virtio_net: xsk: rx: support recv merge mode

Support AF-XDP for merge mode.

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://patch.msgid.link/20240708112537.96291-11-xuanzhuo@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c9c65948b71fd02efe61424eb703ab5fe22cdf94..b6323346208dd0b1ebff272b849753176f4f6f98 100644 (file)
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -504,6 +504,10 @@ static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
                               struct virtnet_rq_stats *stats);
 static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *rq,
                                 struct sk_buff *skb, u8 flags);
+static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb,
+                                              struct sk_buff *curr_skb,
+                                              struct page *page, void *buf,
+                                              int len, int truesize);
 
 static bool is_xdp_frame(void *ptr)
 {
@@ -984,6 +988,11 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
 
        rq = &vi->rq[i];
 
+       if (rq->xsk_pool) {
+               xsk_buff_free((struct xdp_buff *)buf);
+               return;
+       }
+
        if (!vi->big_packets || vi->mergeable_rx_bufs)
                virtnet_rq_unmap(rq, buf, 0);
 
@@ -1152,6 +1161,139 @@ static struct sk_buff *virtnet_receive_xsk_small(struct net_device *dev, struct
        }
 }
 
+static void xsk_drop_follow_bufs(struct net_device *dev,
+                                struct receive_queue *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_INC(dev, rx_length_errors);
+                       break;
+               }
+               u64_stats_add(&stats->bytes, len);
+               xsk_buff_free(xdp);
+       }
+}
+
+static int xsk_append_merge_buffer(struct virtnet_info *vi,
+                                  struct receive_queue *rq,
+                                  struct sk_buff *head_skb,
+                                  u32 num_buf,
+                                  struct virtio_net_hdr_mrg_rxbuf *hdr,
+                                  struct virtnet_rq_stats *stats)
+{
+       struct sk_buff *curr_skb;
+       struct xdp_buff *xdp;
+       u32 len, truesize;
+       struct page *page;
+       void *buf;
+
+       curr_skb = head_skb;
+
+       while (--num_buf) {
+               buf = virtqueue_get_buf(rq->vq, &len);
+               if (unlikely(!buf)) {
+                       pr_debug("%s: rx error: %d buffers out of %d missing\n",
+                                vi->dev->name, num_buf,
+                                virtio16_to_cpu(vi->vdev,
+                                                hdr->num_buffers));
+                       DEV_STATS_INC(vi->dev, rx_length_errors);
+                       return -EINVAL;
+               }
+
+               u64_stats_add(&stats->bytes, len);
+
+               xdp = buf_to_xdp(vi, rq, buf, len);
+               if (!xdp)
+                       goto err;
+
+               buf = napi_alloc_frag(len);
+               if (!buf) {
+                       xsk_buff_free(xdp);
+                       goto err;
+               }
+
+               memcpy(buf, xdp->data - vi->hdr_len, len);
+
+               xsk_buff_free(xdp);
+
+               page = virt_to_page(buf);
+
+               truesize = len;
+
+               curr_skb  = virtnet_skb_append_frag(head_skb, curr_skb, page,
+                                                   buf, len, truesize);
+               if (!curr_skb) {
+                       put_page(page);
+                       goto err;
+               }
+       }
+
+       return 0;
+
+err:
+       xsk_drop_follow_bufs(vi->dev, rq, num_buf, stats);
+       return -EINVAL;
+}
+
+static struct sk_buff *virtnet_receive_xsk_merge(struct net_device *dev, struct virtnet_info *vi,
+                                                struct receive_queue *rq, struct xdp_buff *xdp,
+                                                unsigned int *xdp_xmit,
+                                                struct virtnet_rq_stats *stats)
+{
+       struct virtio_net_hdr_mrg_rxbuf *hdr;
+       struct bpf_prog *prog;
+       struct sk_buff *skb;
+       u32 ret, num_buf;
+
+       hdr = xdp->data - vi->hdr_len;
+       num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
+
+       ret = XDP_PASS;
+       rcu_read_lock();
+       prog = rcu_dereference(rq->xdp_prog);
+       /* TODO: support multi buffer. */
+       if (prog && num_buf == 1)
+               ret = virtnet_xdp_handler(prog, xdp, dev, xdp_xmit, stats);
+       rcu_read_unlock();
+
+       switch (ret) {
+       case XDP_PASS:
+               skb = xsk_construct_skb(rq, xdp);
+               if (!skb)
+                       goto drop_bufs;
+
+               if (xsk_append_merge_buffer(vi, rq, skb, num_buf, hdr, stats)) {
+                       dev_kfree_skb(skb);
+                       goto drop;
+               }
+
+               return skb;
+
+       case XDP_TX:
+       case XDP_REDIRECT:
+               return NULL;
+
+       default:
+               /* drop packet */
+               xsk_buff_free(xdp);
+       }
+
+drop_bufs:
+       xsk_drop_follow_bufs(dev, rq, num_buf, stats);
+
+drop:
+       u64_stats_inc(&stats->drops);
+       return NULL;
+}
+
 static void virtnet_receive_xsk_buf(struct virtnet_info *vi, struct receive_queue *rq,
                                    void *buf, u32 len,
                                    unsigned int *xdp_xmit,
@@ -1181,6 +1323,8 @@ static void virtnet_receive_xsk_buf(struct virtnet_info *vi, struct receive_queu
 
        if (!vi->mergeable_rx_bufs)
                skb = virtnet_receive_xsk_small(dev, vi, rq, xdp, xdp_xmit, stats);
+       else
+               skb = virtnet_receive_xsk_merge(dev, vi, rq, xdp, xdp_xmit, stats);
 
        if (skb)
                virtnet_receive_done(vi, rq, skb, flags);