1 files changed, 84 insertions, 132 deletions

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 8ff30c3bdfce..6e65832051d6 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -11,32 +11,18 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
-#include <linux/types.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
-#include <linux/skbuff.h>
-#include <linux/rculist.h>
-#include <linux/netdevice.h>
-#include <linux/in.h>
-#include <linux/ip.h>
 #include <linux/udp.h>
 #include <linux/igmp.h>
-#include <linux/etherdevice.h>
 #include <linux/if_ether.h>
-#include <linux/if_vlan.h>
-#include <linux/hash.h>
 #include <linux/ethtool.h>
 #include <net/arp.h>
 #include <net/ndisc.h>
 #include <net/ip.h>
-#include <net/ip_tunnels.h>
 #include <net/icmp.h>
-#include <net/udp.h>
-#include <net/udp_tunnel.h>
 #include <net/rtnetlink.h>
-#include <net/route.h>
-#include <net/dsfield.h>
 #include <net/inet_ecn.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
@@ -44,12 +30,9 @@
 #include <net/protocol.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-#include <net/ipv6.h>
-#include <net/addrconf.h>
 #include <net/ip6_tunnel.h>
 #include <net/ip6_checksum.h>
 #endif
-#include <net/dst_metadata.h>
 
 #define VXLAN_VERSION	"0.1"
 
@@ -619,42 +602,6 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
-/* Notify netdevs that UDP port started listening */
-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 = vxlan_get_sk_family(vs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_add_vxlan_port)
-			dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
-							    port);
-	}
-	rcu_read_unlock();
-}
-
-/* Notify netdevs that UDP port is no more listening */
-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 = vxlan_get_sk_family(vs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_del_vxlan_port)
-			dev->netdev_ops->ndo_del_vxlan_port(dev, sa_family,
-							    port);
-	}
-	rcu_read_unlock();
-}
-
 /* Add new entry to forwarding table -- assumes lock held */
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
@@ -1050,7 +997,10 @@ static bool __vxlan_sock_release_prep(struct vxlan_sock *vs)
 	vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id);
 	spin_lock(&vn->sock_lock);
 	hlist_del_rcu(&vs->hlist);
-	vxlan_notify_del_rx_port(vs);
+	udp_tunnel_notify_del_rx_port(vs->sock,
+				      (vs->flags & VXLAN_F_GPE) ?
+				      UDP_TUNNEL_TYPE_VXLAN_GPE :
+				      UDP_TUNNEL_TYPE_VXLAN);
 	spin_unlock(&vn->sock_lock);
 
 	return true;
@@ -1861,7 +1811,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
 	fl4.flowi4_mark = skb->mark;
 	fl4.flowi4_proto = IPPROTO_UDP;
 	fl4.daddr = daddr;
-	fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr;
+	fl4.saddr = *saddr;
 
 	rt = ip_route_output_key(vxlan->net, &fl4);
 	if (!IS_ERR(rt)) {
@@ -1897,7 +1847,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_oif = oif;
 	fl6.daddr = *daddr;
-	fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr;
+	fl6.saddr = *saddr;
 	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label);
 	fl6.flowi6_mark = skb->mark;
 	fl6.flowi6_proto = IPPROTO_UDP;
@@ -1970,7 +1920,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	struct rtable *rt = NULL;
 	const struct iphdr *old_iph;
 	union vxlan_addr *dst;
-	union vxlan_addr remote_ip;
+	union vxlan_addr remote_ip, local_ip;
+	union vxlan_addr *src;
 	struct vxlan_metadata _md;
 	struct vxlan_metadata *md = &_md;
 	__be16 src_port = 0, dst_port;
@@ -1988,6 +1939,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
 		vni = rdst->remote_vni;
 		dst = &rdst->remote_ip;
+		src = &vxlan->cfg.saddr;
 		dst_cache = &rdst->dst_cache;
 	} else {
 		if (!info) {
@@ -1998,11 +1950,15 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
 		vni = vxlan_tun_id_to_vni(info->key.tun_id);
 		remote_ip.sa.sa_family = ip_tunnel_info_af(info);
-		if (remote_ip.sa.sa_family == AF_INET)
+		if (remote_ip.sa.sa_family == AF_INET) {
 			remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst;
-		else
+			local_ip.sin.sin_addr.s_addr = info->key.u.ipv4.src;
+		} else {
 			remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst;
+			local_ip.sin6.sin6_addr = info->key.u.ipv6.src;
+		}
 		dst = &remote_ip;
+		src = &local_ip;
 		dst_cache = &info->dst_cache;
 	}
 
