1 files changed, 122 insertions, 10 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 60027b439021..fb3908798458 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -298,6 +298,10 @@ 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 */
@@ -501,6 +505,8 @@ 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 void virtnet_sq_free_unused_buf_done(struct virtqueue *vq);
 static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp,
@@ -759,6 +765,26 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
 	return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1);
 }
 
+static int check_mergeable_len(struct net_device *dev, void *mrg_ctx,
+			       unsigned int len)
+{
+	unsigned int headroom, tailroom, room, truesize;
+
+	truesize = mergeable_ctx_to_truesize(mrg_ctx);
+	headroom = mergeable_ctx_to_headroom(mrg_ctx);
+	tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
+	room = SKB_DATA_ALIGN(headroom + tailroom);
+
+	if (len > truesize - room) {
+		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+			 dev->name, len, (unsigned long)(truesize - room));
+		DEV_STATS_INC(dev, rx_length_errors);
+		return -1;
+	}
+
+	return 0;
+}
+
 static struct sk_buff *virtnet_build_skb(void *buf, unsigned int buflen,
 					 unsigned int headroom,
 					 unsigned int len)
@@ -1092,15 +1118,29 @@ static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len)
 	sg->length = len;
 }
 
+/* Note that @len is the length of received data without virtio header */
 static struct xdp_buff *buf_to_xdp(struct virtnet_info *vi,
-				   struct receive_queue *rq, void *buf, u32 len)
+				   struct receive_queue *rq, void *buf,
+				   u32 len, bool first_buf)
 {
 	struct xdp_buff *xdp;
 	u32 bufsize;
 
 	xdp = (struct xdp_buff *)buf;
 
-	bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool) + vi->hdr_len;
+	/* In virtnet_add_recvbuf_xsk, we use part of XDP_PACKET_HEADROOM for
+	 * virtio header and ask the vhost to fill data from
+	 *         hard_start + XDP_PACKET_HEADROOM - vi->hdr_len
+	 * The first buffer has virtio header so the remaining region for frame
+	 * data is
+	 *         xsk_pool_get_rx_frame_size()
+	 * While other buffers than the first one do not have virtio header, so
+	 * the maximum frame data's length can be
+	 *         xsk_pool_get_rx_frame_size() + vi->hdr_len
+	 */
+	bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool);
+	if (!first_buf)
+		bufsize += vi->hdr_len;
 
 	if (unlikely(len > bufsize)) {
 		pr_debug("%s: rx error: len %u exceeds truesize %u\n",
@@ -1225,7 +1265,7 @@ static int xsk_append_merge_buffer(struct virtnet_info *vi,
 
 		u64_stats_add(&stats->bytes, len);
 
-		xdp = buf_to_xdp(vi, rq, buf, len);
+		xdp = buf_to_xdp(vi, rq, buf, len, false);
 		if (!xdp)
 			goto err;
 
@@ -1323,7 +1363,7 @@ static void virtnet_receive_xsk_buf(struct virtnet_info *vi, struct receive_queu
 
 	u64_stats_add(&stats->bytes, len);
 
-	xdp = buf_to_xdp(vi, rq, buf, len);
+	xdp = buf_to_xdp(vi, rq, buf, len, true);
 	if (!xdp)
 		return;
 
@@ -1643,7 +1683,8 @@ static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
  * across multiple buffers (num_buf > 1), and we make sure buffers
  * have enough headroom.
  */
-static struct page *xdp_linearize_page(struct receive_queue *rq,
+static struct page *xdp_linearize_page(struct net_device *dev,
+				       struct receive_queue *rq,
 				       int *num_buf,
 				       struct page *p,
 				       int offset,
@@ -1663,18 +1704,27 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 	memcpy(page_address(page) + page_off, page_address(p) + offset, *len);
 	page_off += *len;
 
+	/* Only mergeable mode can go inside this while loop. In small mode,
+	 * *num_buf == 1, so it cannot go inside.
+	 */
 	while (--*num_buf) {
 		unsigned int buflen;
 		void *buf;
+		void *ctx;
 		int off;
 
-		buf = virtnet_rq_get_buf(rq, &buflen, NULL);
+		buf = virtnet_rq_get_buf(rq, &buflen, &ctx);
 		if (unlikely(!buf))
 			goto err_buf;
 
 		p = virt_to_head_page(buf);
 		off = buf - page_address(p);
 
+		if (check_mergeable_len(dev, ctx, buflen)) {
+			put_page(p);
+			goto err_buf;
+		}
+
 		/* guard against a misconfigured or uncooperative backend that
 		 * is sending packet larger than the MTU.
 		 */
@@ -1763,7 +1813,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
 		headroom = vi->hdr_len + header_offset;
 		buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
 			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-		xdp_page = xdp_linearize_page(rq, &num_buf, page,
+		xdp_page = xdp_linearize_page(dev, rq, &num_buf, page,
 					      offset, header_offset,
 					      &tlen);
 		if (!xdp_page)
@@ -2098,7 +2148,7 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi,
 	 */
 	if (!xdp_prog->aux->xdp_has_frags) {
 		/* linearize data for XDP */
-		xdp_page = xdp_linearize_page(rq, num_buf,
+		xdp_page = xdp_linearize_page(vi->dev, rq, num_buf,
 					      *page, offset,
 					      XDP_PACKET_HEADROOM,
 					      len);
@@ -3225,6 +3275,12 @@ static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq,
 {
 	int qindex, err;
 
+	if (ring_num <= MAX_SKB_FRAGS + 2) {
+		netdev_err(vi->dev, "tx size (%d) cannot be smaller than %d\n",
+			   ring_num, MAX_SKB_FRAGS + 2);
+		return -EINVAL;
+	}
+
 	qindex = sq - vi->sq;
 
 	virtnet_tx_pause(vi, sq);
@@ -5421,6 +5477,10 @@ static void virtnet_get_base_stats(struct net_device *dev,
 
 	if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED)
 		tx->hw_drop_ratelimits = 0;
+
+	netdev_stat_queue_sum(dev,
+			      dev->real_num_rx_queues, vi->max_queue_pairs, rx,
+			      dev->real_num_tx_queues, vi->max_queue_pairs, tx);
 }
 
 static const struct netdev_stat_ops virtnet_stat_ops = {
@@ -5537,7 +5597,7 @@ static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queu
 
 	virtnet_rx_pause(vi, rq);
 
-	err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf);
+	err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf, NULL);
 	if (err) {
 		netdev_err(vi->dev, "reset rx fail: rx queue index: %d err: %d\n", qindex, err);
 
@@ -5556,6 +5616,30 @@ 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,
+			      virtnet_sq_free_unused_buf_done);
+	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)
@@ -5564,6 +5648,7 @@ 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))
@@ -5601,6 +5686,13 @@ 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)) {
+		err = -ENOMEM;
+		goto err_free_buffs;
+	}
+
 	err = xsk_pool_dma_map(pool, dma_dev, 0);
 	if (err)
 		goto err_xsk_map;
@@ -5609,11 +5701,26 @@ 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);
+err_free_buffs:
+	kvfree(rq->xsk_buffs);
 	return err;
 }
 
@@ -5622,19 +5729,24 @@ 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;
@@ -6696,7 +6808,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	   otherwise get link status from config. */
 	netif_carrier_off(dev);
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
-		virtnet_config_changed_work(&vi->config_work);
+		virtio_config_changed(vi->vdev);
 	} else {
 		vi->status = VIRTIO_NET_S_LINK_UP;
 		virtnet_update_settings(vi);