Lightweight & flow based tunneling

index bfc0a18..d3964fa 100644
@@ -1634,6 +1634,8 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->dst.output = ip_output;
 
 	rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag);
+	if (lwtunnel_output_redirect(rth->rt_lwtstate))
+		rth->dst.output = lwtunnel_output;
 	skb_dst_set(skb, &rth->dst);
 out:
 	err = 0;

new file mode 100644
index 0000000..ef29eb2
@@ -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 */

new file mode 100644
index 0000000..4757997
@@ -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

new file mode 100644
index 0000000..d80a049
@@ -0,0 +1,28 @@
+/*
+ *	mpls tunnel api
+ *
+ *	Authors:
+ *		Roopa Prabhu <[email protected]>
+ *
+ *	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 */

229 lines not on this page · raw message

index fdd8f07..0d3d3cc 100644
@@ -308,6 +308,8 @@ enum rtattr_type_t {
 	RTA_VIA,
 	RTA_NEWDST,
 	RTA_PREF,
+	RTA_ENCAP_TYPE,
+	RTA_ENCAP,
 	__RTA_MAX
 };
 

new file mode 100644
index 0000000..97f32f8
@@ -0,0 +1,6 @@
+#ifndef _LINUX_LWTUNNEL_H_
+#define _LINUX_LWTUNNEL_H_
+
+#include <uapi/linux/lwtunnel.h>
+
+#endif /* _LINUX_LWTUNNEL_H_ */

132 lines not on this page · raw message

new file mode 100644
index 0000000..aa611d9
@@ -0,0 +1,15 @@
+#ifndef _UAPI_LWTUNNEL_H_
+#define _UAPI_LWTUNNEL_H_
+
+#include <linux/types.h>
+
+enum lwtunnel_encap_types {
+	LWTUNNEL_ENCAP_NONE,
+	LWTUNNEL_ENCAP_MPLS,
+	__LWTUNNEL_ENCAP_MAX,
+};
+
+#define LWTUNNEL_ENCAP_MAX (__LWTUNNEL_ENCAP_MAX - 1)
+
+
+#endif /* _UAPI_LWTUNNEL_H_ */

172 lines not on this page · raw message

index 49c142b..5e01960 100644
@@ -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;
 };
 
 /*

index fe22d03..2d45f41 100644
@@ -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)

index 6bbc549..9b2019c 100644
@@ -591,6 +591,8 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
 	[RTA_METRICS]		= { .type = NLA_NESTED },
 	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
 	[RTA_FLOW]		= { .type = NLA_U32 },
+	[RTA_ENCAP_TYPE]	= { .type = NLA_U16 },
+	[RTA_ENCAP]		= { .type = NLA_NESTED },
 };
 
 static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,

@@ -656,6 +658,12 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		case RTA_TABLE:
 			cfg->fc_table = nla_get_u32(attr);
 			break;
+		case RTA_ENCAP:
+			cfg->fc_encap = attr;
+			break;
+		case RTA_ENCAP_TYPE:
+			cfg->fc_encap_type = nla_get_u16(attr);
+			break;
 		}
 	}
 

180 lines not on this page · raw message

index d0362a2..bfc0a18 100644
@@ -102,6 +102,7 @@
 #include <net/tcp.h>
 #include <net/icmp.h>
 #include <net/xfrm.h>
+#include <net/lwtunnel.h>
 #include <net/netevent.h>
 #include <net/rtnetlink.h>
 #ifdef CONFIG_SYSCTL

@@ -1355,6 +1356,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 		list_del(&rt->rt_uncached);
 		spin_unlock_bh(&ul->lock);
 	}
+	lwtunnel_state_put(rt->rt_lwtstate);
 }
 
 void rt_flush_dev(struct net_device *dev)

@@ -1403,6 +1405,12 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
 #endif
+		if (nh->nh_lwtstate) {
+			lwtunnel_state_get(nh->nh_lwtstate);
+			rt->rt_lwtstate = nh->nh_lwtstate;
+		} else {
+			rt->rt_lwtstate = NULL;
+		}
 		if (unlikely(fnhe))
 			cached = rt_bind_exception(rt, fnhe, daddr);
 		else if (!(rt->dst.flags & DST_NOCACHE))

@@ -1488,6 +1496,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	rth->rt_lwtstate = NULL;
 	if (our) {
 		rth->dst.input= ip_local_deliver;
 		rth->rt_flags |= RTCF_LOCAL;

@@ -1618,6 +1627,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	rth->rt_lwtstate = NULL;
 	RT_CACHE_STAT_INC(in_slow_tot);
 
 	rth->dst.input = ip_forward;

@@ -1792,6 +1802,8 @@ local_input:
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	rth->rt_lwtstate = NULL;
+
 	RT_CACHE_STAT_INC(in_slow_tot);
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;

@@ -1981,7 +1993,7 @@ add:
 	rth->rt_gateway = 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
-
+	rth->rt_lwtstate = NULL;
 	RT_CACHE_STAT_INC(out_slow_tot);
 
 	if (flags & RTCF_LOCAL)

@@ -2261,7 +2273,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_uses_gateway = ort->rt_uses_gateway;
 
 		INIT_LIST_HEAD(&rt->rt_uncached);
-
+		rt->rt_lwtstate = NULL;
 		dst_free(new);
 	}
 

index 3b76849..276328e 100644
@@ -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)

index 55d1986..d715f2e 100644
@@ -32,6 +32,7 @@
 #include <net/ipv6.h>
 #include <net/ndisc.h>
 #include <net/addrconf.h>
+#include <net/lwtunnel.h>
 
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>

@@ -177,6 +178,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 static void rt6_release(struct rt6_info *rt)
 {
 	if (atomic_dec_and_test(&rt->rt6i_ref)) {
+		lwtunnel_state_put(rt->rt6i_lwtstate);
 		rt6_free_pcpu(rt);
 		dst_free(&rt->dst);
 	}

index 1a1122a..acfe25d 100644
@@ -58,6 +58,7 @@
 #include <net/netevent.h>
 #include <net/netlink.h>
 #include <net/nexthop.h>
+#include <net/lwtunnel.h>
 
 #include <asm/uaccess.h>
 

@@ -1773,6 +1774,17 @@ int ip6_route_add(struct fib6_config *cfg)
 
 	rt->dst.output = ip6_output;
 
+	if (cfg->fc_encap) {
+		struct lwtunnel_state *lwtstate;
+
+		err = lwtunnel_build_state(dev, cfg->fc_encap_type,
+					   cfg->fc_encap, &lwtstate);
+		if (err)
+			goto out;
+		lwtunnel_state_get(lwtstate);
+		rt->rt6i_lwtstate = lwtstate;
+	}
+
 	ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
 	rt->rt6i_dst.plen = cfg->fc_dst_len;
 	if (rt->rt6i_dst.plen == 128)

@@ -2598,6 +2610,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_METRICS]           = { .type = NLA_NESTED },
 	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
 	[RTA_PREF]              = { .type = NLA_U8 },
+	[RTA_ENCAP_TYPE]	= { .type = NLA_U16 },
+	[RTA_ENCAP]		= { .type = NLA_NESTED },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,

@@ -2692,6 +2706,12 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cfg->fc_flags |= RTF_PREF(pref);
 	}
 
+	if (tb[RTA_ENCAP])
+		cfg->fc_encap = tb[RTA_ENCAP];
+
+	if (tb[RTA_ENCAP_TYPE])
+		cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
+
 	err = 0;
 errout:
 	return err;

@@ -2724,6 +2744,10 @@ beginning:
 				r_cfg.fc_gateway = nla_get_in6_addr(nla);
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
+			r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
+			if (nla)
+				r_cfg.fc_encap_type = nla_get_u16(nla);
 		}
 		err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg);
 		if (err) {

@@ -2786,7 +2810,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return ip6_route_add(&cfg);
 }
 
-static inline size_t rt6_nlmsg_size(void)
+static inline size_t rt6_nlmsg_size(struct rt6_info *rt)
 {
 	return NLMSG_ALIGN(sizeof(struct rtmsg))
 	       + nla_total_size(16) /* RTA_SRC */

@@ -2800,7 +2824,8 @@ static inline size_t rt6_nlmsg_size(void)
 	       + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
 	       + nla_total_size(sizeof(struct rta_cacheinfo))
 	       + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
-	       + nla_total_size(1); /* RTA_PREF */
+	       + nla_total_size(1) /* RTA_PREF */
+	       + lwtunnel_get_encap_size(rt->rt6i_lwtstate);
 }
 
 static int rt6_fill_node(struct net *net,

@@ -2948,6 +2973,8 @@ static int rt6_fill_node(struct net *net,
 	if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
 		goto nla_put_failure;
 
+	lwtunnel_fill_encap(skb, rt->rt6i_lwtstate);
+
 	nlmsg_end(skb, nlh);
 	return 0;
 

@@ -3074,7 +3101,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
 	err = -ENOBUFS;
 	seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
-	skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
+	skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
 	if (!skb)
 		goto errout;
 

index df24b36..918e03c 100644
@@ -69,6 +69,8 @@ int lwtunnel_fill_encap(struct sk_buff *skb,
 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
 

@@ -127,6 +129,16 @@ static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a,
 	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 */

65 lines not on this page · raw message

index acfe25d..6c328bb 100644
@@ -1783,6 +1783,7 @@ int ip6_route_add(struct fib6_config *cfg)
 			goto out;
 		lwtunnel_state_get(lwtstate);
 		rt->rt6i_lwtstate = lwtstate;
+		rt->dst.output = lwtunnel_output6;
 	}
 
 	ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);

index 1f93a59..6e66911 100644
@@ -58,10 +58,11 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
 	return rcu_dereference_rtnl(dev->mpls_ptr);
 }
 
-static bool mpls_output_possible(const struct net_device *dev)
+bool mpls_output_possible(const struct net_device *dev)
 {
 	return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
 }
+EXPORT_SYMBOL_GPL(mpls_output_possible);
 
 static unsigned int mpls_rt_header_size(const struct mpls_route *rt)
 {

@@ -69,13 +70,14 @@ static unsigned int mpls_rt_header_size(const struct mpls_route *rt)
 	return rt->rt_labels * sizeof(struct mpls_shim_hdr);
 }
 
