From: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
To: Jason Wang <jasowang@redhat.com>
Cc: netdev@vger.kernel.org, "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>,
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: Re: [PATCH net-next v1 08/19] virtio_net: sq support premapped mode
Date: Fri, 20 Oct 2023 15:16:48 +0800 [thread overview]
Message-ID: <1697786208.7535846-1-xuanzhuo@linux.alibaba.com> (raw)
In-Reply-To: <CACGkMEuq8i9_PX+vRESS3g2BpaWBv3FxDLMryG=aEJ+gAOsSaA@mail.gmail.com>
On Fri, 20 Oct 2023 14:50:52 +0800, Jason Wang <jasowang@redhat.com> wrote:
> On Mon, Oct 16, 2023 at 8:01 PM Xuan Zhuo <xuanzhuo@linux.alibaba.com> wrote:
> >
> > If the xsk is enabling, the xsk tx will share the send queue.
> > But the xsk requires that the send queue use the premapped mode.
> > So the send queue must support premapped mode.
> >
> > Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> > ---
> > drivers/net/virtio/main.c | 108 ++++++++++++++++++++++++++++----
> > drivers/net/virtio/virtio_net.h | 54 +++++++++++++++-
> > 2 files changed, 149 insertions(+), 13 deletions(-)
> >
> > diff --git a/drivers/net/virtio/main.c b/drivers/net/virtio/main.c
> > index 8da84ea9bcbe..02d27101fef1 100644
> > --- a/drivers/net/virtio/main.c
> > +++ b/drivers/net/virtio/main.c
> > @@ -514,20 +514,104 @@ static void *virtnet_rq_alloc(struct virtnet_rq *rq, u32 size, gfp_t gfp)
> > return buf;
> > }
> >
> > -static void virtnet_rq_set_premapped(struct virtnet_info *vi)
> > +static int virtnet_sq_set_premapped(struct virtnet_sq *sq)
> > {
> > - int i;
> > + struct virtnet_sq_dma *d;
> > + int err, size, i;
> >
> > - /* disable for big mode */
> > - if (!vi->mergeable_rx_bufs && vi->big_packets)
> > - return;
>
> Not specific to this patch but any plan to fix the big mode?
>
For big, we should make it support XDP and do dma first.
>
> > + size = virtqueue_get_vring_size(sq->vq);
> > +
> > + size += MAX_SKB_FRAGS + 2;
> > +
> > + sq->dmainfo.head = kcalloc(size, sizeof(*sq->dmainfo.head), GFP_KERNEL);
> > + if (!sq->dmainfo.head)
> > + return -ENOMEM;
> > +
> > + err = virtqueue_set_dma_premapped(sq->vq);
> > + if (err) {
> > + kfree(sq->dmainfo.head);
> > + return err;
> > + }
> > +
> > + sq->dmainfo.free = NULL;
> > +
[...]
> > +
> > + d->addr = sg->dma_address;
> > + d->len = sg->length;
> > +
> > + d->next = head;
> > + head = d;
>
> It's really a pity that we need to duplicate those DMA metata twice.
> Could we invent a new API to just fetch it from the virtio core?
Actually, I posted that patch.
Consider this is pushing to net-next. We can do that on top.
>
> > + }
> > +
> > + head->data = data;
> > +
> > + return (void *)((unsigned long)head | ((unsigned long)data & VIRTIO_XMIT_DATA_MASK));
>
> If we packed everything into dmainfo, we can leave the type (XDP vs
> skb) there to avoid trick like packing it into the pointer here?
Yes. But if the virtio has not _ACCESS_PLATFORM, the driver will
has not the DMA meta data.
Thanks.
