netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
To: netdev@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Jason Wang <jasowang@redhat.com>,
	Xuan Zhuo <xuanzhuo@linux.alibaba.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Jesper Dangaard Brouer <hawk@kernel.org>,
	John Fastabend <john.fastabend@gmail.com>,
	virtualization@lists.linux-foundation.org, bpf@vger.kernel.org
Subject: [PATCH net-next v3 00/27] virtio-net: support AF_XDP zero copy
Date: Fri, 29 Dec 2023 15:30:41 +0800	[thread overview]
Message-ID: <20231229073108.57778-1-xuanzhuo@linux.alibaba.com> (raw)

## AF_XDP

XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
copy feature of xsk (XDP socket) needs to be supported by the driver. The
performance of zero copy is very good. mlx5 and intel ixgbe already support
this feature, This patch set allows virtio-net to support xsk's zerocopy xmit
feature.

At present, we have completed some preparation:

1. vq-reset (virtio spec and kernel code)
2. virtio-core premapped dma
3. virtio-net xdp refactor

So it is time for Virtio-Net to complete the support for the XDP Socket
Zerocopy.

Virtio-net can not increase the queue num at will, so xsk shares the queue with
kernel.

On the other hand, Virtio-Net does not support generate interrupt from driver
manually, so when we wakeup tx xmit, we used some tips. If the CPU run by TX
NAPI last time is other CPUs, use IPI to wake up NAPI on the remote CPU. If it
is also the local CPU, then we wake up napi directly.

This patch set includes some refactor to the virtio-net to let that to support
AF_XDP.

## performance

ENV: Qemu with vhost-user(polling mode).
Host CPU: Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz

### virtio PMD in guest with testpmd

testpmd> show port stats all

 ######################## NIC statistics for port 0 ########################
 RX-packets: 19531092064 RX-missed: 0     RX-bytes: 1093741155584
 RX-errors: 0
 RX-nombuf: 0
 TX-packets: 5959955552 TX-errors: 0     TX-bytes: 371030645664


 Throughput (since last show)
 Rx-pps:   8861574     Rx-bps:  3969985208
 Tx-pps:   8861493     Tx-bps:  3969962736
 ############################################################################

### AF_XDP PMD in guest with testpmd

testpmd> show port stats all

  ######################## NIC statistics for port 0  ########################
  RX-packets: 68152727   RX-missed: 0          RX-bytes:  3816552712
  RX-errors: 0
  RX-nombuf:  0
  TX-packets: 68114967   TX-errors: 33216      TX-bytes:  3814438152

  Throughput (since last show)
  Rx-pps:      6333196          Rx-bps:   2837272088
  Tx-pps:      6333227          Tx-bps:   2837285936
  ############################################################################

But AF_XDP consumes more CPU for tx and rx napi(100% and 86%).

## maintain

I am currently a reviewer for virtio-net. I commit to maintain AF_XDP support in
virtio-net.

Please review.

Thanks.

v3
    1. virtio introduces helpers for virtio-net sq using premapped dma
    2. xsk has more complete support for merge mode
    3. fix some problems

v2
    1. wakeup uses the way of GVE. No send ipi to wakeup napi on remote cpu.
    2. remove rcu. Because we synchronize all operat, so the rcu is not needed.
    3. split the commit "move to virtio_net.h" in last patch set. Just move the
       struct/api to header when we use them.
    4. add comments for some code

v1:
    1. remove two virtio commits. Push this patchset to net-next
    2. squash "virtio_net: virtnet_poll_tx support rescheduled" to xsk: support tx
    3. fix some warnings



Xuan Zhuo (27):
  virtio_net: rename free_old_xmit_skbs to free_old_xmit
  virtio_net: unify the code for recycling the xmit ptr
  virtio_net: independent directory
  virtio_net: move core structures to virtio_net.h
  virtio_net: add prefix virtnet to all struct inside virtio_net.h
  virtio_ring: introduce virtqueue_get_buf_ctx_dma()
  virtio_ring: virtqueue_disable_and_recycle let the callback detach
    bufs
  virtio_ring: introduce virtqueue_detach_unused_buf_dma()
  virtio_ring: introduce virtqueue_get_dma_premapped()
  virtio_net: sq support premapped mode
  virtio_net: separate virtnet_rx_resize()
  virtio_net: separate virtnet_tx_resize()
  virtio_net: xsk: bind/unbind xsk
  virtio_net: xsk: prevent disable tx napi
  virtio_net: move some api to header
  virtio_net: xsk: tx: support xmit xsk buffer
  virtio_net: xsk: tx: support wakeup
  virtio_net: xsk: tx: handle the transmitted xsk buffer
  virtio_net: xsk: tx: free the unused xsk buffer
  virtio_net: separate receive_mergeable
  virtio_net: separate receive_buf
  virtio_net: xsk: rx: support fill with xsk buffer
  virtio_net: xsk: rx: support recv merge mode
  virtio_net: xsk: rx: support recv small mode
  virtio_net: xsk: rx: free the unused xsk buffer
  virtio_net: update tx timeout record
  virtio_net: xdp_features add NETDEV_XDP_ACT_XSK_ZEROCOPY