-static unsigned int mpls_dev_mtu(const struct net_device *dev)
+unsigned int mpls_dev_mtu(const struct net_device *dev)
 {
 	/* The amount of data the layer 2 frame can hold */
 	return dev->mtu;
 }
+EXPORT_SYMBOL_GPL(mpls_dev_mtu);
 
-static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 {
 	if (skb->len <= mtu)
 		return false;

@@ -85,6 +87,7 @@ static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
 
 static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
 			struct mpls_entry_decoded dec)

@@ -626,6 +629,7 @@ int nla_put_labels(struct sk_buff *skb, int attrtype,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nla_put_labels);
 
 int nla_get_labels(const struct nlattr *nla,
 		   u32 max_labels, u32 *labels, u32 label[])

@@ -671,6 +675,7 @@ int nla_get_labels(const struct nlattr *nla,
 	*labels = nla_labels;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nla_get_labels);
 
 static int rtm_to_route_config(struct sk_buff *skb,  struct nlmsghdr *nlh,
 			       struct mpls_route_config *cfg)

index 8cabeb5..8e3af1e 100644
@@ -52,5 +52,8 @@ static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr *
 
 int nla_put_labels(struct sk_buff *skb, int attrtype,  u8 labels, const u32 label[]);
 int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]);
+bool mpls_output_possible(const struct net_device *dev);
+unsigned int mpls_dev_mtu(const struct net_device *dev);
+bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu);
 
 #endif /* MPLS_INTERNAL_H */

index d8214cb..6b9d559 100644
@@ -22,6 +22,28 @@
 /* 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. */
+
+struct ip_tunnel_info {
+	struct ip_tunnel_key	key;
+	const void		*options;
+	u8			options_len;
+};
+
 /* 6rd prefix/relay information */
 #ifdef CONFIG_IPV6_SIT_6RD
 struct ip_tunnel_6rd_parm {

@@ -136,6 +158,47 @@ 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);

index 1dab776..d6b8854 100644
@@ -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
 };

index 8a8c0b8..27c1687 100644
@@ -611,7 +611,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 			    struct sw_flow_key *key, const struct nlattr *attr,
 			    const struct nlattr *actions, int actions_len)
 {
-	struct ovs_tunnel_info info;
+	struct ip_tunnel_info info;
 	struct dp_upcall_info upcall;
 	const struct nlattr *a;
 	int rem;

index cd691e9..6b28c5c 100644
@@ -25,6 +25,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/u64_stats_sync.h>
+#include <net/ip_tunnels.h>
 
 #include "flow.h"
 #include "flow_table.h"

@@ -98,7 +99,7 @@ struct datapath {
  * when a packet is received by OVS.
  */
 struct ovs_skb_cb {
-	struct ovs_tunnel_info  *egress_tun_info;
+	struct ip_tunnel_info  *egress_tun_info;
 	struct vport		*input_vport;
 };
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)

@@ -114,7 +115,7 @@ struct ovs_skb_cb {
  * @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY.
  */
 struct dp_upcall_info {
-	const struct ovs_tunnel_info *egress_tun_info;
+	const struct ip_tunnel_info *egress_tun_info;
 	const struct nlattr *userdata;
 	const struct nlattr *actions;
 	int actions_len;

index bc7b0ab..8db22ef 100644
@@ -682,12 +682,12 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
 	return key_extract(skb, key);
 }
 
-int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info,
+int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 			 struct sk_buff *skb, struct sw_flow_key *key)
 {
 	/* Extract metadata from packet. */
 	if (tun_info) {
-		memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key));
+		memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key));
 
 		if (tun_info->options) {
 			BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) *

103 lines not on this page · raw message

index 624e41c..ecfa530 100644
@@ -641,7 +641,7 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb,
 }
 
 static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
-				const struct ovs_key_ipv4_tunnel *output,
+				const struct ip_tunnel_key *output,
 				const void *tun_opts, int swkey_tun_opts_len)
 {
 	if (output->tun_flags & TUNNEL_KEY &&

@@ -689,7 +689,7 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
 }
 
 static int ipv4_tun_to_nlattr(struct sk_buff *skb,
-			      const struct ovs_key_ipv4_tunnel *output,
+			      const struct ip_tunnel_key *output,
 			      const void *tun_opts, int swkey_tun_opts_len)
 {
 	struct nlattr *nla;

@@ -708,9 +708,9 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
 }
 
 int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
-				  const struct ovs_tunnel_info *egress_tun_info)
+				  const struct ip_tunnel_info *egress_tun_info)
 {
-	return __ipv4_tun_to_nlattr(skb, &egress_tun_info->tunnel,
+	return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key,
 				    egress_tun_info->options,
 				    egress_tun_info->options_len);
 }

@@ -1746,7 +1746,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 {
 	struct sw_flow_match match;
 	struct sw_flow_key key;
-	struct ovs_tunnel_info *tun_info;
+	struct ip_tunnel_info *tun_info;
 	struct nlattr *a;
 	int err = 0, start, opts_type;
 

@@ -1777,7 +1777,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 		return PTR_ERR(a);
 
 	tun_info = nla_data(a);
-	tun_info->tunnel = key.tun_key;
+	tun_info->key = key.tun_key;
 	tun_info->options_len = key.tun_opts_len;
 
 	if (tun_info->options_len) {

@@ -2227,13 +2227,13 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 
 	switch (key_type) {
 	case OVS_KEY_ATTR_TUNNEL_INFO: {
-		struct ovs_tunnel_info *tun_info = nla_data(ovs_key);
+		struct ip_tunnel_info *tun_info = nla_data(ovs_key);
 
 		start = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
 		if (!start)
 			return -EMSGSIZE;
 
-		err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel,
+		err = ipv4_tun_to_nlattr(skb, &tun_info->key,
 					 tun_info->options_len ?
 						tun_info->options : NULL,
 					 tun_info->options_len);

index 5c3d75b..ec53eb6 100644
@@ -55,7 +55,7 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb);
 int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key,
 		      const struct nlattr *mask, bool log);
 int ovs_nla_put_egress_tunnel_key(struct sk_buff *,
-				  const struct ovs_tunnel_info *);
+				  const struct ip_tunnel_info *);
 
 bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log);
 int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,

index 208c576..1da3a14 100644
@@ -77,7 +77,7 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
 	struct vport *vport = gs->rcv_data;
 	struct genevehdr *geneveh = geneve_hdr(skb);
 	int opts_len;
-	struct ovs_tunnel_info tun_info;
+	struct ip_tunnel_info tun_info;
 	__be64 key;
 	__be16 flags;
 

@@ -90,10 +90,9 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
 
 	key = vni_to_tunnel_id(geneveh->vni);
 
-	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb),
-			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
-			       key, flags,
-			       geneveh->options, opts_len);
+	ip_tunnel_info_init(&tun_info, ip_hdr(skb),
+			    udp_hdr(skb)->source, udp_hdr(skb)->dest,
+			    key, flags, geneveh->options, opts_len);
 
 	ovs_vport_receive(vport, skb, &tun_info);
 }

@@ -165,8 +164,8 @@ error:
 
 static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
 {
-	const struct ovs_key_ipv4_tunnel *tun_key;
-	struct ovs_tunnel_info *tun_info;
+	const struct ip_tunnel_key *tun_key;
+	struct ip_tunnel_info *tun_info;
 	struct net *net = ovs_dp_get_net(vport->dp);
 	struct geneve_port *geneve_port = geneve_vport(vport);
 	__be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;

@@ -183,7 +182,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
 		goto error;
 	}
 
-	tun_key = &tun_info->tunnel;
+	tun_key = &tun_info->key;
 	rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);

@@ -225,7 +224,7 @@ static const char *geneve_get_name(const struct vport *vport)
 }
 
 static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
-				      struct ovs_tunnel_info *egress_tun_info)
+				      struct ip_tunnel_info *egress_tun_info)
 {
 	struct geneve_port *geneve_port = geneve_vport(vport);
 	struct net *net = ovs_dp_get_net(vport->dp);

index f17ac96..b87656c 100644
@@ -67,9 +67,9 @@ static struct sk_buff *__build_header(struct sk_buff *skb,
 				      int tunnel_hlen)
 {
 	struct tnl_ptk_info tpi;
-	const struct ovs_key_ipv4_tunnel *tun_key;
+	const struct ip_tunnel_key *tun_key;
 
-	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
+	tun_key = &OVS_CB(skb)->egress_tun_info->key;
 
 	skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM));
 	if (IS_ERR(skb))

@@ -97,7 +97,7 @@ static __be64 key_to_tunnel_id(__be32 key, __be32 seq)
 static int gre_rcv(struct sk_buff *skb,
 		   const struct tnl_ptk_info *tpi)
 {
-	struct ovs_tunnel_info tun_info;
+	struct ip_tunnel_info tun_info;
 	struct ovs_net *ovs_net;
 	struct vport *vport;
 	__be64 key;

@@ -108,8 +108,8 @@ static int gre_rcv(struct sk_buff *skb,
 		return PACKET_REJECT;
 
 	key = key_to_tunnel_id(tpi->key, tpi->seq);
-	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), 0, 0, key,
-			       filter_tnl_flags(tpi->flags), NULL, 0);
+	ip_tunnel_info_init(&tun_info, ip_hdr(skb), 0, 0, key,
+			    filter_tnl_flags(tpi->flags), NULL, 0);
 
 	ovs_vport_receive(vport, skb, &tun_info);
 	return PACKET_RCVD;

@@ -134,7 +134,7 @@ static int gre_err(struct sk_buff *skb, u32 info,
 static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 {
 	struct net *net = ovs_dp_get_net(vport->dp);
-	const struct ovs_key_ipv4_tunnel *tun_key;
+	const struct ip_tunnel_key *tun_key;
 	struct flowi4 fl;
 	struct rtable *rt;
 	int min_headroom;

@@ -147,7 +147,7 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 		goto err_free_skb;
 	}
 
-	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
+	tun_key = &OVS_CB(skb)->egress_tun_info->key;
 	rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_GRE);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);

