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

Pull networking changes from David Miller:
 "Noteworthy changes this time around:

   1) Multicast rejoin support for team driver, from Jiri Pirko.

   2) Centralize and simplify TCP RTT measurement handling in order to
      reduce the impact of bad RTO seeding from SYN/ACKs.  Also, when
      both timestamps and local RTT measurements are available prefer
      the later because there are broken middleware devices which
      scramble the timestamp.

      From Yuchung Cheng.

   3) Add TCP_NOTSENT_LOWAT socket option to limit the amount of kernel
      memory consumed to queue up unsend user data.  From Eric Dumazet.

   4) Add a "physical port ID" abstraction for network devices, from
      Jiri Pirko.

   5) Add a "suppress" operation to influence fib_rules lookups, from
      Stefan Tomanek.

   6) Add a networking development FAQ, from Paul Gortmaker.

   7) Extend the information provided by tcp_probe and add ipv6 support,
      from Daniel Borkmann.

   8) Use RCU locking more extensively in openvswitch data paths, from
      Pravin B Shelar.

   9) Add SCTP support to openvswitch, from Joe Stringer.

  10) Add EF10 chip support to SFC driver, from Ben Hutchings.

  11) Add new SYNPROXY netfilter target, from Patrick McHardy.

  12) Compute a rate approximation for sending in TCP sockets, and use
      this to more intelligently coalesce TSO frames.  Furthermore, add
      a new packet scheduler which takes advantage of this estimate when
      available.  From Eric Dumazet.

  13) Allow AF_PACKET fanouts with random selection, from Daniel
      Borkmann.

  14) Add ipv6 support to vxlan driver, from Cong Wang"

Resolved conflicts as per discussion.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1218 commits)
  openvswitch: Fix alignment of struct sw_flow_key.
  netfilter: Fix build errors with xt_socket.c
  tcp: Add missing braces to do_tcp_setsockopt
  caif: Add missing braces to multiline if in cfctrl_linkup_request
  bnx2x: Add missing braces in bnx2x:bnx2x_link_initialize
  vxlan: Fix kernel panic on device delete.
  net: mvneta: implement ->ndo_do_ioctl() to support PHY ioctls
  net: mvneta: properly disable HW PHY polling and ensure adjust_link() works
  icplus: Use netif_running to determine device state
  ethernet/arc/arc_emac: Fix huge delays in large file copies
  tuntap: orphan frags before trying to set tx timestamp
  tuntap: purge socket error queue on detach
  qlcnic: use standard NAPI weights
  ipv6:introduce function to find route for redirect
  bnx2x: VF RSS support - VF side
  bnx2x: VF RSS support - PF side
  vxlan: Notify drivers for listening UDP port changes
  net: usbnet: update addr_assign_type if appropriate
  driver/net: enic: update enic maintainers and driver
  driver/net: enic: Exposing symbols for Cisco's low latency driver
  ...

1 files changed, 36 insertions, 8 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3d2a90a..defec2b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -106,6 +106,9 @@ struct virtnet_info {
 	/* Has control virtqueue */
 	bool has_cvq;
 
+	/* Host can handle any s/g split between our header and packet data */
+	bool any_header_sg;
+
 	/* enable config space updates */
 	bool config_enable;
 
@@ -669,12 +672,28 @@ static void free_old_xmit_skbs(struct send_queue *sq)
 
 static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 {
-	struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
+	struct skb_vnet_hdr *hdr;
 	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
 	struct virtnet_info *vi = sq->vq->vdev->priv;
 	unsigned num_sg;
+	unsigned hdr_len;
+	bool can_push;
 
 	pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
+	if (vi->mergeable_rx_bufs)
+		hdr_len = sizeof hdr->mhdr;
+	else
+		hdr_len = sizeof hdr->hdr;
+
+	can_push = vi->any_header_sg &&
+		!((unsigned long)skb->data & (__alignof__(*hdr) - 1)) &&
+		!skb_header_cloned(skb) && skb_headroom(skb) >= hdr_len;
+	/* Even if we can, don't push here yet as this would skew
+	 * csum_start offset below. */
+	if (can_push)
+		hdr = (struct skb_vnet_hdr *)(skb->data - hdr_len);
+	else
+		hdr = skb_vnet_hdr(skb);
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
@@ -703,15 +722,18 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 		hdr->hdr.gso_size = hdr->hdr.hdr_len = 0;
 	}
 
-	hdr->mhdr.num_buffers = 0;
-
-	/* Encode metadata header at front. */
 	if (vi->mergeable_rx_bufs)
-		sg_set_buf(sq->sg, &hdr->mhdr, sizeof hdr->mhdr);
-	else
-		sg_set_buf(sq->sg, &hdr->hdr, sizeof hdr->hdr);
+		hdr->mhdr.num_buffers = 0;
 
-	num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1;
+	if (can_push) {
+		__skb_push(skb, hdr_len);
+		num_sg = skb_to_sgvec(skb, sq->sg, 0, skb->len);
+		/* Pull header back to avoid skew in tx bytes calculations. */
+		__skb_pull(skb, hdr_len);
+	} else {
+		sg_set_buf(sq->sg, hdr, hdr_len);
+		num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1;
+	}
 	return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC);
 }
 
@@ -1516,6 +1538,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 			dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO);
 		/* (!csum && gso) case will be fixed by register_netdev() */
 	}
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
+		dev->features |= NETIF_F_RXCSUM;
 
 	dev->vlan_features = dev->features;
 
@@ -1552,6 +1576,9 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
 		vi->mergeable_rx_bufs = true;
 
+	if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT))
+		vi->any_header_sg = true;
+
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
 		vi->has_cvq = true;
 
@@ -1727,6 +1754,7 @@ static unsigned int features[] = {
 	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
 	VIRTIO_NET_F_CTRL_MAC_ADDR,
+	VIRTIO_F_ANY_LAYOUT,
 };
 
 static struct virtio_driver virtio_net_driver = {