virtio_net: xsk: bind/unbind xsk for rx

This patch implement the logic of bind/unbind xsk pool to rq.
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/20240708112537.96291-7-xuanzhuo@linux.alibaba.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/virtio_net.c

@@ -25,6 +25,7 @@
 #include <net/net_failover.h>
 #include <net/netdev_rx_queue.h>
 #include <net/netdev_queues.h>
+#include <net/xdp_sock_drv.h>
 
 static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);
@@ -348,6 +349,11 @@ struct receive_queue {
 
 	/* Record the last dma info to free after new pages is allocated. */
 	struct virtnet_rq_dma *last_dma;
+
+	struct xsk_buff_pool *xsk_pool;
+
+	/* xdp rxq used by xsk */
+	struct xdp_rxq_info xsk_rxq_info;
 };
 
 /* This structure can contain rss message with maximum settings for indirection table and keysize
@@ -5026,6 +5032,132 @@ static int virtnet_restore_guest_offloads(struct virtnet_info *vi)
 	return virtnet_set_guest_offloads(vi, offloads);
 }
 
+static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queue *rq,
+				    struct xsk_buff_pool *pool)
+{
+	int err, qindex;
+
+	qindex = rq - vi->rq;
+
+	if (pool) {
+		err = xdp_rxq_info_reg(&rq->xsk_rxq_info, vi->dev, qindex, rq->napi.napi_id);
+		if (err < 0)
+			return err;
+
+		err = xdp_rxq_info_reg_mem_model(&rq->xsk_rxq_info,
+						 MEM_TYPE_XSK_BUFF_POOL, NULL);
+		if (err < 0)
+			goto unreg;
+
+		xsk_pool_set_rxq_info(pool, &rq->xsk_rxq_info);
+	}
+
+	virtnet_rx_pause(vi, rq);
+
+	err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf);
+	if (err) {
+		netdev_err(vi->dev, "reset rx fail: rx queue index: %d err: %d\n", qindex, err);
+
+		pool = NULL;
+	}
+
+	rq->xsk_pool = pool;
+
+	virtnet_rx_resume(vi, rq);
+
+	if (pool)
+		return 0;
+
+unreg:
+	xdp_rxq_info_unreg(&rq->xsk_rxq_info);
+	return err;
+}
+
+static int virtnet_xsk_pool_enable(struct net_device *dev,
+				   struct xsk_buff_pool *pool,
+				   u16 qid)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	struct receive_queue *rq;
+	struct device *dma_dev;
+	struct send_queue *sq;
+	int err;
+
+	if (vi->hdr_len > xsk_pool_get_headroom(pool))
+		return -EINVAL;
+
+	/* In big_packets mode, xdp cannot work, so there is no need to
+	 * initialize xsk of rq.
+	 */
+	if (vi->big_packets && !vi->mergeable_rx_bufs)
+		return -ENOENT;
+
+	if (qid >= vi->curr_queue_pairs)
+		return -EINVAL;
+
+	sq = &vi->sq[qid];
+	rq = &vi->rq[qid];
+
+	/* xsk assumes that tx and rx must have the same dma device. The af-xdp
+	 * may use one buffer to receive from the rx and reuse this buffer to
+	 * send by the tx. So the dma dev of sq and rq must be the same one.
+	 *
+	 * But vq->dma_dev allows every vq has the respective dma dev. So I
+	 * check the dma dev of vq and sq is the same dev.
+	 */
+	if (virtqueue_dma_dev(rq->vq) != virtqueue_dma_dev(sq->vq))
+		return -EINVAL;
+
+	dma_dev = virtqueue_dma_dev(rq->vq);
+	if (!dma_dev)
+		return -EINVAL;
+
+	err = xsk_pool_dma_map(pool, dma_dev, 0);
+	if (err)
+		goto err_xsk_map;
+
+	err = virtnet_rq_bind_xsk_pool(vi, rq, pool);
+	if (err)
+		goto err_rq;
+
+	return 0;
+
+err_rq:
+	xsk_pool_dma_unmap(pool, 0);
+err_xsk_map:
+	return err;
+}
+
+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;
+	int err;
+
+	if (qid >= vi->curr_queue_pairs)
+		return -EINVAL;
+
+	rq = &vi->rq[qid];
+
+	pool = rq->xsk_pool;
+
+	err = virtnet_rq_bind_xsk_pool(vi, rq, NULL);
+
+	xsk_pool_dma_unmap(pool, 0);
+
+	return err;
+}
+
+static int virtnet_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	if (xdp->xsk.pool)
+		return virtnet_xsk_pool_enable(dev, xdp->xsk.pool,
+					       xdp->xsk.queue_id);
+	else
+		return virtnet_xsk_pool_disable(dev, xdp->xsk.queue_id);
+}
+
 static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			   struct netlink_ext_ack *extack)
 {
@@ -5151,6 +5283,8 @@ static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
+	case XDP_SETUP_XSK_POOL:
+		return virtnet_xsk_pool_setup(dev, xdp);
 	default:
 		return -EINVAL;
 	}