Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) BPF debugger and asm tool by Daniel Borkmann.

 2) Speed up create/bind in AF_PACKET, also from Daniel Borkmann.

 3) Correct reciprocal_divide and update users, from Hannes Frederic
    Sowa and Daniel Borkmann.

 4) Currently we only have a "set" operation for the hw timestamp socket
    ioctl, add a "get" operation to match.  From Ben Hutchings.

 5) Add better trace events for debugging driver datapath problems, also
    from Ben Hutchings.

 6) Implement auto corking in TCP, from Eric Dumazet.  Basically, if we
    have a small send and a previous packet is already in the qdisc or
    device queue, defer until TX completion or we get more data.

 7) Allow userspace to manage ipv6 temporary addresses, from Jiri Pirko.

 8) Add a qdisc bypass option for AF_PACKET sockets, from Daniel
    Borkmann.

 9) Share IP header compression code between Bluetooth and IEEE802154
    layers, from Jukka Rissanen.

10) Fix ipv6 router reachability probing, from Jiri Benc.

11) Allow packets to be captured on macvtap devices, from Vlad Yasevich.

12) Support tunneling in GRO layer, from Jerry Chu.

13) Allow bonding to be configured fully using netlink, from Scott
    Feldman.

14) Allow AF_PACKET users to obtain the VLAN TPID, just like they can
    already get the TCI.  From Atzm Watanabe.

15) New "Heavy Hitter" qdisc, from Terry Lam.

16) Significantly improve the IPSEC support in pktgen, from Fan Du.

17) Allow ipv4 tunnels to cache routes, just like sockets.  From Tom
    Herbert.

18) Add Proportional Integral Enhanced packet scheduler, from Vijay
    Subramanian.

19) Allow openvswitch to mmap'd netlink, from Thomas Graf.

20) Key TCP metrics blobs also by source address, not just destination
    address.  From Christoph Paasch.

21) Support 10G in generic phylib.  From Andy Fleming.

22) Try to short-circuit GRO flow compares using device provided RX
    hash, if provided.  From Tom Herbert.

The wireless and netfilter folks have been busy little bees too.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2064 commits)
  net/cxgb4: Fix referencing freed adapter
  ipv6: reallocate addrconf router for ipv6 address when lo device up
  fib_frontend: fix possible NULL pointer dereference
  rtnetlink: remove IFLA_BOND_SLAVE definition
  rtnetlink: remove check for fill_slave_info in rtnl_have_link_slave_info
  qlcnic: update version to 5.3.55
  qlcnic: Enhance logic to calculate msix vectors.
  qlcnic: Refactor interrupt coalescing code for all adapters.
  qlcnic: Update poll controller code path
  qlcnic: Interrupt code cleanup
  qlcnic: Enhance Tx timeout debugging.
  qlcnic: Use bool for rx_mac_learn.
  bonding: fix u64 division
  rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC
  sfc: Use the correct maximum TX DMA ring size for SFC9100
  Add Shradha Shah as the sfc driver maintainer.
  net/vxlan: Share RX skb de-marking and checksum checks with ovs
  tulip: cleanup by using ARRAY_SIZE()
  ip_tunnel: clear IPCB in ip_tunnel_xmit() in case dst_link_failure() is called
  net/cxgb4: Don't retrieve stats during recovery
  ...

1 files changed, 162 insertions, 92 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5d776447d9c3..d75f8edf4fb3 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -13,8 +13,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 //#define DEBUG
 #include <linux/netdevice.h>
@@ -27,6 +26,7 @@
 #include <linux/if_vlan.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/average.h>
 
 static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);
@@ -37,11 +37,18 @@ module_param(gso, bool, 0444);
 
 /* FIXME: MTU in config. */
 #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
-#define MERGE_BUFFER_LEN (ALIGN(GOOD_PACKET_LEN + \
-                                sizeof(struct virtio_net_hdr_mrg_rxbuf), \
-                                L1_CACHE_BYTES))
 #define GOOD_COPY_LEN	128
 
+/* Weight used for the RX packet size EWMA. The average packet size is used to
+ * determine the packet buffer size when refilling RX rings. As the entire RX
+ * ring may be refilled at once, the weight is chosen so that the EWMA will be
+ * insensitive to short-term, transient changes in packet size.
+ */
+#define RECEIVE_AVG_WEIGHT 64
+
+/* Minimum alignment for mergeable packet buffers. */
+#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256)
+
 #define VIRTNET_DRIVER_VERSION "1.0.0"
 
 struct virtnet_stats {
@@ -73,12 +80,15 @@ struct receive_queue {
 
 	struct napi_struct napi;
 
