Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) BPF debugger and asm tool by Daniel Borkmann.

 2) Speed up create/bind in AF_PACKET, also from Daniel Borkmann.

 3) Correct reciprocal_divide and update users, from Hannes Frederic
    Sowa and Daniel Borkmann.

 4) Currently we only have a "set" operation for the hw timestamp socket
    ioctl, add a "get" operation to match.  From Ben Hutchings.

 5) Add better trace events for debugging driver datapath problems, also
    from Ben Hutchings.

 6) Implement auto corking in TCP, from Eric Dumazet.  Basically, if we
    have a small send and a previous packet is already in the qdisc or
    device queue, defer until TX completion or we get more data.

 7) Allow userspace to manage ipv6 temporary addresses, from Jiri Pirko.

 8) Add a qdisc bypass option for AF_PACKET sockets, from Daniel
    Borkmann.

 9) Share IP header compression code between Bluetooth and IEEE802154
    layers, from Jukka Rissanen.

10) Fix ipv6 router reachability probing, from Jiri Benc.

11) Allow packets to be captured on macvtap devices, from Vlad Yasevich.

12) Support tunneling in GRO layer, from Jerry Chu.

13) Allow bonding to be configured fully using netlink, from Scott
    Feldman.

14) Allow AF_PACKET users to obtain the VLAN TPID, just like they can
    already get the TCI.  From Atzm Watanabe.

15) New "Heavy Hitter" qdisc, from Terry Lam.

16) Significantly improve the IPSEC support in pktgen, from Fan Du.

17) Allow ipv4 tunnels to cache routes, just like sockets.  From Tom
    Herbert.

18) Add Proportional Integral Enhanced packet scheduler, from Vijay
    Subramanian.

19) Allow openvswitch to mmap'd netlink, from Thomas Graf.

20) Key TCP metrics blobs also by source address, not just destination
    address.  From Christoph Paasch.

21) Support 10G in generic phylib.  From Andy Fleming.

22) Try to short-circuit GRO flow compares using device provided RX
    hash, if provided.  From Tom Herbert.

The wireless and netfilter folks have been busy little bees too.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2064 commits)
  net/cxgb4: Fix referencing freed adapter
  ipv6: reallocate addrconf router for ipv6 address when lo device up
  fib_frontend: fix possible NULL pointer dereference
  rtnetlink: remove IFLA_BOND_SLAVE definition
  rtnetlink: remove check for fill_slave_info in rtnl_have_link_slave_info
  qlcnic: update version to 5.3.55
  qlcnic: Enhance logic to calculate msix vectors.
  qlcnic: Refactor interrupt coalescing code for all adapters.
  qlcnic: Update poll controller code path
  qlcnic: Interrupt code cleanup
  qlcnic: Enhance Tx timeout debugging.
  qlcnic: Use bool for rx_mac_learn.
  bonding: fix u64 division
  rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC
  sfc: Use the correct maximum TX DMA ring size for SFC9100
  Add Shradha Shah as the sfc driver maintainer.
  net/vxlan: Share RX skb de-marking and checksum checks with ovs
  tulip: cleanup by using ARRAY_SIZE()
  ip_tunnel: clear IPCB in ip_tunnel_xmit() in case dst_link_failure() is called
  net/cxgb4: Don't retrieve stats during recovery
  ...

1 files changed, 233 insertions, 75 deletions

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ed384fee76a..026a313c2d2 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -40,6 +40,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/vxlan.h>
+#include <net/protocol.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
 #include <net/addrconf.h>
@@ -554,13 +555,106 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
 	return 1;
 }
 
