From: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
To: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Cc: "Petr Machata" <petrm@nvidia.com>,
"Menglong Dong" <imagedong@tencent.com>,
"Jesper Dangaard Brouer" <hawk@kernel.org>,
"Daniel Borkmann" <daniel@iogearbox.net>,
"Michael S. Tsirkin" <mst@redhat.com>,
netdev@vger.kernel.org,
"John Fastabend" <john.fastabend@gmail.com>,
"Björn Töpel" <bjorn@kernel.org>,
"Alexei Starovoitov" <ast@kernel.org>,
"Eric Dumazet" <edumazet@google.com>,
"Kuniyuki Iwashima" <kuniyu@amazon.com>,
"Sebastian Andrzej Siewior" <bigeasy@linutronix.de>,
"Jonathan Lemon" <jonathan.lemon@gmail.com>,
"Jakub Kicinski" <kuba@kernel.org>,
bpf@vger.kernel.org, "Paolo Abeni" <pabeni@redhat.com>,
virtualization@lists.linux-foundation.org,
"David S. Miller" <davem@davemloft.net>,
"Magnus Karlsson" <magnus.karlsson@intel.com>
Subject: Re: [PATCH 29/33] virtio_net: xsk: tx: support tx
Date: Fri, 3 Feb 2023 16:55:26 +0800 [thread overview]
Message-ID: <1675414526.084923-4-xuanzhuo@linux.alibaba.com> (raw)
In-Reply-To: <Y9zIPdKmTvXqyuYS@boxer>
On Fri, 3 Feb 2023 09:39:25 +0100, Maciej Fijalkowski <maciej.fijalkowski@intel.com> wrote:
> On Thu, Feb 02, 2023 at 07:00:54PM +0800, Xuan Zhuo wrote:
> > The driver's tx napi is very important for XSK. It is responsible for
> > obtaining data from the XSK queue and sending it out.
> >
> > At the beginning, we need to trigger tx napi.
> >
> > Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> > ---
> > drivers/net/virtio/main.c | 12 +++-
> > drivers/net/virtio/xsk.c | 146 ++++++++++++++++++++++++++++++++++++++
> > drivers/net/virtio/xsk.h | 2 +
> > 3 files changed, 159 insertions(+), 1 deletion(-)
> >
>
> (...)
>
> > +static int virtnet_xsk_xmit_batch(struct send_queue *sq,
> > + struct xsk_buff_pool *pool,
> > + unsigned int budget,
> > + struct virtnet_sq_stats *stats)
> > +{
> > + int ret = XSK_XMIT_NO_BUDGET;
> > + struct xdp_desc desc;
> > + int err, packet = 0;
> > +
> > + while (budget-- > 0) {
> > + if (sq->vq->num_free < 2) {
> > + __free_old_xmit(sq, true, stats);
> > + if (sq->vq->num_free < 2) {
> > + ret = XSK_XMIT_DEV_BUSY;
> > + break;
> > + }
> > + }
> > +
> > + if (!xsk_tx_peek_desc(pool, &desc)) {
>
> anything that stopped from using xsk_tx_peek_release_desc_batch() ?
Great!
Will fix.
Thanks.
>
> > + ret = XSK_XMIT_DONE;
> > + break;
> > + }
> > +
> > + err = virtnet_xsk_xmit_one(sq, pool, &desc);
> > + if (unlikely(err)) {
> > + ret = XSK_XMIT_DEV_BUSY;
> > + break;
> > + }
> > +
> > + ++packet;
> > +
> > + if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq))
> > + ++stats->kicks;
> > + }
> > +
> > + if (packet) {
> > + stats->xdp_tx += packet;
> > +
> > + xsk_tx_release(pool);
> > + }
> > +
> > + return ret;
> > +}
> > +
> > +bool virtnet_xsk_xmit(struct send_queue *sq, struct xsk_buff_pool *pool,
> > + int budget)
> > +{
> > + struct virtnet_sq_stats stats = {};
> > + bool busy;
> > + int ret;
> > +
> > + __free_old_xmit(sq, true, &stats);
> > +
> > + if (xsk_uses_need_wakeup(pool))
> > + xsk_set_tx_need_wakeup(pool);
> > +
> > + ret = virtnet_xsk_xmit_batch(sq, pool, budget, &stats);
> > + switch (ret) {
> > + case XSK_XMIT_DONE:
> > + /* xsk tx qeueu has been consumed done. should complete napi. */
> > + busy = false;
> > + break;
> > +
> > + case XSK_XMIT_NO_BUDGET:
> > + /* reach the budget limit. should let napi run again. */
> > + busy = true;
> > + break;
> > +
> > + case XSK_XMIT_DEV_BUSY:
> > + /* sq vring is full, should complete napi. wait for tx napi been
> > + * triggered by interrupt.