>
> Thanks
>
next prev parent reply other threads:[~2023-10-20 7:23 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-16 12:00 [PATCH net-next v1 00/19] virtio-net: support AF_XDP zero copy Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 01/19] virtio_net: rename free_old_xmit_skbs to free_old_xmit Xuan Zhuo
2023-10-19 4:17 ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 02/19] virtio_net: unify the code for recycling the xmit ptr Xuan Zhuo
2023-10-19 4:23 ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 03/19] virtio_net: independent directory Xuan Zhuo
2023-10-19 6:10 ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 04/19] virtio_net: move to virtio_net.h Xuan Zhuo
2023-10-19 6:12 ` Jason Wang
2023-10-19 7:16 ` Xuan Zhuo
2023-10-20 6:59 ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 05/19] virtio_net: add prefix virtnet to all struct/api inside virtio_net.h Xuan Zhuo
2023-10-19 6:14 ` Jason Wang
2023-10-19 6:36 ` Michael S. Tsirkin
2023-10-16 12:00 ` [PATCH net-next v1 06/19] virtio_net: separate virtnet_rx_resize() Xuan Zhuo
2023-10-19 6:17 ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 07/19] virtio_net: separate virtnet_tx_resize() Xuan Zhuo
2023-10-19 6:18 ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 08/19] virtio_net: sq support premapped mode Xuan Zhuo
2023-10-20 6:50 ` Jason Wang
2023-10-20 7:16 ` Xuan Zhuo [this message]
2023-10-16 12:00 ` [PATCH net-next v1 09/19] virtio_net: xsk: bind/unbind xsk Xuan Zhuo
2023-10-20 6:51 ` Jason Wang
2023-10-20 7:28 ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 10/19] virtio_net: xsk: prevent disable tx napi Xuan Zhuo
2023-10-20 6:51 ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 11/19] virtio_net: xsk: tx: support tx Xuan Zhuo
2023-10-20 6:52 ` Jason Wang
2023-10-20 8:06 ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 12/19] virtio_net: xsk: tx: support wakeup Xuan Zhuo
2023-10-20 6:52 ` Jason Wang
2023-10-20 8:09 ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 13/19] virtio_net: xsk: tx: virtnet_free_old_xmit() distinguishes xsk buffer Xuan Zhuo
2023-10-16 23:44 ` Jakub Kicinski
2023-10-17 2:02 ` Xuan Zhuo
2023-10-19 6:38 ` Michael S. Tsirkin
2023-10-19 7:13 ` Xuan Zhuo
2023-10-19 8:42 ` Michael S. Tsirkin
2023-10-16 12:00 ` [PATCH net-next v1 14/19] virtio_net: xsk: tx: virtnet_sq_free_unused_buf() check " Xuan Zhuo
2023-10-20 6:53 ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 15/19] virtio_net: xsk: rx: introduce add_recvbuf_xsk() Xuan Zhuo
2023-10-20 6:56 ` Jason Wang
2023-10-23 6:56 ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 16/19] virtio_net: xsk: rx: introduce receive_xsk() to recv xsk buffer Xuan Zhuo
2023-10-20 6:57 ` Jason Wang
2023-10-23 2:39 ` Xuan Zhuo
2023-11-15 2:35 ` Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 17/19] virtio_net: xsk: rx: virtnet_rq_free_unused_buf() check " Xuan Zhuo
2023-10-16 12:00 ` [PATCH net-next v1 18/19] virtio_net: update tx timeout record Xuan Zhuo
2023-10-20 6:57 ` Jason Wang
2023-10-16 12:00 ` [PATCH net-next v1 19/19] virtio_net: xdp_features add NETDEV_XDP_ACT_XSK_ZEROCOPY Xuan Zhuo
2023-10-17 2:53 ` [PATCH net-next v1 00/19] virtio-net: support AF_XDP zero copy Jason Wang
2023-10-17 3:02 ` Xuan Zhuo
2023-10-17 3:20 ` Jason Wang
2023-10-17 3:22 ` Xuan Zhuo
2023-10-17 3:28 ` Jason Wang
2023-10-17 5:27 ` Jason Wang
2023-10-17 6:06 ` Xuan Zhuo
2023-10-17 6:26 ` Jason Wang
2023-10-17 6:43 ` Xuan Zhuo
2023-10-17 11:19 ` Xuan Zhuo
2023-10-18 2:46 ` Jason Wang
2023-10-18 2:56 ` Xuan Zhuo
2023-10-18 3:32 ` Xuan Zhuo
2023-10-18 3:40 ` Jason Wang
2023-10-18 1:02 ` 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=1697786208.7535846-1-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).