[PATCH net-next v3 0/2] net: add local address bind support to vxlan and geneve

[PATCH net-next v3 0/2] net: add local address bind support to vxlan and geneve

[Richard Gobert]

This series adds local address bind support to both vxlan
and geneve sockets.

v2 -> v3:
  - Fix typo and nit problem (Simon)
  - v2: https://lore.kernel.org/netdev/20240708111103.9742-1-richardbgobert@gmail.com/

v1 -> v2:
  - Change runtime checking of CONFIG_IPV6 to compile time in geneve
  - Change {geneve,vxlan}_find_sock to check listening address
  - Fix incorrect usage of IFLA_VXLAN_LOCAL6 in geneve
  - Use NLA_POLICY_EXACT_LEN instead of changing strict_start_type in geneve
  - v1: https://lore.kernel.org/netdev/df300a49-7811-4126-a56a-a77100c8841b@gmail.com/

Richard Gobert (2):
  net: vxlan: enable local address bind for vxlan sockets
  net: geneve: enable local address bind for geneve sockets

 drivers/net/geneve.c               | 82 +++++++++++++++++++++++++++---
 drivers/net/vxlan/vxlan_core.c     | 55 ++++++++++++++------
 include/net/geneve.h               |  6 +++
 include/uapi/linux/if_link.h       |  2 +
 tools/include/uapi/linux/if_link.h |  2 +
 5 files changed, 124 insertions(+), 23 deletions(-)

-- 
2.36.1

[PATCH net-next v3 1/2] net: vxlan: enable local address bind for vxlan sockets

[Richard Gobert]

This patch adds support for binding to a local address in vxlan sockets.
It achieves this by using vxlan_addr union to represent a local address
to bind to, and copying it to udp_port_cfg in vxlan_create_sock.

Also change vxlan_find_sock to search the socket based on listening address.

Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
---
 drivers/net/vxlan/vxlan_core.c | 55 ++++++++++++++++++++++++----------
 1 file changed, 40 insertions(+), 15 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index ba59e92ab941..b6e34e037d4b 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -72,22 +72,35 @@ 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).
+ * bounded 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 (inet->inet_sport == port &&
 		    vxlan_get_sk_family(vs) == family &&
 		    vs->flags == flags &&
-		    vs->sock->sk->sk_bound_dev_if == ifindex)
-			return vs;
+		    vs->sock->sk->sk_bound_dev_if == ifindex) {
+			if (family == AF_INET &&
+			    inet->inet_rcv_saddr == saddr->sin.sin_addr.s_addr)
+				return vs;
+#if IS_ENABLED(CONFIG_IPV6)
+			else if (ipv6_addr_cmp(&sk->sk_v6_rcv_saddr,
+					       &saddr->sin6.sin6_addr) == 0)
+				return vs;
+#endif
+		}
+
 	}
 	return NULL;
 }
@@ -135,11 +148,12 @@ 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;
 
@@ -2315,7 +2329,7 @@ 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,
@@ -3503,8 +3517,9 @@ 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;
@@ -3517,8 +3532,17 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 		udp_conf.use_udp6_rx_checksums =
 		    !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX);
 		udp_conf.ipv6_v6only = 1;
+#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.family = AF_INET;
+		udp_conf.local_ip.s_addr = addr->sin.sin_addr.s_addr;
+		memcpy(&udp_conf.local_ip.s_addr,
+		       &addr->sin.sin_addr.s_addr,
+		       sizeof(addr->sin.sin_addr.s_addr));
 	}
 
 	udp_conf.local_udp_port = port;
@@ -3536,7 +3560,8 @@ 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_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_sock *vs;
@@ -3551,7 +3576,7 @@ 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);
@@ -3605,7 +3630,7 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 		spin_lock(&vn->sock_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)) {
 			spin_unlock(&vn->sock_lock);
 			return -EBUSY;
@@ -3615,7 +3640,7 @@ 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

[PATCH net-next v3 2/2] net: geneve: enable local address bind for geneve sockets

[Richard Gobert]

This patch adds support for binding to a local address in geneve sockets.
It achieves this by adding a new netlink local argument and geneve_addr union
to represent local address to bind to, and copying it to udp_port_cfg in
geneve_create_sock.

Also change geneve_find_sock to search the socket based on listening address.

Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
---
 drivers/net/geneve.c               | 82 +++++++++++++++++++++++++++---
 include/net/geneve.h               |  6 +++
 include/uapi/linux/if_link.h       |  2 +
 tools/include/uapi/linux/if_link.h |  2 +
 4 files changed, 84 insertions(+), 8 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 838e85ddec67..6756851598b7 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -57,6 +57,7 @@ struct geneve_config {
 	bool			ttl_inherit;
 	enum ifla_geneve_df	df;
 	bool			inner_proto_inherit;
+	union geneve_addr saddr;
 };
 
 /* Pseudo network device */
@@ -461,7 +462,8 @@ static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb)
 }
 
 static struct socket *geneve_create_sock(struct net *net, bool ipv6,
-					 __be16 port, bool ipv6_rx_csum)
+					 __be16 port, bool ipv6_rx_csum,
+					 union geneve_addr *local_addr)
 {
 	struct socket *sock;
 	struct udp_port_cfg udp_conf;
@@ -473,9 +475,17 @@ static struct socket *geneve_create_sock(struct net *net, bool ipv6,
 		udp_conf.family = AF_INET6;
 		udp_conf.ipv6_v6only = 1;
 		udp_conf.use_udp6_rx_checksums = ipv6_rx_csum;
+#if IS_ENABLED(CONFIG_IPV6)
+		memcpy(&udp_conf.local_ip6,
+		       &local_addr->sin6.sin6_addr,
+		       sizeof(local_addr->sin6.sin6_addr));
+#endif
 	} else {
 		udp_conf.family = AF_INET;
 		udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+		memcpy(&udp_conf.local_ip,
+		       &local_addr->sin.sin_addr,
+		       sizeof(local_addr->sin.sin_addr));
 	}
 
 	udp_conf.local_udp_port = port;
@@ -582,7 +592,8 @@ static int geneve_gro_complete(struct sock *sk, struct sk_buff *skb,
 
 /* Create new listen socket if needed */
 static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
-						bool ipv6, bool ipv6_rx_csum)
+						bool ipv6, bool ipv6_rx_csum,
+						union geneve_addr *local_addr)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
@@ -594,7 +605,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	if (!gs)
 		return ERR_PTR(-ENOMEM);
 
-	sock = geneve_create_sock(net, ipv6, port, ipv6_rx_csum);
+	sock = geneve_create_sock(net, ipv6, port, ipv6_rx_csum, local_addr);
 	if (IS_ERR(sock)) {
 		kfree(gs);
 		return ERR_CAST(sock);
@@ -653,16 +664,28 @@ static void geneve_sock_release(struct geneve_dev *geneve)
 
 static struct geneve_sock *geneve_find_sock(struct geneve_net *gn,
 					    sa_family_t family,
-					    __be16 dst_port)
+					    __be16 dst_port,
+					    union geneve_addr *saddr)
 {
 	struct geneve_sock *gs;
 
 	list_for_each_entry(gs, &gn->sock_list, list) {
-		if (inet_sk(gs->sock->sk)->inet_sport == dst_port &&
+		struct sock *sk = gs->sock->sk;
+		struct inet_sock *inet = inet_sk(sk);
+
+		if (inet->inet_sport == dst_port &&
 		    geneve_get_sk_family(gs) == family) {
-			return gs;
+			if (family == AF_INET &&
+			    inet->inet_rcv_saddr == saddr->sin.sin_addr.s_addr)
+				return gs;
+#if IS_ENABLED(CONFIG_IPV6)
+			else if (ipv6_addr_cmp(&sk->sk_v6_rcv_saddr,
+					       &saddr->sin6.sin6_addr) == 0)
+				return gs;
+#endif
 		}
 	}
+
 	return NULL;
 }
 
@@ -675,14 +698,16 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
 	__u8 vni[3];
 	__u32 hash;
 
-	gs = geneve_find_sock(gn, ipv6 ? AF_INET6 : AF_INET, geneve->cfg.info.key.tp_dst);
+	gs = geneve_find_sock(gn, ipv6 ? AF_INET6 : AF_INET,
+			      geneve->cfg.info.key.tp_dst, &geneve->cfg.saddr);
 	if (gs) {
 		gs->refcnt++;
 		goto out;
 	}
 
 	gs = geneve_socket_create(net, geneve->cfg.info.key.tp_dst, ipv6,
-				  geneve->cfg.use_udp6_rx_checksums);
+				  geneve->cfg.use_udp6_rx_checksums,
+				  &geneve->cfg.saddr);
 	if (IS_ERR(gs))
 		return PTR_ERR(gs);
 
