1 files changed, 51 insertions, 102 deletions

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index beb377b2d4b7..be4649a49c5e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -42,6 +42,7 @@
 #include <net/netns/generic.h>
 #include <net/vxlan.h>
 #include <net/protocol.h>
+#include <net/udp_tunnel.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
 #include <net/addrconf.h>
@@ -66,12 +67,6 @@
 
 #define VXLAN_FLAGS 0x08000000	/* struct vxlanhdr.vx_flags required value. */
 
-/* VXLAN protocol header */
-struct vxlanhdr {
-	__be32 vx_flags;
-	__be32 vx_vni;
-};
-
 /* UDP port for VXLAN traffic.
  * The IANA assigned port is 4789, but the Linux default is 8472
  * for compatibility with early adopters.
@@ -274,13 +269,15 @@ static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb)
 	return list_first_entry(&fdb->remotes, struct vxlan_rdst, list);
 }
 
-/* Find VXLAN socket based on network namespace and UDP port */
-static struct vxlan_sock *vxlan_find_sock(struct net *net, __be16 port)
+/* Find VXLAN socket based on network namespace, address family and UDP port */
+static struct vxlan_sock *vxlan_find_sock(struct net *net,
+					  sa_family_t family, __be16 port)
 {
 	struct vxlan_sock *vs;
 
 	hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
-		if (inet_sk(vs->sock->sk)->inet_sport == port)
+		if (inet_sk(vs->sock->sk)->inet_sport == port &&
+		    inet_sk(vs->sock->sk)->sk.sk_family == family)
 			return vs;
 	}
 	return NULL;
@@ -299,11 +296,12 @@ static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id)
 }
 
 /* Look up VNI in a per net namespace table */
-static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, __be16 port)
+static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id,
+					sa_family_t family, __be16 port)
 {
 	struct vxlan_sock *vs;
 
-	vs = vxlan_find_sock(net, port);
+	vs = vxlan_find_sock(net, family, port);
 	if (!vs)
 		return NULL;
 
@@ -620,6 +618,8 @@ static int vxlan_gro_complete(struct sk_buff *skb, int nhoff)
 	int vxlan_len  = sizeof(struct vxlanhdr) + sizeof(struct ethhdr);
 	int err = -ENOSYS;
 
+	udp_tunnel_gro_complete(skb, nhoff);
+
 	eh = (struct ethhdr *)(skb->data + nhoff + sizeof(struct vxlanhdr));
 	type = eh->h_proto;
 
@@ -1062,7 +1062,6 @@ void vxlan_sock_release(struct vxlan_sock *vs)
 
 	spin_lock(&vn->sock_lock);
 	hlist_del_rcu(&vs->hlist);
-	rcu_assign_sk_user_data(vs->sock->sk, NULL);
 	vxlan_notify_del_rx_port(vs);
 	spin_unlock(&vn->sock_lock);
 
@@ -1158,8 +1157,6 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	if (!vs)
 		goto drop;
 
-	skb_pop_rcv_encapsulation(skb);
-
 	vs->rcv(vs, skb, vxh->vx_vni);
 	return 0;
 
@@ -1338,7 +1335,6 @@ out:
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-
 static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	struct neighbour *n, bool isrouter)
 {
@@ -1440,9 +1436,6 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
 	if (!in6_dev)
 		goto out;
 
-	if (!pskb_may_pull(skb, skb->len))
-		goto out;
-
 	iphdr = ipv6_hdr(skb);
 	saddr = &iphdr->saddr;
 	daddr = &iphdr->daddr;
@@ -1572,13 +1565,6 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	return false;
 }
 
-static inline struct sk_buff *vxlan_handle_offloads(struct sk_buff *skb,
-						    bool udp_csum)
-{
-	int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
-	return iptunnel_handle_offloads(skb, udp_csum, type);
-}
-
 #if IS_ENABLED(CONFIG_IPV6)
 static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 			   struct dst_entry *dst, struct sk_buff *skb,
@@ -1587,13 +1573,12 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 			   __be16 src_port, __be16 dst_port, __be32 vni,
 			   bool xnet)
 {
-	struct ipv6hdr *ip6h;
 	struct vxlanhdr *vxh;
-	struct udphdr *uh;
 	int min_headroom;
 	int err;
+	bool udp_sum = !udp_get_no_check6_tx(vs->sock->sk);
 
-	skb = vxlan_handle_offloads(skb, !udp_get_no_check6_tx(vs->sock->sk));
+	skb = udp_tunnel_handle_offloads(skb, udp_sum);
 	if (IS_ERR(skb))
 		return -EINVAL;
 
@@ -1621,38 +1606,10 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	vxh->vx_flags = htonl(VXLAN_FLAGS);
 	vxh->vx_vni = vni;
 
