vxlan: bump version

@@ -42,7 +42,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
-#define VXLAN_VERSION	"0.1"
+#define VXLAN_VERSION	"0.2"
 
 #define PORT_HASH_BITS	8
 #define PORT_HASH_SIZE  (1<<PORT_HASH_BITS)

@@ -210,9 +210,9 @@ static struct vxlan_dev *vxlan_find_vni(
 
 /* Fill in neighbour message in skbuff. */
 static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
-			   const struct vxlan_fdb *fdb,
-			   u32 portid, u32 seq, int type, unsigned int flags,
-			   const struct vxlan_rdst *rdst)
+			  const struct vxlan_fdb *fdb,
+			  u32 portid, u32 seq, int type, unsigned int flags,
+			  const struct vxlan_rdst *rdst)
 {
 	unsigned long now = jiffies;
 	struct nda_cacheinfo ci;

@@ -1032,7 +1032,7 @@ static void vxlan_xmit_one(struct sk_buf
 	struct flowi4 fl4;
 	__be32 dst;
 	__be16 src_port, dst_port;
-        u32 vni;
+	u32 vni;
 	__be16 df = 0;
 	__u8 tos, ttl;
 

@@ -311,14 +311,13 @@ errout:
 static void vxlan_ip_miss(struct net_device *dev, __be32 ipa)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_fdb f;
-	struct vxlan_rdst remote;
-
-	memset(&f, 0, sizeof f);
-	f.state = NUD_STALE;
-
-	remote.remote_ip = ipa; /* goes to NDA_DST */
-	remote.remote_vni = VXLAN_N_VID;
+	struct vxlan_fdb f = {
+		.state = NUD_STALE,
+	};
+	struct vxlan_rdst remote = {
+		.remote_ip = ipa, /* goes to NDA_DST */
+		.remote_vni = VXLAN_N_VID,
+	};
 
 	INIT_LIST_HEAD(&f.remotes);
 	list_add_rcu(&remote.list, &f.remotes);

@@ -328,11 +327,11 @@ static void vxlan_ip_miss(struct net_dev
 
 static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
 {
-	struct vxlan_fdb	f;
+	struct vxlan_fdb f = {
+		.state = NUD_STALE,
+	};
 
-	memset(&f, 0, sizeof f);
 	INIT_LIST_HEAD(&f.remotes);
-	f.state = NUD_STALE;
 	memcpy(f.eth_addr, eth_addr, ETH_ALEN);
 
 	vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);

@@ -1501,6 +1500,7 @@ static struct vxlan_sock *vxlan_socket_c
 	struct sockaddr_in vxlan_addr = {
 		.sin_family = AF_INET,
 		.sin_addr.s_addr = htonl(INADDR_ANY),
+		.sin_port = port,
 	};
 	int rc;
 	unsigned int h;

@@ -1526,8 +1526,6 @@ static struct vxlan_sock *vxlan_socket_c
 	sk = vs->sock->sk;
 	sk_change_net(sk, net);
 
-	vxlan_addr.sin_port = port;
-
 	rc = kernel_bind(vs->sock, (struct sockaddr *) &vxlan_addr,
 			 sizeof(vxlan_addr));
 	if (rc < 0) {

@@ -70,8 +70,8 @@ struct vxlanhdr {
  * The IANA assigned port is 4789, but the Linux default is 8472
  * for compatability with early adopters.
  */
-static unsigned int vxlan_port __read_mostly = 8472;
-module_param_named(udp_port, vxlan_port, uint, 0444);
+static unsigned short vxlan_port __read_mostly = 8472;
+module_param_named(udp_port, vxlan_port, ushort, 0444);
 MODULE_PARM_DESC(udp_port, "Destination UDP port");
 
 static bool log_ecn_error = true;

@@ -1008,8 +1008,8 @@ static void vxlan_encap_bypass(struct sk
 	}
 }
 
-static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
-				  struct vxlan_rdst *rdst, bool did_rsc)
+static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
+			   struct vxlan_rdst *rdst, bool did_rsc)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct rtable *rt;

@@ -1032,7 +1032,7 @@ static netdev_tx_t vxlan_xmit_one(struct
 		if (did_rsc) {
 			/* short-circuited back to local bridge */
 			vxlan_encap_bypass(skb, vxlan, vxlan);
-			return NETDEV_TX_OK;
+			return;
 		}
 		goto drop;
 	}

