virtio_net: xsk: bind/unbind xsk for tx

This patch implement the logic of bind/unbind xsk pool to sq and rq.

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20241112012928.102478-10-xuanzhuo@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 53 insertions, 0 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 539a43777f86..6cd9fdb23b8a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -295,6 +295,10 @@ struct send_queue {
 
 	/* Record whether sq is in reset state. */
 	bool reset;
+
+	struct xsk_buff_pool *xsk_pool;
+
+	dma_addr_t xsk_hdr_dma_addr;
 };
 
 /* Internal representation of a receive virtqueue */
@@ -495,6 +499,8 @@ struct virtio_net_common_hdr {
 	};
 };
 
+static struct virtio_net_common_hdr xsk_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,
@@ -5561,6 +5567,29 @@ unreg:
 	return err;
 }
 
+static int virtnet_sq_bind_xsk_pool(struct virtnet_info *vi,
+				    struct send_queue *sq,
+				    struct xsk_buff_pool *pool)
+{
+	int err, qindex;
+
+	qindex = sq - vi->sq;
+
+	virtnet_tx_pause(vi, sq);
+
+	err = virtqueue_reset(sq->vq, virtnet_sq_free_unused_buf);
+	if (err) {
+		netdev_err(vi->dev, "reset tx fail: tx queue index: %d err: %d\n", qindex, err);
+		pool = NULL;
+	}
+
+	sq->xsk_pool = pool;
+
+	virtnet_tx_resume(vi, sq);
+
+	return err;
+}
+
 static int virtnet_xsk_pool_enable(struct net_device *dev,
 				   struct xsk_buff_pool *pool,
 				   u16 qid)
@@ -5569,6 +5598,7 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
 	struct receive_queue *rq;
 	struct device *dma_dev;
 	struct send_queue *sq;
+	dma_addr_t hdr_dma;
 	int err, size;
 
 	if (vi->hdr_len > xsk_pool_get_headroom(pool))
@@ -5606,6 +5636,11 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
 	if (!rq->xsk_buffs)
 		return -ENOMEM;
 
+	hdr_dma = virtqueue_dma_map_single_attrs(sq->vq, &xsk_hdr, vi->hdr_len,
+						 DMA_TO_DEVICE, 0);
+	if (virtqueue_dma_mapping_error(sq->vq, hdr_dma))
+		return -ENOMEM;
+
 	err = xsk_pool_dma_map(pool, dma_dev, 0);
 	if (err)
 		goto err_xsk_map;
@@ -5614,11 +5649,24 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
 	if (err)
 		goto err_rq;
 
+	err = virtnet_sq_bind_xsk_pool(vi, sq, pool);
+	if (err)
+		goto err_sq;
+
+	/* Now, we do not support tx offload(such as tx csum), so all the tx
+	 * virtnet hdr is zero. So all the tx packets can share a single hdr.
+	 */
+	sq->xsk_hdr_dma_addr = hdr_dma;
+
 	return 0;
 
+err_sq:
+	virtnet_rq_bind_xsk_pool(vi, rq, NULL);
 err_rq:
 	xsk_pool_dma_unmap(pool, 0);
 err_xsk_map:
+	virtqueue_dma_unmap_single_attrs(rq->vq, hdr_dma, vi->hdr_len,
+					 DMA_TO_DEVICE, 0);
 	return err;
 }
 
@@ -5627,19 +5675,24 @@ static int virtnet_xsk_pool_disable(struct net_device *dev, u16 qid)
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct xsk_buff_pool *pool;
 	struct receive_queue *rq;
+	struct send_queue *sq;
 	int err;
 
 	if (qid >= vi->curr_queue_pairs)
 		return -EINVAL;
 
+	sq = &vi->sq[qid];
 	rq = &vi->rq[qid];
 
 	pool = rq->xsk_pool;
 
 	err = virtnet_rq_bind_xsk_pool(vi, rq, NULL);
+	err |= virtnet_sq_bind_xsk_pool(vi, sq, NULL);
 
 	xsk_pool_dma_unmap(pool, 0);
 
+	virtqueue_dma_unmap_single_attrs(sq->vq, sq->xsk_hdr_dma_addr,
+					 vi->hdr_len, DMA_TO_DEVICE, 0);
 	kvfree(rq->xsk_buffs);
 
 	return err;