-	__skb_push(skb, sizeof(*uh));
-	skb_reset_transport_header(skb);
-	uh = udp_hdr(skb);
-
-	uh->dest = dst_port;
-	uh->source = src_port;
-
-	uh->len = htons(skb->len);
+	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
-	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
-			      IPSKB_REROUTED);
-	skb_dst_set(skb, dst);
-
-	udp6_set_csum(udp_get_no_check6_tx(vs->sock->sk), skb,
-		      saddr, daddr, skb->len);
-
-	__skb_push(skb, sizeof(*ip6h));
-	skb_reset_network_header(skb);
-	ip6h		  = ipv6_hdr(skb);
-	ip6h->version	  = 6;
-	ip6h->priority	  = prio;
-	ip6h->flow_lbl[0] = 0;
-	ip6h->flow_lbl[1] = 0;
-	ip6h->flow_lbl[2] = 0;
-	ip6h->payload_len = htons(skb->len);
-	ip6h->nexthdr     = IPPROTO_UDP;
-	ip6h->hop_limit   = ttl;
-	ip6h->daddr	  = *daddr;
-	ip6h->saddr	  = *saddr;
-
-	ip6tunnel_xmit(skb, dev);
+	udp_tunnel6_xmit_skb(vs->sock, dst, skb, dev, saddr, daddr, prio,
+			     ttl, src_port, dst_port);
 	return 0;
 }
 #endif
@@ -1663,11 +1620,11 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 		   __be16 src_port, __be16 dst_port, __be32 vni, bool xnet)
 {
 	struct vxlanhdr *vxh;
-	struct udphdr *uh;
 	int min_headroom;
 	int err;
+	bool udp_sum = !vs->sock->sk->sk_no_check_tx;
 
-	skb = vxlan_handle_offloads(skb, !vs->sock->sk->sk_no_check_tx);
+	skb = udp_tunnel_handle_offloads(skb, udp_sum);
 	if (IS_ERR(skb))
 		return -EINVAL;
 
@@ -1693,20 +1650,10 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 	vxh->vx_flags = htonl(VXLAN_FLAGS);
 	vxh->vx_vni = vni;
 
-	__skb_push(skb, sizeof(*uh));
-	skb_reset_transport_header(skb);
-	uh = udp_hdr(skb);
-
-	uh->dest = dst_port;
-	uh->source = src_port;
-
-	uh->len = htons(skb->len);
-
-	udp_set_csum(vs->sock->sk->sk_no_check_tx, skb,
-		     src, dst, skb->len);
+	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
-	return iptunnel_xmit(vs->sock->sk, rt, skb, src, dst, IPPROTO_UDP,
-			     tos, ttl, df, xnet);
+	return udp_tunnel_xmit_skb(vs->sock, rt, skb, src, dst, tos,
+				   ttl, df, src_port, dst_port, xnet);
 }
 EXPORT_SYMBOL_GPL(vxlan_xmit_skb);
 
@@ -1717,6 +1664,8 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 	struct pcpu_sw_netstats *tx_stats, *rx_stats;
 	union vxlan_addr loopback;
 	union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
+	struct net_device *dev = skb->dev;
+	int len = skb->len;
 
 	tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
 	rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
@@ -1740,16 +1689,16 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 
 	u64_stats_update_begin(&tx_stats->syncp);
 	tx_stats->tx_packets++;
-	tx_stats->tx_bytes += skb->len;
+	tx_stats->tx_bytes += len;
 	u64_stats_update_end(&tx_stats->syncp);
 
 	if (netif_rx(skb) == NET_RX_SUCCESS) {
 		u64_stats_update_begin(&rx_stats->syncp);
 		rx_stats->rx_packets++;
-		rx_stats->rx_bytes += skb->len;
+		rx_stats->rx_bytes += len;
 		u64_stats_update_end(&rx_stats->syncp);
 	} else {
-		skb->dev->stats.rx_dropped++;
+		dev->stats.rx_dropped++;
 	}
 }
 
@@ -1821,7 +1770,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			struct vxlan_dev *dst_vxlan;
 
 			ip_rt_put(rt);
-			dst_vxlan = vxlan_find_vni(vxlan->net, vni, dst_port);
+			dst_vxlan = vxlan_find_vni(vxlan->net, vni,
+						   dst->sa.sa_family, dst_port);
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -1875,7 +1825,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			struct vxlan_dev *dst_vxlan;
 
 			dst_release(ndst);
-			dst_vxlan = vxlan_find_vni(vxlan->net, vni, dst_port);
+			dst_vxlan = vxlan_find_vni(vxlan->net, vni,
+						   dst->sa.sa_family, dst_port);
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -1927,7 +1878,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 			return arp_reduce(dev, skb);
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
-			 skb->len >= sizeof(struct ipv6hdr) + sizeof(struct nd_msg) &&
+			 pskb_may_pull(skb, sizeof(struct ipv6hdr)
+				       + sizeof(struct nd_msg)) &&
 			 ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
 				struct nd_msg *msg;
 
