Merge branch 'lwt-ipv6'

Jiri Benc says: ==================== lwtunnel: per route ipv6 support for vxlan v3: Moved LWTUNNEL_ENCAP_IP6 definition in patch 13. v2: Fixed issues in patch 4 pointed out by Alexei. This series enables IPv6 tunnels based on lwtunnel infrastructure. Only vxlan is supported for now. Tested in all combinations of IPv4 over IPv6, IPv6 over IPv4 and IPv6 over IPv6. ==================== Signed-off-by: David S. Miller <[email protected]>
josf · Aug 20, 2015 · 08617f4 · 08617f4
2 parents 938049e + 32a2b00
commit 08617f4
Show file tree

Hide file tree

Showing 30 changed files with 312 additions and 233 deletions.
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
@@ -295,7 +295,6 @@ static struct rtable *vrf_rtable_create(struct net_device *dev)
 		rth->rt_uses_gateway = 0;
 		INIT_LIST_HEAD(&rth->rt_uncached);
 		rth->rt_uncached_list = NULL;
-		rth->rt_lwtstate = NULL;
 	}
 
 	return rth;

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
@@ -236,7 +236,7 @@ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
 
 	hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
 		if (inet_sk(vs->sock->sk)->inet_sport == port &&
-		    inet_sk(vs->sock->sk)->sk.sk_family == family &&
+		    vxlan_get_sk_family(vs) == family &&
 		    vs->flags == flags)
 			return vs;
 	}
@@ -625,7 +625,7 @@ static void vxlan_notify_add_rx_port(struct vxlan_sock *vs)
 	struct net_device *dev;
 	struct sock *sk = vs->sock->sk;
 	struct net *net = sock_net(sk);
-	sa_family_t sa_family = sk->sk_family;
+	sa_family_t sa_family = vxlan_get_sk_family(vs);
 	__be16 port = inet_sk(sk)->inet_sport;
 	int err;
 
@@ -650,7 +650,7 @@ static void vxlan_notify_del_rx_port(struct vxlan_sock *vs)
 	struct net_device *dev;
 	struct sock *sk = vs->sock->sk;
 	struct net *net = sock_net(sk);
-	sa_family_t sa_family = sk->sk_family;
+	sa_family_t sa_family = vxlan_get_sk_family(vs);
 	__be16 port = inet_sk(sk)->inet_sport;
 
 	rcu_read_lock();
@@ -1269,17 +1269,27 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	}
 
 	if (vxlan_collect_metadata(vs)) {
-		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;
+		if (vxlan_get_sk_family(vs) == AF_INET) {
+			const struct iphdr *iph = ip_hdr(skb);
+
+			info->key.u.ipv4.src = iph->saddr;
+			info->key.u.ipv4.dst = iph->daddr;
+			info->key.tos = iph->tos;
+			info->key.ttl = iph->ttl;
+		} else {
+			const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+
+			info->key.u.ipv6.src = ip6h->saddr;
+			info->key.u.ipv6.dst = ip6h->daddr;
+			info->key.tos = ipv6_get_dsfield(ip6h);
+			info->key.ttl = ip6h->hop_limit;
+		}
+
 		info->key.tp_src = udp_hdr(skb)->source;
 		info->key.tp_dst = udp_hdr(skb)->dest;
 
@@ -1894,6 +1904,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	struct ip_tunnel_info *info;
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct sock *sk = vxlan->vn_sock->sock->sk;
+	unsigned short family = vxlan_get_sk_family(vxlan->vn_sock);
 	struct rtable *rt = NULL;
 	const struct iphdr *old_iph;
 	struct flowi4 fl4;
@@ -1908,8 +1919,7 @@ 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);
+	info = skb_tunnel_info(skb);
 
 	if (rdst) {
 		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
@@ -1924,8 +1934,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		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;
+		remote_ip.sa.sa_family = family;
+		if (family == AF_INET)
+			remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst;
+		else
+			remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst;
 		dst = &remote_ip;
 	}
 
@@ -1951,23 +1964,24 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
 				     vxlan->cfg.port_max, true);
 
