Merge branch 'lwtunnel'

Thomas Graf says:

====================
Lightweight & flow based encapsulation

This series combines the work previously posted by Roopa, Robert and
myself. It's according to what we discussed at NFWS. The motivation
of this series is to:

 * Consolidate code between OVS and the rest of the kernel and get
   rid of OVS vports and instead represent them as pure net_devices.
 * Introduce a lightweight tunneling mechanism which enables flow
   based encapsulation to improve scalability on both RX and TX.
 * Do the above in an encapsulation unspecific way so that the
   encapsulation type is eventually abstracted away from the user.
 * Use the same forwarding decision for both native forwarding and
   encapsulation thus allowing to switch between native IPv6 and
   UDP encapsulation based on endpoint without requiring additional
   logic

The fundamental changes introduces in this series are:
 * A new RTA_ENCAP Netlink attribute for routes carrying encapsulation
   instructions. Depending on the specified type, the instructions
   apply to UDP encapsulations, MPLS and possible other in the future.
 * Depending on the encapsulation type, the output function of the
   dst is directly overwritten or the dst merely attaches metadata and
   relies on a subsequent net_device to apply it to the packet. The
   latter is typically used if an inner and outer IP header exist which
   require two subsequent routing lookups to be performed.
 * A new metadata_dst structure which can be attached to skbs to
   carry metadata in between subsystems. This new metadata transport
   is used to provide a single interface for VXLAN, routing and OVS
   to communicate through metadata.

The OVS interfaces remain as-is but will transparently create a real
VXLAN net_device in the background. iproute2 is extended with a new
use cases:

  VXLAN:
  ip route add 40.1.1.1/32 encap vxlan id 10 dst 50.1.1.2 dev vxlan0

  MPLS:
  ip route add 10.1.1.0/30 encap mpls 200 via inet 10.1.1.1 dev swp1

Performance implications:
  The additional memory allocation in the receive path should have
  performance implications although it is not observable in standard
  throughput tests if GRO is properly done. The correct net_device
  model outweights the additional cost of the allocation. Furthermore,
  this implication can be relaxed by reintroducing a direct unqueued
  path from a software device to a consumer like bridge or OVS if
  needed.

    $ netperf  -t TCP_STREAM -H 15.1.1.201
    MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to
    15.1.1.201 (15.1.1.201) port 0 AF_INET : demo
    Recv   Send    Send
    Socket Socket  Message  Elapsed
    Size   Size    Size     Time     Throughput
    bytes  bytes   bytes    secs.    10^6bits/sec

     87380  16384  16384    10.00    9118.17

Changes since v1:
 * Properly initialize tun_id as reported by Julian
 * Drop dupliate netif_keep_dst() as reported by Alexei
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

21 files changed, 490 insertions, 22 deletions

diff --git a/include/linux/lwtunnel.h b/include/linux/lwtunnel.h
new file mode 100644
index 000000000000..97f32f8b4ae1
--- /dev/null
+++ b/include/linux/lwtunnel.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_LWTUNNEL_H_
+#define _LINUX_LWTUNNEL_H_
+
+#include <uapi/linux/lwtunnel.h>
+
+#endif /* _LINUX_LWTUNNEL_H_ */
diff --git a/include/linux/mpls_iptunnel.h b/include/linux/mpls_iptunnel.h
new file mode 100644
index 000000000000..ef29eb2d6dfd
--- /dev/null
+++ b/include/linux/mpls_iptunnel.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_MPLS_IPTUNNEL_H
+#define _LINUX_MPLS_IPTUNNEL_H
+
+#include <uapi/linux/mpls_iptunnel.h>
+
+#endif  /* _LINUX_MPLS_IPTUNNEL_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6bd96fe9416a..648a2c241993 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3469,5 +3469,6 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
 			       skb_network_header(skb);
 	return hdr_len + skb_gso_transport_seglen(skb);
 }
+
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/include/net/dst.h b/include/net/dst.h
index 2bc73f8a00a9..2578811cef51 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -57,6 +57,7 @@ struct dst_entry {
 #define DST_FAKE_RTABLE		0x0040
 #define DST_XFRM_TUNNEL		0x0080
 #define DST_XFRM_QUEUE		0x0100
+#define DST_METADATA		0x0200
 
 	unsigned short		pending_confirm;
 
@@ -356,6 +357,9 @@ static inline int dst_discard(struct sk_buff *skb)
 }
 void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
 		int initial_obsolete, unsigned short flags);
+void dst_init(struct dst_entry *dst, struct dst_ops *ops,
+	      struct net_device *dev, int initial_ref, int initial_obsolete,
+	      unsigned short flags);
 void __dst_free(struct dst_entry *dst);
 struct dst_entry *dst_destroy(struct dst_entry *dst);
 