-	/* Number of input buffers, and max we've ever had. */
-	unsigned int num, max;
-
 	/* Chain pages by the private ptr. */
 	struct page *pages;
 
+	/* Average packet length for mergeable receive buffers. */
+	struct ewma mrg_avg_pkt_len;
+
+	/* Page frag for packet buffer allocation. */
+	struct page_frag alloc_frag;
+
 	/* RX: fragments + linear part + virtio header */
 	struct scatterlist sg[MAX_SKB_FRAGS + 2];
 
@@ -127,11 +137,6 @@ struct virtnet_info {
 	/* Lock for config space updates */
 	struct mutex config_lock;
 
-	/* Page_frag for GFP_KERNEL packet buffer allocation when we run
-	 * low on memory.
-	 */
-	struct page_frag alloc_frag;
-
 	/* Does the affinity hint is set for virtqueues? */
 	bool affinity_hint_set;
 
@@ -222,6 +227,24 @@ static void skb_xmit_done(struct virtqueue *vq)
 	netif_wake_subqueue(vi->dev, vq2txq(vq));
 }
 
+static unsigned int mergeable_ctx_to_buf_truesize(unsigned long mrg_ctx)
+{
+	unsigned int truesize = mrg_ctx & (MERGEABLE_BUFFER_ALIGN - 1);
+	return (truesize + 1) * MERGEABLE_BUFFER_ALIGN;
+}
+
+static void *mergeable_ctx_to_buf_address(unsigned long mrg_ctx)
+{
+	return (void *)(mrg_ctx & -MERGEABLE_BUFFER_ALIGN);
+
+}
+
+static unsigned long mergeable_buf_to_ctx(void *buf, unsigned int truesize)
+{
+	unsigned int size = truesize / MERGEABLE_BUFFER_ALIGN;
+	return (unsigned long)buf | (size - 1);
+}
+
 /* Called from bottom half context */
 static struct sk_buff *page_to_skb(struct receive_queue *rq,
 				   struct page *page, unsigned int offset,
@@ -330,38 +353,34 @@ err:
 
 static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 struct receive_queue *rq,
-					 void *buf,
+					 unsigned long ctx,
 					 unsigned int len)
 {
+	void *buf = mergeable_ctx_to_buf_address(ctx);
 	struct skb_vnet_hdr *hdr = buf;
 	int num_buf = hdr->mhdr.num_buffers;
 	struct page *page = virt_to_head_page(buf);
 	int offset = buf - page_address(page);
-	struct sk_buff *head_skb = page_to_skb(rq, page, offset, len,
-					       MERGE_BUFFER_LEN);
+	unsigned int truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
+
+	struct sk_buff *head_skb = page_to_skb(rq, page, offset, len, truesize);
 	struct sk_buff *curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
 		goto err_skb;
-
 	while (--num_buf) {
 		int num_skb_frags;
 
-		buf = virtqueue_get_buf(rq->vq, &len);
-		if (unlikely(!buf)) {
+		ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
+		if (unlikely(!ctx)) {
 			pr_debug("%s: rx error: %d buffers out of %d missing\n",
 				 dev->name, num_buf, hdr->mhdr.num_buffers);
 			dev->stats.rx_length_errors++;
 			goto err_buf;
 		}
-		if (unlikely(len > MERGE_BUFFER_LEN)) {
-			pr_debug("%s: rx error: merge buffer too long\n",
-				 dev->name);
-			len = MERGE_BUFFER_LEN;
-		}
 
+		buf = mergeable_ctx_to_buf_address(ctx);
 		page = virt_to_head_page(buf);
-		--rq->num;
 
 		num_skb_frags = skb_shinfo(curr_skb)->nr_frags;
 		if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) {
@@ -377,37 +396,38 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			head_skb->truesize += nskb->truesize;
 			num_skb_frags = 0;
 		}
+		truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
 		if (curr_skb != head_skb) {
 			head_skb->data_len += len;
 			head_skb->len += len;
-			head_skb->truesize += MERGE_BUFFER_LEN;
+			head_skb->truesize += truesize;
 		}
 		offset = buf - page_address(page);
 		if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) {
 			put_page(page);
 			skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,
-					     len, MERGE_BUFFER_LEN);
+					     len, truesize);
 		} else {
 			skb_add_rx_frag(curr_skb, num_skb_frags, page,
-					offset, len, MERGE_BUFFER_LEN);
+					offset, len, truesize);
 		}
 	}
 