> > + */
> > + busy = false;
> > + break;
> > + }
> > +
> > + virtnet_xsk_check_queue(sq);
> > +
> > + u64_stats_update_begin(&sq->stats.syncp);
> > + sq->stats.packets += stats.packets;
> > + sq->stats.bytes += stats.bytes;
> > + sq->stats.kicks += stats.kicks;
> > + sq->stats.xdp_tx += stats.xdp_tx;
> > + u64_stats_update_end(&sq->stats.syncp);
> > +
> > + return busy;
> > +}
> > +
> > static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queue *rq,
> > struct xsk_buff_pool *pool, struct net_device *dev)
> > {
> > diff --git a/drivers/net/virtio/xsk.h b/drivers/net/virtio/xsk.h
> > index ad684c812091..15f1540a5803 100644
> > --- a/drivers/net/virtio/xsk.h
> > +++ b/drivers/net/virtio/xsk.h
> > @@ -20,4 +20,6 @@ static inline u32 ptr_to_xsk(void *ptr)
> > }
> >
> > int virtnet_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp);
> > +bool virtnet_xsk_xmit(struct send_queue *sq, struct xsk_buff_pool *pool,
> > + int budget);
> > #endif
> > --
> > 2.32.0.3.g01195cf9f
> >
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2023-02-03 8:55 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-02 11:00 [PATCH 00/33] virtio-net: support AF_XDP zero copy Xuan Zhuo
2023-02-02 11:00 ` [PATCH 01/33] virtio_ring: virtqueue_add() support premapped Xuan Zhuo
2023-02-02 11:00 ` [PATCH 02/33] virtio_ring: split: virtqueue_add_split() " Xuan Zhuo
2023-02-02 11:00 ` [PATCH 03/33] virtio_ring: packed: virtqueue_add_packed() " Xuan Zhuo
2023-02-03 9:16 ` Michael S. Tsirkin
2023-02-02 11:00 ` [PATCH 04/33] virtio_ring: introduce virtqueue_add_outbuf_premapped() Xuan Zhuo
2023-02-02 11:00 ` [PATCH 05/33] virtio_ring: introduce virtqueue_add_inbuf_premapped() Xuan Zhuo
2023-02-02 11:00 ` [PATCH 06/33] virtio_ring: introduce virtqueue_reset() Xuan Zhuo
2023-02-03 9:05 ` Michael S. Tsirkin
2023-02-03 9:09 ` Xuan Zhuo
2023-02-13 12:15 ` Michael S. Tsirkin
2023-02-14 1:53 ` Xuan Zhuo
2023-02-02 11:00 ` [PATCH 07/33] virtio_ring: add api virtio_dma_map() for advance dma Xuan Zhuo
2023-02-03 9:07 ` Michael S. Tsirkin
2023-02-02 11:00 ` [PATCH 08/33] virtio_ring: introduce dma sync api for virtio Xuan Zhuo
2023-02-03 9:24 ` Michael S. Tsirkin
2023-02-02 11:00 ` [PATCH 09/33] xsk: xsk_buff_pool add callback for dma_sync Xuan Zhuo
[not found] ` <CAJ8uoz2+4+wUFYF1GjF51DFBV8ZsBRtTEVWpu_2fBmFUEQzOLQ@mail.gmail.com>
2023-02-03 7:01 ` Xuan Zhuo
2023-02-02 11:00 ` [PATCH 10/33] xsk: support virtio DMA map Xuan Zhuo
2023-02-05 22:04 ` kernel test robot
2023-02-02 11:00 ` [PATCH 11/33] virtio_net: rename free_old_xmit_skbs to free_old_xmit Xuan Zhuo
2023-02-02 11:00 ` [PATCH 12/33] virtio_net: unify the code for recycling the xmit ptr Xuan Zhuo
2023-02-02 11:00 ` [PATCH 13/33] virtio_net: virtnet_poll_tx support rescheduled Xuan Zhuo
2023-02-02 11:00 ` [PATCH 14/33] virtio_net: independent directory Xuan Zhuo
2023-02-02 11:00 ` [PATCH 15/33] virtio_net: move to virtio_net.h Xuan Zhuo
2023-02-03 8:53 ` Michael S. Tsirkin
2023-02-03 9:04 ` Xuan Zhuo
2023-02-03 9:26 ` Michael S. Tsirkin
2023-02-02 11:00 ` [PATCH 16/33] virtio_net: introduce virtnet_xdp_handler() to seprate the logic of run xdp Xuan Zhuo
2023-02-03 8:55 ` Michael S. Tsirkin
2023-02-03 9:01 ` Xuan Zhuo