@@ -277,7 +277,7 @@ static void gre_tnl_destroy(struct vport *vport)
 }
 
 static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
-				   struct ovs_tunnel_info *egress_tun_info)
+				   struct ip_tunnel_info *egress_tun_info)
 {
 	return ovs_tunnel_get_egress_info(egress_tun_info,
 					  ovs_dp_get_net(vport->dp),

index 6d39766..6f7986f 100644
@@ -64,7 +64,7 @@ static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
 static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
 		      struct vxlan_metadata *md)
 {
-	struct ovs_tunnel_info tun_info;
+	struct ip_tunnel_info tun_info;
 	struct vxlan_port *vxlan_port;
 	struct vport *vport = vs->data;
 	struct iphdr *iph;

@@ -82,9 +82,9 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
 	/* Save outer tunnel values */
 	iph = ip_hdr(skb);
 	key = cpu_to_be64(ntohl(md->vni) >> 8);
-	ovs_flow_tun_info_init(&tun_info, iph,
-			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
-			       key, flags, &opts, sizeof(opts));
+	ip_tunnel_info_init(&tun_info, iph,
+			    udp_hdr(skb)->source, udp_hdr(skb)->dest,
+			    key, flags, &opts, sizeof(opts));
 
 	ovs_vport_receive(vport, skb, &tun_info);
 }

@@ -205,13 +205,13 @@ error:
 
 static int vxlan_ext_gbp(struct sk_buff *skb)
 {
-	const struct ovs_tunnel_info *tun_info;
+	const struct ip_tunnel_info *tun_info;
 	const struct ovs_vxlan_opts *opts;
 
 	tun_info = OVS_CB(skb)->egress_tun_info;
 	opts = tun_info->options;
 
-	if (tun_info->tunnel.tun_flags & TUNNEL_VXLAN_OPT &&
+	if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT &&
 	    tun_info->options_len >= sizeof(*opts))
 		return opts->gbp;
 	else

@@ -224,7 +224,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	struct vxlan_port *vxlan_port = vxlan_vport(vport);
 	struct sock *sk = vxlan_port->vs->sock->sk;
 	__be16 dst_port = inet_sk(sk)->inet_sport;
-	const struct ovs_key_ipv4_tunnel *tun_key;
+	const struct ip_tunnel_key *tun_key;
 	struct vxlan_metadata md = {0};
 	struct rtable *rt;
 	struct flowi4 fl;

@@ -238,7 +238,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 		goto error;
 	}
 
-	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
+	tun_key = &OVS_CB(skb)->egress_tun_info->key;
 	rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);

@@ -269,7 +269,7 @@ error:
 }
 
 static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
-				     struct ovs_tunnel_info *egress_tun_info)
+				     struct ip_tunnel_info *egress_tun_info)
 {
 	struct net *net = ovs_dp_get_net(vport->dp);
 	struct vxlan_port *vxlan_port = vxlan_vport(vport);

index 067a3ff..af23ba0 100644
@@ -469,7 +469,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb)
  * skb->data should point to the Ethernet header.
  */
 void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
-		       const struct ovs_tunnel_info *tun_info)
+		       const struct ip_tunnel_info *tun_info)
 {
 	struct pcpu_sw_netstats *stats;
 	struct sw_flow_key key;

@@ -572,22 +572,22 @@ void ovs_vport_deferred_free(struct vport *vport)
 }
 EXPORT_SYMBOL_GPL(ovs_vport_deferred_free);
 
-int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+int ovs_tunnel_get_egress_info(struct ip_tunnel_info *egress_tun_info,
 			       struct net *net,
-			       const struct ovs_tunnel_info *tun_info,
+			       const struct ip_tunnel_info *tun_info,
 			       u8 ipproto,
 			       u32 skb_mark,
 			       __be16 tp_src,
 			       __be16 tp_dst)
 {
-	const struct ovs_key_ipv4_tunnel *tun_key;
+	const struct ip_tunnel_key *tun_key;
 	struct rtable *rt;
 	struct flowi4 fl;
 
 	if (unlikely(!tun_info))
 		return -EINVAL;
 
-	tun_key = &tun_info->tunnel;
+	tun_key = &tun_info->key;
 
 	/* Route lookup to get srouce IP address.
 	 * The process may need to be changed if the corresponding process

@@ -602,22 +602,22 @@ int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
 	/* Generate egress_tun_info based on tun_info,
 	 * saddr, tp_src and tp_dst
 	 */
-	__ovs_flow_tun_info_init(egress_tun_info,
-				 fl.saddr, tun_key->ipv4_dst,
-				 tun_key->ipv4_tos,
-				 tun_key->ipv4_ttl,
-				 tp_src, tp_dst,
-				 tun_key->tun_id,
-				 tun_key->tun_flags,
-				 tun_info->options,
-				 tun_info->options_len);
+	__ip_tunnel_info_init(egress_tun_info,
+			      fl.saddr, tun_key->ipv4_dst,
+			      tun_key->ipv4_tos,
+			      tun_key->ipv4_ttl,
+			      tp_src, tp_dst,
+			      tun_key->tun_id,
+			      tun_key->tun_flags,
+			      tun_info->options,
+			      tun_info->options_len);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info);
 
 int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
-				  struct ovs_tunnel_info *info)
+				  struct ip_tunnel_info *info)
 {
 	/* get_egress_tun_info() is only implemented on tunnel ports. */
 	if (unlikely(!vport->ops->get_egress_tun_info))

index bc85331..4750fb6 100644
@@ -58,15 +58,15 @@ u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *);
 
 int ovs_vport_send(struct vport *, struct sk_buff *);
 
-int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+int ovs_tunnel_get_egress_info(struct ip_tunnel_info *egress_tun_info,
 			       struct net *net,
-			       const struct ovs_tunnel_info *tun_info,
+			       const struct ip_tunnel_info *tun_info,
 			       u8 ipproto,
 			       u32 skb_mark,
 			       __be16 tp_src,
 			       __be16 tp_dst);
 int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
-				  struct ovs_tunnel_info *info);
+				  struct ip_tunnel_info *info);
 
 /* The following definitions are for implementers of vport devices: */
 

@@ -176,7 +176,7 @@ struct vport_ops {
 
 	int (*send)(struct vport *, struct sk_buff *);
 	int (*get_egress_tun_info)(struct vport *, struct sk_buff *,
-				   struct ovs_tunnel_info *);
+				   struct ip_tunnel_info *);
 
 	struct module *owner;
 	struct list_head list;

@@ -226,7 +226,7 @@ static inline struct vport *vport_from_priv(void *priv)
 }
 
 void ovs_vport_receive(struct vport *, struct sk_buff *,
-		       const struct ovs_tunnel_info *);
+		       const struct ip_tunnel_info *);
 
 static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
 				      const void *start, unsigned int len)

@@ -239,7 +239,7 @@ int ovs_vport_ops_register(struct vport_ops *ops);
 void ovs_vport_ops_unregister(struct vport_ops *ops);
 
 static inline struct rtable *ovs_tunnel_route_lookup(struct net *net,
-						     const struct ovs_key_ipv4_tunnel *key,
+						     const struct ip_tunnel_key *key,
 						     u32 mark,
 						     struct flowi4 *fl,
 						     u8 protocol)

index 2bc73f8a..fd69bb9 100644
@@ -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 +357,8 @@ 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 +460,7 @@ 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 {

new file mode 100644
index 0000000..4f7694f
@@ -0,0 +1,32 @@
+#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;
+};
+
+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 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 */

index 6778a99..97f6d47 100644
@@ -7640,7 +7640,7 @@ static int __init net_dev_init(void)
 	open_softirq(NET_RX_SOFTIRQ, net_rx_action);
 
 	hotcpu_notifier(dev_cpu_callback, 0);
-	dst_init();
+	dst_subsys_init();
 	rc = 0;
 out:
 	return rc;

107 lines not on this page · raw message

index 2db4c87..f4fc8a7 100644
@@ -146,6 +146,7 @@
 #include <net/xfrm.h>
 #include <linux/mroute.h>
 #include <linux/netlink.h>
+#include <net/dst_metadata.h>
 
 /*
  *	Process Router Attention IP option (RFC 2113)

@@ -331,7 +332,7 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb)
 	 *	Initialise the virtual path cache for the packet. It describes
 	 *	how the packet travels inside Linux networking.
 	 */
-	if (!skb_dst(skb)) {
+	if (!skb_valid_dst(skb)) {
 		int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
 					       iph->tos, skb->dev);
 		if (unlikely(err)) {

index d3964fa..ea48880 100644
@@ -1691,6 +1691,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	   by fib_lookup.
 	 */
 
+	skb_dst_drop(skb);
+
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
 		goto martian_source;
 

index 933a928..3400aea 100644
@@ -291,6 +291,46 @@ static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb)
 	kfree_skb(skb);
 }
 
+/*
+ *	Create and send an arp packet.
+ */
+static void arp_send_dst(int type, int ptype, __be32 dest_ip,
+			 struct net_device *dev, __be32 src_ip,
+			 const unsigned char *dest_hw,
+			 const unsigned char *src_hw,
+			 const unsigned char *target_hw, struct sk_buff *oskb)
+{
+	struct sk_buff *skb;
+
+	/*
+	 *	No arp on this interface.
+	 */
+
+	if (dev->flags&IFF_NOARP)
+		return;
+
+	skb = arp_create(type, ptype, dest_ip, dev, src_ip,
+			 dest_hw, src_hw, target_hw);
+	if (!skb)
+		return;
+
+	if (oskb)
+		skb_dst_copy(skb, oskb);
+
+	arp_xmit(skb);
+}
+
+void arp_send(int type, int ptype, __be32 dest_ip,
+	      struct net_device *dev, __be32 src_ip,
+	      const unsigned char *dest_hw, const unsigned char *src_hw,
+	      const unsigned char *target_hw)
+{
+	arp_send_dst(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw,
+		     target_hw, NULL);
+}
+EXPORT_SYMBOL(arp_send);
+
+
 static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
 {
 	__be32 saddr = 0;

@@ -346,8 +386,9 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
 		}
 	}
 
-	arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr,
-		 dst_hw, dev->dev_addr, NULL);
+	arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr,
+		     dst_hw, dev->dev_addr, NULL,
+		     dev->priv_flags & IFF_XMIT_DST_RELEASE ? NULL : skb);
 }
 
 static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip)

@@ -597,32 +638,6 @@ void arp_xmit(struct sk_buff *skb)
 EXPORT_SYMBOL(arp_xmit);
 