+	ewma_add(&rq->mrg_avg_pkt_len, head_skb->len);
 	return head_skb;
 
 err_skb:
 	put_page(page);
 	while (--num_buf) {
-		buf = virtqueue_get_buf(rq->vq, &len);
-		if (unlikely(!buf)) {
+		ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
+		if (unlikely(!ctx)) {
 			pr_debug("%s: rx error: %d buffers missing\n",
 				 dev->name, num_buf);
 			dev->stats.rx_length_errors++;
 			break;
 		}
-		page = virt_to_head_page(buf);
+		page = virt_to_head_page(mergeable_ctx_to_buf_address(ctx));
 		put_page(page);
-		--rq->num;
 	}
 err_buf:
 	dev->stats.rx_dropped++;
@@ -426,17 +446,20 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
 	if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
 		dev->stats.rx_length_errors++;
-		if (vi->mergeable_rx_bufs)
-			put_page(virt_to_head_page(buf));
-		else if (vi->big_packets)
+		if (vi->mergeable_rx_bufs) {
+			unsigned long ctx = (unsigned long)buf;
+			void *base = mergeable_ctx_to_buf_address(ctx);
+			put_page(virt_to_head_page(base));
+		} else if (vi->big_packets) {
 			give_pages(rq, buf);
-		else
+		} else {
 			dev_kfree_skb(buf);
+		}
 		return;
 	}
 
 	if (vi->mergeable_rx_bufs)
-		skb = receive_mergeable(dev, rq, buf, len);
+		skb = receive_mergeable(dev, rq, (unsigned long)buf, len);
 	else if (vi->big_packets)
 		skb = receive_big(dev, rq, buf, len);
 	else
@@ -577,28 +600,45 @@ static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp)
 	return err;
 }
 
+static unsigned int get_mergeable_buf_len(struct ewma *avg_pkt_len)
+{
+	const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+	unsigned int len;
+
+	len = hdr_len + clamp_t(unsigned int, ewma_read(avg_pkt_len),
+			GOOD_PACKET_LEN, PAGE_SIZE - hdr_len);
+	return ALIGN(len, MERGEABLE_BUFFER_ALIGN);
+}
+
 static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
 {
-	struct virtnet_info *vi = rq->vq->vdev->priv;
-	char *buf = NULL;
+	struct page_frag *alloc_frag = &rq->alloc_frag;
+	char *buf;
+	unsigned long ctx;
 	int err;
+	unsigned int len, hole;
 
-	if (gfp & __GFP_WAIT) {
-		if (skb_page_frag_refill(MERGE_BUFFER_LEN, &vi->alloc_frag,
-					 gfp)) {
-			buf = (char *)page_address(vi->alloc_frag.page) +
-			      vi->alloc_frag.offset;
-			get_page(vi->alloc_frag.page);
-			vi->alloc_frag.offset += MERGE_BUFFER_LEN;
-		}
-	} else {
-		buf = netdev_alloc_frag(MERGE_BUFFER_LEN);
-	}
-	if (!buf)
+	len = get_mergeable_buf_len(&rq->mrg_avg_pkt_len);
+	if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
 		return -ENOMEM;
 
-	sg_init_one(rq->sg, buf, MERGE_BUFFER_LEN);
-	err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, buf, gfp);
+	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
+	ctx = mergeable_buf_to_ctx(buf, len);
+	get_page(alloc_frag->page);
+	alloc_frag->offset += len;
+	hole = alloc_frag->size - alloc_frag->offset;
+	if (hole < len) {
+		/* To avoid internal fragmentation, if there is very likely not
+		 * enough space for another buffer, add the remaining space to
+		 * the current buffer. This extra space is not included in
+		 * the truesize stored in ctx.
+		 */
+		len += hole;
+		alloc_frag->offset += hole;
+	}
+
+	sg_init_one(rq->sg, buf, len);
+	err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, (void *)ctx, gfp);
 	if (err < 0)
 		put_page(virt_to_head_page(buf));
 
@@ -618,6 +658,7 @@ static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
 	int err;
 	bool oom;
 
+	gfp |= __GFP_COLD;
 	do {
 		if (vi->mergeable_rx_bufs)
 			err = add_recvbuf_mergeable(rq, gfp);
@@ -629,10 +670,7 @@ static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
 		oom = err == -ENOMEM;
 		if (err)
 			break;
-		++rq->num;
 	} while (rq->vq->num_free);
-	if (unlikely(rq->num > rq->max))
-		rq->max = rq->num;
 	if (unlikely(!virtqueue_kick(rq->vq)))
 		return false;
 	return !oom;
@@ -700,11 +738,10 @@ again:
 	while (received < budget &&
 	       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
 		receive_buf(rq, buf, len);
-		--rq->num;
 		received++;
 	}
 