+static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+	struct sk_buff *p, **pp = NULL;
+	struct vxlanhdr *vh, *vh2;
+	struct ethhdr *eh, *eh2;
+	unsigned int hlen, off_vx, off_eth;
+	const struct packet_offload *ptype;
+	__be16 type;
+	int flush = 1;
+
+	off_vx = skb_gro_offset(skb);
+	hlen = off_vx + sizeof(*vh);
+	vh   = skb_gro_header_fast(skb, off_vx);
+	if (skb_gro_header_hard(skb, hlen)) {
+		vh = skb_gro_header_slow(skb, hlen, off_vx);
+		if (unlikely(!vh))
+			goto out;
+	}
+	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
+
+	off_eth = skb_gro_offset(skb);
+	hlen = off_eth + sizeof(*eh);
+	eh   = skb_gro_header_fast(skb, off_eth);
+	if (skb_gro_header_hard(skb, hlen)) {
+		eh = skb_gro_header_slow(skb, hlen, off_eth);
+		if (unlikely(!eh))
+			goto out;
+	}
+
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		vh2 = (struct vxlanhdr *)(p->data + off_vx);
+		eh2 = (struct ethhdr   *)(p->data + off_eth);
+		if (vh->vx_vni != vh2->vx_vni || compare_ether_header(eh, eh2)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+		goto found;
+	}
+
+found:
+	type = eh->h_proto;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (ptype == NULL) {
+		flush = 1;
+		goto out_unlock;
+	}
+
+	skb_gro_pull(skb, sizeof(*eh)); /* pull inner eth header */
+	pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+
+static int vxlan_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct ethhdr *eh;
+	struct packet_offload *ptype;
+	__be16 type;
+	int vxlan_len  = sizeof(struct vxlanhdr) + sizeof(struct ethhdr);
+	int err = -ENOSYS;
+
+	eh = (struct ethhdr *)(skb->data + nhoff + sizeof(struct vxlanhdr));
+	type = eh->h_proto;
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype != NULL)
+		err = ptype->callbacks.gro_complete(skb, nhoff + vxlan_len);
+
+	rcu_read_unlock();
+	return err;
+}
+
 /* Notify netdevs that UDP port started listening */
-static void vxlan_notify_add_rx_port(struct sock *sk)
+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 = sk->sk_family;
 	__be16 port = inet_sk(sk)->inet_sport;
+	int err;
+
+	if (sa_family == AF_INET) {
+		err = udp_add_offload(&vs->udp_offloads);
+		if (err)
+			pr_warn("vxlan: udp_add_offload failed with status %d\n", err);
+	}
 
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
@@ -572,9 +666,10 @@ static void vxlan_notify_add_rx_port(struct sock *sk)
 }
 
 /* Notify netdevs that UDP port is no more listening */
-static void vxlan_notify_del_rx_port(struct sock *sk)
+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 = sk->sk_family;
 	__be16 port = inet_sk(sk)->inet_sport;
@@ -586,6 +681,9 @@ static void vxlan_notify_del_rx_port(struct sock *sk)
 							    port);
 	}
 	rcu_read_unlock();
+
+	if (sa_family == AF_INET)
+		udp_del_offload(&vs->udp_offloads);
 }
 
 /* Add new entry to forwarding table -- assumes lock held */
@@ -741,10 +839,9 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
 		if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
 			return -EINVAL;
 		*ifindex = nla_get_u32(tb[NDA_IFINDEX]);
-		tdev = dev_get_by_index(net, *ifindex);
+		tdev = __dev_get_by_index(net, *ifindex);
 		if (!tdev)
 			return -EADDRNOTAVAIL;
-		dev_put(tdev);
 	} else {
 		*ifindex = 0;
 	}
@@ -916,17 +1013,32 @@ static bool vxlan_snoop(struct net_device *dev,
 }
 
 /* See if multicast group is already in use by other ID */
-static bool vxlan_group_used(struct vxlan_net *vn, union vxlan_addr *remote_ip)
+static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
 {
 	struct vxlan_dev *vxlan;
 
+	/* The vxlan_sock is only used by dev, leaving group has
+	 * no effect on other vxlan devices.
+	 */
+	if (atomic_read(&dev->vn_sock->refcnt) == 1)
+		return false;
+
 	list_for_each_entry(vxlan, &vn->vxlan_list, next) {
-		if (!netif_running(vxlan->dev))
+		if (!netif_running(vxlan->dev) || vxlan == dev)
 			continue;
 
-		if (vxlan_addr_equal(&vxlan->default_dst.remote_ip,
-				     remote_ip))
-			return true;
+		if (vxlan->vn_sock != dev->vn_sock)
+			continue;
+
+		if (!vxlan_addr_equal(&vxlan->default_dst.remote_ip,
+				      &dev->default_dst.remote_ip))
+			continue;
+
+		if (vxlan->default_dst.remote_ifindex !=
+		    dev->default_dst.remote_ifindex)
+			continue;
+
+		return true;
 	}
 
 	return false;
@@ -949,7 +1061,7 @@ 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(sk);
+	vxlan_notify_del_rx_port(vs);
 	spin_unlock(&vn->sock_lock);
 
 	queue_work(vxlan_wq, &vs->del_work);
@@ -1047,6 +1159,16 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	if (!vs)
 		goto drop;
 