@@ -2042,15 +1998,14 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (dst->sa.sa_family == AF_INET) {
-		__be32 saddr;
-
 		if (!vxlan->vn4_sock)
 			goto drop;
 		sk = vxlan->vn4_sock->sock->sk;
 
 		rt = vxlan_get_route(vxlan, skb,
 				     rdst ? rdst->remote_ifindex : 0, tos,
-				     dst->sin.sin_addr.s_addr, &saddr,
+				     dst->sin.sin_addr.s_addr,
+				     &src->sin.sin_addr.s_addr,
 				     dst_cache, info);
 		if (IS_ERR(rt)) {
 			netdev_dbg(dev, "no route to %pI4\n",
@@ -2067,7 +2022,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		}
 
 		/* Bypass encapsulation if the destination is local */
-		if (rt->rt_flags & RTCF_LOCAL &&
+		if (!info && rt->rt_flags & RTCF_LOCAL &&
 		    !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
 			struct vxlan_dev *dst_vxlan;
 
@@ -2093,13 +2048,12 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (err < 0)
 			goto xmit_tx_error;
 
-		udp_tunnel_xmit_skb(rt, sk, skb, saddr,
+		udp_tunnel_xmit_skb(rt, sk, skb, src->sin.sin_addr.s_addr,
 				    dst->sin.sin_addr.s_addr, tos, ttl, df,
 				    src_port, dst_port, xnet, !udp_sum);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
 		struct dst_entry *ndst;
-		struct in6_addr saddr;
 		u32 rt6i_flags;
 
 		if (!vxlan->vn6_sock)
@@ -2108,7 +2062,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		ndst = vxlan6_get_route(vxlan, skb,
 					rdst ? rdst->remote_ifindex : 0, tos,
-					label, &dst->sin6.sin6_addr, &saddr,
+					label, &dst->sin6.sin6_addr,
+					&src->sin6.sin6_addr,
 					dst_cache, info);
 		if (IS_ERR(ndst)) {
 			netdev_dbg(dev, "no route to %pI6\n",
@@ -2127,7 +2082,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		/* Bypass encapsulation if the destination is local */
 		rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;
-		if (rt6i_flags & RTF_LOCAL &&
+		if (!info && rt6i_flags & RTF_LOCAL &&
 		    !(rt6i_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
 			struct vxlan_dev *dst_vxlan;
 
@@ -2154,7 +2109,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			return;
 		}
 		udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
-				     &saddr, &dst->sin6.sin6_addr, tos, ttl,
+				     &src->sin6.sin6_addr,
+				     &dst->sin6.sin6_addr, tos, ttl,
 				     label, src_port, dst_port, !udp_sum);
 #endif
 	}
@@ -2525,30 +2481,24 @@ static struct device_type vxlan_type = {
 	.name = "vxlan",
 };
 
-/* Calls the ndo_add_vxlan_port of the caller in order to
+/* Calls the ndo_udp_tunnel_add of the caller in order to
  * supply the listening VXLAN udp ports. Callers are expected
- * to implement the ndo_add_vxlan_port.
+ * to implement the ndo_udp_tunnel_add.
  */
 static void vxlan_push_rx_ports(struct net_device *dev)
 {
 	struct vxlan_sock *vs;
 	struct net *net = dev_net(dev);
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
-	sa_family_t sa_family;
-	__be16 port;
 	unsigned int i;
 
-	if (!dev->netdev_ops->ndo_add_vxlan_port)
-		return;
-
 	spin_lock(&vn->sock_lock);
 	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 = vxlan_get_sk_family(vs);
-			dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
-							    port);
-		}
+		hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist)
+			udp_tunnel_push_rx_port(dev, vs->sock,
+						(vs->flags & VXLAN_F_GPE) ?
+						UDP_TUNNEL_TYPE_VXLAN_GPE :
+						UDP_TUNNEL_TYPE_VXLAN);
 	}
 	spin_unlock(&vn->sock_lock);
 }
@@ -2750,7 +2700,10 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
 
 	spin_lock(&vn->sock_lock);
 	hlist_add_head_rcu(&vs->hlist, vs_head(net, port));
-	vxlan_notify_add_rx_port(vs);
+	udp_tunnel_notify_add_rx_port(sock,
+				      (vs->flags & VXLAN_F_GPE) ?
+				      UDP_TUNNEL_TYPE_VXLAN_GPE :
+				      UDP_TUNNEL_TYPE_VXLAN);
 	spin_unlock(&vn->sock_lock);
 