 /*
- *	Create and send an arp packet.
- */
-void arp_send(int type, int ptype, __be32 dest_ip,
-	      struct net_device *dev, __be32 src_ip,
-	      const unsigned char *dest_hw, const unsigned char *src_hw,
-	      const unsigned char *target_hw)
-{
-	struct sk_buff *skb;
-
-	/*
-	 *	No arp on this interface.
-	 */
-
-	if (dev->flags&IFF_NOARP)
-		return;
-
-	skb = arp_create(type, ptype, dest_ip, dev, src_ip,
-			 dest_hw, src_hw, target_hw);
-	if (!skb)
-		return;
-
-	arp_xmit(skb);
-}
-EXPORT_SYMBOL(arp_send);
-
-/*
  *	Process an arp request.
  */
 

index 34c519e..4dfb8a7 100644
@@ -49,6 +49,7 @@
 #include <net/ip6_tunnel.h>
 #include <net/ip6_checksum.h>
 #endif
+#include <net/dst_metadata.h>
 
 #define VXLAN_VERSION	"0.1"
 

@@ -1164,10 +1165,13 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh,
 /* Callback from net/ipv4/udp.c to receive packets */
 static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
+	struct metadata_dst *tun_dst = NULL;
+	struct ip_tunnel_info *info;
 	struct vxlan_sock *vs;
 	struct vxlanhdr *vxh;
 	u32 flags, vni;
-	struct vxlan_metadata md = {0};
+	struct vxlan_metadata _md;
+	struct vxlan_metadata *md = &_md;
 
 	/* Need Vxlan and inner Ethernet header to be present */
 	if (!pskb_may_pull(skb, VXLAN_HLEN))

@@ -1202,6 +1206,33 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		vni &= VXLAN_VNI_MASK;
 	}
 
+	if (vs->flags & VXLAN_F_FLOW_BASED) {
+		const struct iphdr *iph = ip_hdr(skb);
+
+		tun_dst = metadata_dst_alloc(sizeof(*md), GFP_ATOMIC);
+		if (!tun_dst)
+			goto drop;
+
+		info = &tun_dst->u.tun_info;
+		info->key.ipv4_src = iph->saddr;
+		info->key.ipv4_dst = iph->daddr;
+		info->key.ipv4_tos = iph->tos;
+		info->key.ipv4_ttl = iph->ttl;
+		info->key.tp_src = udp_hdr(skb)->source;
+		info->key.tp_dst = udp_hdr(skb)->dest;
+
+		info->mode = IP_TUNNEL_INFO_RX;
+		info->key.tun_flags = TUNNEL_KEY;
+		info->key.tun_id = cpu_to_be64(vni >> 8);
+		if (udp_hdr(skb)->check != 0)
+			info->key.tun_flags |= TUNNEL_CSUM;
+
+		md = ip_tunnel_info_opts(info, sizeof(*md));
+		md->tun_dst = tun_dst;
+	} else {
+		memset(md, 0, sizeof(*md));
+	}
+
 	/* For backwards compatibility, only allow reserved fields to be
 	 * used by VXLAN extensions if explicitly requested.
 	 */

@@ -1209,13 +1240,16 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		struct vxlanhdr_gbp *gbp;
 
 		gbp = (struct vxlanhdr_gbp *)vxh;
-		md.gbp = ntohs(gbp->policy_id);
+		md->gbp = ntohs(gbp->policy_id);
+
+		if (tun_dst)
+			info->key.tun_flags |= TUNNEL_VXLAN_OPT;
 
 		if (gbp->dont_learn)
-			md.gbp |= VXLAN_GBP_DONT_LEARN;
+			md->gbp |= VXLAN_GBP_DONT_LEARN;
 
 		if (gbp->policy_applied)
-			md.gbp |= VXLAN_GBP_POLICY_APPLIED;
+			md->gbp |= VXLAN_GBP_POLICY_APPLIED;
 
 		flags &= ~VXLAN_GBP_USED_BITS;
 	}

@@ -1233,8 +1267,8 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		goto bad_flags;
 	}
 
-	md.vni = vxh->vx_vni;
-	vs->rcv(vs, skb, &md);
+	md->vni = vxh->vx_vni;
+	vs->rcv(vs, skb, md);
 	return 0;
 
 drop:

@@ -1247,6 +1281,9 @@ bad_flags:
 		   ntohl(vxh->vx_flags), ntohl(vxh->vx_vni));
 
 error:
+	if (tun_dst)
+		dst_release((struct dst_entry *)tun_dst);
+
 	/* Return non vxlan pkt */
 	return 1;
 }

@@ -1263,7 +1300,12 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
 	int err = 0;
 	union vxlan_addr *remote_ip;
 
-	vni = ntohl(md->vni) >> 8;
+	/* For flow based devices, map all packets to VNI 0 */
+	if (vs->flags & VXLAN_F_FLOW_BASED)
+		vni = 0;
+	else
+		vni = ntohl(md->vni) >> 8;
+
 	/* Is this VNI defined? */
 	vxlan = vxlan_vs_find_vni(vs, vni);
 	if (!vxlan)

@@ -1292,12 +1334,19 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
 #endif
 	}
 
+	if (md->tun_dst) {
+		skb_dst_set(skb, (struct dst_entry *)md->tun_dst);
+		md->tun_dst = NULL;
+	}
+
 	if ((vxlan->flags & VXLAN_F_LEARN) &&
 	    vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source))
 		goto drop;
 
 	skb_reset_network_header(skb);
-	skb->mark = md->gbp;
+	/* In flow-based mode, GBP is carried in dst_metadata */
+	if (!(vs->flags & VXLAN_F_FLOW_BASED))
+		skb->mark = md->gbp;
 
 	if (oip6)
 		err = IP6_ECN_decapsulate(oip6, skb);

@@ -1330,6 +1379,9 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
 
 	return;
 drop:
+	if (md->tun_dst)
+		dst_release((struct dst_entry *)md->tun_dst);
+
 	/* Consume bad packet */
 	kfree_skb(skb);
 }

@@ -1878,22 +1930,40 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			   struct vxlan_rdst *rdst, bool did_rsc)
 {
+	struct ip_tunnel_info *info = skb_tunnel_info(skb);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct sock *sk = vxlan->vn_sock->sock->sk;
 	struct rtable *rt = NULL;
 	const struct iphdr *old_iph;
 	struct flowi4 fl4;
 	union vxlan_addr *dst;
-	struct vxlan_metadata md;
+	union vxlan_addr remote_ip;
+	struct vxlan_metadata _md;
+	struct vxlan_metadata *md = &_md;
 	__be16 src_port = 0, dst_port;
 	u32 vni;
 	__be16 df = 0;
 	__u8 tos, ttl;
 	int err;
+	u32 flags = vxlan->flags;
+
+	if (rdst) {
+		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port;
+		vni = rdst->remote_vni;
+		dst = &rdst->remote_ip;
+	} else {
+		if (!info) {
+			WARN_ONCE(1, "%s: Missing encapsulation instructions\n",
+				  dev->name);
+			goto drop;
+		}
 
-	dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port;
-	vni = rdst->remote_vni;
-	dst = &rdst->remote_ip;
+		dst_port = info->key.tp_dst ? : vxlan->dst_port;
+		vni = be64_to_cpu(info->key.tun_id);
+		remote_ip.sin.sin_family = AF_INET;
+		remote_ip.sin.sin_addr.s_addr = info->key.ipv4_dst;
+		dst = &remote_ip;
+	}
 
 	if (vxlan_addr_any(dst)) {
 		if (did_rsc) {

@@ -1918,8 +1988,25 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 				     vxlan->port_max, true);
 
 	if (dst->sa.sa_family == AF_INET) {
+		if (info) {
+			if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
+				df = htons(IP_DF);
+			if (info->key.tun_flags & TUNNEL_CSUM)
+				flags |= VXLAN_F_UDP_CSUM;
+			else
+				flags &= ~VXLAN_F_UDP_CSUM;
+
+			ttl = info->key.ipv4_ttl;
+			tos = info->key.ipv4_tos;
+
+			if (info->options_len)
+				md = ip_tunnel_info_opts(info, sizeof(*md));
+		} else {
+			md->gbp = skb->mark;
+		}
+
 		memset(&fl4, 0, sizeof(fl4));
-		fl4.flowi4_oif = rdst->remote_ifindex;
+		fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0;
 		fl4.flowi4_tos = RT_TOS(tos);
 		fl4.flowi4_mark = skb->mark;
 		fl4.flowi4_proto = IPPROTO_UDP;

@@ -1958,14 +2045,12 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
-		md.vni = htonl(vni << 8);
-		md.gbp = skb->mark;
-
+		md->vni = htonl(vni << 8);
 		err = vxlan_xmit_skb(rt, sk, skb, fl4.saddr,
 				     dst->sin.sin_addr.s_addr, tos, ttl, df,
-				     src_port, dst_port, &md,
+				     src_port, dst_port, md,
 				     !net_eq(vxlan->net, dev_net(vxlan->dev)),
-				     vxlan->flags);
+				     flags);
 		if (err < 0) {
 			/* skb is already freed. */
 			skb = NULL;

@@ -1980,7 +2065,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		u32 flags;
 
 		memset(&fl6, 0, sizeof(fl6));
-		fl6.flowi6_oif = rdst->remote_ifindex;
+		fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0;
 		fl6.daddr = dst->sin6.sin6_addr;
 		fl6.saddr = vxlan->saddr.sin6.sin6_addr;
 		fl6.flowi6_mark = skb->mark;

@@ -2018,11 +2103,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		}
 
 		ttl = ttl ? : ip6_dst_hoplimit(ndst);
-		md.vni = htonl(vni << 8);
-		md.gbp = skb->mark;
+		md->vni = htonl(vni << 8);
+		md->gbp = skb->mark;
 
 		err = vxlan6_xmit_skb(ndst, sk, skb, dev, &fl6.saddr, &fl6.daddr,
-				      0, ttl, src_port, dst_port, &md,
+				      0, ttl, src_port, dst_port, md,
 				      !net_eq(vxlan->net, dev_net(vxlan->dev)),
 				      vxlan->flags);
 #endif

@@ -2051,6 +2136,7 @@ tx_free:
 static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	const struct ip_tunnel_info *info = skb_tunnel_info(skb);
 	struct ethhdr *eth;
 	bool did_rsc = false;
 	struct vxlan_rdst *rdst, *fdst = NULL;

