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, 38 insertions, 39 deletions

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 2a89da080317..ff111a89e17f 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -11,7 +11,6 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 #include <linux/slab.h>
-#include <linux/init.h>
 #include <linux/wait.h>
 #include <linux/cdev.h>
 #include <linux/idr.h>
@@ -70,6 +69,11 @@ static const struct proto_ops macvtap_socket_ops;
 #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
 #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
 
+static struct macvlan_dev *macvtap_get_vlan_rcu(const struct net_device *dev)
+{
+	return rcu_dereference(dev->rx_handler_data);
+}
+
 /*
  * RCU usage:
  * The macvtap_queue and the macvlan_dev are loosely coupled, the
@@ -219,7 +223,7 @@ static struct macvtap_queue *macvtap_get_queue(struct net_device *dev,
 		goto out;
 
 	/* Check if we can use flow to select a queue */
-	rxq = skb_get_rxhash(skb);
+	rxq = skb_get_hash(skb);
 	if (rxq) {
 		tap = rcu_dereference(vlan->taps[rxq % numvtaps]);
 		goto out;
@@ -271,24 +275,27 @@ static void macvtap_del_queues(struct net_device *dev)
 		sock_put(&qlist[j]->sk);
 }
 
-/*
- * Forward happens for data that gets sent from one macvlan
- * endpoint to another one in bridge mode. We just take
- * the skb and put it into the receive queue.
- */
-static int macvtap_forward(struct net_device *dev, struct sk_buff *skb)
+static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb)
 {
-	struct macvlan_dev *vlan = netdev_priv(dev);
-	struct macvtap_queue *q = macvtap_get_queue(dev, skb);
+	struct sk_buff *skb = *pskb;
+	struct net_device *dev = skb->dev;
+	struct macvlan_dev *vlan;
+	struct macvtap_queue *q;
 	netdev_features_t features = TAP_FEATURES;
 
+	vlan = macvtap_get_vlan_rcu(dev);
+	if (!vlan)
+		return RX_HANDLER_PASS;
+
+	q = macvtap_get_queue(dev, skb);
 	if (!q)
-		goto drop;
+		return RX_HANDLER_PASS;
 
 	if (skb_queue_len(&q->sk.sk_receive_queue) >= dev->tx_queue_len)
 		goto drop;
 
-	skb->dev = dev;
+	skb_push(skb, ETH_HLEN);
+
 	/* Apply the forward feature mask so that we perform segmentation
 	 * according to users wishes.  This only works if VNET_HDR is
 	 * enabled.
@@ -320,22 +327,13 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb)
 
 wake_up:
 	wake_up_interruptible_poll(sk_sleep(&q->sk), POLLIN | POLLRDNORM | POLLRDBAND);
-	return NET_RX_SUCCESS;
+	return RX_HANDLER_CONSUMED;
 
 drop:
+	/* Count errors/drops only here, thus don't care about args. */
+	macvlan_count_rx(vlan, 0, 0, 0);
 	kfree_skb(skb);
-	return NET_RX_DROP;
-}
-
-/*
- * Receive is for data from the external interface (lowerdev),
- * in case of macvtap, we can treat that the same way as
- * forward, which macvlan cannot.
- */
-static int macvtap_receive(struct sk_buff *skb)
-{
-	skb_push(skb, ETH_HLEN);
-	return macvtap_forward(skb->dev, skb);
+	return RX_HANDLER_CONSUMED;
 }
 
 static int macvtap_get_minor(struct macvlan_dev *vlan)
@@ -385,6 +383,8 @@ static int macvtap_newlink(struct net *src_net,
 			   struct nlattr *data[])
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
+	int err;
+
 	INIT_LIST_HEAD(&vlan->queue_list);
 
 	/* Since macvlan supports all offloads by default, make
@@ -392,16 +392,20 @@ static int macvtap_newlink(struct net *src_net,
 	 */
 	vlan->tap_features = TUN_OFFLOADS;
 
+	err = netdev_rx_handler_register(dev, macvtap_handle_frame, vlan);
+	if (err)
+		return err;
+
 	/* Don't put anything that may fail after macvlan_common_newlink
 	 * because we can't undo what it does.
 	 */
-	return macvlan_common_newlink(src_net, dev, tb, data,
-				      macvtap_receive, macvtap_forward);
+	return macvlan_common_newlink(src_net, dev, tb, data);
 }
 
 static void macvtap_dellink(struct net_device *dev,
 			    struct list_head *head)
 {
+	netdev_rx_handler_unregister(dev);
 	macvtap_del_queues(dev);
 	macvlan_dellink(dev, head);
 }
@@ -588,7 +592,7 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
 	return 0;
 }
 
-static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
+static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
 				   struct virtio_net_hdr *vnet_hdr)
 {
 	memset(vnet_hdr, 0, sizeof(*vnet_hdr));
@@ -619,8 +623,6 @@ static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
 	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 		vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
 	} /* else everything is zero */
-
-	return 0;
 }
 
 /* Get packet from user space buffer */
@@ -727,9 +729,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
 	}
 	if (vlan) {
-		local_bh_disable();
-		macvlan_start_xmit(skb, vlan->dev);
-		local_bh_enable();
+		skb->dev = vlan->dev;
+		dev_queue_xmit(skb);
 	} else {
 		kfree_skb(skb);
 	}
@@ -778,9 +779,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 		if ((len -= vnet_hdr_len) < 0)
 			return -EINVAL;
 
-		ret = macvtap_skb_to_vnet_hdr(skb, &vnet_hdr);
-		if (ret)
-			return ret;
+		macvtap_skb_to_vnet_hdr(skb, &vnet_hdr);
 
 		if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
 			return -EFAULT;
@@ -824,7 +823,7 @@ done:
 	return ret ? ret : total;
 }
 
-static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,
+static ssize_t macvtap_do_read(struct macvtap_queue *q,
 			       const struct iovec *iv, unsigned long len,
 			       int noblock)
 {
@@ -875,7 +874,7 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
 		goto out;
 	}
 
-	ret = macvtap_do_read(q, iocb, iv, len, file->f_flags & O_NONBLOCK);
+	ret = macvtap_do_read(q, iv, len, file->f_flags & O_NONBLOCK);
 	ret = min_t(ssize_t, ret, len);
 	if (ret > 0)
 		iocb->ki_pos = ret;
@@ -1109,7 +1108,7 @@ static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
 	int ret;
 	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
 		return -EINVAL;
-	ret = macvtap_do_read(q, iocb, m->msg_iov, total_len,
+	ret = macvtap_do_read(q, m->msg_iov, total_len,
 			  flags & MSG_DONTWAIT);
 	if (ret > total_len) {
 		m->msg_flags |= MSG_TRUNC;