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@xxxxxxxxxxxxxxxxx>
---
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 55a643a1f129..61be5a353ff3 100644
--- a/drivers/net/virtio/main.c
+++ b/drivers/net/virtio/main.c
@@ -828,10 +828,10 @@ 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;
@@ -1595,13 +1595,17 @@ 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 532df71a4c08..a8aa1a68a237 100644
--- a/drivers/net/virtio/virtio_net.h
+++ b/drivers/net/virtio/virtio_net.h
@@ -345,6 +345,10 @@ 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 d7f0a81e8635..7abd46bb0e3d 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)
+{
+ struct virtio_net_hdr_mrg_rxbuf *hdr;
+ struct sk_buff *skb = NULL;
+ u32 ret, headroom, num_buf;
+ struct bpf_prog *prog;
+ struct xdp_buff *xdp;
+
+ len -= vi->hdr_len;
+
+ xdp = (struct xdp_buff *)buf;
+
+ xsk_buff_set_size(xdp, len);
+
+ hdr = xdp->data - vi->hdr_len;
+
+ num_buf = virtnet_receive_buf_num(vi, (char *)hdr);
+ if (num_buf > 1)
+ goto drop;
+
+ headroom = xdp->data - xdp->data_hard_start;
+
+ xdp_prepare_buff(xdp, xdp->data_hard_start, headroom, len, true);
+ xsk_buff_dma_sync_for_cpu(xdp, rq->xsk.pool);
+
+ ret = XDP_PASS;
+ rcu_read_lock();
+ prog = rcu_dereference(rq->xdp_prog);
+ if (prog)
+ ret = virtnet_xdp_handler(prog, xdp, dev, xdp_xmit, stats);
+ rcu_read_unlock();
+
+ switch (ret) {
+ case XDP_PASS:
+ skb = construct_skb(rq, xdp);
+ xsk_buff_free(xdp);
+ break;
+
+ case XDP_TX:
+ case XDP_REDIRECT:
+ goto consumed;
+
+ default:
+ goto drop;
+ }
+
+ return skb;
+
+drop:
+ stats->drops++;
+
+ xsk_buff_free(xdp);
+
+ if (num_buf > 1)
+ merge_drop_follow_xdp(dev, rq, num_buf, stats);
+consumed:
+ return NULL;
+}
+
static int virtnet_add_recvbuf_batch(struct virtnet_info *vi, struct virtnet_rq *rq,
struct xsk_buff_pool *pool, gfp_t gfp)
{
diff --git a/drivers/net/virtio/xsk.h b/drivers/net/virtio/xsk.h
index bef41a3f954e..dbd2839a5f61 100644
--- a/drivers/net/virtio/xsk.h
+++ b/drivers/net/virtio/xsk.h
@@ -25,4 +25,8 @@ bool virtnet_xsk_xmit(struct virtnet_sq *sq, struct xsk_buff_pool *pool,
int virtnet_xsk_wakeup(struct net_device *dev, u32 qid, u32 flag);
int virtnet_add_recvbuf_xsk(struct virtnet_info *vi, struct virtnet_rq *rq,
struct xsk_buff_pool *pool, gfp_t gfp);
+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);
#endif
--
2.32.0.3.g01195cf9f