+	if (info) {
+		if (info->key.tun_flags & TUNNEL_CSUM)
+			flags |= VXLAN_F_UDP_CSUM;
+		else
+			flags &= ~VXLAN_F_UDP_CSUM;
+
+		ttl = info->key.ttl;
+		tos = info->key.tos;
+
+		if (info->options_len)
+			md = ip_tunnel_info_opts(info, sizeof(*md));
+	} else {
+		md->gbp = skb->mark;
+	}
+
 	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;
-		}
+		if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT))
+			df = htons(IP_DF);
 
 		memset(&fl4, 0, sizeof(fl4));
 		fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0;
@@ -2025,7 +2039,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	} else {
 		struct dst_entry *ndst;
 		struct flowi6 fl6;
-		u32 flags;
+		u32 rt6i_flags;
 
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0;
@@ -2050,9 +2064,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		}
 
 		/* Bypass encapsulation if the destination is local */
-		flags = ((struct rt6_info *)ndst)->rt6i_flags;
-		if (flags & RTF_LOCAL &&
-		    !(flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
+		rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;
+		if (rt6i_flags & RTF_LOCAL &&
+		    !(rt6i_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
 			struct vxlan_dev *dst_vxlan;
 
 			dst_release(ndst);
@@ -2066,12 +2080,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		}
 
 		ttl = ttl ? : ip6_dst_hoplimit(ndst);
-		md->gbp = skb->mark;
-
 		err = vxlan6_xmit_skb(ndst, sk, skb, dev, &fl6.saddr, &fl6.daddr,
 				      0, ttl, src_port, dst_port, htonl(vni << 8), md,
 				      !net_eq(vxlan->net, dev_net(vxlan->dev)),
-				      vxlan->flags);
+				      flags);
 #endif
 	}
 
@@ -2104,8 +2116,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct vxlan_rdst *rdst, *fdst = NULL;
 	struct vxlan_fdb *f;
 
-	/* FIXME: Support IPv6 */
-	info = skb_tunnel_info(skb, AF_INET);
+	info = skb_tunnel_info(skb);
 
 	skb_reset_mac_header(skb);
 	eth = eth_hdr(skb);
@@ -2390,7 +2401,7 @@ void vxlan_get_rx_port(struct net_device *dev)
 	for (i = 0; i < PORT_HASH_SIZE; ++i) {
 		hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) {
 			port = inet_sk(vs->sock->sk)->inet_sport;
-			sa_family = vs->sock->sk->sk_family;
+			sa_family = vxlan_get_sk_family(vs);
 			dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
 							    port);
 		}

diff --git a/include/net/dst.h b/include/net/dst.h
@@ -44,6 +44,7 @@ struct dst_entry {
 #else
 	void			*__pad1;
 #endif
+	struct lwtunnel_state   *lwtstate;
 	int			(*input)(struct sk_buff *);
 	int			(*output)(struct sock *sk, struct sk_buff *skb);
 
@@ -89,7 +90,7 @@ struct dst_entry {
 	 * (L1_CACHE_SIZE would be too much)
 	 */
 #ifdef CONFIG_64BIT
-	long			__pad_to_align_refcnt[2];
+	long			__pad_to_align_refcnt[1];
 #endif
 	/*
 	 * __refcnt wants to be on a different cache line from

diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
@@ -23,22 +23,17 @@ 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,
-						     int family)
+static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
 {
 	struct metadata_dst *md_dst = skb_metadata_dst(skb);
-	struct rtable *rt;
+	struct dst_entry *dst;
 
 	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;
-	}
+	dst = skb_dst(skb);
+	if (dst && dst->lwtstate)
+		return lwt_tun_info(dst->lwtstate);
 
 	return NULL;
 }

diff --git a/include/net/flow.h b/include/net/flow.h
@@ -130,6 +130,7 @@ struct flowi6 {
 #define flowi6_proto		__fl_common.flowic_proto
 #define flowi6_flags		__fl_common.flowic_flags
 #define flowi6_secid		__fl_common.flowic_secid
+#define flowi6_tun_key		__fl_common.flowic_tun_key
 	struct in6_addr		daddr;
 	struct in6_addr		saddr;
 	__be32			flowlabel;