@@ -1088,7 +1088,7 @@ static netdev_tx_t vxlan_xmit_one(struct
 		if (!dst_vxlan)
 			goto tx_error;
 		vxlan_encap_bypass(skb, vxlan, dst_vxlan);
-		return NETDEV_TX_OK;
+		return;
 	}
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));

@@ -1132,7 +1132,7 @@ static netdev_tx_t vxlan_xmit_one(struct
 		goto drop;
 
 	iptunnel_xmit(skb, dev);
-	return NETDEV_TX_OK;
+	return;
 
 drop:
 	dev->stats.tx_dropped++;

@@ -1142,7 +1142,6 @@ tx_error:
 	dev->stats.tx_errors++;
 tx_free:
 	dev_kfree_skb(skb);
-	return NETDEV_TX_OK;
 }
 
 /* Transmit local packets over Vxlan

@@ -1158,7 +1157,6 @@ static netdev_tx_t vxlan_xmit(struct sk_
 	bool did_rsc = false;
 	struct vxlan_rdst *rdst0, *rdst;
 	struct vxlan_fdb *f;
-	int rc1, rc;
 
 	skb_reset_mac_header(skb);
 	eth = eth_hdr(skb);

@@ -1186,24 +1184,18 @@ static netdev_tx_t vxlan_xmit(struct sk_
 	} else
 		rdst0 = &f->remote;
 
-	rc = NETDEV_TX_OK;
 
 	/* if there are multiple destinations, send copies */
 	for (rdst = rdst0->remote_next; rdst; rdst = rdst->remote_next) {
 		struct sk_buff *skb1;
 
 		skb1 = skb_clone(skb, GFP_ATOMIC);
-		if (skb1) {
-			rc1 = vxlan_xmit_one(skb1, dev, rdst, did_rsc);
-			if (rc == NETDEV_TX_OK)
-				rc = rc1;
-		}
+		if (skb1)
+			vxlan_xmit_one(skb1, dev, rdst, did_rsc);
 	}
 
-	rc1 = vxlan_xmit_one(skb, dev, rdst0, did_rsc);
-	if (rc == NETDEV_TX_OK)
-		rc = rc1;
-	return rc;
+	vxlan_xmit_one(skb, dev, rdst0, did_rsc);
+	return NETDEV_TX_OK;
 }
 
 /* Walk the forwarding table and purge stale entries */

@@ -1272,6 +1272,17 @@ static int vxlan_init(struct net_device
 	return 0;
 }
 
+static void vxlan_uninit(struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+	struct vxlan_sock *vs = vxlan->vn_sock;
+
+	if (vs)
+		vxlan_sock_release(vn, vs);
+	free_percpu(dev->tstats);
+}
+
 /* Start ageing timer and join group when device is brought up */
 static int vxlan_open(struct net_device *dev)
 {

@@ -1337,6 +1348,7 @@ static void vxlan_set_multicast_list(str
 
 static const struct net_device_ops vxlan_netdev_ops = {
 	.ndo_init		= vxlan_init,
+	.ndo_uninit		= vxlan_uninit,
 	.ndo_open		= vxlan_open,
 	.ndo_stop		= vxlan_stop,
 	.ndo_start_xmit		= vxlan_xmit,

@@ -1355,12 +1367,6 @@ static struct device_type vxlan_type = {
 	.name = "vxlan",
 };
 
-static void vxlan_free(struct net_device *dev)
-{
-	free_percpu(dev->tstats);
-	free_netdev(dev);
-}
-
 /* Initialize the device structure. */
 static void vxlan_setup(struct net_device *dev)
 {

@@ -1373,7 +1379,7 @@ static void vxlan_setup(struct net_devic
 	dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
-	dev->destructor = vxlan_free;
+	dev->destructor = free_netdev;
 	SET_NETDEV_DEVTYPE(dev, &vxlan_type);
 
 	dev->tx_queue_len = 0;

@@ -1676,14 +1682,10 @@ static int vxlan_newlink(struct net *net
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
-	struct vxlan_sock *vs = vxlan->vn_sock;
 
 	hlist_del_rcu(&vxlan->hlist);
 	list_del(&vxlan->next);
 	unregister_netdevice_queue(dev, head);
-	if (vs)
-		vxlan_sock_release(vn, vs);
 }
 
 static size_t vxlan_get_size(const struct net_device *dev)

@@ -94,6 +94,7 @@ struct vxlan_sock {
 struct vxlan_net {
 	struct list_head  vxlan_list;
 	struct hlist_head sock_list[PORT_HASH_SIZE];
+	spinlock_t	  sock_lock;
 };
 
 struct vxlan_rdst {

@@ -131,7 +132,9 @@ struct vxlan_dev {
 	__u8		  ttl;
 	u32		  flags;	/* VXLAN_F_* below */
 