2023-02-02 11:00 ` [PATCH 17/33] virtio_net: receive_small() use virtnet_xdp_handler() Xuan Zhuo
2023-02-02 11:00 ` [PATCH 18/33] virtio_net: receive_merageable() " Xuan Zhuo
2023-02-02 17:16 ` Michael S. Tsirkin
2023-02-02 11:00 ` [PATCH 19/33] virtio_net: introduce virtnet_tx_reset() Xuan Zhuo
2023-02-02 17:23 ` Michael S. Tsirkin
2023-02-03 4:35 ` Xuan Zhuo
2023-02-02 11:00 ` [PATCH 20/33] virtio_net: xsk: introduce virtnet_rq_bind_xsk_pool() Xuan Zhuo
2023-02-03 8:48 ` Michael S. Tsirkin
2023-02-03 8:52 ` Xuan Zhuo
2023-02-03 9:28 ` Michael S. Tsirkin
2023-02-02 11:00 ` [PATCH 21/33] virtio_net: xsk: introduce virtnet_xsk_pool_enable() Xuan Zhuo
2023-02-02 11:00 ` [PATCH 22/33] virtio_net: xsk: introduce xsk disable Xuan Zhuo
2023-02-02 23:02 ` kernel test robot
2023-02-12 7:56 ` kernel test robot
2023-02-02 11:00 ` [PATCH 23/33] virtio_net: xsk: support xsk setup Xuan Zhuo
2023-02-02 11:00 ` [PATCH 24/33] virtio_net: xsk: stop disable tx napi Xuan Zhuo
2023-02-02 17:25 ` Michael S. Tsirkin
2023-02-03 3:24 ` Xuan Zhuo
2023-02-03 8:33 ` Michael S. Tsirkin
2023-02-03 8:49 ` Xuan Zhuo
2023-02-03 9:29 ` Michael S. Tsirkin
2023-02-02 11:00 ` [PATCH 25/33] virtio_net: xsk: __free_old_xmit distinguishes xsk buffer Xuan Zhuo
2023-02-02 11:00 ` [PATCH 26/33] virtio_net: virtnet_sq_free_unused_buf() check " Xuan Zhuo
2023-02-02 11:00 ` [PATCH 27/33] virtio_net: virtnet_rq_free_unused_buf() " Xuan Zhuo
2023-02-02 11:00 ` [PATCH 28/33] net: introduce napi_tx_raise() Xuan Zhuo
2023-02-02 11:00 ` [PATCH 29/33] virtio_net: xsk: tx: support tx Xuan Zhuo
[not found] ` <Y9zIPdKmTvXqyuYS@boxer>
2023-02-03 8:55 ` Xuan Zhuo [this message]
2023-02-02 11:00 ` [PATCH 30/33] virtio_net: xsk: tx: support wakeup Xuan Zhuo
2023-02-02 11:00 ` [PATCH 31/33] virtio_net: xsk: tx: auto wakeup when free old xmit Xuan Zhuo
2023-02-02 11:00 ` [PATCH 32/33] virtio_net: xsk: rx: introduce add_recvbuf_xsk() Xuan Zhuo
[not found] ` <Y9zJS+ugeY9qEMt9@boxer>
2023-02-03 8:56 ` Xuan Zhuo
2023-02-02 11:00 ` [PATCH 33/33] virtio_net: xsk: rx: introduce receive_xsk() to recv xsk buffer Xuan Zhuo
2023-02-02 11:08 ` [PATCH 00/33] virtio-net: support AF_XDP zero copy Xuan Zhuo
2023-02-02 11:08 ` Michael S. Tsirkin
2023-02-02 11:11 ` Xuan Zhuo
2023-02-02 11:44 ` Xuan Zhuo
2023-02-03 9:08 ` Michael S. Tsirkin
2023-02-03 9:09 ` Xuan Zhuo
2023-02-02 14:41 ` Paolo Abeni
2023-02-03 3:33 ` Xuan Zhuo
2023-02-03 8:37 ` Michael S. Tsirkin
[not found] ` <Y9zJ9j0GthvRSFHL@boxer>
2023-02-03 9:09 ` Michael S. Tsirkin
2023-02-03 9:17 ` Michael S. Tsirkin
2023-02-06 2:41 ` Xuan Zhuo
2023-02-13 12:14 ` Michael S. Tsirkin
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=1675414526.084923-4-xuanzhuo@linux.alibaba.com \
--to=xuanzhuo@linux.alibaba.com \
--cc=ast@kernel.org \
--cc=bigeasy@linutronix.de \
--cc=bjorn@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=imagedong@tencent.com \
--cc=john.fastabend@gmail.com \
--cc=jonathan.lemon@gmail.com \
--cc=kuba@kernel.org \
--cc=kuniyu@amazon.com \
--cc=maciej.fijalkowski@intel.com \
--cc=magnus.karlsson@intel.com \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=petrm@nvidia.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).