@@ -2078,6 +2164,12 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 #endif
 	}
 
+	if (vxlan->flags & VXLAN_F_FLOW_BASED &&
+	    info && info->mode == IP_TUNNEL_INFO_TX) {
+		vxlan_xmit_one(skb, dev, NULL, false);
+		return NETDEV_TX_OK;
+	}
+
 	f = vxlan_find_mac(vxlan, eth->h_dest);
 	did_rsc = false;
 

@@ -2373,6 +2465,12 @@ static void vxlan_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
+	/* If in flow based mode, keep the dst including encapsulation
+	 * instructions for vxlan_xmit().
+	 */
+	if (vxlan->flags & VXLAN_F_FLOW_BASED)
+		netif_keep_dst(dev);
+
 	INIT_LIST_HEAD(&vxlan->next);
 	spin_lock_init(&vxlan->hash_lock);
 

@@ -2405,6 +2503,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_RSC]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_L2MISS]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_L3MISS]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_FLOWBASED]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_PORT]	= { .type = NLA_U16 },
 	[IFLA_VXLAN_UDP_CSUM]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]	= { .type = NLA_U8 },

@@ -2681,6 +2780,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (data[IFLA_VXLAN_LIMIT])
 		vxlan->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]);
 
+	if (data[IFLA_VXLAN_FLOWBASED] && nla_get_u8(data[IFLA_VXLAN_FLOWBASED]))
+		vxlan->flags |= VXLAN_F_FLOW_BASED;
+
 	if (data[IFLA_VXLAN_PORT_RANGE]) {
 		const struct ifla_vxlan_port_range *p
 			= nla_data(data[IFLA_VXLAN_PORT_RANGE]);

@@ -2777,6 +2879,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_RSC */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_L2MISS */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_L3MISS */
+		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_FLOWBASED */
 		nla_total_size(sizeof(__u32)) +	/* IFLA_VXLAN_AGEING */
 		nla_total_size(sizeof(__u32)) +	/* IFLA_VXLAN_LIMIT */
 		nla_total_size(sizeof(struct ifla_vxlan_port_range)) +

@@ -2843,6 +2946,8 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			!!(vxlan->flags & VXLAN_F_L2MISS)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_L3MISS,
 			!!(vxlan->flags & VXLAN_F_L3MISS)) ||
+	    nla_put_u8(skb, IFLA_VXLAN_FLOWBASED,
+			!!(vxlan->flags & VXLAN_F_FLOW_BASED)) ||
 	    nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->age_interval) ||
 	    nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->addrmax) ||
 	    nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->dst_port) ||

index d6cdd6e..ce079c2 100644
@@ -3468,5 +3468,6 @@ 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 */

index 4f7694f..e843937 100644
@@ -8,6 +8,9 @@
 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)

@@ -20,6 +23,16 @@ static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
 	return NULL;
 }
 
+static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
+{
+	struct metadata_dst *md_dst = skb_metadata_dst(skb);
+
+	if (md_dst)
+		return &md_dst->u.tun_info;
+
+	return NULL;
+}
+
 static inline bool skb_valid_dst(const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);

index 6b9d559..d11530f 100644
@@ -38,10 +38,19 @@ struct ip_tunnel_key {
 	__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 */

@@ -284,6 +293,11 @@ 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;
+}
+
 #endif /* CONFIG_INET */
 
 #endif /* __NET_IP_TUNNELS_H */

index 0082b5d..b262bfa 100644
@@ -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)

@@ -97,6 +98,9 @@ struct vxlanhdr {
 struct vxlan_metadata {
 	__be32		vni;
 	u32		gbp;
+
+	/* Temporary until vxlan_rcv() API is gone */
+	struct metadata_dst *tun_dst;
 };
 
 struct vxlan_sock;

@@ -130,6 +134,7 @@ struct vxlan_sock {
 #define VXLAN_F_REMCSUM_RX		0x400
 #define VXLAN_F_GBP			0x800
 #define VXLAN_F_REMCSUM_NOPARTIAL	0x1000
+#define VXLAN_F_FLOW_BASED		0x2000
 
 /* Flags that are used in the receive path. These flags must match in
  * order for a socket to be shareable

@@ -137,7 +142,8 @@ 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)
+					 VXLAN_F_REMCSUM_NOPARTIAL |	\
+					 VXLAN_F_FLOW_BASED)
 
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 				  vxlan_rcv_t *rcv, void *data,

index 2c7e8e3..392f9fa 100644
@@ -381,6 +381,7 @@ 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)

index 8109a15..c15fb5e 100644
@@ -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;

@@ -165,6 +171,7 @@ 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)

index ea48880..bf84164c 100644
@@ -91,6 +91,7 @@
 #include <linux/slab.h>
 #include <linux/jhash.h>
 #include <net/dst.h>
+#include <net/dst_metadata.h>
 #include <net/net_namespace.h>
 #include <net/protocol.h>
 #include <net/ip.h>

@@ -110,6 +111,7 @@
 #include <linux/kmemleak.h>
 #endif
 #include <net/secure_seq.h>
+#include <net/ip_tunnels.h>
 
 #define RT_FL_TOS(oldflp4) \
 	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))

@@ -1674,6 +1676,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 {
 	struct fib_result res;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	struct ip_tunnel_info *tun_info;
 	struct flowi4	fl4;
 	unsigned int	flags = 0;
 	u32		itag = 0;

@@ -1691,6 +1694,9 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	   by fib_lookup.
 	 */
 
+	tun_info = skb_tunnel_info(skb);
+	if (tun_info && tun_info->mode == IP_TUNNEL_INFO_RX)
+		fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id;
 	skb_dst_drop(skb);
 
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))

index 4dfb8a7..773b6bf 100644
@@ -1930,7 +1930,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			   struct vxlan_rdst *rdst, bool did_rsc)
 {
-	struct ip_tunnel_info *info = skb_tunnel_info(skb);
+	struct ip_tunnel_info *info;
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct sock *sk = vxlan->vn_sock->sock->sk;
 	struct rtable *rt = NULL;

@@ -1947,6 +1947,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	int err;
 	u32 flags = vxlan->flags;
 
+	/* FIXME: Support IPv6 */
+	info = skb_tunnel_info(skb, AF_INET);
+
 	if (rdst) {
 		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port;
 		vni = rdst->remote_vni;

@@ -2136,12 +2139,15 @@ tx_free:
 static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	const struct ip_tunnel_info *info = skb_tunnel_info(skb);
+	const struct ip_tunnel_info *info;
 	struct ethhdr *eth;
 	bool did_rsc = false;
 	struct vxlan_rdst *rdst, *fdst = NULL;
 	struct vxlan_fdb *f;
 
+	/* FIXME: Support IPv6 */
+	info = skb_tunnel_info(skb, AF_INET);
+
 	skb_reset_mac_header(skb);
 	eth = eth_hdr(skb);
 

index e843937..fc03491 100644
@@ -23,13 +23,23 @@ static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
 	return NULL;
 }
 
-static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
+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;
 }
 

index d11530f..0b7e18c 100644
@@ -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>

@@ -298,6 +298,11 @@ 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;
+}
+
 #endif /* CONFIG_INET */
 
 #endif /* __NET_IP_TUNNELS_H */

index aa611d9..31377bb 100644
@@ -6,6 +6,7 @@
 enum lwtunnel_encap_types {
 	LWTUNNEL_ENCAP_NONE,
 	LWTUNNEL_ENCAP_MPLS,
+	LWTUNNEL_ENCAP_IP,
 	__LWTUNNEL_ENCAP_MAX,
 };
 

index 0d3d3cc..47d24cb 100644
@@ -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,

117 lines not on this page · raw message

index bf84164c..af8c7cd 100644
@@ -1694,7 +1694,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	   by fib_lookup.
 	 */
 
-	tun_info = skb_tunnel_info(skb);
+	tun_info = skb_tunnel_info(skb, AF_INET);
 	if (tun_info && tun_info->mode == IP_TUNNEL_INFO_RX)
 		fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id;
 	skb_dst_drop(skb);

index 4750fb6..75d6824 100644
@@ -27,6 +27,7 @@
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
 #include <linux/u64_stats_sync.h>
+#include <net/route.h>
 
 #include "datapath.h"
 

index 903a55e..4e8f804 100644
@@ -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;
 

index 2b82d7e..96161b8 100644
@@ -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 */

index 9a12668..6da78c9 100644
@@ -186,6 +186,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 	if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
 		goto out;
 
+	if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id))
+		goto out;
+
 	ret = ops->match(rule, fl, flags);
 out:
 	return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;

@@ -330,6 +333,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 	if (tb[FRA_FWMASK])
 		rule->mark_mask = nla_get_u32(tb[FRA_FWMASK]);
 
+	if (tb[FRA_TUN_ID])
+		rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
+
 	rule->action = frh->action;
 	rule->flags = frh->flags;
 	rule->table = frh_get_table(frh, tb);

@@ -473,6 +479,10 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 		    (rule->mark_mask != nla_get_u32(tb[FRA_FWMASK])))
 			continue;
 
+		if (tb[FRA_TUN_ID] &&
+		    (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID])))
+			continue;
+
 		if (!ops->compare(rule, frh, tb))
 			continue;
 

@@ -535,7 +545,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 			 + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */
 			 + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
 			 + nla_total_size(4) /* FRA_FWMARK */
-			 + nla_total_size(4); /* FRA_FWMASK */
+			 + nla_total_size(4) /* FRA_FWMASK */
+			 + nla_total_size(8); /* FRA_TUN_ID */
 
 	if (ops->nlmsg_payload)
 		payload += ops->nlmsg_payload(rule);

@@ -591,7 +602,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	    ((rule->mark_mask || rule->mark) &&
 	     nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) ||
 	    (rule->target &&
-	     nla_put_u32(skb, FRA_GOTO, rule->target)))
+	     nla_put_u32(skb, FRA_GOTO, rule->target)) ||
+	    (rule->tun_id &&
+	     nla_put_be64(skb, FRA_TUN_ID, rule->tun_id)))
 		goto nla_put_failure;
 
 	if (rule->suppress_ifgroup != -1) {

index 773b6bf..020c941 100644
@@ -55,10 +55,6 @@
 
 #define PORT_HASH_BITS	8
 #define PORT_HASH_SIZE  (1<<PORT_HASH_BITS)
-#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)
 #define FDB_AGE_DEFAULT 300 /* 5 min */
 #define FDB_AGE_INTERVAL (10 * HZ)	/* rescan interval */
 