+	struct work_struct sock_work;
 	struct work_struct igmp_work;
+
 	unsigned long	  age_interval;
 	struct timer_list age_timer;
 	spinlock_t	  hash_lock;

@@ -151,6 +154,8 @@ struct vxlan_dev {
 static u32 vxlan_salt __read_mostly;
 static struct workqueue_struct *vxlan_wq;
 
+static void vxlan_sock_work(struct work_struct *work);
+
 /* Virtual Network hash table head */
 static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id)
 {

@@ -670,12 +675,15 @@ static void vxlan_sock_hold(struct vxlan
 	atomic_inc(&vs->refcnt);
 }
 
-static void vxlan_sock_release(struct vxlan_sock *vs)
+static void vxlan_sock_release(struct vxlan_net *vn, struct vxlan_sock *vs)
 {
 	if (!atomic_dec_and_test(&vs->refcnt))
 		return;
 
+	spin_lock(&vn->sock_lock);
 	hlist_del_rcu(&vs->hlist);
+	spin_unlock(&vn->sock_lock);
+
 	queue_work(vxlan_wq, &vs->del_work);
 }
 

@@ -700,7 +708,7 @@ static void vxlan_igmp_work(struct work_
 		ip_mc_leave_group(sk, &mreq);
 	release_sock(sk);
 
-	vxlan_sock_release(vs);
+	vxlan_sock_release(vn, vs);
 	dev_put(vxlan->dev);
 }
 

@@ -1238,10 +1246,29 @@ static void vxlan_cleanup(unsigned long
 /* Setup stats when device is created */
 static int vxlan_init(struct net_device *dev)
 {
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+	struct vxlan_sock *vs;
+	__u32 vni = vxlan->default_dst.remote_vni;
+
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	spin_lock(&vn->sock_lock);
+	vs = vxlan_find_port(dev_net(dev), vxlan->dst_port);
+	if (vs) {
+		/* If we have a socket with same port already, reuse it */
+		atomic_inc(&vs->refcnt);
+		vxlan->vn_sock = vs;
+		hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni));
+	} else {
+		/* otherwise make new socket outside of RTNL */
+		dev_hold(dev);
+		queue_work(vxlan_wq, &vxlan->sock_work);
+	}
+	spin_unlock(&vn->sock_lock);
+
 	return 0;
 }
 

@@ -1249,9 +1276,14 @@ static int vxlan_init(struct net_device
 static int vxlan_open(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_sock *vs = vxlan->vn_sock;
+
+	/* socket hasn't been created */
+	if (!vs)
+		return -ENOTCONN;
 
 	if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
-		vxlan_sock_hold(vxlan->vn_sock);
+		vxlan_sock_hold(vs);
 		dev_hold(dev);
 		queue_work(vxlan_wq, &vxlan->igmp_work);
 	}

@@ -1283,9 +1315,10 @@ static void vxlan_flush(struct vxlan_dev
 static int vxlan_stop(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_sock *vs = vxlan->vn_sock;
 
-	if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
-		vxlan_sock_hold(vxlan->vn_sock);
+	if (vs && IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
+		vxlan_sock_hold(vs);
 		dev_hold(dev);
 		queue_work(vxlan_wq, &vxlan->igmp_work);
 	}

@@ -1358,6 +1391,7 @@ static void vxlan_setup(struct net_devic
 	INIT_LIST_HEAD(&vxlan->next);
 	spin_lock_init(&vxlan->hash_lock);
 	INIT_WORK(&vxlan->igmp_work, vxlan_igmp_work);
+	INIT_WORK(&vxlan->sock_work, vxlan_sock_work);
 
 	init_timer_deferrable(&vxlan->age_timer);
 	vxlan->age_timer.function = vxlan_cleanup;

@@ -1449,7 +1483,6 @@ static void vxlan_del_work(struct work_s
 	kfree_rcu(vs, rcu);
 }
 
-/* Create new listen socket if needed */
 static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port)
 {
 	struct vxlan_sock *vs;

@@ -1506,13 +1539,52 @@ static struct vxlan_sock *vxlan_socket_c
 	return vs;
 }
 
+/* Scheduled at device creation to bind to a socket */
+static void vxlan_sock_work(struct work_struct *work)
+{
+	struct vxlan_dev *vxlan
+		= container_of(work, struct vxlan_dev, sock_work);
+	struct net_device *dev = vxlan->dev;
+	struct net *net = dev_net(dev);
+	__u32 vni = vxlan->default_dst.remote_vni;
+	__be16 port = vxlan->dst_port;
+	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	struct vxlan_sock *nvs, *ovs;
+
+	nvs = vxlan_socket_create(net, port);
+	if (IS_ERR(nvs)) {
+		netdev_err(vxlan->dev, "Can not create UDP socket, %ld\n",
+			   PTR_ERR(nvs));
+		goto out;
+	}
+
+	spin_lock(&vn->sock_lock);
+	/* Look again to see if can reuse socket */
+	ovs = vxlan_find_port(net, port);
+	if (ovs) {
+		atomic_inc(&ovs->refcnt);
+		vxlan->vn_sock = ovs;
+		hlist_add_head_rcu(&vxlan->hlist, vni_head(ovs, vni));
+		spin_unlock(&vn->sock_lock);
+
+		sk_release_kernel(nvs->sock->sk);
+		kfree(nvs);
+	} else {
+		vxlan->vn_sock = nvs;
+		hlist_add_head_rcu(&nvs->hlist, vs_head(net, port));
+		hlist_add_head_rcu(&vxlan->hlist, vni_head(nvs, vni));
+		spin_unlock(&vn->sock_lock);
+	}
+out:
+	dev_put(dev);
+}
+
 static int vxlan_newlink(struct net *net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *dst = &vxlan->default_dst;
-	struct vxlan_sock *vs;
 	__u32 vni;
 	int err;
 

@@ -1590,31 +1662,13 @@ static int vxlan_newlink(struct net *net
 		return -EEXIST;
 	}
 
-	vs = vxlan_find_port(net, vxlan->dst_port);
-	if (vs)
-		atomic_inc(&vs->refcnt);
-	else {
-		/* Drop lock because socket create acquires RTNL lock */
-		rtnl_unlock();
-		vs = vxlan_socket_create(net, vxlan->dst_port);
-		rtnl_lock();
-		if (IS_ERR(vs))
-			return PTR_ERR(vs);
-
-		hlist_add_head_rcu(&vs->hlist, vs_head(net, vxlan->dst_port));
-	}
-	vxlan->vn_sock = vs;
-
 	SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops);
 
 	err = register_netdevice(dev);
-	if (err) {
-		vxlan_sock_release(vs);
+	if (err)
 		return err;
-	}
 
 	list_add(&vxlan->next, &vn->vxlan_list);
-	hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni));
 
 	return 0;
 }

@@ -1622,12 +1676,14 @@ static int vxlan_newlink(struct net *net
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_sock *vs = vxlan->vn_sock;
 
 	hlist_del_rcu(&vxlan->hlist);
 	list_del(&vxlan->next);
 	unregister_netdevice_queue(dev, head);
-	vxlan_sock_release(vs);
+	if (vs)
+		vxlan_sock_release(vn, vs);
 }
 
 static size_t vxlan_get_size(const struct net_device *dev)

@@ -1716,6 +1772,7 @@ static __net_init int vxlan_init_net(str
 	unsigned int h;
 
 	INIT_LIST_HEAD(&vn->vxlan_list);
+	spin_lock_init(&vn->sock_lock);
 
 	for (h = 0; h < PORT_HASH_SIZE; ++h)
 		INIT_HLIST_HEAD(&vn->sock_list[h]);

@@ -629,6 +629,7 @@ static bool vxlan_snoop(struct net_devic
 
 		f->remote.remote_ip = src_ip;
 		f->updated = jiffies;
+		vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH);
 	} else {
 		/* learned new entry */
 		spin_lock(&vxlan->hash_lock);

@@ -85,7 +85,7 @@ struct vxlan_sock {
 	struct hlist_node hlist;
 	struct rcu_head	  rcu;
 	struct work_struct del_work;
-	unsigned int	  refcnt;
+	atomic_t	  refcnt;
 	struct socket	  *sock;
 	struct hlist_head vni_list[VNI_HASH_SIZE];
 };

@@ -131,6 +131,7 @@ struct vxlan_dev {
 	__u8		  ttl;
 	u32		  flags;	/* VXLAN_F_* below */
 
+	struct work_struct igmp_work;
 	unsigned long	  age_interval;
 	struct timer_list age_timer;
 	spinlock_t	  hash_lock;