@@ -1234,6 +1259,8 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
 	[IFLA_GENEVE_TTL_INHERIT]	= { .type = NLA_U8 },
 	[IFLA_GENEVE_DF]		= { .type = NLA_U8 },
 	[IFLA_GENEVE_INNER_PROTO_INHERIT]	= { .type = NLA_FLAG },
+	[IFLA_GENEVE_LOCAL]	= NLA_POLICY_EXACT_LEN(sizeof_field(struct iphdr, saddr)),
+	[IFLA_GENEVE_LOCAL6]	= NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
 };
 
 static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -1561,6 +1588,34 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[],
 		cfg->inner_proto_inherit = true;
 	}
 
+	if (data[IFLA_GENEVE_LOCAL]) {
+		if (changelink && cfg->saddr.sa.sa_family != AF_INET) {
+			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_LOCAL],
+					    "New local address family does not match old");
+			return -EOPNOTSUPP;
+		}
+
+		cfg->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_GENEVE_LOCAL]);
+		cfg->saddr.sa.sa_family = AF_INET;
+	}
+
+	if (data[IFLA_GENEVE_LOCAL6]) {
+#if IS_ENABLED(CONFIG_IPV6)
+		if (changelink && cfg->saddr.sa.sa_family != AF_INET6) {
+			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_LOCAL6],
+					    "New local address family does not match old");
+			return -EOPNOTSUPP;
+		}
+
+		cfg->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_GENEVE_LOCAL6]);
+		cfg->saddr.sa.sa_family = AF_INET6;
+#else
+		NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_LOCAL6],
+				    "IPv6 support not enabled in the kernel");
+		return -EPFNOSUPPORT;
+#endif
+	}
+
 	return 0;
 change_notsup:
 	NL_SET_ERR_MSG_ATTR(extack, data[attrtype],
@@ -1741,6 +1796,7 @@ static size_t geneve_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */
 		nla_total_size(0) +	 /* IFLA_GENEVE_INNER_PROTO_INHERIT */
+		nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_LOCAL{6} */
 		0;
 }
 
@@ -1762,6 +1818,11 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE,
 				    info->key.u.ipv4.dst))
 			goto nla_put_failure;
+
+		if (nla_put_in_addr(skb, IFLA_GENEVE_LOCAL,
+				    info->key.u.ipv4.src))
+			goto nla_put_failure;
+
 		if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM,
 			       test_bit(IP_TUNNEL_CSUM_BIT,
 					info->key.tun_flags)))
@@ -1772,6 +1833,11 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6,
 				     &info->key.u.ipv6.dst))
 			goto nla_put_failure;
+
+		if (nla_put_in6_addr(skb, IFLA_GENEVE_LOCAL6,
+				     &info->key.u.ipv6.src))
+			goto nla_put_failure;
+
 		if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
 			       !test_bit(IP_TUNNEL_CSUM_BIT,
 					 info->key.tun_flags)))
diff --git a/include/net/geneve.h b/include/net/geneve.h
index 5c96827a487e..8dcd7fff2c0f 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -68,6 +68,12 @@ static inline bool netif_is_geneve(const struct net_device *dev)
 	       !strcmp(dev->rtnl_link_ops->kind, "geneve");
 }
 
+union geneve_addr {
+	struct sockaddr_in sin;
+	struct sockaddr_in6 sin6;
+	struct sockaddr sa;
+};
+
 #ifdef CONFIG_INET
 struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 					u8 name_assign_type, u16 dst_port);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 6dc258993b17..25ddf4dda47b 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1419,6 +1419,8 @@ enum {
 	IFLA_GENEVE_TTL_INHERIT,
 	IFLA_GENEVE_DF,
 	IFLA_GENEVE_INNER_PROTO_INHERIT,
+	IFLA_GENEVE_LOCAL,
+	IFLA_GENEVE_LOCAL6,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index f0d71b2a3f1e..8321c8b32f6e 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -888,6 +888,8 @@ enum {
 	IFLA_GENEVE_TTL_INHERIT,
 	IFLA_GENEVE_DF,
 	IFLA_GENEVE_INNER_PROTO_INHERIT,
+	IFLA_GENEVE_LOCAL,
+	IFLA_GENEVE_LOCAL6,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
-- 
2.36.1

Re: [PATCH net-next v3 0/2] net: add local address bind support to vxlan and geneve

[Jakub Kicinski]

On Thu, 11 Jul 2024 15:14:09 +0200 Richard Gobert wrote:
> This series adds local address bind support to both vxlan
> and geneve sockets.

I think that this breaks a lot of vxlan related subtests:
https://netdev.bots.linux.dev/contest.html?pw-n=0&branch=net-next-2024-07-11--15-00&pw-n=0&pass=0