diff mbox series

[net-next,v7,08/10] virtio_net: xsk: rx: support fill with xsk buffer

Message ID 20240705073734.93905-9-xuanzhuo@linux.alibaba.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series virtio-net: support AF_XDP zero copy | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 816 this patch: 816
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 14 of 14 maintainers
netdev/build_clang success Errors and warnings before: 821 this patch: 821
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 821 this patch: 821
netdev/checkpatch warning WARNING: line length of 82 exceeds 80 columns WARNING: line length of 85 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-07-05--15-00 (tests: 694)

Commit Message

Xuan Zhuo July 5, 2024, 7:37 a.m. UTC 
Implement the logic of filling rq with XSK buffers.

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---

v7:
   1. some small fixes

 drivers/net/virtio_net.c | 70 +++++++++++++++++++++++++++++++++++++---
 1 file changed, 66 insertions(+), 4 deletions(-)

--
2.32.0.3.g01195cf9f

Comments

Jason Wang July 8, 2024, 6:49 a.m. UTC | #1 
On Fri, Jul 5, 2024 at 3:37 PM Xuan Zhuo <xuanzhuo@linux.alibaba.com> wrote:
>
> Implement the logic of filling rq with XSK buffers.
>
> Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> ---
>
> v7:
>    1. some small fixes
>
>  drivers/net/virtio_net.c | 70 +++++++++++++++++++++++++++++++++++++---
>  1 file changed, 66 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 29fa25ce1a7f..2b27f5ada64a 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -354,6 +354,8 @@ struct receive_queue {
>
>         /* xdp rxq used by xsk */
>         struct xdp_rxq_info xsk_rxq_info;
> +
> +       struct xdp_buff **xsk_buffs;
>  };
>
>  /* This structure can contain rss message with maximum settings for indirection table and keysize
> @@ -1054,6 +1056,53 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
>         }
>  }
>
> +static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len)
> +{
> +       sg->dma_address = addr;
> +       sg->length = len;
> +}
> +
> +static int virtnet_add_recvbuf_xsk(struct virtnet_info *vi, struct receive_queue *rq,
> +                                  struct xsk_buff_pool *pool, gfp_t gfp)
> +{
> +       struct xdp_buff **xsk_buffs;
> +       dma_addr_t addr;
> +       int err = 0;
> +       u32 len, i;
> +       int num;
> +
> +       xsk_buffs = rq->xsk_buffs;
> +
> +       num = xsk_buff_alloc_batch(pool, xsk_buffs, rq->vq->num_free);
> +       if (!num)
> +               return -ENOMEM;
> +
> +       len = xsk_pool_get_rx_frame_size(pool) + vi->hdr_len;
> +
> +       for (i = 0; i < num; ++i) {
> +               /* use the part of XDP_PACKET_HEADROOM as the virtnet hdr space */

It's better to also say we assume hdr->len is larger than
XDP_PACKET_HEADROOM. (see function xyz).

> +               addr = xsk_buff_xdp_get_dma(xsk_buffs[i]) - vi->hdr_len;
> +
> +               sg_init_table(rq->sg, 1);
> +               sg_fill_dma(rq->sg, addr, len);
> +
> +               err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, xsk_buffs[i], gfp);
> +               if (err)
> +                       goto err;
> +       }
> +
> +       return num;
> +
> +err:
> +       if (i)
> +               err = i;

Any reason to assign an index to err here?

Others look good.

Thanks
Xuan Zhuo July 8, 2024, 7:57 a.m. UTC | #2 
On Mon, 8 Jul 2024 14:49:35 +0800, Jason Wang <jasowang@redhat.com> wrote:
> On Fri, Jul 5, 2024 at 3:37 PM Xuan Zhuo <xuanzhuo@linux.alibaba.com> wrote:
> >
> > Implement the logic of filling rq with XSK buffers.
> >
> > Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> > ---
> >
> > v7:
> >    1. some small fixes
> >
> >  drivers/net/virtio_net.c | 70 +++++++++++++++++++++++++++++++++++++---
> >  1 file changed, 66 insertions(+), 4 deletions(-)
> >
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index 29fa25ce1a7f..2b27f5ada64a 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -354,6 +354,8 @@ struct receive_queue {
> >
> >         /* xdp rxq used by xsk */
> >         struct xdp_rxq_info xsk_rxq_info;
> > +
> > +       struct xdp_buff **xsk_buffs;
> >  };
> >
> >  /* This structure can contain rss message with maximum settings for indirection table and keysize
> > @@ -1054,6 +1056,53 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
> >         }
> >  }
> >
> > +static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len)
> > +{
> > +       sg->dma_address = addr;
> > +       sg->length = len;
> > +}
> > +
> > +static int virtnet_add_recvbuf_xsk(struct virtnet_info *vi, struct receive_queue *rq,
> > +                                  struct xsk_buff_pool *pool, gfp_t gfp)
> > +{
> > +       struct xdp_buff **xsk_buffs;
> > +       dma_addr_t addr;
> > +       int err = 0;
> > +       u32 len, i;
> > +       int num;
> > +
> > +       xsk_buffs = rq->xsk_buffs;
> > +
> > +       num = xsk_buff_alloc_batch(pool, xsk_buffs, rq->vq->num_free);
> > +       if (!num)
> > +               return -ENOMEM;
> > +
> > +       len = xsk_pool_get_rx_frame_size(pool) + vi->hdr_len;
> > +
> > +       for (i = 0; i < num; ++i) {
> > +               /* use the part of XDP_PACKET_HEADROOM as the virtnet hdr space */
>
> It's better to also say we assume hdr->len is larger than
> XDP_PACKET_HEADROOM. (see function xyz).
>
> > +               addr = xsk_buff_xdp_get_dma(xsk_buffs[i]) - vi->hdr_len;
> > +
> > +               sg_init_table(rq->sg, 1);
> > +               sg_fill_dma(rq->sg, addr, len);
> > +
> > +               err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, xsk_buffs[i], gfp);
> > +               if (err)
> > +                       goto err;
> > +       }
> > +
> > +       return num;
> > +
> > +err:
> > +       if (i)
> > +               err = i;
>
> Any reason to assign an index to err here?

