Miller" <davem@davemloft.net>
Subject: Re: [PATCH net-next v3 0/5] TC: refactor act_mirred packets re-injection
Date: Wed, 25 Jul 2018 13:53:45 +0200	[thread overview]
Message-ID: <20180725115345.GC2164@nanopsycho> (raw)
In-Reply-To: <cover.1532437050.git.pabeni@redhat.com>

Tue, Jul 24, 2018 at 10:06:38PM CEST, pabeni@redhat.com wrote:
>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 3 patches introduce some cleanup and safeguards to allow extending 
>tca_result - we will use it to store RCU protected redirect information - and
>introduce a clear separation between user-space accessible tcfa_action
>value and internal values accessible only by the kernel.
>Then a new tcfa_action value is introduced: TC_ACT_REINJECT, similar to
>TC_ACT_REDIRECT, but preserving the mirred semantic. Such value is not
>accessible from user-space.
>The last patch exploits the newly introduced infrastructure in the act_mirred
>action, to avoid a skb_clone, when possible.
>
>Overall this the above gives a ~10% performance improvement in forwarding tput,
>when using the TC S/W datapath.
>
>v1 -> v2:
> - preserve the rcu lock in act_bpf
> - add and use a new action value to reinject the packets, preserving the mirred
>   semantic
>
>v2 -> v3:
> - renamed to new action as TC_ACT_REINJECT
> - TC_ACT_REINJECT is not exposed to user-space
>
>Paolo Abeni (5):
>  tc/act: user space can't use TC_ACT_REDIRECT directly
>  net/sched: user-space can't set unknown tcfa_action values
>  tc/act: remove unneeded RCU lock in action callback
>  net/tc: introduce TC_ACT_REINJECT.
>  act_mirred: use TC_ACT_REINJECT when possible

Could you please send the userspace iproute2 patch and list some
examples of usage along with the next patchset version?

Also, I would like you to do selftest script to test this and have it as
a part of this patchset.

Thanks!


>
> include/net/act_api.h        |  2 +-
> include/net/pkt_cls.h        |  3 +++
> include/net/sch_generic.h    | 21 ++++++++++++++++++++
> include/uapi/linux/pkt_cls.h |  6 ++++--
> net/core/dev.c               |  6 +++++-
> net/sched/act_api.c          | 15 +++++++++++++-
> net/sched/act_csum.c         | 12 +++---------
> net/sched/act_ife.c          |  5 +----
> net/sched/act_mirred.c       | 38 ++++++++++++++++++++++++------------
> 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 +++++++-----------
> 14 files changed, 98 insertions(+), 70 deletions(-)
>
>-- 
>2.17.1
>

  parent reply	other threads:[~2018-07-25 13:07 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-24 20:06 [PATCH net-next v3 0/5] TC: refactor act_mirred packets re-injection Paolo Abeni
2018-07-24 20:06 ` [PATCH net-next v3 1/5] tc/act: user space can't use TC_ACT_REDIRECT directly Paolo Abeni
2018-07-25 11:55   ` Jamal Hadi Salim
2018-07-25 11:56   ` Jiri Pirko
2018-07-25 12:54     ` Paolo Abeni
2018-07-25 13:03       ` Jiri Pirko
2018-07-25 15:48         ` Paolo Abeni
2018-07-25 16:29           ` Paolo Abeni
2018-07-25 16:29           ` Daniel Borkmann
2018-07-26  7:43             ` Jiri Pirko
2018-07-27  2:48               ` Daniel Borkmann
2018-07-24 20:06 ` [PATCH net-next v3 2/5] net/sched: user-space can't set unknown tcfa_action values Paolo Abeni
2018-07-25 12:26   ` Jiri Pirko
2018-07-24 20:06 ` [PATCH net-next v3 3/5] tc/act: remove unneeded RCU lock in action callback Paolo Abeni
2018-07-25 11:59   ` Jamal Hadi Salim
2018-07-25 18:24     ` Marcelo Ricardo Leitner
2018-07-25 12:32   ` Jiri Pirko
2018-07-24 20:06 ` [PATCH net-next v3 4/5] net/tc: introduce TC_ACT_REINJECT Paolo Abeni
2018-07-24 20:38   ` Cong Wang
2018-07-24 20:50     ` Cong Wang
2018-07-25  8:29       ` Paolo Abeni
2018-07-25 12:27         ` Jamal Hadi Salim
2018-07-25 14:24           ` Paolo Abeni
2018-07-25 15:26             ` Jamal Hadi Salim
2018-07-25 16:48           ` Cong Wang
2018-07-25 17:09             ` Marcelo Ricardo Leitner
2018-07-26 12:52               ` Jamal Hadi Salim
2018-07-26 23:25                 ` Cong Wang
2018-07-25 12:16   ` Jamal Hadi Salim
2018-07-25 12:59     ` Jiri Pirko
2018-07-25 13:55     ` Paolo Abeni
2018-07-25 12:57   ` Jiri Pirko
2018-07-24 20:06 ` [PATCH net-next v3 5/5] act_mirred: use TC_ACT_REINJECT when possible Paolo Abeni
2018-07-24 21:15   ` Cong Wang
2018-07-25 10:14     ` Paolo Abeni
2018-07-25 13:30       ` Jiri Pirko
2018-07-25 11:50     ` Jamal Hadi Salim
2018-07-25 13:52   ` Jiri Pirko
2018-07-25 14:04     ` Paolo Abeni
2018-07-25 14:30       ` Jiri Pirko
2018-07-25 11:53 ` Jiri Pirko [this message]
2018-07-25 12:07   ` [PATCH net-next v3 0/5] TC: refactor act_mirred packets re-injection Paolo Abeni
2018-07-25 12:17     ` Jiri Pirko

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=20180725115345.GC2164@nanopsycho \
    --to=jiri@resnulli.us \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=eyal.birger@gmail.com \
    --cc=jhs@mojatatu.com \
    --cc=marcelo.leitner@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.