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
@@ -133,7 +133,6 @@ 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_tunnels.h b/include/net/ip_tunnels.h
@@ -23,20 +23,32 @@
 #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))
+#define IP_TUNNEL_KEY_SIZE	offsetofend(struct ip_tunnel_key, tp_dst)
+
+/* Used to memset ipv4 address padding. */
+#define IP_TUNNEL_KEY_IPV4_PAD	offsetofend(struct ip_tunnel_key, u.ipv4.dst)
+#define IP_TUNNEL_KEY_IPV4_PAD_LEN				\
+	(FIELD_SIZEOF(struct ip_tunnel_key, u) -		\
+	 FIELD_SIZEOF(struct ip_tunnel_key, u.ipv4))
 
 struct ip_tunnel_key {
 	__be64			tun_id;
-	__be32			ipv4_src;
-	__be32			ipv4_dst;
+	union {
+		struct {
+			__be32	src;
+			__be32	dst;
+		} ipv4;
+		struct {
+			struct in6_addr src;
+			struct in6_addr dst;
+		} ipv6;
+	} u;
 	__be16			tun_flags;
-	__u8			ipv4_tos;
-	__u8			ipv4_ttl;
+	u8			tos;		/* TOS for IPv4, TC for IPv6 */
+	u8			ttl;		/* TTL for IPv4, HL for IPv6 */
 	__be16			tp_src;
 	__be16			tp_dst;
-} __packed __aligned(4); /* Minimize padding. */
+};
 
 /* Indicates whether the tunnel info structure represents receive
  * or transmit tunnel parameters.
@@ -64,8 +76,8 @@ struct ip_tunnel_6rd_parm {
 #endif
 
 struct ip_tunnel_encap {
-	__u16			type;
-	__u16			flags;
+	u16			type;
+	u16			flags;
 	__be16			sport;
 	__be16			dport;
 };
@@ -95,8 +107,8 @@ struct ip_tunnel {
 					 * arrived */
 
 	/* These four fields used only by GRE */
-	__u32		i_seqno;	/* The last seen seqno	*/
-	__u32		o_seqno;	/* The last output seqno */
+	u32		i_seqno;	/* The last seen seqno	*/
+	u32		o_seqno;	/* The last output seqno */
 	int		tun_hlen;	/* Precalculated header length */
 	int		mlink;
 
@@ -179,10 +191,12 @@ static inline void __ip_tunnel_info_init(struct ip_tunnel_info *tun_info,
 					 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.u.ipv4.src = saddr;
+	tun_info->key.u.ipv4.dst = daddr;
+	memset((unsigned char *)&tun_info->key + IP_TUNNEL_KEY_IPV4_PAD,
+	       0, IP_TUNNEL_KEY_IPV4_PAD_LEN);
+	tun_info->key.tos = tos;
+	tun_info->key.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
@@ -273,8 +287,8 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
 
 int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);
 int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
-		  __be32 src, __be32 dst, __u8 proto,
-		  __u8 tos, __u8 ttl, __be16 df, bool xnet);
+		  __be32 src, __be32 dst, u8 proto,
+		  u8 tos, u8 ttl, __be16 df, bool xnet);
 
 struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
 					 int gso_type_mask);

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
@@ -87,9 +87,7 @@ 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);
 int lwtunnel_input(struct sk_buff *skb);
-int lwtunnel_input6(struct sk_buff *skb);
 
 #else
 
@@ -164,21 +162,11 @@ 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;
-}
-
 static inline int lwtunnel_input(struct sk_buff *skb)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline int lwtunnel_input6(struct sk_buff *skb)
-{
-	return -EOPNOTSUPP;
-}
-
 #endif
 
 #endif /* __NET_LWTUNNEL_H */
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
@@ -182,7 +182,8 @@ int ndisc_rcv(struct sk_buff *skb);
 
 void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
 		   const struct in6_addr *solicit,
-		   const struct in6_addr *daddr, const struct in6_addr *saddr);
+		   const struct in6_addr *daddr, const struct in6_addr *saddr,
+		   struct sk_buff *oskb);
 
 void ndisc_send_rs(struct net_device *dev,
 		   const struct in6_addr *saddr, const struct in6_addr *daddr);

diff --git a/include/net/route.h b/include/net/route.h
@@ -66,7 +66,6 @@ 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)