@@ -457,7 +461,7 @@ static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie)
 	return dst;
 }
 
-void dst_init(void);
+void dst_subsys_init(void);
 
 /* Flags for xfrm_lookup flags argument. */
 enum {
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
new file mode 100644
index 000000000000..7b0306894663
--- /dev/null
+++ b/include/net/dst_metadata.h
@@ -0,0 +1,55 @@
+#ifndef __NET_DST_METADATA_H
+#define __NET_DST_METADATA_H 1
+
+#include <linux/skbuff.h>
+#include <net/ip_tunnels.h>
+#include <net/dst.h>
+
+struct metadata_dst {
+	struct dst_entry		dst;
+	size_t				opts_len;
+	union {
+		struct ip_tunnel_info	tun_info;
+	} u;
+};
+
+static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
+{
+	struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb);
+
+	if (md_dst && md_dst->dst.flags & DST_METADATA)
+		return md_dst;
+
+	return NULL;
+}
+
+static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb,
+						     int family)
+{
+	struct metadata_dst *md_dst = skb_metadata_dst(skb);
+	struct rtable *rt;
+
+	if (md_dst)
+		return &md_dst->u.tun_info;
+
+	switch (family) {
+	case AF_INET:
+		rt = (struct rtable *)skb_dst(skb);
+		if (rt && rt->rt_lwtstate)
+			return lwt_tun_info(rt->rt_lwtstate);
+		break;
+	}
+
+	return NULL;
+}
+
+static inline bool skb_valid_dst(const struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+
+	return dst && !(dst->flags & DST_METADATA);
+}
+
+struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
+
+#endif /* __NET_DST_METADATA_H */
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 903a55efbffe..4e8f804f4589 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -19,6 +19,7 @@ struct fib_rule {
 	u8			action;
 	/* 3 bytes hole, try to use */
 	u32			target;
+	__be64			tun_id;
 	struct fib_rule __rcu	*ctarget;
 	struct net		*fr_net;
 
diff --git a/include/net/flow.h b/include/net/flow.h
index 8109a159d1b3..3098ae33a178 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -19,6 +19,10 @@
 
 #define LOOPBACK_IFINDEX	1
 
+struct flowi_tunnel {
+	__be64			tun_id;
+};
+
 struct flowi_common {
 	int	flowic_oif;
 	int	flowic_iif;
@@ -30,6 +34,7 @@ struct flowi_common {
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_KNOWN_NH		0x02
 	__u32	flowic_secid;
+	struct flowi_tunnel flowic_tun_key;
 };
 
 union flowi_uli {
@@ -66,6 +71,7 @@ struct flowi4 {
 #define flowi4_proto		__fl_common.flowic_proto
 #define flowi4_flags		__fl_common.flowic_flags
 #define flowi4_secid		__fl_common.flowic_secid
+#define flowi4_tun_key		__fl_common.flowic_tun_key
 
 	/* (saddr,daddr) must be grouped, same order as in IP header */
 	__be32			saddr;
@@ -95,6 +101,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 	fl4->flowi4_proto = proto;
 	fl4->flowi4_flags = flags;
 	fl4->flowi4_secid = 0;
+	fl4->flowi4_tun_key.tun_id = 0;
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;
@@ -165,6 +172,7 @@ struct flowi {
 #define flowi_proto	u.__fl_common.flowic_proto
 #define flowi_flags	u.__fl_common.flowic_flags
 #define flowi_secid	u.__fl_common.flowic_secid
+#define flowi_tun_key	u.__fl_common.flowic_tun_key
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 3b76849c190f..276328e3daa6 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -51,6 +51,8 @@ struct fib6_config {
 	struct nlattr	*fc_mp;
 
 	struct nl_info	fc_nlinfo;
+	struct nlattr	*fc_encap;
+	u16		fc_encap_type;
 };
 
 struct fib6_node {
@@ -131,6 +133,7 @@ struct rt6_info {
 	/* more non-fragment space at head required */
 	unsigned short			rt6i_nfheader_len;
 	u8				rt6i_protocol;
+	struct lwtunnel_state		*rt6i_lwtstate;
 };
 
 static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 49c142bdf01e..5e0196084f1e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -44,7 +44,9 @@ struct fib_config {
 	u32			fc_flow;
 	u32			fc_nlflags;
 	struct nl_info		fc_nlinfo;
- };
+	struct nlattr		*fc_encap;
+	u16			fc_encap_type;
+};
 
 struct fib_info;
 struct rtable;
@@ -89,6 +91,7 @@ struct fib_nh {
 	struct rtable __rcu * __percpu *nh_pcpu_rth_output;
 	struct rtable __rcu	*nh_rth_input;
 	struct fnhe_hash_bucket	__rcu *nh_exceptions;
+	struct lwtunnel_state	*nh_lwtstate;
 };
 
