1 files changed, 77 insertions, 29 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 78a01c71a17c..8a58a2f013af 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -380,7 +380,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct page *page, unsigned int offset,
 				   unsigned int len, unsigned int truesize,
 				   bool hdr_valid, unsigned int metasize,
-				   unsigned int headroom)
+				   bool whole_page)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -398,16 +398,28 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
-	/* If headroom is not 0, there is an offset between the beginning of the
+	/* If whole_page, there is an offset between the beginning of the
 	 * data and the allocated space, otherwise the data and the allocated
 	 * space are aligned.
 	 *
 	 * Buffers with headroom use PAGE_SIZE as alloc size, see
 	 * add_recvbuf_mergeable() + get_mergeable_buf_len()
 	 */
-	truesize = headroom ? PAGE_SIZE : truesize;
-	tailroom = truesize - len - headroom - (hdr_padded_len - hdr_len);
-	buf = p - headroom;
+	if (whole_page) {
+		/* Buffers with whole_page use PAGE_SIZE as alloc size,
+		 * see add_recvbuf_mergeable() + get_mergeable_buf_len()
+		 */
+		truesize = PAGE_SIZE;
+
+		/* page maybe head page, so we should get the buf by p, not the
+		 * page
+		 */
+		tailroom = truesize - len - offset_in_page(p);
+		buf = (char *)((unsigned long)p & PAGE_MASK);
+	} else {
+		tailroom = truesize - len;
+		buf = p;
+	}
 
 	len -= hdr_len;
 	offset += hdr_padded_len;
@@ -721,6 +733,12 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	len -= vi->hdr_len;
 	stats->bytes += len;
 
+	if (unlikely(len > GOOD_PACKET_LEN)) {
+		pr_debug("%s: rx error: len %u exceeds max size %d\n",
+			 dev->name, len, GOOD_PACKET_LEN);
+		dev->stats.rx_length_errors++;
+		goto err_len;
+	}
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
@@ -824,6 +842,7 @@ err:
 err_xdp:
 	rcu_read_unlock();
 	stats->xdp_drops++;
+err_len:
 	stats->drops++;
 	put_page(page);
 xdp_xmit:
@@ -877,6 +896,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	head_skb = NULL;
 	stats->bytes += len - vi->hdr_len;
 
+	if (unlikely(len > truesize)) {
+		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+			 dev->name, len, (unsigned long)ctx);
+		dev->stats.rx_length_errors++;
+		goto err_skb;
+	}
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
@@ -953,8 +978,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 				put_page(page);
 				head_skb = page_to_skb(vi, rq, xdp_page, offset,
 						       len, PAGE_SIZE, false,
-						       metasize,
-						       VIRTIO_XDP_HEADROOM);
+						       metasize, true);
 				return head_skb;
 			}
 			break;
@@ -1004,15 +1028,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	}
 	rcu_read_unlock();
 
-	if (unlikely(len > truesize)) {
-		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
-			 dev->name, len, (unsigned long)ctx);
-		dev->stats.rx_length_errors++;
-		goto err_skb;
-	}
-
 	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog,
-			       metasize, headroom);
+			       metasize, !!headroom);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
@@ -1499,12 +1516,16 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 		return;
 
 	if (__netif_tx_trylock(txq)) {
-		free_old_xmit_skbs(sq, true);
+		do {
+			virtqueue_disable_cb(sq->vq);
+			free_old_xmit_skbs(sq, true);
+		} while (unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
+
+		if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
+			netif_tx_wake_queue(txq);
+
 		__netif_tx_unlock(txq);
 	}
-
-	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
-		netif_tx_wake_queue(txq);
 }
 
 static int virtnet_poll(struct napi_struct *napi, int budget)
@@ -1575,6 +1596,8 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 	struct virtnet_info *vi = sq->vq->vdev->priv;
 	unsigned int index = vq2txq(sq->vq);
 	struct netdev_queue *txq;
+	int opaque;
+	bool done;
 
 	if (unlikely(is_xdp_raw_buffer_queue(vi, index))) {
 		/* We don't need to enable cb for XDP */
@@ -1584,14 +1607,32 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 
 	txq = netdev_get_tx_queue(vi->dev, index);
 	__netif_tx_lock(txq, raw_smp_processor_id());
+	virtqueue_disable_cb(sq->vq);
 	free_old_xmit_skbs(sq, true);
-	__netif_tx_unlock(txq);
-
-	virtqueue_napi_complete(napi, sq->vq, 0);
 
 	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
 		netif_tx_wake_queue(txq);
 
+	opaque = virtqueue_enable_cb_prepare(sq->vq);
+
+	done = napi_complete_done(napi, 0);
+
+	if (!done)
+		virtqueue_disable_cb(sq->vq);
+
+	__netif_tx_unlock(txq);
+
+	if (done) {
+		if (unlikely(virtqueue_poll(sq->vq, opaque))) {
+			if (napi_schedule_prep(napi)) {
+				__netif_tx_lock(txq, raw_smp_processor_id());
+				virtqueue_disable_cb(sq->vq);
+				__netif_tx_unlock(txq);
+				__napi_schedule(napi);
+			}
+		}
+	}
+
 	return 0;
 }
 
@@ -1619,7 +1660,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
 				    virtio_is_little_endian(vi->vdev), false,
 				    0))
-		BUG();
+		return -EPROTO;
 
 	if (vi->mergeable_rx_bufs)
 		hdr->num_buffers = 0;
@@ -1653,10 +1694,14 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool use_napi = sq->napi.weight;
 
 	/* Free up any pending old buffers before queueing new ones. */
-	free_old_xmit_skbs(sq, false);
+	do {
+		if (use_napi)
+			virtqueue_disable_cb(sq->vq);
+
+		free_old_xmit_skbs(sq, false);
 
-	if (use_napi && kick)
-		virtqueue_enable_cb_delayed(sq->vq);
+	} while (use_napi && kick &&
+	       unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
 
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
@@ -2830,8 +2875,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 			ctx[rxq2vq(i)] = true;
 	}
 
-	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
-					 names, ctx, NULL);
+	ret = virtio_find_vqs_ctx(vi->vdev, total_vqs, vqs, callbacks,
+				  names, ctx, NULL);
 	if (ret)
 		goto err_find;
 
@@ -3293,8 +3338,11 @@ static __maybe_unused int virtnet_restore(struct virtio_device *vdev)
 	virtnet_set_queues(vi, vi->curr_queue_pairs);
 
 	err = virtnet_cpu_notif_add(vi);
-	if (err)
+	if (err) {
+		virtnet_freeze_down(vdev);
+		remove_vq_common(vi);
 		return err;
+	}
 
 	return 0;
 }