 	/* Mark socket as an encapsulation socket. */
@@ -2829,14 +2782,15 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	struct net_device *lowerdev = NULL;
 
 	if (conf->flags & VXLAN_F_GPE) {
-		if (conf->flags & ~VXLAN_F_ALLOWED_GPE)
-			return -EINVAL;
 		/* For now, allow GPE only together with COLLECT_METADATA.
 		 * This can be relaxed later; in such case, the other side
 		 * of the PtP link will have to be provided.
 		 */
-		if (!(conf->flags & VXLAN_F_COLLECT_METADATA))
+		if ((conf->flags & ~VXLAN_F_ALLOWED_GPE) ||
+		    !(conf->flags & VXLAN_F_COLLECT_METADATA)) {
+			pr_info("unsupported combination of extensions\n");
 			return -EINVAL;
+		}
 
 		vxlan_raw_setup(dev);
 	} else {
@@ -2889,6 +2843,9 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 			dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 
 		needed_headroom = lowerdev->hard_header_len;
+	} else if (vxlan_addr_multicast(&dst->remote_ip)) {
+		pr_info("multicast destination requires interface to be specified\n");
+		return -EINVAL;
 	}
 
 	if (conf->mtu) {
@@ -2921,8 +2878,10 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		     tmp->cfg.saddr.sa.sa_family == AF_INET6) == use_ipv6 &&
 		    tmp->cfg.dst_port == vxlan->cfg.dst_port &&
 		    (tmp->flags & VXLAN_F_RCV_FLAGS) ==
-		    (vxlan->flags & VXLAN_F_RCV_FLAGS))
-		return -EEXIST;
+		    (vxlan->flags & VXLAN_F_RCV_FLAGS)) {
+			pr_info("duplicate VNI %u\n", be32_to_cpu(conf->vni));
+			return -EEXIST;
+		}
 	}
 
 	dev->ethtool_ops = &vxlan_ethtool_ops;
@@ -2952,35 +2911,10 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	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;
 
 	memset(&conf, 0, sizeof(conf));
 
@@ -3086,26 +3020,10 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
 		conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL;
 
-	err = vxlan_dev_configure(src_net, dev, &conf);
-	switch (err) {
-	case -ENODEV:
-		pr_info("ifindex %d does not exist\n", conf.remote_ifindex);
-		break;
-
-	case -EPERM:
-		pr_info("IPv6 is disabled via sysctl\n");
-		break;
-
-	case -EEXIST:
-		pr_info("duplicate VNI %u\n", be32_to_cpu(conf.vni));
-		break;
+	if (tb[IFLA_MTU])
+		conf.mtu = nla_get_u32(tb[IFLA_MTU]);
 
-	case -EINVAL:
-		pr_info("unsupported combination of extensions\n");
-		break;
-	}
-
-	return err;
+	return vxlan_dev_configure(src_net, dev, &conf);
 }
 
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
@@ -3265,6 +3183,40 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = {
 	.get_link_net	= vxlan_get_link_net,
 };
 
+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);
+	}
+
+	err = rtnl_configure_link(dev, NULL);
+	if (err < 0) {
+		LIST_HEAD(list_kill);
+
+		vxlan_dellink(dev, &list_kill);
+		unregister_netdevice_many(&list_kill);
+		return ERR_PTR(err);
+	}
+
+	return dev;
+}
+EXPORT_SYMBOL_GPL(vxlan_dev_create);
+
 static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn,
 					     struct net_device *dev)
 {
@@ -3295,7 +3247,7 @@ static int vxlan_netdevice_event(struct notifier_block *unused,
 
 	if (event == NETDEV_UNREGISTER)
 		vxlan_handle_lowerdev_unregister(vn, dev);
-	else if (event == NETDEV_OFFLOAD_PUSH_VXLAN)
+	else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO)
 		vxlan_push_rx_ports(dev);
 
 	return NOTIFY_DONE;