[PATCH net-next v5 3/5] net: vxlan: bind vxlan sockets to their local address if configured

[Richard Gobert <richardbgobert@gmail.com>]

Bind VXLAN sockets to the local addresses if the IFLA_VXLAN_LOCALBIND
option is set. This is the new default.

Change vxlan_find_sock to search for the socket using the listening
address.

This is implemented by copying the VXLAN local address to the udp_port_cfg
passed to udp_sock_create. The freebind option is set because VXLAN
interfaces may be UP before their outgoing interface is.

This fixes multiple VXLAN selftests that fail because of that race.

Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
---
 drivers/net/vxlan/vxlan_core.c | 59 ++++++++++++++++++++++++++--------
 1 file changed, 46 insertions(+), 13 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 15fe9d83c724..12da9595436e 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -78,18 +78,34 @@ static inline bool vxlan_collect_metadata(struct vxlan_sock *vs)
 }
 
 /* Find VXLAN socket based on network namespace, address family, UDP port,
- * enabled unshareable flags and socket device binding (see l3mdev with
- * non-default VRF).
+ * bound address, enabled unshareable flags and socket device binding
+ * (see l3mdev with non-default VRF).
  */
 static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
-					  __be16 port, u32 flags, int ifindex)
+					  __be16 port, u32 flags, int ifindex,
+					  union vxlan_addr *saddr)
 {
 	struct vxlan_sock *vs;
 
 	flags &= VXLAN_F_RCV_FLAGS;
 
 	hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
-		if (inet_sk(vs->sock->sk)->inet_sport == port &&
+		struct sock *sk = vs->sock->sk;
+		struct inet_sock *inet = inet_sk(sk);
+
+		if (flags & VXLAN_F_LOCALBIND) {
+			if (family == AF_INET &&
+			    inet->inet_rcv_saddr != saddr->sin.sin_addr.s_addr)
+				continue;
+#if IS_ENABLED(CONFIG_IPV6)
+			else if (family == AF_INET6 &&
+				 ipv6_addr_cmp(&sk->sk_v6_rcv_saddr,
+					       &saddr->sin6.sin6_addr) != 0)
+				continue;
+#endif
+		}
+
+		if (inet->inet_sport == port &&
 		    vxlan_get_sk_family(vs) == family &&
 		    vs->flags == flags &&
 		    vs->sock->sk->sk_bound_dev_if == ifindex)
@@ -141,11 +157,12 @@ static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs,
 /* Look up VNI in a per net namespace table */
 static struct vxlan_dev *vxlan_find_vni(struct net *net, int ifindex,
 					__be32 vni, sa_family_t family,
-					__be16 port, u32 flags)
+					__be16 port, u32 flags,
+					union vxlan_addr *saddr)
 {
 	struct vxlan_sock *vs;
 
-	vs = vxlan_find_sock(net, family, port, flags, ifindex);
+	vs = vxlan_find_sock(net, family, port, flags, ifindex, saddr);
 	if (!vs)
 		return NULL;
 
@@ -2309,7 +2326,7 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,
 		dst_release(dst);
 		dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni,
 					   addr_family, dst_port,
-					   vxlan->cfg.flags);
+					   vxlan->cfg.flags, &vxlan->cfg.saddr);
 		if (!dst_vxlan) {
 			DEV_STATS_INC(dev, tx_errors);
 			vxlan_vnifilter_count(vxlan, vni, NULL,
@@ -3508,8 +3525,9 @@ static const struct ethtool_ops vxlan_ethtool_ops = {
 	.get_link_ksettings	= vxlan_get_link_ksettings,
 };
 
-static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
-					__be16 port, u32 flags, int ifindex)
+static struct socket *vxlan_create_sock(struct net *net, bool ipv6, __be16 port,
+					u32 flags, int ifindex,
+					union vxlan_addr *addr)
 {
 	struct socket *sock;
 	struct udp_port_cfg udp_conf;
@@ -3526,6 +3544,20 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 		udp_conf.family = AF_INET;
 	}
 
+	if (flags & VXLAN_F_LOCALBIND) {
+		if (ipv6) {
+#if IS_ENABLED(CONFIG_IPV6)
+			memcpy(&udp_conf.local_ip6.s6_addr32,
+			       &addr->sin6.sin6_addr.s6_addr32,
+			       sizeof(addr->sin6.sin6_addr.s6_addr32));
+#endif
+		} else {
+			udp_conf.local_ip.s_addr = addr->sin.sin_addr.s_addr;
+		}
+
+		udp_conf.freebind = 1;
+	}
+
 	udp_conf.local_udp_port = port;
 	udp_conf.bind_ifindex = ifindex;
 
@@ -3541,7 +3573,8 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 /* Create new listen socket if needed */
 static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
 					      __be16 port, u32 flags,
-					      int ifindex)
+					      int ifindex,
+					      union vxlan_addr *addr)
 {
 	struct vxlan_sock *vs;
 	struct socket *sock;
@@ -3557,7 +3590,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
 	for (h = 0; h < VNI_HASH_SIZE; ++h)
 		INIT_HLIST_HEAD(&vs->vni_list[h]);
 
-	sock = vxlan_create_sock(net, ipv6, port, flags, ifindex);
+	sock = vxlan_create_sock(net, ipv6, port, flags, ifindex, addr);
 	if (IS_ERR(sock)) {
 		kfree(vs);
 		return ERR_CAST(sock);
@@ -3610,7 +3643,7 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 		rcu_read_lock();
 		vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET,
 				     vxlan->cfg.dst_port, vxlan->cfg.flags,
-				     l3mdev_index);
+				     l3mdev_index, &vxlan->cfg.saddr);
 		if (vs && !refcount_inc_not_zero(&vs->refcnt)) {
 			rcu_read_unlock();
 			return -EBUSY;
@@ -3620,7 +3653,7 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 	if (!vs)
 		vs = vxlan_socket_create(vxlan->net, ipv6,
 					 vxlan->cfg.dst_port, vxlan->cfg.flags,
-					 l3mdev_index);
+					 l3mdev_index, &vxlan->cfg.saddr);
 	if (IS_ERR(vs))
 		return PTR_ERR(vs);
 #if IS_ENABLED(CONFIG_IPV6)
-- 
2.36.1