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

Pull networking updates from David Miller:
 "Highlights:

   1) Steady transitioning of the BPF instructure to a generic spot so
      all kernel subsystems can make use of it, from Alexei Starovoitov.

   2) SFC driver supports busy polling, from Alexandre Rames.

   3) Take advantage of hash table in UDP multicast delivery, from David
      Held.

   4) Lighten locking, in particular by getting rid of the LRU lists, in
      inet frag handling.  From Florian Westphal.

   5) Add support for various RFC6458 control messages in SCTP, from
      Geir Ola Vaagland.

   6) Allow to filter bridge forwarding database dumps by device, from
      Jamal Hadi Salim.

   7) virtio-net also now supports busy polling, from Jason Wang.

   8) Some low level optimization tweaks in pktgen from Jesper Dangaard
      Brouer.

   9) Add support for ipv6 address generation modes, so that userland
      can have some input into the process.  From Jiri Pirko.

  10) Consolidate common TCP connection request code in ipv4 and ipv6,
      from Octavian Purdila.

  11) New ARP packet logger in netfilter, from Pablo Neira Ayuso.

  12) Generic resizable RCU hash table, with intial users in netlink and
      nftables.  From Thomas Graf.

  13) Maintain a name assignment type so that userspace can see where a
      network device name came from (enumerated by kernel, assigned
      explicitly by userspace, etc.) From Tom Gundersen.

  14) Automatic flow label generation on transmit in ipv6, from Tom
      Herbert.

  15) New packet timestamping facilities from Willem de Bruijn, meant to
      assist in measuring latencies going into/out-of the packet
      scheduler, latency from TCP data transmission to ACK, etc"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1536 commits)
  cxgb4 : Disable recursive mailbox commands when enabling vi
  net: reduce USB network driver config options.
  tg3: Modify tg3_tso_bug() to handle multiple TX rings
  amd-xgbe: Perform phy connect/disconnect at dev open/stop
  amd-xgbe: Use dma_set_mask_and_coherent to set DMA mask
  net: sun4i-emac: fix memory leak on bad packet
  sctp: fix possible seqlock seadlock in sctp_packet_transmit()
  Revert "net: phy: Set the driver when registering an MDIO bus device"
  cxgb4vf: Turn off SGE RX/TX Callback Timers and interrupts in PCI shutdown routine
  team: Simplify return path of team_newlink
  bridge: Update outdated comment on promiscuous mode
  net-timestamp: ACK timestamp for bytestreams
  net-timestamp: TCP timestamping
  net-timestamp: SCHED timestamp on entering packet scheduler
  net-timestamp: add key to disambiguate concurrent datagrams
  net-timestamp: move timestamp flags out of sk_flags
  net-timestamp: extend SCM_TIMESTAMPING ancillary data struct
  cxgb4i : Move stray CPL definitions to cxgb4 driver
  tcp: reduce spurious retransmits due to transient SACK reneging
  qlcnic: Initialize dcbnl_ops before register_netdev
  ...

1 files changed, 28 insertions, 116 deletions

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 9f79192c9aa0..1fb7b37d1402 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -33,6 +33,7 @@
 #include <net/ip_tunnels.h>
 #include <net/icmp.h>
 #include <net/udp.h>
+#include <net/udp_tunnel.h>
 #include <net/rtnetlink.h>
 #include <net/route.h>
 #include <net/dsfield.h>
@@ -933,7 +934,8 @@ out:
 
 /* Dump forwarding table */
 static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
-			  struct net_device *dev, int idx)
+			  struct net_device *dev,
+			  struct net_device *filter_dev, int idx)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	unsigned int h;
@@ -1570,25 +1572,6 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	return false;
 }
 
-/* Compute source port for outgoing packet
- *   first choice to use L4 flow hash since it will spread
- *     better and maybe available from hardware
- *   secondary choice is to use jhash on the Ethernet header
- */
-__be16 vxlan_src_port(__u16 port_min, __u16 port_max, struct sk_buff *skb)
-{
-	unsigned int range = (port_max - port_min) + 1;
-	u32 hash;
-
-	hash = skb_get_hash(skb);
-	if (!hash)
-		hash = jhash(skb->data, 2 * ETH_ALEN,
-			     (__force u32) skb->protocol);
-
-	return htons((((u64) hash * range) >> 32) + port_min);
-}
-EXPORT_SYMBOL_GPL(vxlan_src_port);
-
 static inline struct sk_buff *vxlan_handle_offloads(struct sk_buff *skb,
 						    bool udp_csum)
 {
@@ -1807,7 +1790,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	if (tos == 1)
 		tos = ip_tunnel_get_dsfield(old_iph, skb);
 
-	src_port = vxlan_src_port(vxlan->port_min, vxlan->port_max, skb);
+	src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->port_min,
+				     vxlan->port_max, true);
 
 	if (dst->sa.sa_family == AF_INET) {
 		memset(&fl4, 0, sizeof(fl4));
@@ -2235,7 +2219,6 @@ static void vxlan_setup(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	unsigned int h;
-	int low, high;
 
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
@@ -2272,9 +2255,6 @@ static void vxlan_setup(struct net_device *dev)
 	vxlan->age_timer.function = vxlan_cleanup;
 	vxlan->age_timer.data = (unsigned long) vxlan;
 
