On Fri, 20 Oct 2023 14:57:06 +0800, Jason Wang [off-list ref] wrote:

On Mon, Oct 16, 2023 at 8:01 PM Xuan Zhuo [off-list ref] wrote:

quoted

Implementing the logic of xsk rx. If this packet is not for XSK
determined in XDP, then we need to copy once to generate a SKB.
If it is for XSK, it is a zerocopy receive packet process.

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
 drivers/net/virtio/main.c       |  14 ++--
 drivers/net/virtio/virtio_net.h |   4 ++
 drivers/net/virtio/xsk.c        | 120 ++++++++++++++++++++++++++++++++
 drivers/net/virtio/xsk.h        |   4 ++
 4 files changed, 137 insertions(+), 5 deletions(-)

diff --git a/drivers/net/virtio/main.c b/drivers/net/virtio/main.c
index 0e740447b142..003dd67ab707 100644
--- a/drivers/net/virtio/main.c
+++ b/drivers/net/virtio/main.c

@@ -822,10 +822,10 @@ static void put_xdp_frags(struct xdp_buff *xdp)
        }
 }

-static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
-                              struct net_device *dev,
-                              unsigned int *xdp_xmit,
-                              struct virtnet_rq_stats *stats)
+int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
+                       struct net_device *dev,
+                       unsigned int *xdp_xmit,
+                       struct virtnet_rq_stats *stats)
 {
        struct xdp_frame *xdpf;
        int err;

@@ -1589,13 +1589,17 @@ static void receive_buf(struct virtnet_info *vi, struct virtnet_rq *rq,
                return;
        }

-       if (vi->mergeable_rx_bufs)
+       rcu_read_lock();
+       if (rcu_dereference(rq->xsk.pool))
+               skb = virtnet_receive_xsk(dev, vi, rq, buf, len, xdp_xmit, stats);
+       else if (vi->mergeable_rx_bufs)
                skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit,
                                        stats);
        else if (vi->big_packets)
                skb = receive_big(dev, vi, rq, buf, len, stats);
        else
                skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats);
+       rcu_read_unlock();

        if (unlikely(!skb))
                return;

diff --git a/drivers/net/virtio/virtio_net.h b/drivers/net/virtio/virtio_net.h
index 6e71622fca45..fd7f34703c9b 100644
--- a/drivers/net/virtio/virtio_net.h
+++ b/drivers/net/virtio/virtio_net.h

@@ -346,6 +346,10 @@ static inline bool virtnet_is_xdp_raw_buffer_queue(struct virtnet_info *vi, int
                return false;
 }

+int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
+                       struct net_device *dev,
+                       unsigned int *xdp_xmit,
+                       struct virtnet_rq_stats *stats);
 void virtnet_rx_pause(struct virtnet_info *vi, struct virtnet_rq *rq);
 void virtnet_rx_resume(struct virtnet_info *vi, struct virtnet_rq *rq);
 void virtnet_tx_pause(struct virtnet_info *vi, struct virtnet_sq *sq);

diff --git a/drivers/net/virtio/xsk.c b/drivers/net/virtio/xsk.c
index 841fb078882a..f1c64414fac9 100644
--- a/drivers/net/virtio/xsk.c
+++ b/drivers/net/virtio/xsk.c

@@ -13,6 +13,18 @@ static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len)
        sg->length = len;
 }

+static unsigned int virtnet_receive_buf_num(struct virtnet_info *vi, char *buf)
+{
+       struct virtio_net_hdr_mrg_rxbuf *hdr;
+
+       if (vi->mergeable_rx_bufs) {
+               hdr = (struct virtio_net_hdr_mrg_rxbuf *)buf;
+               return virtio16_to_cpu(vi->vdev, hdr->num_buffers);
+       }
+
+       return 1;
+}
+
 static void virtnet_xsk_check_queue(struct virtnet_sq *sq)
 {
        struct virtnet_info *vi = sq->vq->vdev->priv;

@@ -37,6 +49,114 @@ static void virtnet_xsk_check_queue(struct virtnet_sq *sq)
                netif_stop_subqueue(dev, qnum);
 }

+static void merge_drop_follow_xdp(struct net_device *dev,
+                                 struct virtnet_rq *rq,
+                                 u32 num_buf,
+                                 struct virtnet_rq_stats *stats)
+{
+       struct xdp_buff *xdp;
+       u32 len;
+
+       while (num_buf-- > 1) {
+               xdp = virtqueue_get_buf(rq->vq, &len);
+               if (unlikely(!xdp)) {
+                       pr_debug("%s: rx error: %d buffers missing\n",
+                                dev->name, num_buf);
+                       dev->stats.rx_length_errors++;
+                       break;
+               }
+               stats->bytes += len;
+               xsk_buff_free(xdp);
+       }
+}
+
+static struct sk_buff *construct_skb(struct virtnet_rq *rq,
+                                    struct xdp_buff *xdp)
+{
+       unsigned int metasize = xdp->data - xdp->data_meta;
+       struct sk_buff *skb;
+       unsigned int size;
+
+       size = xdp->data_end - xdp->data_hard_start;
+       skb = napi_alloc_skb(&rq->napi, size);
+       if (unlikely(!skb))
+               return NULL;
+
+       skb_reserve(skb, xdp->data_meta - xdp->data_hard_start);
+
+       size = xdp->data_end - xdp->data_meta;
+       memcpy(__skb_put(skb, size), xdp->data_meta, size);
+
+       if (metasize) {
+               __skb_pull(skb, metasize);
+               skb_metadata_set(skb, metasize);
+       }
+
+       return skb;
+}
+
+struct sk_buff *virtnet_receive_xsk(struct net_device *dev, struct virtnet_info *vi,
+                                   struct virtnet_rq *rq, void *buf,
+                                   unsigned int len, unsigned int *xdp_xmit,
+                                   struct virtnet_rq_stats *stats)
+{

I wonder if anything blocks us from reusing the existing XDP logic?
Are there some subtle differences?

1. We need to copy data to create skb for XDP_PASS.
2. We need to call xsk_buff_free() to release the buffer.
3. The handle for xdp_buff is difference.

virtnet_xdp_handler() is re-used. So the receive code is simple.

If we pushed this function into existing code, we would have to maintain
code scattered inside merge and small (and big). So I think it is a good
choice for us to put the xsk code into a function.


Thanks.

Thanks