I tried to return the num of bufs added to the ring.

But rethink this, we should return the error of virtqueue_add_inbuf() directly.

Will fix.

Thanks.

>
> Others look good.
>
> Thanks
>
diff mbox series

Patch

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 29fa25ce1a7f..2b27f5ada64a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -354,6 +354,8 @@  struct receive_queue {

 	/* xdp rxq used by xsk */
 	struct xdp_rxq_info xsk_rxq_info;
+
+	struct xdp_buff **xsk_buffs;
 };

 /* This structure can contain rss message with maximum settings for indirection table and keysize
@@ -1054,6 +1056,53 @@  static void check_sq_full_and_disable(struct virtnet_info *vi,
 	}
 }

+static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len)
+{
+	sg->dma_address = addr;
+	sg->length = len;
+}
+
+static int virtnet_add_recvbuf_xsk(struct virtnet_info *vi, struct receive_queue *rq,
+				   struct xsk_buff_pool *pool, gfp_t gfp)
+{
+	struct xdp_buff **xsk_buffs;
+	dma_addr_t addr;
+	int err = 0;
+	u32 len, i;
+	int num;
+
+	xsk_buffs = rq->xsk_buffs;
+
+	num = xsk_buff_alloc_batch(pool, xsk_buffs, rq->vq->num_free);
+	if (!num)
+		return -ENOMEM;
+
+	len = xsk_pool_get_rx_frame_size(pool) + vi->hdr_len;
+
+	for (i = 0; i < num; ++i) {
+		/* use the part of XDP_PACKET_HEADROOM as the virtnet hdr space */
+		addr = xsk_buff_xdp_get_dma(xsk_buffs[i]) - vi->hdr_len;
+
+		sg_init_table(rq->sg, 1);
+		sg_fill_dma(rq->sg, addr, len);
+
+		err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, xsk_buffs[i], gfp);
+		if (err)
+			goto err;
+	}
+
+	return num;
+
+err:
+	if (i)
+		err = i;
+
+	for (; i < num; ++i)
+		xsk_buff_free(xsk_buffs[i]);
+
+	return err;
+}
+
 static int virtnet_xsk_wakeup(struct net_device *dev, u32 qid, u32 flag)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -2245,7 +2294,11 @@  static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 			  gfp_t gfp)
 {
 	int err;
-	bool oom;
+
+	if (rq->xsk_pool) {
+		err = virtnet_add_recvbuf_xsk(vi, rq, rq->xsk_pool, gfp);
+		goto kick;
+	}

 	do {
 		if (vi->mergeable_rx_bufs)
@@ -2255,10 +2308,11 @@  static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 		else
 			err = add_recvbuf_small(vi, rq, gfp);

-		oom = err == -ENOMEM;
 		if (err)
 			break;
 	} while (rq->vq->num_free);
+
+kick:
 	if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) {
 		unsigned long flags;

@@ -2267,7 +2321,7 @@  static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 		u64_stats_update_end_irqrestore(&rq->stats.syncp, flags);
 	}

-	return !oom;
+	return err != -ENOMEM;
 }

 static void skb_recv_done(struct virtqueue *rvq)
@@ -5104,7 +5158,7 @@  static int virtnet_xsk_pool_enable(struct net_device *dev,
 	struct receive_queue *rq;
 	struct device *dma_dev;
 	struct send_queue *sq;
-	int err;
+	int err, size;

 	if (vi->hdr_len > xsk_pool_get_headroom(pool))
 		return -EINVAL;
@@ -5135,6 +5189,12 @@  static int virtnet_xsk_pool_enable(struct net_device *dev,
 	if (!dma_dev)
 		return -EPERM;

+	size = virtqueue_get_vring_size(rq->vq);
+
+	rq->xsk_buffs = kvcalloc(size, sizeof(*rq->xsk_buffs), GFP_KERNEL);
+	if (!rq->xsk_buffs)
+		return -ENOMEM;
+
 	err = xsk_pool_dma_map(pool, dma_dev, 0);
 	if (err)
 		goto err_xsk_map;
@@ -5169,6 +5229,8 @@  static int virtnet_xsk_pool_disable(struct net_device *dev, u16 qid)

 	xsk_pool_dma_unmap(pool, 0);

+	kvfree(rq->xsk_buffs);
+
 	return err;
 }