-	if (rq->num < rq->max / 2) {
+	if (rq->vq->num_free > virtqueue_get_vring_size(rq->vq) / 2) {
 		if (!try_fill_recv(rq, GFP_ATOMIC))
 			schedule_delayed_work(&vi->refill, 0);
 	}
@@ -874,16 +911,15 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 /*
  * Send command via the control virtqueue and check status.  Commands
  * supported by the hypervisor, as indicated by feature bits, should
- * never fail unless improperly formated.
+ * never fail unless improperly formatted.
  */
 static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
-				 struct scatterlist *out,
-				 struct scatterlist *in)
+				 struct scatterlist *out)
 {
 	struct scatterlist *sgs[4], hdr, stat;
 	struct virtio_net_ctrl_hdr ctrl;
 	virtio_net_ctrl_ack status = ~0;
-	unsigned out_num = 0, in_num = 0, tmp;
+	unsigned out_num = 0, tmp;
 
 	/* Caller should know better */
 	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
@@ -896,16 +932,13 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 
 	if (out)
 		sgs[out_num++] = out;
-	if (in)
-		sgs[out_num + in_num++] = in;
 
 	/* Add return status. */
 	sg_init_one(&stat, &status, sizeof(status));
-	sgs[out_num + in_num++] = &stat;
+	sgs[out_num] = &stat;
 
-	BUG_ON(out_num + in_num > ARRAY_SIZE(sgs));
-	BUG_ON(virtqueue_add_sgs(vi->cvq, sgs, out_num, in_num, vi, GFP_ATOMIC)
-	       < 0);
+	BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
+	BUG_ON(virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC) < 0);
 
 	if (unlikely(!virtqueue_kick(vi->cvq)))
 		return status == VIRTIO_NET_OK;
@@ -935,8 +968,7 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p)
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) {
 		sg_init_one(&sg, addr->sa_data, dev->addr_len);
 		if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
-					  VIRTIO_NET_CTRL_MAC_ADDR_SET,
-					  &sg, NULL)) {
+					  VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) {
 			dev_warn(&vdev->dev,
 				 "Failed to set mac address by vq command.\n");
 			return -EINVAL;
@@ -1009,7 +1041,7 @@ static void virtnet_ack_link_announce(struct virtnet_info *vi)
 {
 	rtnl_lock();
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_ANNOUNCE,
-				  VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL, NULL))
+				  VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL))
 		dev_warn(&vi->dev->dev, "Failed to ack link announce.\n");
 	rtnl_unlock();
 }
@@ -1027,7 +1059,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	sg_init_one(&sg, &s, sizeof(s));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
-				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg, NULL)) {
+				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) {
 		dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n",
 			 queue_pairs);
 		return -EINVAL;
@@ -1067,7 +1099,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	void *buf;
 	int i;
 
-	/* We can't dynamicaly set ndo_set_rx_mode, so return gracefully */
+	/* We can't dynamically set ndo_set_rx_mode, so return gracefully */
 	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
 		return;
 
@@ -1077,16 +1109,14 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	sg_init_one(sg, &promisc, sizeof(promisc));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
-				  VIRTIO_NET_CTRL_RX_PROMISC,
-				  sg, NULL))
+				  VIRTIO_NET_CTRL_RX_PROMISC, sg))
 		dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
 			 promisc ? "en" : "dis");
 
 	sg_init_one(sg, &allmulti, sizeof(allmulti));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
-				  VIRTIO_NET_CTRL_RX_ALLMULTI,
-				  sg, NULL))
+				  VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
 		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
 			 allmulti ? "en" : "dis");
 
@@ -1122,8 +1152,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 		   sizeof(mac_data->entries) + (mc_count * ETH_ALEN));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
-				  VIRTIO_NET_CTRL_MAC_TABLE_SET,
-				  sg, NULL))
+				  VIRTIO_NET_CTRL_MAC_TABLE_SET, sg))
 		dev_warn(&dev->dev, "Failed to set MAC filter table.\n");
 
 	kfree(buf);
@@ -1138,7 +1167,7 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
 	sg_init_one(&sg, &vid, sizeof(vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
-				  VIRTIO_NET_CTRL_VLAN_ADD, &sg, NULL))
+				  VIRTIO_NET_CTRL_VLAN_ADD, &sg))
 		dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid);
 	return 0;
 }
@@ -1152,7 +1181,7 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
 	sg_init_one(&sg, &vid, sizeof(vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
-				  VIRTIO_NET_CTRL_VLAN_DEL, &sg, NULL))
+				  VIRTIO_NET_CTRL_VLAN_DEL, &sg))
 		dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid);
 	return 0;
 }
@@ -1386,6 +1415,14 @@ static void free_receive_bufs(struct virtnet_info *vi)
 	}
 }
 