@@ -648,76 +649,58 @@ static bool vxlan_snoop(struct net_devic
 
 
 /* See if multicast group is already in use by other ID */
-static bool vxlan_group_used(struct vxlan_net *vn,
-			     const struct vxlan_dev *this)
+static bool vxlan_group_used(struct vxlan_net *vn, __be32 remote_ip)
 {
 	struct vxlan_dev *vxlan;
 
 	list_for_each_entry(vxlan, &vn->vxlan_list, next) {
-		if (vxlan == this)
-			continue;
-
 		if (!netif_running(vxlan->dev))
 			continue;
 
-		if (vxlan->default_dst.remote_ip == this->default_dst.remote_ip)
+		if (vxlan->default_dst.remote_ip == remote_ip)
 			return true;
 	}
 
 	return false;
 }
 
-/* kernel equivalent to IP_ADD_MEMBERSHIP */
-static int vxlan_join_group(struct net_device *dev)
+static void vxlan_sock_hold(struct vxlan_sock *vs)
 {
-	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
-	struct sock *sk = vxlan->vn_sock->sock->sk;
-	struct ip_mreqn mreq = {
-		.imr_multiaddr.s_addr	= vxlan->default_dst.remote_ip,
-		.imr_ifindex		= vxlan->default_dst.remote_ifindex,
-	};
-	int err;
-
-	/* Already a member of group */
-	if (vxlan_group_used(vn, vxlan))
-		return 0;
+	atomic_inc(&vs->refcnt);
+}
 
-	/* Need to drop RTNL to call multicast join */
-	rtnl_unlock();
-	lock_sock(sk);
-	err = ip_mc_join_group(sk, &mreq);
-	release_sock(sk);
-	rtnl_lock();
+static void vxlan_sock_release(struct vxlan_sock *vs)
+{
+	if (!atomic_dec_and_test(&vs->refcnt))
+		return;
 
-	return err;
+	hlist_del_rcu(&vs->hlist);
+	queue_work(vxlan_wq, &vs->del_work);
 }
 
-
-/* kernel equivalent to IP_DROP_MEMBERSHIP */
-static int vxlan_leave_group(struct net_device *dev)
+/* Callback to update multicast group membership.
+ * Scheduled when vxlan goes up/down.
+ */
+static void vxlan_igmp_work(struct work_struct *work)
 {
-	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
-	int err = 0;
-	struct sock *sk = vxlan->vn_sock->sock->sk;
+	struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_work);
+	struct vxlan_net *vn = net_generic(dev_net(vxlan->dev), vxlan_net_id);
+	struct vxlan_sock *vs = vxlan->vn_sock;
+	struct sock *sk = vs->sock->sk;
 	struct ip_mreqn mreq = {
 		.imr_multiaddr.s_addr	= vxlan->default_dst.remote_ip,
 		.imr_ifindex		= vxlan->default_dst.remote_ifindex,
 	};
 
-	/* Only leave group when last vxlan is done. */
-	if (vxlan_group_used(vn, vxlan))
-		return 0;
-
-	/* Need to drop RTNL to call multicast leave */
-	rtnl_unlock();
 	lock_sock(sk);
-	err = ip_mc_leave_group(sk, &mreq);
+	if (vxlan_group_used(vn, vxlan->default_dst.remote_ip))
+		ip_mc_join_group(sk, &mreq);
+	else
+		ip_mc_leave_group(sk, &mreq);
 	release_sock(sk);
-	rtnl_lock();
 
-	return err;
+	vxlan_sock_release(vs);
+	dev_put(vxlan->dev);
 }
 
 /* Callback from net/ipv4/udp.c to receive packets */

@@ -1265,12 +1248,11 @@ static int vxlan_init(struct net_device
 static int vxlan_open(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	int err;
 
 	if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
-		err = vxlan_join_group(dev);
-		if (err)
-			return err;
+		vxlan_sock_hold(vxlan->vn_sock);
+		dev_hold(dev);
+		queue_work(vxlan_wq, &vxlan->igmp_work);
 	}
 
 	if (vxlan->age_interval)

@@ -1301,8 +1283,11 @@ static int vxlan_stop(struct net_device
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 
-	if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)))
-		vxlan_leave_group(dev);
+	if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
+		vxlan_sock_hold(vxlan->vn_sock);
+		dev_hold(dev);
+		queue_work(vxlan_wq, &vxlan->igmp_work);
+	}
 
 	del_timer_sync(&vxlan->age_timer);
 