 /*
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index d8214cb88bbc..0a5a7763eec2 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -9,9 +9,9 @@
 #include <net/dsfield.h>
 #include <net/gro_cells.h>
 #include <net/inet_ecn.h>
-#include <net/ip.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
+#include <net/lwtunnel.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -22,6 +22,37 @@
 /* Keep error state on tunnel for 30 sec */
 #define IPTUNNEL_ERR_TIMEO	(30*HZ)
 
+/* Used to memset ip_tunnel padding. */
+#define IP_TUNNEL_KEY_SIZE					\
+	(offsetof(struct ip_tunnel_key, tp_dst) +		\
+	 FIELD_SIZEOF(struct ip_tunnel_key, tp_dst))
+
+struct ip_tunnel_key {
+	__be64			tun_id;
+	__be32			ipv4_src;
+	__be32			ipv4_dst;
+	__be16			tun_flags;
+	__u8			ipv4_tos;
+	__u8			ipv4_ttl;
+	__be16			tp_src;
+	__be16			tp_dst;
+} __packed __aligned(4); /* Minimize padding. */
+
+/* Indicates whether the tunnel info structure represents receive
+ * or transmit tunnel parameters.
+ */
+enum {
+	IP_TUNNEL_INFO_RX,
+	IP_TUNNEL_INFO_TX,
+};
+
+struct ip_tunnel_info {
+	struct ip_tunnel_key	key;
+	const void		*options;
+	u8			options_len;
+	u8			mode;
+};
+
 /* 6rd prefix/relay information */
 #ifdef CONFIG_IPV6_SIT_6RD
 struct ip_tunnel_6rd_parm {
@@ -136,6 +167,47 @@ int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op,
 int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
 			    unsigned int num);
 
+static inline void __ip_tunnel_info_init(struct ip_tunnel_info *tun_info,
+					 __be32 saddr, __be32 daddr,
+					 u8 tos, u8 ttl,
+					 __be16 tp_src, __be16 tp_dst,
+					 __be64 tun_id, __be16 tun_flags,
+					 const void *opts, u8 opts_len)
+{
+	tun_info->key.tun_id = tun_id;
+	tun_info->key.ipv4_src = saddr;
+	tun_info->key.ipv4_dst = daddr;
+	tun_info->key.ipv4_tos = tos;
+	tun_info->key.ipv4_ttl = ttl;
+	tun_info->key.tun_flags = tun_flags;
+
+	/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
+	 * the upper tunnel are used.
+	 * E.g: GRE over IPSEC, the tp_src and tp_port are zero.
+	 */
+	tun_info->key.tp_src = tp_src;
+	tun_info->key.tp_dst = tp_dst;
+
+	/* Clear struct padding. */
+	if (sizeof(tun_info->key) != IP_TUNNEL_KEY_SIZE)
+		memset((unsigned char *)&tun_info->key + IP_TUNNEL_KEY_SIZE,
+		       0, sizeof(tun_info->key) - IP_TUNNEL_KEY_SIZE);
+
+	tun_info->options = opts;
+	tun_info->options_len = opts_len;
+}
+
+static inline void ip_tunnel_info_init(struct ip_tunnel_info *tun_info,
+				       const struct iphdr *iph,
+				       __be16 tp_src, __be16 tp_dst,
+				       __be64 tun_id, __be16 tun_flags,
+				       const void *opts, u8 opts_len)
+{
+	__ip_tunnel_info_init(tun_info, iph->saddr, iph->daddr,
+			      iph->tos, iph->ttl, tp_src, tp_dst,
+			      tun_id, tun_flags, opts, opts_len);
+}
+
 #ifdef CONFIG_INET
 
 int ip_tunnel_init(struct net_device *dev);
@@ -221,6 +293,27 @@ static inline void iptunnel_xmit_stats(int err,
 	}
 }
 
+static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info, size_t n)
+{
+	return info + 1;
+}
+
+static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
+{
+	return (struct ip_tunnel_info *)lwtstate->data;
+}
+
+extern struct static_key ip_tunnel_metadata_cnt;
+
+/* Returns > 0 if metadata should be collected */
+static inline int ip_tunnel_collect_metadata(void)
+{
+	return static_key_false(&ip_tunnel_metadata_cnt);
+}
+
+void ip_tunnel_need_metadata(void);
+void ip_tunnel_unneed_metadata(void);
+
 #endif /* CONFIG_INET */
 