@@ -1936,6 +1888,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 				    msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
 					return neigh_reduce(dev, skb);
 		}
+		eth = eth_hdr(skb);
 #endif
 	}
 
@@ -2033,13 +1986,15 @@ static int vxlan_init(struct net_device *dev)
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	struct vxlan_sock *vs;
+	bool ipv6 = vxlan->flags & VXLAN_F_IPV6;
 
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
 	spin_lock(&vn->sock_lock);
-	vs = vxlan_find_sock(vxlan->net, vxlan->dst_port);
+	vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET,
+			     vxlan->dst_port);
 	if (vs) {
 		/* If we have a socket with same port already, reuse it */
 		atomic_inc(&vs->refcnt);
@@ -2242,7 +2197,7 @@ static void vxlan_setup(struct net_device *dev)
 	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
-	dev->priv_flags	&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	INIT_LIST_HEAD(&vxlan->next);
@@ -2335,8 +2290,7 @@ static const struct ethtool_ops vxlan_ethtool_ops = {
 static void vxlan_del_work(struct work_struct *work)
 {
 	struct vxlan_sock *vs = container_of(work, struct vxlan_sock, del_work);
-
-	sk_release_kernel(vs->sock->sk);
+	udp_tunnel_sock_release(vs->sock);
 	kfree_rcu(vs, rcu);
 }
 
@@ -2352,9 +2306,9 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 	if (ipv6) {
 		udp_conf.family = AF_INET6;
 		udp_conf.use_udp6_tx_checksums =
-		    !!(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
+		    !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
 		udp_conf.use_udp6_rx_checksums =
-		    !!(flags & VXLAN_F_UDP_ZERO_CSUM6_RX);
+		    !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX);
 	} else {
 		udp_conf.family = AF_INET;
 		udp_conf.local_ip.s_addr = INADDR_ANY;
@@ -2369,9 +2323,6 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 	if (err < 0)
 		return ERR_PTR(err);
 
-	/* Disable multicast loopback */
-	inet_sk(sock->sk)->mc_loop = 0;
-
 	return sock;
 }
 
@@ -2383,9 +2334,9 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_sock *vs;
 	struct socket *sock;
-	struct sock *sk;
 	unsigned int h;
 	bool ipv6 = !!(flags & VXLAN_F_IPV6);
+	struct udp_tunnel_sock_cfg tunnel_cfg;
 
 	vs = kzalloc(sizeof(*vs), GFP_KERNEL);
 	if (!vs)
@@ -2403,11 +2354,9 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 	}
 
 	vs->sock = sock;
-	sk = sock->sk;
 	atomic_set(&vs->refcnt, 1);
 	vs->rcv = rcv;
 	vs->data = data;
-	rcu_assign_sk_user_data(vs->sock->sk, vs);
 
 	/* Initialize the vxlan udp offloads structure */
 	vs->udp_offloads.port = port;
@@ -2420,14 +2369,12 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 	spin_unlock(&vn->sock_lock);
 
 	/* Mark socket as an encapsulation socket. */
-	udp_sk(sk)->encap_type = 1;
-	udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv;
-#if IS_ENABLED(CONFIG_IPV6)
-	if (ipv6)
-		ipv6_stub->udpv6_encap_enable();
-	else
-#endif
-		udp_encap_enable();
+	tunnel_cfg.sk_user_data = vs;
+	tunnel_cfg.encap_type = 1;
+	tunnel_cfg.encap_rcv = vxlan_udp_encap_recv;
+	tunnel_cfg.encap_destroy = NULL;
+
+	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
 
 	return vs;
 }
@@ -2438,6 +2385,7 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_sock *vs;
+	bool ipv6 = flags & VXLAN_F_IPV6;
 
 	vs = vxlan_socket_create(net, port, rcv, data, flags);
 	if (!IS_ERR(vs))
@@ -2447,7 +2395,7 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 		return vs;
 
 	spin_lock(&vn->sock_lock);
-	vs = vxlan_find_sock(net, port);
+	vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port);
 	if (vs) {
 		if (vs->rcv == rcv)
 			atomic_inc(&vs->refcnt);
@@ -2606,7 +2554,8 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
 		vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
 
-	if (vxlan_find_vni(net, vni, vxlan->dst_port)) {
+	if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
+			   vxlan->dst_port)) {
 		pr_info("duplicate VNI %u\n", vni);
 		return -EEXIST;
 	}