@@ -1371,6 +1356,7 @@ static void vxlan_setup(struct net_devic
 
 	INIT_LIST_HEAD(&vxlan->next);
 	spin_lock_init(&vxlan->hash_lock);
+	INIT_WORK(&vxlan->igmp_work, vxlan_igmp_work);
 
 	init_timer_deferrable(&vxlan->age_timer);
 	vxlan->age_timer.function = vxlan_cleanup;

@@ -1514,8 +1500,8 @@ static struct vxlan_sock *vxlan_socket_c
 	udp_sk(sk)->encap_type = 1;
 	udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv;
 	udp_encap_enable();
+	atomic_set(&vs->refcnt, 1);
 
-	vs->refcnt = 1;
 	return vs;
 }
 

@@ -1605,7 +1591,7 @@ static int vxlan_newlink(struct net *net
 
 	vs = vxlan_find_port(net, vxlan->dst_port);
 	if (vs)
-		++vs->refcnt;
+		atomic_inc(&vs->refcnt);
 	else {
 		/* Drop lock because socket create acquires RTNL lock */
 		rtnl_unlock();

@@ -1622,12 +1608,7 @@ static int vxlan_newlink(struct net *net
 
 	err = register_netdevice(dev);
 	if (err) {
-		if (--vs->refcnt == 0) {
-			rtnl_unlock();
-			sk_release_kernel(vs->sock->sk);
-			kfree(vs);
-			rtnl_lock();
-		}
+		vxlan_sock_release(vs);
 		return err;
 	}
 

@@ -1645,11 +1626,7 @@ static void vxlan_dellink(struct net_dev
 	hlist_del_rcu(&vxlan->hlist);
 	list_del(&vxlan->next);
 	unregister_netdevice_queue(dev, head);
-
-	if (--vs->refcnt == 0) {
-		hlist_del_rcu(&vs->hlist);
-		queue_work(vxlan_wq, &vs->del_work);
-	}
+	vxlan_sock_release(vs);
 }
 
 static size_t vxlan_get_size(const struct net_device *dev)

@@ -611,7 +611,6 @@ static bool vxlan_snoop(struct net_devic
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_fdb *f;
-	int err;
 
 	f = vxlan_find_mac(vxlan, src_mac);
 	if (likely(f)) {

@@ -632,12 +631,15 @@ static bool vxlan_snoop(struct net_devic
 	} else {
 		/* learned new entry */
 		spin_lock(&vxlan->hash_lock);
-		err = vxlan_fdb_create(vxlan, src_mac, src_ip,
-				       NUD_REACHABLE,
-				       NLM_F_EXCL|NLM_F_CREATE,
-				       vxlan->dst_port,
-				       vxlan->default_dst.remote_vni,
-				       0, NTF_SELF);
+
+		/* close off race between vxlan_flush and incoming packets */
+		if (netif_running(dev))
+			vxlan_fdb_create(vxlan, src_mac, src_ip,
+					 NUD_REACHABLE,
+					 NLM_F_EXCL|NLM_F_CREATE,
+					 vxlan->dst_port,
+					 vxlan->default_dst.remote_vni,
+					 0, NTF_SELF);
 		spin_unlock(&vxlan->hash_lock);
 	}
 

@@ -148,6 +148,7 @@ struct vxlan_dev {
 
 /* salt for hash table */
 static u32 vxlan_salt __read_mostly;
+static struct workqueue_struct *vxlan_wq;
 
 /* Virtual Network hash table head */
 static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id)

@@ -1645,7 +1646,7 @@ static void vxlan_dellink(struct net_dev
 
 	if (--vs->refcnt == 0) {
 		hlist_del_rcu(&vs->hlist);
-		schedule_work(&vs->del_work);
+		queue_work(vxlan_wq, &vs->del_work);
 	}
 }
 

@@ -1764,6 +1765,10 @@ static int __init vxlan_init_module(void
 {
 	int rc;
 
+	vxlan_wq = alloc_workqueue("vxlan", 0, 0);
+	if (!vxlan_wq)
+		return -ENOMEM;
+
 	get_random_bytes(&vxlan_salt, sizeof(vxlan_salt));
 
 	rc = register_pernet_device(&vxlan_net_ops);

@@ -1779,6 +1784,7 @@ static int __init vxlan_init_module(void
 out2:
 	unregister_pernet_device(&vxlan_net_ops);
 out1:
+	destroy_workqueue(vxlan_wq);
 	return rc;
 }
 late_initcall(vxlan_init_module);

