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

Pull networking fixes from David Miller:

 1) Fix association failures not triggering a connect-failure event in
    cfg80211, from Johannes Berg.

 2) Eliminate a potential NULL deref with older iptables tools when
    configuring xt_socket rules, from Eric Dumazet.

 3) Missing RTNL locking in wireless regulatory code, from Johannes
    Berg.

 4) Fix OOPS caused by firmware loading races in ath9k_htc, from Alexey
    Khoroshilov.

 5) Fix usb URB leak in usb_8dev CAN driver, also from Alexey
    Khoroshilov.

 6) VXLAN namespace teardown fails to unregister devices, from Stephen
    Hemminger.

 7) Fix multicast settings getting dropped by firmware in qlcnic driver,
    from Sucheta Chakraborty.

 8) Add sysctl range enforcement for tcp_syn_retries, from Michal Tesar.

 9) Fix a nasty bug in bridging where an active timer would get
    reinitialized with a setup_timer() call.  From Eric Dumazet.

10) Fix use after free in new mlx5 driver, from Dan Carpenter.

11) Fix freed pointer reference in ipv6 multicast routing on namespace
    cleanup, from Hannes Frederic Sowa.

12) Some usbnet drivers report TSO and SG in their feature set, but the
    usbnet layer doesn't really support them.  From Eric Dumazet.

13) Fix crash on EEH errors in tg3 driver, from Gavin Shan.

14) Drop cb_lock when requesting modules in genetlink, from Stanislaw
    Gruszka.

15) Kernel stack leaks in cbq scheduler and af_key pfkey messages, from
    Dan Carpenter.

16) FEC driver erroneously signals NETDEV_TX_BUSY on transmit leading to
    endless loops, from Uwe Kleine-König.

17) Fix hangs from loading mvneta driver, from Arnaud Patard.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (84 commits)
  mlx5: fix error return code in mlx5_alloc_uuars()
  mvneta: Try to fix mvneta when compiled as module
  mvneta: Fix hang when loading the mvneta driver
  atl1c: Fix misuse of netdev_alloc_skb in refilling rx ring
  genetlink: fix usage of NLM_F_EXCL or NLM_F_REPLACE
  af_key: more info leaks in pfkey messages
  net/fec: Don't let ndo_start_xmit return NETDEV_TX_BUSY without link
  net_sched: Fix stack info leak in cbq_dump_wrr().
  igb: fix vlan filtering in promisc mode when not in VT mode
  ixgbe: Fix Tx Hang issue with lldpad on 82598EB
  genetlink: release cb_lock before requesting additional module
  net: fec: workaround stop tx during errata ERR006358
  qlcnic: Fix diagnostic interrupt test for 83xx adapters.
  qlcnic: Fix setting Guest VLAN
  qlcnic: Fix operation type and command type.
  qlcnic: Fix initialization of work function.
  Revert "atl1c: Fix misuse of netdev_alloc_skb in refilling rx ring"
  atl1c: Fix misuse of netdev_alloc_skb in refilling rx ring
  net/tg3: Fix warning from pci_disable_device()
  net/tg3: Fix kernel crash
  ...

1 files changed, 41 insertions, 16 deletions

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a5ba8dd7e6be..f4c6db419ddb 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -136,7 +136,8 @@ struct vxlan_dev {
 	u32		  flags;	/* VXLAN_F_* below */
 
 	struct work_struct sock_work;
-	struct work_struct igmp_work;
+	struct work_struct igmp_join;
+	struct work_struct igmp_leave;
 
 	unsigned long	  age_interval;
 	struct timer_list age_timer;
@@ -736,7 +737,6 @@ static bool vxlan_snoop(struct net_device *dev,
 	return false;
 }
 
-
 /* See if multicast group is already in use by other ID */
 static bool vxlan_group_used(struct vxlan_net *vn, __be32 remote_ip)
 {
@@ -770,12 +770,13 @@ static void vxlan_sock_release(struct vxlan_net *vn, struct vxlan_sock *vs)
 	queue_work(vxlan_wq, &vs->del_work);
 }
 
-/* Callback to update multicast group membership.
- * Scheduled when vxlan goes up/down.
+/* Callback to update multicast group membership when first VNI on
+ * multicast asddress is brought up
+ * Done as workqueue because ip_mc_join_group acquires RTNL.
  */
-static void vxlan_igmp_work(struct work_struct *work)
+static void vxlan_igmp_join(struct work_struct *work)
 {
-	struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_work);
+	struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join);
 	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;
@@ -785,10 +786,27 @@ static void vxlan_igmp_work(struct work_struct *work)
 	};
 
 	lock_sock(sk);
-	if (vxlan_group_used(vn, vxlan->default_dst.remote_ip))
-		ip_mc_join_group(sk, &mreq);
-	else
-		ip_mc_leave_group(sk, &mreq);
+	ip_mc_join_group(sk, &mreq);
+	release_sock(sk);
+
+	vxlan_sock_release(vn, vs);
+	dev_put(vxlan->dev);
+}
+
+/* Inverse of vxlan_igmp_join when last VNI is brought down */
+static void vxlan_igmp_leave(struct work_struct *work)
+{
+	struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave);
+	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,
+	};
+
+	lock_sock(sk);
+	ip_mc_leave_group(sk, &mreq);
 	release_sock(sk);
 
 	vxlan_sock_release(vn, vs);
@@ -1359,6 +1377,7 @@ 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;
 
@@ -1366,10 +1385,11 @@ static int vxlan_open(struct net_device *dev)
 	if (!vs)
 		return -ENOTCONN;
 
-	if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
+	if (IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)) &&
+	    ! vxlan_group_used(vn, vxlan->default_dst.remote_ip)) {
 		vxlan_sock_hold(vs);
 		dev_hold(dev);
-		queue_work(vxlan_wq, &vxlan->igmp_work);
+		queue_work(vxlan_wq, &vxlan->igmp_join);
 	}
 
 	if (vxlan->age_interval)
@@ -1400,13 +1420,15 @@ static void vxlan_flush(struct vxlan_dev *vxlan)
 /* Cleanup timer and forwarding table on shutdown */
 static int vxlan_stop(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;
 
-	if (vs && IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip))) {
+	if (vs && IN_MULTICAST(ntohl(vxlan->default_dst.remote_ip)) &&
+	    ! vxlan_group_used(vn, vxlan->default_dst.remote_ip)) {
 		vxlan_sock_hold(vs);
 		dev_hold(dev);
-		queue_work(vxlan_wq, &vxlan->igmp_work);
+		queue_work(vxlan_wq, &vxlan->igmp_leave);
 	}
 
 	del_timer_sync(&vxlan->age_timer);
@@ -1471,7 +1493,8 @@ static void vxlan_setup(struct net_device *dev)
 
 	INIT_LIST_HEAD(&vxlan->next);
 	spin_lock_init(&vxlan->hash_lock);
-	INIT_WORK(&vxlan->igmp_work, vxlan_igmp_work);
+	INIT_WORK(&vxlan->igmp_join, vxlan_igmp_join);
+	INIT_WORK(&vxlan->igmp_leave, vxlan_igmp_leave);
 	INIT_WORK(&vxlan->sock_work, vxlan_sock_work);
 
 	init_timer_deferrable(&vxlan->age_timer);
@@ -1878,10 +1901,12 @@ 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)
-		dev_close(vxlan->dev);
+		unregister_netdevice_queue(vxlan->dev, &list);
+	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }