From: Jesper Dangaard Brouer <brouer@redhat.com>
To: netdev@vger.kernel.org, Daniel Borkmann <borkmann@iogearbox.net>,
Alexei Starovoitov <alexei.starovoitov@gmail.com>,
Jesper Dangaard Brouer <brouer@redhat.com>
Cc: liu.song.a23@gmail.com, songliubraving@fb.com,
John Fastabend <john.fastabend@gmail.com>
Subject: [bpf-next V2 PATCH 0/8] bpf/xdp: add flags argument to ndo_xdp_xmit and flag flush operation
Date: Thu, 31 May 2018 10:59:42 +0200 [thread overview]
Message-ID: <152775714013.24817.5067576840614810786.stgit@firesoul> (raw)
As I mentioned in merge commit 10f678683e4 ("Merge branch 'xdp_xmit-bulking'")
I plan to change the API for ndo_xdp_xmit once more, by adding a flags
argument, which is done in this patchset.
I know it is late in the cycle (currently at rc7), but it would be
nice to avoid changing NDOs over several kernel releases, as it is
annoying to vendors and distro backporters, but it is not strictly
UAPI so it is allowed (according to Alexei).
The end-goal is getting rid of the ndo_xdp_flush operation, as it will
make it possible for drivers to implement a TXQ synchronization mechanism
that is not necessarily derived from the CPU id (smp_processor_id).
This patchset removes all callers of the ndo_xdp_flush operation, but
it doesn't take the last step of removing it from all drivers. This
can be done later, or I can update the patchset on request.
Micro-benchmarks only show a very small performance improvement, for
map-redirect around ~2 ns, and for non-map redirect ~7 ns. I've not
benchmarked this with CONFIG_RETPOLINE, but the performance benefit
should be more visible given we end-up removing an indirect call.
---
V2: Updated based on feedback from Song Liu <songliubraving@fb.com>
Jesper Dangaard Brouer (8):
xdp: add flags argument to ndo_xdp_xmit API
i40e: implement flush flag for ndo_xdp_xmit
ixgbe: implement flush flag for ndo_xdp_xmit
tun: implement flush flag for ndo_xdp_xmit
virtio_net: implement flush flag for ndo_xdp_xmit
xdp: done implementing ndo_xdp_xmit flush flag for all drivers
bpf/xdp: non-map redirect can avoid calling ndo_xdp_flush
bpf/xdp: devmap can avoid calling ndo_xdp_flush
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 14 ++++++++++++--
drivers/net/ethernet/intel/i40e/i40e_txrx.h | 3 ++-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 23 +++++++++++++++++------
drivers/net/tun.c | 25 ++++++++++++++++++-------
drivers/net/virtio_net.c | 9 ++++++++-
include/linux/netdevice.h | 7 ++++---
include/net/xdp.h | 4 ++++
kernel/bpf/devmap.c | 19 ++++++-------------
net/core/filter.c | 3 +--
9 files changed, 72 insertions(+), 35 deletions(-)
next reply other threads:[~2018-05-31 8:59 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-31 8:59 Jesper Dangaard Brouer [this message]
2018-05-31 8:59 ` [bpf-next V2 PATCH 1/8] xdp: add flags argument to ndo_xdp_xmit API Jesper Dangaard Brouer
2018-05-31 8:59 ` [bpf-next V2 PATCH 2/8] i40e: implement flush flag for ndo_xdp_xmit Jesper Dangaard Brouer
2018-06-04 13:11 ` Daniel Borkmann
2018-05-31 8:59 ` [bpf-next V2 PATCH 3/8] ixgbe: " Jesper Dangaard Brouer
2018-05-31 16:14 ` Song Liu
2018-06-04 13:19 ` Daniel Borkmann
2018-06-04 13:53 ` Jesper Dangaard Brouer
2018-05-31 9:00 ` [bpf-next V2 PATCH 4/8] tun: " Jesper Dangaard Brouer
2018-05-31 16:14 ` Song Liu
2018-05-31 9:00 ` [bpf-next V2 PATCH 5/8] virtio_net: " Jesper Dangaard Brouer
2018-05-31 16:15 ` Song Liu
2018-05-31 9:00 ` [bpf-next V2 PATCH 6/8] xdp: done implementing ndo_xdp_xmit flush flag for all drivers Jesper Dangaard Brouer
2018-05-31 16:16 ` Song Liu
2018-05-31 9:00 ` [bpf-next V2 PATCH 7/8] bpf/xdp: non-map redirect can avoid calling ndo_xdp_flush Jesper Dangaard Brouer
2018-05-31 16:16 ` Song Liu
2018-05-31 9:00 ` [bpf-next V2 PATCH 8/8] bpf/xdp: devmap " Jesper Dangaard Brouer
2018-05-31 16:06 ` Song Liu
2018-06-03 15:17 ` [bpf-next V2 PATCH 0/8] bpf/xdp: add flags argument to ndo_xdp_xmit and flag flush operation Alexei Starovoitov
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=152775714013.24817.5067576840614810786.stgit@firesoul \
--to=brouer@redhat.com \
--cc=alexei.starovoitov@gmail.com \
--cc=borkmann@iogearbox.net \
--cc=john.fastabend@gmail.com \
--cc=liu.song.a23@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=songliubraving@fb.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