 MAINTAINERS                                 |   2 +-
 drivers/net/Kconfig                         |   8 +-
 drivers/net/Makefile                        |   2 +-
 drivers/net/virtio/Kconfig                  |  13 +
 drivers/net/virtio/Makefile                 |   8 +
 drivers/net/{virtio_net.c => virtio/main.c} | 806 +++++++++-----------
 drivers/net/virtio/virtio_net.h             | 337 ++++++++
 drivers/net/virtio/xsk.c                    | 626 +++++++++++++++
 drivers/net/virtio/xsk.h                    |  32 +
 drivers/virtio/virtio_ring.c                | 235 ++++--
 include/linux/virtio.h                      |  22 +-
 11 files changed, 1582 insertions(+), 509 deletions(-)
 create mode 100644 drivers/net/virtio/Kconfig
 create mode 100644 drivers/net/virtio/Makefile
 rename drivers/net/{virtio_net.c => virtio/main.c} (90%)
 create mode 100644 drivers/net/virtio/virtio_net.h
 create mode 100644 drivers/net/virtio/xsk.c
 create mode 100644 drivers/net/virtio/xsk.h

--
2.32.0.3.g01195cf9f


             reply	other threads:[~2023-12-29  7:31 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-29  7:30 Xuan Zhuo [this message]
2023-12-29  7:30 ` [PATCH net-next v3 01/27] virtio_net: rename free_old_xmit_skbs to free_old_xmit Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 02/27] virtio_net: unify the code for recycling the xmit ptr Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 03/27] virtio_net: independent directory Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 04/27] virtio_net: move core structures to virtio_net.h Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 05/27] virtio_net: add prefix virtnet to all struct inside virtio_net.h Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 06/27] virtio_ring: introduce virtqueue_get_buf_ctx_dma() Xuan Zhuo
2024-01-11  8:34   ` Jason Wang
2024-01-16  7:32     ` Xuan Zhuo
2024-01-22  4:18       ` Jason Wang
2024-01-22  6:04         ` Xuan Zhuo
2024-01-22  6:54           ` Jason Wang
2023-12-29  7:30 ` [PATCH net-next v3 07/27] virtio_ring: virtqueue_disable_and_recycle let the callback detach bufs Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 08/27] virtio_ring: introduce virtqueue_detach_unused_buf_dma() Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 09/27] virtio_ring: introduce virtqueue_get_dma_premapped() Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 10/27] virtio_net: sq support premapped mode Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 11/27] virtio_net: separate virtnet_rx_resize() Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 12/27] virtio_net: separate virtnet_tx_resize() Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 13/27] virtio_net: xsk: bind/unbind xsk Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 14/27] virtio_net: xsk: prevent disable tx napi Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 15/27] virtio_net: move some api to header Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 16/27] virtio_net: xsk: tx: support xmit xsk buffer Xuan Zhuo
2023-12-30  0:28   ` kernel test robot
2023-12-29  7:30 ` [PATCH net-next v3 17/27] virtio_net: xsk: tx: support wakeup Xuan Zhuo
2023-12-29  7:30 ` [PATCH net-next v3 18/27] virtio_net: xsk: tx: handle the transmitted xsk buffer Xuan Zhuo
2023-12-29  7:31 ` [PATCH net-next v3 19/27] virtio_net: xsk: tx: free the unused " Xuan Zhuo
2023-12-29  7:31 ` [PATCH net-next v3 20/27] virtio_net: separate receive_mergeable Xuan Zhuo
2023-12-29  7:31 ` [PATCH net-next v3 21/27] virtio_net: separate receive_buf Xuan Zhuo
2023-12-29  7:31 ` [PATCH net-next v3 22/27] virtio_net: xsk: rx: support fill with xsk buffer Xuan Zhuo
2023-12-29  7:31 ` [PATCH net-next v3 23/27] virtio_net: xsk: rx: support recv merge mode Xuan Zhuo
2023-12-29 21:03   ` kernel test robot
2023-12-30  1:01   ` kernel test robot
2023-12-29  7:31 ` [PATCH net-next v3 24/27] virtio_net: xsk: rx: support recv small mode Xuan Zhuo
2023-12-29  7:31 ` [PATCH net-next v3 25/27] virtio_net: xsk: rx: free the unused xsk buffer Xuan Zhuo
2023-12-29  7:31 ` [PATCH net-next v3 26/27] virtio_net: update tx timeout record Xuan Zhuo
2023-12-29  7:31 ` [PATCH net-next v3 27/27] virtio_net: xdp_features add NETDEV_XDP_ACT_XSK_ZEROCOPY Xuan Zhuo
2024-01-11  3:27 ` [PATCH net-next v3 00/27] virtio-net: support AF_XDP zero copy Jason Wang

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=20231229073108.57778-1-xuanzhuo@linux.alibaba.com \
    --to=xuanzhuo@linux.alibaba.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=hawk@kernel.org \
    --cc=jasowang@redhat.com \
    --cc=john.fastabend@gmail.com \
    --cc=kuba@kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=virtualization@lists.linux-foundation.org \
    /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).