@@ -102,7 +102,7 @@ struct vxlan_rdst {
 	__be16			 remote_port;
 	u32			 remote_vni;
 	u32			 remote_ifindex;
-	struct vxlan_rdst	*remote_next;
+	struct list_head	 list;
 };
 
 /* Forwarding table entry */

@@ -111,7 +111,7 @@ struct vxlan_fdb {
 	struct rcu_head	  rcu;
 	unsigned long	  updated;	/* jiffies */
 	unsigned long	  used;
-	struct vxlan_rdst remote;
+	struct list_head  remotes;
 	u16		  state;	/* see ndm_state */
 	u8		  flags;	/* see ndm_flags */
 	u8		  eth_addr[ETH_ALEN];

@@ -170,6 +170,14 @@ static inline struct hlist_head *vs_head
 	return &vn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
 }
 
+/* First remote destination for a forwarding entry.
+ * Guaranteed to be non-NULL because remotes are never deleted.
+ */
+static inline struct vxlan_rdst *first_remote(struct vxlan_fdb *fdb)
+{
+	return list_first_or_null_rcu(&fdb->remotes, struct vxlan_rdst, list);
+}
+
 /* Find VXLAN socket based on network namespace and UDP port */
 static struct vxlan_sock *vxlan_find_port(struct net *net, __be16 port)
 {

@@ -275,7 +283,7 @@ static inline size_t vxlan_nlmsg_size(vo
 }
 
 static void vxlan_fdb_notify(struct vxlan_dev *vxlan,
-			     const struct vxlan_fdb *fdb, int type)
+			     struct vxlan_fdb *fdb, int type)
 {
 	struct net *net = dev_net(vxlan->dev);
 	struct sk_buff *skb;

@@ -285,7 +293,7 @@ static void vxlan_fdb_notify(struct vxla
 	if (skb == NULL)
 		goto errout;
 
-	err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, &fdb->remote);
+	err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, first_remote(fdb));
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);

@@ -304,11 +312,16 @@ static void vxlan_ip_miss(struct net_dev
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_fdb f;
+	struct vxlan_rdst remote;
 
 	memset(&f, 0, sizeof f);
 	f.state = NUD_STALE;
-	f.remote.remote_ip = ipa; /* goes to NDA_DST */
-	f.remote.remote_vni = VXLAN_N_VID;
+
+	remote.remote_ip = ipa; /* goes to NDA_DST */
+	remote.remote_vni = VXLAN_N_VID;
+
+	INIT_LIST_HEAD(&f.remotes);
+	list_add_rcu(&remote.list, &f.remotes);
 
 	vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);
 }

@@ -318,6 +331,7 @@ static void vxlan_fdb_miss(struct vxlan_
 	struct vxlan_fdb	f;
 
 	memset(&f, 0, sizeof f);
+	INIT_LIST_HEAD(&f.remotes);
 	f.state = NUD_STALE;
 	memcpy(f.eth_addr, eth_addr, ETH_ALEN);
 

@@ -377,17 +391,17 @@ static struct vxlan_fdb *vxlan_find_mac(
 static int vxlan_fdb_append(struct vxlan_fdb *f,
 			    __be32 ip, __be16 port, __u32 vni, __u32 ifindex)
 {
-	struct vxlan_rdst *rd_prev, *rd;
+	struct vxlan_rdst *rd;
 
-	rd_prev = NULL;
-	for (rd = &f->remote; rd; rd = rd->remote_next) {
+	/* protected by vxlan->hash_lock */
+	list_for_each_entry(rd, &f->remotes, list) {
 		if (rd->remote_ip == ip &&
 		    rd->remote_port == port &&
 		    rd->remote_vni == vni &&
 		    rd->remote_ifindex == ifindex)
 			return 0;
-		rd_prev = rd;
 	}
+
 	rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
 	if (rd == NULL)
 		return -ENOBUFS;

@@ -395,8 +409,9 @@ static int vxlan_fdb_append(struct vxlan
 	rd->remote_port = port;
 	rd->remote_vni = vni;
 	rd->remote_ifindex = ifindex;
-	rd->remote_next = NULL;
-	rd_prev->remote_next = rd;
+
+	list_add_tail_rcu(&rd->list, &f->remotes);
+
 	return 1;
 }
 

@@ -448,16 +463,14 @@ static int vxlan_fdb_create(struct vxlan
 			return -ENOMEM;
 
 		notify = 1;
-		f->remote.remote_ip = ip;
-		f->remote.remote_port = port;
-		f->remote.remote_vni = vni;
-		f->remote.remote_ifindex = ifindex;
-		f->remote.remote_next = NULL;
 		f->state = state;
 		f->flags = ndm_flags;
 		f->updated = f->used = jiffies;
+		INIT_LIST_HEAD(&f->remotes);
 		memcpy(f->eth_addr, mac, ETH_ALEN);
 