+	/* If the NIC driver gave us an encapsulated packet
+	 * with the encapsulation mark, the device checksummed it
+	 * for us. Otherwise force the upper layers to verify it.
+	 */
+	if ((skb->ip_summed != CHECKSUM_UNNECESSARY && skb->ip_summed != CHECKSUM_PARTIAL) ||
+	    !skb->encapsulation)
+		skb->ip_summed = CHECKSUM_NONE;
+
+	skb->encapsulation = 0;
+
 	vs->rcv(vs, skb, vxh->vx_vni);
 	return 0;
 
@@ -1066,7 +1188,7 @@ static void vxlan_rcv(struct vxlan_sock *vs,
 	struct iphdr *oip = NULL;
 	struct ipv6hdr *oip6 = NULL;
 	struct vxlan_dev *vxlan;
-	struct pcpu_tstats *stats;
+	struct pcpu_sw_netstats *stats;
 	union vxlan_addr saddr;
 	__u32 vni;
 	int err = 0;
@@ -1105,17 +1227,6 @@ static void vxlan_rcv(struct vxlan_sock *vs,
 
 	skb_reset_network_header(skb);
 
-	/* If the NIC driver gave us an encapsulated packet with
-	 * CHECKSUM_UNNECESSARY and Rx checksum feature is enabled,
-	 * leave the CHECKSUM_UNNECESSARY, the device checksummed it
-	 * for us. Otherwise force the upper layers to verify it.
-	 */
-	if (skb->ip_summed != CHECKSUM_UNNECESSARY || !skb->encapsulation ||
-	    !(vxlan->dev->features & NETIF_F_RXCSUM))
-		skb->ip_summed = CHECKSUM_NONE;
-
-	skb->encapsulation = 0;
-
 	if (oip6)
 		err = IP6_ECN_decapsulate(oip6, skb);
 	if (oip)
@@ -1366,20 +1477,6 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	return false;
 }
 
-static void vxlan_sock_put(struct sk_buff *skb)
-{
-	sock_put(skb->sk);
-}
-
-/* On transmit, associate with the tunnel socket */
-static void vxlan_set_owner(struct sock *sk, struct sk_buff *skb)
-{
-	skb_orphan(skb);
-	sock_hold(sk);
-	skb->sk = sk;
-	skb->destructor = vxlan_sock_put;
-}
-
 /* Compute source port for outgoing packet
  *   first choice to use L4 flow hash since it will spread
  *     better and maybe available from hardware
@@ -1390,7 +1487,7 @@ __be16 vxlan_src_port(__u16 port_min, __u16 port_max, struct sk_buff *skb)
 	unsigned int range = (port_max - port_min) + 1;
 	u32 hash;
 
-	hash = skb_get_rxhash(skb);
+	hash = skb_get_hash(skb);
 	if (!hash)
 		hash = jhash(skb->data, 2 * ETH_ALEN,
 			     (__force u32) skb->protocol);
@@ -1499,8 +1596,6 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	ip6h->daddr	  = *daddr;
 	ip6h->saddr	  = *saddr;
 
-	vxlan_set_owner(vs->sock->sk, skb);
-
 	err = handle_offloads(skb);
 	if (err)
 		return err;
@@ -1557,8 +1652,6 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 	uh->len = htons(skb->len);
 	uh->check = 0;
 
-	vxlan_set_owner(vs->sock->sk, skb);
-
 	err = handle_offloads(skb);
 	if (err)
 		return err;
@@ -1572,11 +1665,12 @@ EXPORT_SYMBOL_GPL(vxlan_xmit_skb);
 static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 			       struct vxlan_dev *dst_vxlan)
 {
-	struct pcpu_tstats *tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
-	struct pcpu_tstats *rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
+	struct pcpu_sw_netstats *tx_stats, *rx_stats;
 	union vxlan_addr loopback;
 	union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
 
+	tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
+	rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
 	skb->pkt_type = PACKET_HOST;
 	skb->encapsulation = 0;
 	skb->dev = dst_vxlan->dev;
@@ -1770,7 +1864,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct ethhdr *eth;
 	bool did_rsc = false;
-	struct vxlan_rdst *rdst;
+	struct vxlan_rdst *rdst, *fdst = NULL;
 	struct vxlan_fdb *f;
 
 	skb_reset_mac_header(skb);
@@ -1812,7 +1906,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 				vxlan_fdb_miss(vxlan, eth->h_dest);
 
 			dev->stats.tx_dropped++;
-			dev_kfree_skb(skb);
+			kfree_skb(skb);
 			return NETDEV_TX_OK;
 		}
 	}
@@ -1820,12 +1914,19 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	list_for_each_entry_rcu(rdst, &f->remotes, list) {
 		struct sk_buff *skb1;
 