-	inet_get_local_port_range(dev_net(dev), &low, &high);
-	vxlan->port_min = low;
-	vxlan->port_max = high;
 	vxlan->dst_port = htons(vxlan_port);
 
 	vxlan->dev = dev;
@@ -2360,102 +2340,37 @@ static void vxlan_del_work(struct work_struct *work)
 	kfree_rcu(vs, rcu);
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
-/* Create UDP socket for encapsulation receive. AF_INET6 socket
- * could be used for both IPv4 and IPv6 communications, but
- * users may set bindv6only=1.
- */
-static struct socket *create_v6_sock(struct net *net, __be16 port, u32 flags)
+static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
+					__be16 port, u32 flags)
 {
-	struct sock *sk;
 	struct socket *sock;
-	struct sockaddr_in6 vxlan_addr = {
-		.sin6_family = AF_INET6,
-		.sin6_port = port,
-	};
-	int rc, val = 1;
-
-	rc = sock_create_kern(AF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock);
-	if (rc < 0) {
-		pr_debug("UDPv6 socket create failed\n");
-		return ERR_PTR(rc);
-	}
-
-	/* Put in proper namespace */
-	sk = sock->sk;
-	sk_change_net(sk, net);
-
-	kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
-			  (char *)&val, sizeof(val));
-	rc = kernel_bind(sock, (struct sockaddr *)&vxlan_addr,
-			 sizeof(struct sockaddr_in6));
-	if (rc < 0) {
-		pr_debug("bind for UDPv6 socket %pI6:%u (%d)\n",
-			 &vxlan_addr.sin6_addr, ntohs(vxlan_addr.sin6_port), rc);
-		sk_release_kernel(sk);
-		return ERR_PTR(rc);
-	}
-	/* At this point, IPv6 module should have been loaded in
-	 * sock_create_kern().
-	 */
-	BUG_ON(!ipv6_stub);
-
-	/* Disable multicast loopback */
-	inet_sk(sk)->mc_loop = 0;
-
-	if (flags & VXLAN_F_UDP_ZERO_CSUM6_TX)
-		udp_set_no_check6_tx(sk, true);
-
-	if (flags & VXLAN_F_UDP_ZERO_CSUM6_RX)
-		udp_set_no_check6_rx(sk, true);
-
-	return sock;
-}
-
-#else
-
-static struct socket *create_v6_sock(struct net *net, __be16 port, u32 flags)
-{
-		return ERR_PTR(-EPFNOSUPPORT);
-}
-#endif
+	struct udp_port_cfg udp_conf;
+	int err;
 
-static struct socket *create_v4_sock(struct net *net, __be16 port, u32 flags)
-{
-	struct sock *sk;
-	struct socket *sock;
-	struct sockaddr_in vxlan_addr = {
-		.sin_family = AF_INET,
-		.sin_addr.s_addr = htonl(INADDR_ANY),
-		.sin_port = port,
-	};
-	int rc;
+	memset(&udp_conf, 0, sizeof(udp_conf));
 
-	/* Create UDP socket for encapsulation receive. */
-	rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
-	if (rc < 0) {
-		pr_debug("UDP socket create failed\n");
-		return ERR_PTR(rc);
+	if (ipv6) {
+		udp_conf.family = AF_INET6;
+		udp_conf.use_udp6_tx_checksums =
+		    !!(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
+		udp_conf.use_udp6_rx_checksums =
+		    !!(flags & VXLAN_F_UDP_ZERO_CSUM6_RX);
+	} else {
+		udp_conf.family = AF_INET;
+		udp_conf.local_ip.s_addr = INADDR_ANY;
+		udp_conf.use_udp_checksums =
+		    !!(flags & VXLAN_F_UDP_CSUM);
 	}
 
-	/* Put in proper namespace */
-	sk = sock->sk;
-	sk_change_net(sk, net);
+	udp_conf.local_udp_port = port;
 
-	rc = kernel_bind(sock, (struct sockaddr *) &vxlan_addr,
-			 sizeof(vxlan_addr));
-	if (rc < 0) {
-		pr_debug("bind for UDP socket %pI4:%u (%d)\n",
-			 &vxlan_addr.sin_addr, ntohs(vxlan_addr.sin_port), rc);
-		sk_release_kernel(sk);
-		return ERR_PTR(rc);
-	}
+	/* Open UDP socket */
+	err = udp_sock_create(net, &udp_conf, &sock);
+	if (err < 0)
+		return ERR_PTR(err);
 
 	/* Disable multicast loopback */
-	inet_sk(sk)->mc_loop = 0;
-
-	if (!(flags & VXLAN_F_UDP_CSUM))
-		sock->sk->sk_no_check_tx = 1;
+	inet_sk(sock->sk)->mc_loop = 0;
 
 	return sock;
 }
@@ -2481,10 +2396,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 
 	INIT_WORK(&vs->del_work, vxlan_del_work);
 
-	if (ipv6)
-		sock = create_v6_sock(net, port, flags);
-	else
-		sock = create_v4_sock(net, port, flags);
+	sock = vxlan_create_sock(net, ipv6, port, flags);
 	if (IS_ERR(sock)) {
 		kfree(vs);
 		return ERR_CAST(sock);