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

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 73 insertions, 17 deletions

diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0082b5d..480a319 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -7,6 +7,7 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/udp.h>
+#include <net/dst_metadata.h>
 
 #define VNI_HASH_BITS	10
 #define VNI_HASH_SIZE	(1<<VNI_HASH_BITS)
@@ -94,20 +95,18 @@ struct vxlanhdr {
 #define VXLAN_VNI_MASK  (VXLAN_VID_MASK << 8)
 #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
 
+#define VNI_HASH_BITS	10
+#define VNI_HASH_SIZE	(1<<VNI_HASH_BITS)
+#define FDB_HASH_BITS	8
+#define FDB_HASH_SIZE	(1<<FDB_HASH_BITS)
+
 struct vxlan_metadata {
-	__be32		vni;
 	u32		gbp;
 };
 
-struct vxlan_sock;
-typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb,
-			   struct vxlan_metadata *md);
-
 /* per UDP socket information */
 struct vxlan_sock {
 	struct hlist_node hlist;
-	vxlan_rcv_t	 *rcv;
-	void		 *data;
 	struct work_struct del_work;
 	struct socket	 *sock;
 	struct rcu_head	  rcu;
@@ -117,6 +116,58 @@ struct vxlan_sock {
 	u32		  flags;
 };
 
+union vxlan_addr {
+	struct sockaddr_in sin;
+	struct sockaddr_in6 sin6;
+	struct sockaddr sa;
+};
+
+struct vxlan_rdst {
+	union vxlan_addr	 remote_ip;
+	__be16			 remote_port;
+	u32			 remote_vni;
+	u32			 remote_ifindex;
+	struct list_head	 list;
+	struct rcu_head		 rcu;
+};
+
+struct vxlan_config {
+	union vxlan_addr	remote_ip;
+	union vxlan_addr	saddr;
+	u32			vni;
+	int			remote_ifindex;
+	int			mtu;
+	__be16			dst_port;
+	__u16			port_min;
+	__u16			port_max;
+	__u8			tos;
+	__u8			ttl;
+	u32			flags;
+	unsigned long		age_interval;
+	unsigned int		addrmax;
+	bool			no_share;
+};
+
+/* Pseudo network device */
+struct vxlan_dev {
+	struct hlist_node hlist;	/* vni hash table */
+	struct list_head  next;		/* vxlan's per namespace list */
+	struct vxlan_sock *vn_sock;	/* listening socket */
+	struct net_device *dev;
+	struct net	  *net;		/* netns for packet i/o */
+	struct vxlan_rdst default_dst;	/* default destination */
+	u32		  flags;	/* VXLAN_F_* in vxlan.h */
+
+	struct timer_list age_timer;
+	spinlock_t	  hash_lock;
+	unsigned int	  addrcnt;
+	struct gro_cells  gro_cells;
+
+	struct vxlan_config	cfg;
+
+	struct hlist_head fdb_head[FDB_HASH_SIZE];
+};
+
 #define VXLAN_F_LEARN			0x01
 #define VXLAN_F_PROXY			0x02
 #define VXLAN_F_RSC			0x04
@@ -130,6 +181,7 @@ struct vxlan_sock {
 #define VXLAN_F_REMCSUM_RX		0x400
 #define VXLAN_F_GBP			0x800
 #define VXLAN_F_REMCSUM_NOPARTIAL	0x1000
+#define VXLAN_F_COLLECT_METADATA	0x2000
 
 /* Flags that are used in the receive path. These flags must match in
  * order for a socket to be shareable
@@ -137,18 +189,16 @@ struct vxlan_sock {
 #define VXLAN_F_RCV_FLAGS		(VXLAN_F_GBP |			\
 					 VXLAN_F_UDP_ZERO_CSUM6_RX |	\
 					 VXLAN_F_REMCSUM_RX |		\
-					 VXLAN_F_REMCSUM_NOPARTIAL)
-
-struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
-				  vxlan_rcv_t *rcv, void *data,
-				  bool no_share, u32 flags);
+					 VXLAN_F_REMCSUM_NOPARTIAL |	\
+					 VXLAN_F_COLLECT_METADATA)
 
-void vxlan_sock_release(struct vxlan_sock *vs);
+struct net_device *vxlan_dev_create(struct net *net, const char *name,
+				    u8 name_assign_type, struct vxlan_config *conf);
 
-int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
-		   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
-		   __be16 src_port, __be16 dst_port, struct vxlan_metadata *md,
-		   bool xnet, u32 vxflags);
+static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan)
+{
+	return inet_sk(vxlan->vn_sock->sock->sk)->inet_sport;
+}
 
 static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
 						     netdev_features_t features)
@@ -191,4 +241,10 @@ static inline void vxlan_get_rx_port(struct net_device *netdev)
 {
 }
 #endif
+
+static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs)
+{
+	return vs->sock->sk->sk_family;
+}
+
 #endif