@@ -75,6 +71,7 @@ module_param(log_ecn_error, bool, 0644);
 MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
 
 static int vxlan_net_id;
+static struct rtnl_link_ops vxlan_link_ops;
 
 static const u8 all_zeros_mac[ETH_ALEN];
 

@@ -85,21 +82,6 @@ struct vxlan_net {
 	spinlock_t	  sock_lock;
 };
 
-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;
-};
-
 /* Forwarding table entry */
 struct vxlan_fdb {
 	struct hlist_node hlist;	/* linked list of entries */

@@ -112,31 +94,6 @@ struct vxlan_fdb {
 	u8		  eth_addr[ETH_ALEN];
 };
 
-/* 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 */
-	union vxlan_addr  saddr;	/* source address */
-	__be16		  dst_port;
-	__u16		  port_min;	/* source port range */
-	__u16		  port_max;
-	__u8		  tos;		/* TOS override */
-	__u8		  ttl;
-	u32		  flags;	/* VXLAN_F_* in vxlan.h */
-
-	unsigned long	  age_interval;
-	struct timer_list age_timer;
-	spinlock_t	  hash_lock;
-	unsigned int	  addrcnt;
-	unsigned int	  addrmax;
-
-	struct hlist_head fdb_head[FDB_HASH_SIZE];
-};
-
 /* salt for hash table */
 static u32 vxlan_salt __read_mostly;
 static struct workqueue_struct *vxlan_wq;

@@ -346,7 +303,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 	if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip))
 		goto nla_put_failure;
 
-	if (rdst->remote_port && rdst->remote_port != vxlan->dst_port &&
+	if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port &&
 	    nla_put_be16(skb, NDA_PORT, rdst->remote_port))
 		goto nla_put_failure;
 	if (rdst->remote_vni != vxlan->default_dst.remote_vni &&

@@ -750,7 +707,8 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		if (!(flags & NLM_F_CREATE))
 			return -ENOENT;
 
-		if (vxlan->addrmax && vxlan->addrcnt >= vxlan->addrmax)
+		if (vxlan->cfg.addrmax &&
+		    vxlan->addrcnt >= vxlan->cfg.addrmax)
 			return -ENOSPC;
 
 		/* Disallow replace to add a multicast entry */

@@ -836,7 +794,7 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
 			return -EINVAL;
 		*port = nla_get_be16(tb[NDA_PORT]);
 	} else {
-		*port = vxlan->dst_port;
+		*port = vxlan->cfg.dst_port;
 	}
 
 	if (tb[NDA_VNI]) {

@@ -1022,7 +980,7 @@ static bool vxlan_snoop(struct net_device *dev,
 			vxlan_fdb_create(vxlan, src_mac, src_ip,
 					 NUD_REACHABLE,
 					 NLM_F_EXCL|NLM_F_CREATE,
-					 vxlan->dst_port,
+					 vxlan->cfg.dst_port,
 					 vxlan->default_dst.remote_vni,
 					 0, NTF_SELF);
 		spin_unlock(&vxlan->hash_lock);

@@ -1951,7 +1909,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	info = skb_tunnel_info(skb, AF_INET);
 
 	if (rdst) {
-		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port;
+		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
 		vni = rdst->remote_vni;
 		dst = &rdst->remote_ip;
 	} else {

@@ -1961,7 +1919,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto drop;
 		}
 
-		dst_port = info->key.tp_dst ? : vxlan->dst_port;
+		dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
 		vni = be64_to_cpu(info->key.tun_id);
 		remote_ip.sin.sin_family = AF_INET;
 		remote_ip.sin.sin_addr.s_addr = info->key.ipv4_dst;

@@ -1979,16 +1937,16 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 	old_iph = ip_hdr(skb);
 
-	ttl = vxlan->ttl;
+	ttl = vxlan->cfg.ttl;
 	if (!ttl && vxlan_addr_multicast(dst))
 		ttl = 1;
 
-	tos = vxlan->tos;
+	tos = vxlan->cfg.tos;
 	if (tos == 1)
 		tos = ip_tunnel_get_dsfield(old_iph, skb);
 
-	src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->port_min,
-				     vxlan->port_max, true);
+	src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
+				     vxlan->cfg.port_max, true);
 
 	if (dst->sa.sa_family == AF_INET) {
 		if (info) {

@@ -2014,7 +1972,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		fl4.flowi4_mark = skb->mark;
 		fl4.flowi4_proto = IPPROTO_UDP;
 		fl4.daddr = dst->sin.sin_addr.s_addr;
-		fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr;
+		fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr;
 
 		rt = ip_route_output_key(vxlan->net, &fl4);
 		if (IS_ERR(rt)) {

@@ -2070,7 +2028,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0;
 		fl6.daddr = dst->sin6.sin6_addr;
-		fl6.saddr = vxlan->saddr.sin6.sin6_addr;
+		fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr;
 		fl6.flowi6_mark = skb->mark;
 		fl6.flowi6_proto = IPPROTO_UDP;
 

@@ -2241,7 +2199,7 @@ static void vxlan_cleanup(unsigned long arg)
 			if (f->state & NUD_PERMANENT)
 				continue;
 
-			timeout = f->used + vxlan->age_interval * HZ;
+			timeout = f->used + vxlan->cfg.age_interval * HZ;
 			if (time_before_eq(timeout, jiffies)) {
 				netdev_dbg(vxlan->dev,
 					   "garbage collect %pM\n",

@@ -2305,8 +2263,8 @@ static int vxlan_open(struct net_device *dev)
 	struct vxlan_sock *vs;
 	int ret = 0;
 
-	vs = vxlan_sock_add(vxlan->net, vxlan->dst_port, vxlan_rcv, NULL,
-			    false, vxlan->flags);
+	vs = vxlan_sock_add(vxlan->net, vxlan->cfg.dst_port, vxlan_rcv,
+			    NULL, vxlan->cfg.no_share, vxlan->flags);
 	if (IS_ERR(vs))
 		return PTR_ERR(vs);
 

@@ -2320,7 +2278,7 @@ static int vxlan_open(struct net_device *dev)
 		}
 	}
 
-	if (vxlan->age_interval)
+	if (vxlan->cfg.age_interval)
 		mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL);
 
 	return ret;

@@ -2484,7 +2442,7 @@ static void vxlan_setup(struct net_device *dev)
 	vxlan->age_timer.function = vxlan_cleanup;
 	vxlan->age_timer.data = (unsigned long) vxlan;
 
-	vxlan->dst_port = htons(vxlan_port);
+	vxlan->cfg.dst_port = htons(vxlan_port);
 
 	vxlan->dev = dev;
 

@@ -2684,54 +2642,35 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 }
 EXPORT_SYMBOL_GPL(vxlan_sock_add);
 
-static int vxlan_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[])
+static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
+			       struct vxlan_config *conf)
 {
 	struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *dst = &vxlan->default_dst;
-	__u32 vni;
 	int err;
 	bool use_ipv6 = false;
-
-	if (!data[IFLA_VXLAN_ID])
-		return -EINVAL;
+	__be16 default_port = vxlan->cfg.dst_port;
 
 	vxlan->net = src_net;
 
-	vni = nla_get_u32(data[IFLA_VXLAN_ID]);
-	dst->remote_vni = vni;
+	dst->remote_vni = conf->vni;
 
-	/* Unless IPv6 is explicitly requested, assume IPv4 */
-	dst->remote_ip.sa.sa_family = AF_INET;
-	if (data[IFLA_VXLAN_GROUP]) {
-		dst->remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]);
-	} else if (data[IFLA_VXLAN_GROUP6]) {
-		if (!IS_ENABLED(CONFIG_IPV6))
-			return -EPFNOSUPPORT;
-
-		dst->remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]);
-		dst->remote_ip.sa.sa_family = AF_INET6;
-		use_ipv6 = true;
-	}
+	memcpy(&dst->remote_ip, &conf->remote_ip, sizeof(conf->remote_ip));
 
-	if (data[IFLA_VXLAN_LOCAL]) {
-		vxlan->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]);
-		vxlan->saddr.sa.sa_family = AF_INET;
-	} else if (data[IFLA_VXLAN_LOCAL6]) {
-		if (!IS_ENABLED(CONFIG_IPV6))
-			return -EPFNOSUPPORT;
+	/* Unless IPv6 is explicitly requested, assume IPv4 */
+	if (!dst->remote_ip.sa.sa_family)
+		dst->remote_ip.sa.sa_family = AF_INET;
 
-		/* TODO: respect scope id */
-		vxlan->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]);
-		vxlan->saddr.sa.sa_family = AF_INET6;
+	if (dst->remote_ip.sa.sa_family == AF_INET6 ||
+	    vxlan->cfg.saddr.sa.sa_family == AF_INET6)
 		use_ipv6 = true;
-	}
 
-	if (data[IFLA_VXLAN_LINK] &&
-	    (dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) {
+	if (conf->remote_ifindex) {
 		struct net_device *lowerdev
-			 = __dev_get_by_index(src_net, dst->remote_ifindex);
+			 = __dev_get_by_index(src_net, conf->remote_ifindex);
+
+		dst->remote_ifindex = conf->remote_ifindex;
 
 		if (!lowerdev) {
 			pr_info("ifindex %d does not exist\n", dst->remote_ifindex);

@@ -2749,7 +2688,7 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 		}
 #endif
 
-		if (!tb[IFLA_MTU])
+		if (!conf->mtu)
 			dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 
 		dev->needed_headroom = lowerdev->hard_header_len +

@@ -2757,104 +2696,187 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	} else if (use_ipv6)
 		vxlan->flags |= VXLAN_F_IPV6;
 