+		if (!fdst) {
+			fdst = rdst;
+			continue;
+		}
 		skb1 = skb_clone(skb, GFP_ATOMIC);
 		if (skb1)
 			vxlan_xmit_one(skb1, dev, rdst, did_rsc);
 	}
 
-	dev_kfree_skb(skb);
+	if (fdst)
+		vxlan_xmit_one(skb, dev, fdst, did_rsc);
+	else
+		kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
 
@@ -1882,12 +1983,12 @@ static int vxlan_init(struct net_device *dev)
 	struct vxlan_sock *vs;
 	int i;
 
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
 	for_each_possible_cpu(i) {
-		struct pcpu_tstats *vxlan_stats;
+		struct pcpu_sw_netstats *vxlan_stats;
 		vxlan_stats = per_cpu_ptr(dev->tstats, i);
 		u64_stats_init(&vxlan_stats->syncp);
 	}
@@ -1935,7 +2036,6 @@ static void vxlan_uninit(struct net_device *dev)
 /* Start ageing timer and join group when device is brought up */
 static int vxlan_open(struct net_device *dev)
 {
-	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_sock *vs = vxlan->vn_sock;
 
@@ -1943,8 +2043,7 @@ static int vxlan_open(struct net_device *dev)
 	if (!vs)
 		return -ENOTCONN;
 
-	if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
-	    vxlan_group_used(vn, &vxlan->default_dst.remote_ip)) {
+	if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) {
 		vxlan_sock_hold(vs);
 		dev_hold(dev);
 		queue_work(vxlan_wq, &vxlan->igmp_join);
@@ -1983,7 +2082,7 @@ static int vxlan_stop(struct net_device *dev)
 	struct vxlan_sock *vs = vxlan->vn_sock;
 
 	if (vs && vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
-	    ! vxlan_group_used(vn, &vxlan->default_dst.remote_ip)) {
+	    !vxlan_group_used(vn, vxlan)) {
 		vxlan_sock_hold(vs);
 		dev_hold(dev);
 		queue_work(vxlan_wq, &vxlan->igmp_leave);
@@ -2001,6 +2100,29 @@ static void vxlan_set_multicast_list(struct net_device *dev)
 {
 }
 
+static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_rdst *dst = &vxlan->default_dst;
+	struct net_device *lowerdev;
+	int max_mtu;
+
+	lowerdev = __dev_get_by_index(dev_net(dev), dst->remote_ifindex);
+	if (lowerdev == NULL)
+		return eth_change_mtu(dev, new_mtu);
+
+	if (dst->remote_ip.sa.sa_family == AF_INET6)
+		max_mtu = lowerdev->mtu - VXLAN6_HEADROOM;
+	else
+		max_mtu = lowerdev->mtu - VXLAN_HEADROOM;
+
+	if (new_mtu < 68 || new_mtu > max_mtu)
+		return -EINVAL;
+
+	dev->mtu = new_mtu;
+	return 0;
+}
+
 static const struct net_device_ops vxlan_netdev_ops = {
 	.ndo_init		= vxlan_init,
 	.ndo_uninit		= vxlan_uninit,
@@ -2009,7 +2131,7 @@ static const struct net_device_ops vxlan_netdev_ops = {
 	.ndo_start_xmit		= vxlan_xmit,
 	.ndo_get_stats64	= ip_tunnel_get_stats64,
 	.ndo_set_rx_mode	= vxlan_set_multicast_list,
-	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_change_mtu		= vxlan_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_fdb_add		= vxlan_fdb_add,
@@ -2278,7 +2400,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 	struct sock *sk;
 	unsigned int h;
 
-	vs = kmalloc(sizeof(*vs), GFP_KERNEL);
+	vs = kzalloc(sizeof(*vs), GFP_KERNEL);
 	if (!vs)
 		return ERR_PTR(-ENOMEM);
 
@@ -2303,9 +2425,14 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 	vs->data = data;
 	rcu_assign_sk_user_data(vs->sock->sk, vs);
 