 #endif /* __NET_IP_TUNNELS_H */
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
new file mode 100644
index 000000000000..918e03c1dafa
--- /dev/null
+++ b/include/net/lwtunnel.h
@@ -0,0 +1,144 @@
+#ifndef __NET_LWTUNNEL_H
+#define __NET_LWTUNNEL_H 1
+
+#include <linux/lwtunnel.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <net/route.h>
+
+#define LWTUNNEL_HASH_BITS   7
+#define LWTUNNEL_HASH_SIZE   (1 << LWTUNNEL_HASH_BITS)
+
+/* lw tunnel state flags */
+#define LWTUNNEL_STATE_OUTPUT_REDIRECT 0x1
+
+struct lwtunnel_state {
+	__u16		type;
+	__u16		flags;
+	atomic_t	refcnt;
+	int             len;
+	__u8            data[0];
+};
+
+struct lwtunnel_encap_ops {
+	int (*build_state)(struct net_device *dev, struct nlattr *encap,
+			   struct lwtunnel_state **ts);
+	int (*output)(struct sock *sk, struct sk_buff *skb);
+	int (*fill_encap)(struct sk_buff *skb,
+			  struct lwtunnel_state *lwtstate);
+	int (*get_encap_size)(struct lwtunnel_state *lwtstate);
+	int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b);
+};
+
+extern const struct lwtunnel_encap_ops __rcu *
+		lwtun_encaps[LWTUNNEL_ENCAP_MAX+1];
+
+#ifdef CONFIG_LWTUNNEL
+static inline void lwtunnel_state_get(struct lwtunnel_state *lws)
+{
+	atomic_inc(&lws->refcnt);
+}
+
+static inline void lwtunnel_state_put(struct lwtunnel_state *lws)
+{
+	if (!lws)
+		return;
+
+	if (atomic_dec_and_test(&lws->refcnt))
+		kfree(lws);
+}
+
+static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate)
+{
+	if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_OUTPUT_REDIRECT))
+		return true;
+
+	return false;
+}
+
+int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
+			   unsigned int num);
+int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
+			   unsigned int num);
+int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
+			 struct nlattr *encap,
+			 struct lwtunnel_state **lws);
+int lwtunnel_fill_encap(struct sk_buff *skb,
+			struct lwtunnel_state *lwtstate);
+int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate);
+struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len);
+int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b);
+int lwtunnel_output(struct sock *sk, struct sk_buff *skb);
+int lwtunnel_output6(struct sock *sk, struct sk_buff *skb);
+
+#else
+
+static inline void lwtunnel_state_get(struct lwtunnel_state *lws)
+{
+}
+
+static inline void lwtunnel_state_put(struct lwtunnel_state *lws)
+{
+}
+
+static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate)
+{
+	return false;
+}
+
+static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
+					 unsigned int num)
+{
+	return -EOPNOTSUPP;
+
+}
+
+static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
+					 unsigned int num)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
+				       struct nlattr *encap,
+				       struct lwtunnel_state **lws)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int lwtunnel_fill_encap(struct sk_buff *skb,
+				      struct lwtunnel_state *lwtstate)
+{
+	return 0;
+}
+
+static inline int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate)
+{
+	return 0;
+}
+
+static inline struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len)
+{
+	return NULL;
+}
+
+static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a,
+				     struct lwtunnel_state *b)
+{
+	return 0;
+}
+
+static inline int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int lwtunnel_output6(struct sock *sk, struct sk_buff *skb)
+{
+	return -EOPNOTSUPP;
+}
+
+#endif
+
+#endif /* __NET_LWTUNNEL_H */
diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h
new file mode 100644
index 000000000000..4757997f76ed
--- /dev/null
+++ b/include/net/mpls_iptunnel.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2015 Cumulus Networks, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _NET_MPLS_IPTUNNEL_H
+#define _NET_MPLS_IPTUNNEL_H 1
+
+#define MAX_NEW_LABELS 2
+
+struct mpls_iptunnel_encap {
+	u32	label[MAX_NEW_LABELS];
+	u32	labels;
+};
+
+static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate)
+{
+	return (struct mpls_iptunnel_encap *)lwtstate->data;
+}
+
+#endif
diff --git a/include/net/route.h b/include/net/route.h
index fe22d03afb6a..2d45f419477f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -66,6 +66,7 @@ struct rtable {
 
 	struct list_head	rt_uncached;
 	struct uncached_list	*rt_uncached_list;
+	struct lwtunnel_state   *rt_lwtstate;
 };
 
 static inline bool rt_is_input_route(const struct rtable *rt)
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 343d922d15c2..18fdb98185ab 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -141,6 +141,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 				    unsigned char name_assign_type,
 				    const struct rtnl_link_ops *ops,
 				    struct nlattr *tb[]);
+int rtnl_delete_link(struct net_device *dev);
 int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm);
 
 int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len);
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0082b5d33d7d..eb8d721cdb67 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 +116,57 @@ 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 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 +180,8 @@ 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
+#define VXLAN_F_FLOW_BASED		0x4000
 