+	memcpy(&vxlan->cfg, conf, sizeof(*conf));
+	if (!vxlan->cfg.dst_port)
+		vxlan->cfg.dst_port = default_port;
+	vxlan->flags = conf->flags;
+
+	if (!vxlan->cfg.age_interval)
+		vxlan->cfg.age_interval = FDB_AGE_DEFAULT;
+
+	if (vxlan_find_vni(src_net, conf->vni, use_ipv6 ? AF_INET6 : AF_INET,
+			   vxlan->cfg.dst_port, vxlan->flags))
+		return -EEXIST;
+
+	dev->ethtool_ops = &vxlan_ethtool_ops;
+
+	/* create an fdb entry for a valid default destination */
+	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
+		err = vxlan_fdb_create(vxlan, all_zeros_mac,
+				       &vxlan->default_dst.remote_ip,
+				       NUD_REACHABLE|NUD_PERMANENT,
+				       NLM_F_EXCL|NLM_F_CREATE,
+				       vxlan->cfg.dst_port,
+				       vxlan->default_dst.remote_vni,
+				       vxlan->default_dst.remote_ifindex,
+				       NTF_SELF);
+		if (err)
+			return err;
+	}
+
+	err = register_netdevice(dev);
+	if (err) {
+		vxlan_fdb_delete_default(vxlan);
+		return err;
+	}
+
+	list_add(&vxlan->next, &vn->vxlan_list);
+
+	return 0;
+}
+
+struct net_device *vxlan_dev_create(struct net *net, const char *name,
+				    u8 name_assign_type, struct vxlan_config *conf)
+{
+	struct nlattr *tb[IFLA_MAX+1];
+	struct net_device *dev;
+	int err;
+
+	memset(&tb, 0, sizeof(tb));
+
+	dev = rtnl_create_link(net, name, name_assign_type,
+			       &vxlan_link_ops, tb);
+	if (IS_ERR(dev))
+		return dev;
+
+	err = vxlan_dev_configure(net, dev, conf);
+	if (err < 0) {
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
+
+	return dev;
+}
+EXPORT_SYMBOL_GPL(vxlan_dev_create);
+
+static int vxlan_newlink(struct net *src_net, struct net_device *dev,
+			 struct nlattr *tb[], struct nlattr *data[])
+{
+	struct vxlan_config conf;
+	int err;
+
+	if (!data[IFLA_VXLAN_ID])
+		return -EINVAL;
+
+	memset(&conf, 0, sizeof(conf));
+	conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]);
+
+	if (data[IFLA_VXLAN_GROUP]) {
+		conf.remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]);
+	} else if (data[IFLA_VXLAN_GROUP6]) {
+		if (!IS_ENABLED(CONFIG_IPV6))
+			return -EPFNOSUPPORT;
+
+		conf.remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]);
+		conf.remote_ip.sa.sa_family = AF_INET6;
+	}
+
+	if (data[IFLA_VXLAN_LOCAL]) {
+		conf.saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]);
+		conf.saddr.sa.sa_family = AF_INET;
+	} else if (data[IFLA_VXLAN_LOCAL6]) {
+		if (!IS_ENABLED(CONFIG_IPV6))
+			return -EPFNOSUPPORT;
+
+		/* TODO: respect scope id */
+		conf.saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]);
+		conf.saddr.sa.sa_family = AF_INET6;
+	}
+
+	if (data[IFLA_VXLAN_LINK])
+		conf.remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]);
+
 	if (data[IFLA_VXLAN_TOS])
-		vxlan->tos  = nla_get_u8(data[IFLA_VXLAN_TOS]);
+		conf.tos  = nla_get_u8(data[IFLA_VXLAN_TOS]);
 
 	if (data[IFLA_VXLAN_TTL])
-		vxlan->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]);
+		conf.ttl = nla_get_u8(data[IFLA_VXLAN_TTL]);
 
 	if (!data[IFLA_VXLAN_LEARNING] || nla_get_u8(data[IFLA_VXLAN_LEARNING]))
-		vxlan->flags |= VXLAN_F_LEARN;
+		conf.flags |= VXLAN_F_LEARN;
 
 	if (data[IFLA_VXLAN_AGEING])
-		vxlan->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]);
-	else
-		vxlan->age_interval = FDB_AGE_DEFAULT;
+		conf.age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]);
 
 	if (data[IFLA_VXLAN_PROXY] && nla_get_u8(data[IFLA_VXLAN_PROXY]))
-		vxlan->flags |= VXLAN_F_PROXY;
+		conf.flags |= VXLAN_F_PROXY;
 
 	if (data[IFLA_VXLAN_RSC] && nla_get_u8(data[IFLA_VXLAN_RSC]))
-		vxlan->flags |= VXLAN_F_RSC;
+		conf.flags |= VXLAN_F_RSC;
 
 	if (data[IFLA_VXLAN_L2MISS] && nla_get_u8(data[IFLA_VXLAN_L2MISS]))
-		vxlan->flags |= VXLAN_F_L2MISS;
+		conf.flags |= VXLAN_F_L2MISS;
 
 	if (data[IFLA_VXLAN_L3MISS] && nla_get_u8(data[IFLA_VXLAN_L3MISS]))
-		vxlan->flags |= VXLAN_F_L3MISS;
+		conf.flags |= VXLAN_F_L3MISS;
 
 	if (data[IFLA_VXLAN_LIMIT])
-		vxlan->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]);
+		conf.addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]);
 
 	if (data[IFLA_VXLAN_FLOWBASED] && nla_get_u8(data[IFLA_VXLAN_FLOWBASED]))
-		vxlan->flags |= VXLAN_F_FLOW_BASED;
+		conf.flags |= VXLAN_F_FLOW_BASED;
 
 	if (data[IFLA_VXLAN_PORT_RANGE]) {
 		const struct ifla_vxlan_port_range *p
 			= nla_data(data[IFLA_VXLAN_PORT_RANGE]);
-		vxlan->port_min = ntohs(p->low);
-		vxlan->port_max = ntohs(p->high);
+		conf.port_min = ntohs(p->low);
+		conf.port_max = ntohs(p->high);
 	}
 
 	if (data[IFLA_VXLAN_PORT])
-		vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]);
+		conf.dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]);
 
 	if (data[IFLA_VXLAN_UDP_CSUM] && nla_get_u8(data[IFLA_VXLAN_UDP_CSUM]))
-		vxlan->flags |= VXLAN_F_UDP_CSUM;
+		conf.flags |= VXLAN_F_UDP_CSUM;
 
 	if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] &&
 	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]))
-		vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_TX;
+		conf.flags |= VXLAN_F_UDP_ZERO_CSUM6_TX;
 
 	if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] &&
 	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
-		vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
+		conf.flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
 
 	if (data[IFLA_VXLAN_REMCSUM_TX] &&
 	    nla_get_u8(data[IFLA_VXLAN_REMCSUM_TX]))
-		vxlan->flags |= VXLAN_F_REMCSUM_TX;
+		conf.flags |= VXLAN_F_REMCSUM_TX;
 
 	if (data[IFLA_VXLAN_REMCSUM_RX] &&
 	    nla_get_u8(data[IFLA_VXLAN_REMCSUM_RX]))
-		vxlan->flags |= VXLAN_F_REMCSUM_RX;
+		conf.flags |= VXLAN_F_REMCSUM_RX;
 
 	if (data[IFLA_VXLAN_GBP])
-		vxlan->flags |= VXLAN_F_GBP;
+		conf.flags |= VXLAN_F_GBP;
 
 	if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
-		vxlan->flags |= VXLAN_F_REMCSUM_NOPARTIAL;
+		conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL;
 
-	if (vxlan_find_vni(src_net, vni, use_ipv6 ? AF_INET6 : AF_INET,
-			   vxlan->dst_port, vxlan->flags)) {
-		pr_info("duplicate VNI %u\n", vni);
-		return -EEXIST;
-	}
-
-	dev->ethtool_ops = &vxlan_ethtool_ops;
+	err = vxlan_dev_configure(src_net, dev, &conf);
+	switch (err) {
+	case -ENODEV:
+		pr_info("ifindex %d does not exist\n", conf.remote_ifindex);
+		break;
 
-	/* create an fdb entry for a valid default destination */
-	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
-		err = vxlan_fdb_create(vxlan, all_zeros_mac,
-				       &vxlan->default_dst.remote_ip,
-				       NUD_REACHABLE|NUD_PERMANENT,
-				       NLM_F_EXCL|NLM_F_CREATE,
-				       vxlan->dst_port,
-				       vxlan->default_dst.remote_vni,
-				       vxlan->default_dst.remote_ifindex,
-				       NTF_SELF);
-		if (err)
-			return err;
-	}
+	case -EPERM:
+		pr_info("IPv6 is disabled via sysctl\n");
+		break;
 
-	err = register_netdevice(dev);
-	if (err) {
-		vxlan_fdb_delete_default(vxlan);
-		return err;
+	case -EEXIST:
+		pr_info("duplicate VNI %u\n", conf.vni);
+		break;
 	}
 
-	list_add(&vxlan->next, &vn->vxlan_list);
-
-	return 0;
+	return err;
 }
 
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)

@@ -2903,8 +2925,8 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	const struct vxlan_dev *vxlan = netdev_priv(dev);
 	const struct vxlan_rdst *dst = &vxlan->default_dst;
 	struct ifla_vxlan_port_range ports = {
-		.low =  htons(vxlan->port_min),
-		.high = htons(vxlan->port_max),
+		.low =  htons(vxlan->cfg.port_min),
+		.high = htons(vxlan->cfg.port_max),
 	};
 
 	if (nla_put_u32(skb, IFLA_VXLAN_ID, dst->remote_vni))

@@ -2927,22 +2949,22 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex))
 		goto nla_put_failure;
 
-	if (!vxlan_addr_any(&vxlan->saddr)) {
-		if (vxlan->saddr.sa.sa_family == AF_INET) {
+	if (!vxlan_addr_any(&vxlan->cfg.saddr)) {
+		if (vxlan->cfg.saddr.sa.sa_family == AF_INET) {
 			if (nla_put_in_addr(skb, IFLA_VXLAN_LOCAL,
-					    vxlan->saddr.sin.sin_addr.s_addr))
+					    vxlan->cfg.saddr.sin.sin_addr.s_addr))
 				goto nla_put_failure;
 #if IS_ENABLED(CONFIG_IPV6)
 		} else {
 			if (nla_put_in6_addr(skb, IFLA_VXLAN_LOCAL6,
-					     &vxlan->saddr.sin6.sin6_addr))
+					     &vxlan->cfg.saddr.sin6.sin6_addr))
 				goto nla_put_failure;
 #endif
 		}
 	}
 
