@@ -498,6 +498,12 @@ struct virtio_net_common_hdr {
};
static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf);
+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);
+static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *rq,
+ struct sk_buff *skb, u8 flags);
static bool is_xdp_frame(void *ptr)
{
@@ -1062,6 +1068,124 @@ static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len)
sg->length = len;
}
+static struct xdp_buff *buf_to_xdp(struct virtnet_info *vi,
+ struct receive_queue *rq, void *buf, u32 len)
+{
+ struct xdp_buff *xdp;
+ u32 bufsize;
+
+ xdp = (struct xdp_buff *)buf;
+
+ bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool) + vi->hdr_len;
+
+ if (unlikely(len > bufsize)) {
+ pr_debug("%s: rx error: len %u exceeds truesize %u\n",
+ vi->dev->name, len, bufsize);
+ DEV_STATS_INC(vi->dev, rx_length_errors);
+ xsk_buff_free(xdp);
+ return NULL;
+ }
+
+ xsk_buff_set_size(xdp, len);
+ xsk_buff_dma_sync_for_cpu(xdp);
+
+ return xdp;
+}
+
+static struct sk_buff *xsk_construct_skb(struct receive_queue *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)) {
+ xsk_buff_free(xdp);
+ 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);
+ }
+
+ xsk_buff_free(xdp);
+
+ return skb;
+}
+
+static struct sk_buff *virtnet_receive_xsk_small(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 bpf_prog *prog;
+ u32 ret;
+
+ 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:
+ return xsk_construct_skb(rq, xdp);
+
+ case XDP_TX:
+ case XDP_REDIRECT:
+ return NULL;
+
+ default:
+ /* drop packet */
+ xsk_buff_free(xdp);
+ 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,
+ struct virtnet_rq_stats *stats)
+{
+ struct net_device *dev = vi->dev;
+ struct sk_buff *skb = NULL;
+ struct xdp_buff *xdp;
+ u8 flags;
+
+ len -= vi->hdr_len;
+
+ u64_stats_add(&stats->bytes, len);
+
+ xdp = buf_to_xdp(vi, rq, buf, len);
+ if (!xdp)
+ return;
+
+ if (unlikely(len < ETH_HLEN)) {
+ pr_debug("%s: short packet %i\n", dev->name, len);
+ DEV_STATS_INC(dev, rx_length_errors);
+ xsk_buff_free(xdp);
+ return;
+ }
+
+ flags = ((struct virtio_net_common_hdr *)(xdp->data - vi->hdr_len))->hdr.flags;
+
+ if (!vi->mergeable_rx_bufs)
+ skb = virtnet_receive_xsk_small(dev, vi, rq, xdp, xdp_xmit, stats);
+
+ if (skb)
+ virtnet_receive_done(vi, rq, skb, flags);
+}
+
static int virtnet_add_recvbuf_xsk(struct virtnet_info *vi, struct receive_queue *rq,
struct xsk_buff_pool *pool, gfp_t gfp)
{
@@ -2392,32 +2516,68 @@ static void refill_work(struct work_struct *work)
}
}
-static int virtnet_receive(struct receive_queue *rq, int budget,
- unsigned int *xdp_xmit)
+static int virtnet_receive_xsk_bufs(struct virtnet_info *vi,
+ struct receive_queue *rq,
+ int budget,
+ unsigned int *xdp_xmit,
+ struct virtnet_rq_stats *stats)
+{
+ unsigned int len;
+ int packets = 0;
+ void *buf;
+
+ while (packets < budget) {
+ buf = virtqueue_get_buf(rq->vq, &len);
+ if (!buf)
+ break;
+
+ virtnet_receive_xsk_buf(vi, rq, buf, len, xdp_xmit, stats);
+ packets++;
+ }
+
+ return packets;
+}
+
+static int virtnet_receive_packets(struct virtnet_info *vi,
+ struct receive_queue *rq,
+ int budget,
+ unsigned int *xdp_xmit,
+ struct virtnet_rq_stats *stats)
{
- struct virtnet_info *vi = rq->vq->vdev->priv;
- struct virtnet_rq_stats stats = {};
unsigned int len;
int packets = 0;
void *buf;
- int i;
if (!vi->big_packets || vi->mergeable_rx_bufs) {
void *ctx;
-
while (packets < budget &&
(buf = virtnet_rq_get_buf(rq, &len, &ctx))) {
- receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &stats);
+ receive_buf(vi, rq, buf, len, ctx, xdp_xmit, stats);
packets++;
}
} else {
while (packets < budget &&
(buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
- receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats);
+ receive_buf(vi, rq, buf, len, NULL, xdp_xmit, stats);
packets++;
}
}
+ return packets;
+}
+
+static int virtnet_receive(struct receive_queue *rq, int budget,
+ unsigned int *xdp_xmit)
+{
+ struct virtnet_info *vi = rq->vq->vdev->priv;
+ struct virtnet_rq_stats stats = {};
+ int i, packets;
+
+ if (rq->xsk_pool)
+ packets = virtnet_receive_xsk_bufs(vi, rq, budget, xdp_xmit, &stats);
+ else
+ packets = virtnet_receive_packets(vi, rq, budget, xdp_xmit, &stats);
+
if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
spin_lock(&vi->refill_lock);