 /* Flags that are used in the receive path. These flags must match in
  * order for a socket to be shareable
@@ -137,18 +189,17 @@ 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 |	\
+					 VXLAN_F_FLOW_BASED)
 
-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)
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 2b82d7e30974..96161b8202b5 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -43,7 +43,7 @@ enum {
 	FRA_UNUSED5,
 	FRA_FWMARK,	/* mark */
 	FRA_FLOW,	/* flow/class id */
-	FRA_UNUSED6,
+	FRA_TUN_ID,
 	FRA_SUPPRESS_IFGROUP,
 	FRA_SUPPRESS_PREFIXLEN,
 	FRA_TABLE,	/* Extended table id */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 24d68b797c59..9eeb5d9cf8f0 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -382,6 +382,7 @@ enum {
 	IFLA_VXLAN_REMCSUM_RX,
 	IFLA_VXLAN_GBP,
 	IFLA_VXLAN_REMCSUM_NOPARTIAL,
+	IFLA_VXLAN_FLOWBASED,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h
new file mode 100644
index 000000000000..31377bbea3f8
--- /dev/null
+++ b/include/uapi/linux/lwtunnel.h
@@ -0,0 +1,16 @@
+#ifndef _UAPI_LWTUNNEL_H_
+#define _UAPI_LWTUNNEL_H_
+
+#include <linux/types.h>
+
+enum lwtunnel_encap_types {
+	LWTUNNEL_ENCAP_NONE,
+	LWTUNNEL_ENCAP_MPLS,
+	LWTUNNEL_ENCAP_IP,
+	__LWTUNNEL_ENCAP_MAX,
+};
+
+#define LWTUNNEL_ENCAP_MAX (__LWTUNNEL_ENCAP_MAX - 1)
+
+
+#endif /* _UAPI_LWTUNNEL_H_ */
diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h
new file mode 100644
index 000000000000..d80a0498f77e
--- /dev/null
+++ b/include/uapi/linux/mpls_iptunnel.h
@@ -0,0 +1,28 @@
+/*
+ *	mpls tunnel api
+ *
+ *	Authors:
+ *		Roopa Prabhu <roopa@cumulusnetworks.com>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_MPLS_IPTUNNEL_H
+#define _UAPI_LINUX_MPLS_IPTUNNEL_H
+
+/* MPLS tunnel attributes
+ * [RTA_ENCAP] = {
+ *     [MPLS_IPTUNNEL_DST]
+ * }
+ */
+enum {
+	MPLS_IPTUNNEL_UNSPEC,
+	MPLS_IPTUNNEL_DST,
+	__MPLS_IPTUNNEL_MAX,
+};
+#define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1)
+
+#endif /* _UAPI_LINUX_MPLS_IPTUNNEL_H */
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 1dab77601c21..d6b885460187 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -321,7 +321,7 @@ enum ovs_key_attr {
 				 * the accepted length of the array. */
 
 #ifdef __KERNEL__
-	OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ovs_tunnel_info */
+	OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
 #endif
 	__OVS_KEY_ATTR_MAX
 };
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index fdd8f07f1d34..47d24cb3fbc1 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -286,6 +286,21 @@ enum rt_class_t {
 
 /* Routing message attributes */
 
+enum ip_tunnel_t {
+	IP_TUN_UNSPEC,
+	IP_TUN_ID,
+	IP_TUN_DST,
+	IP_TUN_SRC,
+	IP_TUN_TTL,
+	IP_TUN_TOS,
+	IP_TUN_SPORT,
+	IP_TUN_DPORT,
+	IP_TUN_FLAGS,
+	__IP_TUN_MAX,
+};
+
+#define IP_TUN_MAX (__IP_TUN_MAX - 1)
+
 enum rtattr_type_t {
 	RTA_UNSPEC,
 	RTA_DST,
@@ -308,6 +323,8 @@ enum rtattr_type_t {
 	RTA_VIA,
 	RTA_NEWDST,
 	RTA_PREF,
+	RTA_ENCAP_TYPE,
+	RTA_ENCAP,
 	__RTA_MAX
 };