-	if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) ||
-	    nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) ||
+	if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) ||
+	    nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
 	    nla_put_u8(skb, IFLA_VXLAN_LEARNING,
 			!!(vxlan->flags & VXLAN_F_LEARN)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_PROXY,

@@ -2954,9 +2976,9 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			!!(vxlan->flags & VXLAN_F_L3MISS)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_FLOWBASED,
 			!!(vxlan->flags & VXLAN_F_FLOW_BASED)) ||
-	    nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->age_interval) ||
-	    nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->addrmax) ||
-	    nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->dst_port) ||
+	    nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->cfg.age_interval) ||
+	    nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) ||
+	    nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) ||
 	    nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM,
 			!!(vxlan->flags & VXLAN_F_UDP_CSUM)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX,

77 lines not on this page · raw message

index 27c1687..cf04c2f 100644
@@ -733,7 +733,15 @@ static int execute_set_action(struct sk_buff *skb,
 {
 	/* Only tunnel set execution is supported without a mask. */
 	if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) {
-		OVS_CB(skb)->egress_tun_info = nla_data(a);
+		struct ovs_tunnel_info *tun = nla_data(a);
+
+		skb_dst_drop(skb);
+		dst_hold((struct dst_entry *)tun->tun_dst);
+		skb_dst_set(skb, (struct dst_entry *)tun->tun_dst);
+
+		/* FIXME: Remove when all vports have been converted */
+		OVS_CB(skb)->egress_tun_info = &tun->tun_dst->u.tun_info;
+
 		return 0;
 	}
 

index ff8c4a4..0208210 100644
@@ -1018,7 +1018,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		}
 		ovs_unlock();
 
-		ovs_nla_free_flow_actions(old_acts);
+		ovs_nla_free_flow_actions_rcu(old_acts);
 		ovs_flow_free(new_flow, false);
 	}
 

@@ -1030,7 +1030,7 @@ err_unlock_ovs:
 	ovs_unlock();
 	kfree_skb(reply);
 err_kfree_acts:
-	kfree(acts);
+	ovs_nla_free_flow_actions(acts);
 err_kfree_flow:
 	ovs_flow_free(new_flow, false);
 error:

@@ -1157,7 +1157,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	if (reply)
 		ovs_notify(&dp_flow_genl_family, reply, info);
 	if (old_acts)
-		ovs_nla_free_flow_actions(old_acts);
+		ovs_nla_free_flow_actions_rcu(old_acts);
 
 	return 0;
 

@@ -1165,7 +1165,7 @@ err_unlock_ovs:
 	ovs_unlock();
 	kfree_skb(reply);
 err_kfree_acts:
-	kfree(acts);
+	ovs_nla_free_flow_actions(acts);
 error:
 	return error;
 }

index cadc6c5..3fbf874 100644
@@ -33,6 +33,7 @@
 #include <linux/flex_array.h>
 #include <net/inet_ecn.h>
 #include <net/ip_tunnels.h>
+#include <net/dst_metadata.h>
 
 struct sk_buff;
 

@@ -45,6 +46,11 @@ struct sk_buff;
 #define TUN_METADATA_OPTS(flow_key, opt_len) \
 	((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len)))
 
+struct ovs_tunnel_info
+{
+	struct metadata_dst	*tun_dst;
+};
+
 #define OVS_SW_FLOW_KEY_METADATA_SIZE			\
 	(offsetof(struct sw_flow_key, recirc_id) +	\
 	FIELD_SIZEOF(struct sw_flow_key, recirc_id))

98 lines not on this page · raw message

index ec53eb6..acd0744 100644
@@ -69,5 +69,6 @@ int ovs_nla_put_actions(const struct nlattr *attr,
 			int len, struct sk_buff *skb);
 
 void ovs_nla_free_flow_actions(struct sw_flow_actions *);
+void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *);
 
 #endif /* flow_netlink.h */

index 0208210..19df28e 100644
@@ -188,7 +188,7 @@ static int get_dpifindex(const struct datapath *dp)
 
 	local = ovs_vport_rcu(dp, OVSP_LOCAL);
 	if (local)
-		ifindex = netdev_vport_priv(local)->dev->ifindex;
+		ifindex = local->dev->ifindex;
 	else
 		ifindex = 0;
 

@@ -2219,13 +2219,10 @@ static void __net_exit list_vports_from_net(struct net *net, struct net *dnet,
 			struct vport *vport;
 
 			hlist_for_each_entry(vport, &dp->ports[i], dp_hash_node) {
-				struct netdev_vport *netdev_vport;
-
 				if (vport->ops->type != OVS_VPORT_TYPE_INTERNAL)
 					continue;
 
-				netdev_vport = netdev_vport_priv(vport);
-				if (dev_net(netdev_vport->dev) == dnet)
+				if (dev_net(vport->dev) == dnet)
 					list_add(&vport->detach_list, head);
 			}
 		}

index 2c631fe..a7a80a6 100644
@@ -58,13 +58,10 @@ void ovs_dp_notify_wq(struct work_struct *work)
 			struct hlist_node *n;
 
 			hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) {
-				struct netdev_vport *netdev_vport;
-
 				if (vport->ops->type != OVS_VPORT_TYPE_NETDEV)
 					continue;
 
-				netdev_vport = netdev_vport_priv(vport);
-				if (!(netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH))
+				if (!(vport->dev->priv_flags & IFF_OVS_DATAPATH))
 					dp_detach_port_notify(vport);
 			}
 		}

index 6a55f71..a2c205d 100644
@@ -156,49 +156,44 @@ static void do_setup(struct net_device *netdev)
 static struct vport *internal_dev_create(const struct vport_parms *parms)
 {
 	struct vport *vport;
-	struct netdev_vport *netdev_vport;
 	struct internal_dev *internal_dev;
 	int err;
 
-	vport = ovs_vport_alloc(sizeof(struct netdev_vport),
-				&ovs_internal_vport_ops, parms);
+	vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms);
 	if (IS_ERR(vport)) {
 		err = PTR_ERR(vport);
 		goto error;
 	}
 
-	netdev_vport = netdev_vport_priv(vport);
-
-	netdev_vport->dev = alloc_netdev(sizeof(struct internal_dev),
-					 parms->name, NET_NAME_UNKNOWN,
-					 do_setup);
-	if (!netdev_vport->dev) {
+	vport->dev = alloc_netdev(sizeof(struct internal_dev),
+				  parms->name, NET_NAME_UNKNOWN, do_setup);
+	if (!vport->dev) {
 		err = -ENOMEM;
 		goto error_free_vport;
 	}
 
-	dev_net_set(netdev_vport->dev, ovs_dp_get_net(vport->dp));
-	internal_dev = internal_dev_priv(netdev_vport->dev);
+	dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));
+	internal_dev = internal_dev_priv(vport->dev);
 	internal_dev->vport = vport;
 
 	/* Restrict bridge port to current netns. */
 	if (vport->port_no == OVSP_LOCAL)
-		netdev_vport->dev->features |= NETIF_F_NETNS_LOCAL;
+		vport->dev->features |= NETIF_F_NETNS_LOCAL;
 
 	rtnl_lock();
-	err = register_netdevice(netdev_vport->dev);
+	err = register_netdevice(vport->dev);
 	if (err)
 		goto error_free_netdev;
 
-	dev_set_promiscuity(netdev_vport->dev, 1);
+	dev_set_promiscuity(vport->dev, 1);
 	rtnl_unlock();
-	netif_start_queue(netdev_vport->dev);
+	netif_start_queue(vport->dev);
 
 	return vport;
 
 error_free_netdev:
 	rtnl_unlock();
-	free_netdev(netdev_vport->dev);
+	free_netdev(vport->dev);
 error_free_vport:
 	ovs_vport_free(vport);
 error:

@@ -207,21 +202,19 @@ error:
 
 static void internal_dev_destroy(struct vport *vport)
 {
-	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
-
-	netif_stop_queue(netdev_vport->dev);
+	netif_stop_queue(vport->dev);
 	rtnl_lock();
-	dev_set_promiscuity(netdev_vport->dev, -1);
+	dev_set_promiscuity(vport->dev, -1);
 
 	/* unregister_netdevice() waits for an RCU grace period. */
-	unregister_netdevice(netdev_vport->dev);
+	unregister_netdevice(vport->dev);
 
 	rtnl_unlock();
 }
 
 static int internal_dev_recv(struct vport *vport, struct sk_buff *skb)
 {
-	struct net_device *netdev = netdev_vport_priv(vport)->dev;
+	struct net_device *netdev = vport->dev;
 	int len;
 
 	if (unlikely(!(netdev->flags & IFF_UP))) {

161 lines not on this page · raw message

index 6f7038e..1c52aed 100644
@@ -26,18 +26,6 @@
 
 struct vport *ovs_netdev_get_vport(struct net_device *dev);
 
-struct netdev_vport {
-	struct rcu_head rcu;
-
-	struct net_device *dev;
-};
-
-static inline struct netdev_vport *
-netdev_vport_priv(const struct vport *vport)
-{
-	return vport_priv(vport);
-}
-
 const char *ovs_netdev_get_name(const struct vport *);
 void ovs_netdev_detach_dev(struct vport *);
 

index 75d6824..e05ec68 100644
@@ -107,7 +107,7 @@ struct vport_portids {
  * @detach_list: list used for detaching vport in net-exit call.
  */
 struct vport {
-	struct rcu_head rcu;
+	struct net_device *dev;
 	struct datapath	*dp;
 	struct vport_portids __rcu *upcall_portids;
 	u16 port_no;

@@ -120,6 +120,7 @@ struct vport {
 
 	struct vport_err_stats err_stats;
 	struct list_head detach_list;
+	struct rcu_head rcu;
 };
 
 /**

index 19df28e..ffe984f 100644
@@ -176,7 +176,7 @@ static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
 const char *ovs_dp_name(const struct datapath *dp)
 {
 	struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL);
-	return vport->ops->get_name(vport);
+	return ovs_vport_name(vport);
 }
 
 static int get_dpifindex(const struct datapath *dp)

@@ -1800,7 +1800,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 	if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) ||
 	    nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) ||
 	    nla_put_string(skb, OVS_VPORT_ATTR_NAME,
-			   vport->ops->get_name(vport)))
+			   ovs_vport_name(vport)))
 		goto nla_put_failure;
 
 	ovs_vport_get_stats(vport, &vport_stats);