+	/* Initialize the vxlan udp offloads structure */
+	vs->udp_offloads.port = port;
+	vs->udp_offloads.callbacks.gro_receive  = vxlan_gro_receive;
+	vs->udp_offloads.callbacks.gro_complete = vxlan_gro_complete;
+
 	spin_lock(&vn->sock_lock);
 	hlist_add_head_rcu(&vs->hlist, vs_head(net, port));
-	vxlan_notify_add_rx_port(sk);
+	vxlan_notify_add_rx_port(vs);
 	spin_unlock(&vn->sock_lock);
 
 	/* Mark socket as an encapsulation socket. */
@@ -2630,6 +2757,44 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = {
 	.fill_info	= vxlan_fill_info,
 };
 
+static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn,
+					     struct net_device *dev)
+{
+	struct vxlan_dev *vxlan, *next;
+	LIST_HEAD(list_kill);
+
+	list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) {
+		struct vxlan_rdst *dst = &vxlan->default_dst;
+
+		/* In case we created vxlan device with carrier
+		 * and we loose the carrier due to module unload
+		 * we also need to remove vxlan device. In other
+		 * cases, it's not necessary and remote_ifindex
+		 * is 0 here, so no matches.
+		 */
+		if (dst->remote_ifindex == dev->ifindex)
+			vxlan_dellink(vxlan->dev, &list_kill);
+	}
+
+	unregister_netdevice_many(&list_kill);
+}
+
+static int vxlan_lowerdev_event(struct notifier_block *unused,
+				unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+
+	if (event == NETDEV_UNREGISTER)
+		vxlan_handle_lowerdev_unregister(vn, dev);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block vxlan_notifier_block __read_mostly = {
+	.notifier_call = vxlan_lowerdev_event,
+};
+
 static __net_init int vxlan_init_net(struct net *net)
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
@@ -2644,22 +2809,8 @@ static __net_init int vxlan_init_net(struct net *net)
 	return 0;
 }
 
-static __net_exit void vxlan_exit_net(struct net *net)
-{
-	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
-	struct vxlan_dev *vxlan;
-	LIST_HEAD(list);
-
-	rtnl_lock();
-	list_for_each_entry(vxlan, &vn->vxlan_list, next)
-		unregister_netdevice_queue(vxlan->dev, &list);
-	unregister_netdevice_many(&list);
-	rtnl_unlock();
-}
-
 static struct pernet_operations vxlan_net_ops = {
 	.init = vxlan_init_net,
-	.exit = vxlan_exit_net,
 	.id   = &vxlan_net_id,
 	.size = sizeof(struct vxlan_net),
 };
@@ -2674,18 +2825,23 @@ static int __init vxlan_init_module(void)
 
 	get_random_bytes(&vxlan_salt, sizeof(vxlan_salt));
 
-	rc = register_pernet_device(&vxlan_net_ops);
+	rc = register_pernet_subsys(&vxlan_net_ops);
 	if (rc)
 		goto out1;
 
-	rc = rtnl_link_register(&vxlan_link_ops);
+	rc = register_netdevice_notifier(&vxlan_notifier_block);
 	if (rc)
 		goto out2;
 
-	return 0;
+	rc = rtnl_link_register(&vxlan_link_ops);
+	if (rc)
+		goto out3;
 
+	return 0;
+out3:
+	unregister_netdevice_notifier(&vxlan_notifier_block);
 out2:
-	unregister_pernet_device(&vxlan_net_ops);
+	unregister_pernet_subsys(&vxlan_net_ops);
 out1:
 	destroy_workqueue(vxlan_wq);
 	return rc;
@@ -2695,13 +2851,15 @@ late_initcall(vxlan_init_module);
 static void __exit vxlan_cleanup_module(void)
 {
 	rtnl_link_unregister(&vxlan_link_ops);
+	unregister_netdevice_notifier(&vxlan_notifier_block);
 	destroy_workqueue(vxlan_wq);
-	unregister_pernet_device(&vxlan_net_ops);
-	rcu_barrier();
+	unregister_pernet_subsys(&vxlan_net_ops);
+	/* rcu_barrier() is called by netns */
 }
 module_exit(vxlan_cleanup_module);
 
 MODULE_LICENSE("GPL");
 MODULE_VERSION(VXLAN_VERSION);
 MODULE_AUTHOR("Stephen Hemminger <stephen@networkplumber.org>");
+MODULE_DESCRIPTION("Driver for VXLAN encapsulated traffic");
 MODULE_ALIAS_RTNL_LINK("vxlan");