+static void free_receive_page_frags(struct virtnet_info *vi)
+{
+	int i;
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		if (vi->rq[i].alloc_frag.page)
+			put_page(vi->rq[i].alloc_frag.page);
+}
+
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
@@ -1401,15 +1438,16 @@ static void free_unused_bufs(struct virtnet_info *vi)
 		struct virtqueue *vq = vi->rq[i].vq;
 
 		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (vi->mergeable_rx_bufs)
-				put_page(virt_to_head_page(buf));
-			else if (vi->big_packets)
+			if (vi->mergeable_rx_bufs) {
+				unsigned long ctx = (unsigned long)buf;
+				void *base = mergeable_ctx_to_buf_address(ctx);
+				put_page(virt_to_head_page(base));
+			} else if (vi->big_packets) {
 				give_pages(&vi->rq[i], buf);
-			else
+			} else {
 				dev_kfree_skb(buf);
-			--vi->rq[i].num;
+			}
 		}
-		BUG_ON(vi->rq[i].num != 0);
 	}
 }
 
@@ -1516,6 +1554,7 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 			       napi_weight);
 
 		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
+		ewma_init(&vi->rq[i].mrg_avg_pkt_len, 1, RECEIVE_AVG_WEIGHT);
 		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
 	}
 
@@ -1552,6 +1591,33 @@ err:
 	return ret;
 }
 
+#ifdef CONFIG_SYSFS
+static ssize_t mergeable_rx_buffer_size_show(struct netdev_rx_queue *queue,
+		struct rx_queue_attribute *attribute, char *buf)
+{
+	struct virtnet_info *vi = netdev_priv(queue->dev);
+	unsigned int queue_index = get_netdev_rx_queue_index(queue);
+	struct ewma *avg;
+
+	BUG_ON(queue_index >= vi->max_queue_pairs);
+	avg = &vi->rq[queue_index].mrg_avg_pkt_len;
+	return sprintf(buf, "%u\n", get_mergeable_buf_len(avg));
+}
+
+static struct rx_queue_attribute mergeable_rx_buffer_size_attribute =
+	__ATTR_RO(mergeable_rx_buffer_size);
+
+static struct attribute *virtio_net_mrg_rx_attrs[] = {
+	&mergeable_rx_buffer_size_attribute.attr,
+	NULL
+};
+
+static const struct attribute_group virtio_net_mrg_rx_group = {
+	.name = "virtio_net",
+	.attrs = virtio_net_mrg_rx_attrs
+};
+#endif
+
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int i, err;
@@ -1666,6 +1732,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (err)
 		goto free_stats;
 
+#ifdef CONFIG_SYSFS
+	if (vi->mergeable_rx_bufs)
+		dev->sysfs_rx_queue_group = &virtio_net_mrg_rx_group;
+#endif
 	netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
 	netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);
 
@@ -1680,7 +1750,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 		try_fill_recv(&vi->rq[i], GFP_KERNEL);
 
 		/* If we didn't even get one input buffer, we're useless. */
-		if (vi->rq[i].num == 0) {
+		if (vi->rq[i].vq->num_free ==
+		    virtqueue_get_vring_size(vi->rq[i].vq)) {
 			free_unused_bufs(vi);
 			err = -ENOMEM;
 			goto free_recv_bufs;
@@ -1714,9 +1785,8 @@ free_recv_bufs:
 	unregister_netdev(dev);
 free_vqs:
 	cancel_delayed_work_sync(&vi->refill);
+	free_receive_page_frags(vi);
 	virtnet_del_vqs(vi);
-	if (vi->alloc_frag.page)
-		put_page(vi->alloc_frag.page);
 free_stats:
 	free_percpu(vi->stats);
 free:
@@ -1733,6 +1803,8 @@ static void remove_vq_common(struct virtnet_info *vi)
 
 	free_receive_bufs(vi);
 
+	free_receive_page_frags(vi);
+
 	virtnet_del_vqs(vi);
 }
 
@@ -1750,8 +1822,6 @@ static void virtnet_remove(struct virtio_device *vdev)
 	unregister_netdev(vi->dev);
 
 	remove_vq_common(vi);
-	if (vi->alloc_frag.page)
-		put_page(vi->alloc_frag.page);
 
 	flush_work(&vi->config_work);