+		vxlan_fdb_append(f, ip, port, vni, ifindex);
+
 		++vxlan->addrcnt;
 		hlist_add_head_rcu(&f->hlist,
 				   vxlan_fdb_head(vxlan, mac));

@@ -472,13 +485,10 @@ static int vxlan_fdb_create(struct vxlan
 static void vxlan_fdb_free(struct rcu_head *head)
 {
 	struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
+	struct vxlan_rdst *rd, *nd;
 
-	while (f->remote.remote_next) {
-		struct vxlan_rdst *rd = f->remote.remote_next;
-
-		f->remote.remote_next = rd->remote_next;
+	list_for_each_entry_safe(rd, nd, &f->remotes, list)
 		kfree(rd);
-	}
 	kfree(f);
 }
 

@@ -588,23 +598,24 @@ static int vxlan_fdb_dump(struct sk_buff
 
 		hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
 			struct vxlan_rdst *rd;
-			for (rd = &f->remote; rd; rd = rd->remote_next) {
-				if (idx < cb->args[0])
-					goto skip;
 
+			if (idx < cb->args[0])
+				goto skip;
+
+			list_for_each_entry_rcu(rd, &f->remotes, list) {
 				err = vxlan_fdb_info(skb, vxlan, f,
 						     NETLINK_CB(cb->skb).portid,
 						     cb->nlh->nlmsg_seq,
 						     RTM_NEWNEIGH,
 						     NLM_F_MULTI, rd);
 				if (err < 0)
-					break;
-skip:
-				++idx;
+					goto out;
 			}
+skip:
+			++idx;
 		}
 	}
-
+out:
 	return idx;
 }
 

@@ -620,19 +631,21 @@ static bool vxlan_snoop(struct net_devic
 
 	f = vxlan_find_mac(vxlan, src_mac);
 	if (likely(f)) {
-		if (likely(f->remote.remote_ip == src_ip))
-			return false;
+		struct vxlan_rdst *rdst = first_remote(f);
 
 		/* Don't migrate static entries, drop packets */
 		if (!(f->flags & NTF_SELF))
 			return true;
 
+		if (likely(rdst->remote_ip == src_ip))
+			return false;
+
 		if (net_ratelimit())
 			netdev_info(dev,
 				    "%pM migrated from %pI4 to %pI4\n",
-				    src_mac, &f->remote.remote_ip, &src_ip);
+				    src_mac, &rdst->remote_ip, &src_ip);
 
-		f->remote.remote_ip = src_ip;
+		rdst->remote_ip = src_ip;
 		f->updated = jiffies;
 		vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH);
 	} else {

@@ -866,7 +879,7 @@ static int arp_reduce(struct net_device
 		}
 
 		f = vxlan_find_mac(vxlan, n->ha);
-		if (f && f->remote.remote_ip == htonl(INADDR_ANY)) {
+		if (f && first_remote(f)->remote_ip == htonl(INADDR_ANY)) {
 			/* bridge-local neighbor */
 			neigh_release(n);
 			goto out;

@@ -1181,17 +1194,17 @@ static netdev_tx_t vxlan_xmit(struct sk_
 		    (vxlan->flags & VXLAN_F_L2MISS) &&
 		    !is_multicast_ether_addr(eth->h_dest))
 			vxlan_fdb_miss(vxlan, eth->h_dest);
-	} else
-		rdst0 = &f->remote;
-
-
-	/* if there are multiple destinations, send copies */
-	for (rdst = rdst0->remote_next; rdst; rdst = rdst->remote_next) {
-		struct sk_buff *skb1;
+	} else {
+		rdst = rdst0 = first_remote(f);
 
-		skb1 = skb_clone(skb, GFP_ATOMIC);
-		if (skb1)
-			vxlan_xmit_one(skb1, dev, rdst, did_rsc);
+		/* if there are multiple destinations, send copies */
+		list_for_each_entry_continue_rcu(rdst, &f->remotes, list) {
+			struct sk_buff *skb1;
+
+			skb1 = skb_clone(skb, GFP_ATOMIC);
+			if (skb1)
+				vxlan_xmit_one(skb1, dev, rdst, did_rsc);
+		}
 	}
 
 	vxlan_xmit_one(skb, dev, rdst0, did_rsc);