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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 76 insertions, 30 deletions

diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 014a7bc2a872..5c366ecfa1cb 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -41,8 +41,6 @@
 
 /* via netdev_priv() */
 struct l2tp_eth {
-	struct net_device	*dev;
-	struct sock		*tunnel_sock;
 	struct l2tp_session	*session;
 	atomic_long_t		tx_bytes;
 	atomic_long_t		tx_packets;
@@ -54,15 +52,12 @@ struct l2tp_eth {
 
 /* via l2tp_session_priv() */
 struct l2tp_eth_sess {
-	struct net_device	*dev;
+	struct net_device __rcu *dev;
 };
 
 
 static int l2tp_eth_dev_init(struct net_device *dev)
 {
-	struct l2tp_eth *priv = netdev_priv(dev);
-
-	priv->dev = dev;
 	eth_hw_addr_random(dev);
 	eth_broadcast_addr(dev->broadcast);
 	netdev_lockdep_set_classes(dev);
@@ -72,7 +67,14 @@ static int l2tp_eth_dev_init(struct net_device *dev)
 
 static void l2tp_eth_dev_uninit(struct net_device *dev)
 {
-	dev_put(dev);
+	struct l2tp_eth *priv = netdev_priv(dev);
+	struct l2tp_eth_sess *spriv;
+
+	spriv = l2tp_session_priv(priv->session);
+	RCU_INIT_POINTER(spriv->dev, NULL);
+	/* No need for synchronize_net() here. We're called by
+	 * unregister_netdev*(), which does the synchronisation for us.
+	 */
 }
 
 static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -130,8 +132,8 @@ static void l2tp_eth_dev_setup(struct net_device *dev)
 static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
 {
 	struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
-	struct net_device *dev = spriv->dev;
-	struct l2tp_eth *priv = netdev_priv(dev);
+	struct net_device *dev;
+	struct l2tp_eth *priv;
 
 	if (session->debug & L2TP_MSG_DATA) {
 		unsigned int length;
@@ -155,16 +157,25 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb,
 	skb_dst_drop(skb);
 	nf_reset(skb);
 
+	rcu_read_lock();
+	dev = rcu_dereference(spriv->dev);
+	if (!dev)
+		goto error_rcu;
+
+	priv = netdev_priv(dev);
 	if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) {
 		atomic_long_inc(&priv->rx_packets);
 		atomic_long_add(data_len, &priv->rx_bytes);
 	} else {
 		atomic_long_inc(&priv->rx_errors);
 	}
+	rcu_read_unlock();
+
 	return;
 
+error_rcu:
+	rcu_read_unlock();
 error:
-	atomic_long_inc(&priv->rx_errors);
 	kfree_skb(skb);
 }
 
@@ -175,11 +186,15 @@ static void l2tp_eth_delete(struct l2tp_session *session)
 
 	if (session) {
 		spriv = l2tp_session_priv(session);
-		dev = spriv->dev;
+
+		rtnl_lock();
+		dev = rtnl_dereference(spriv->dev);
 		if (dev) {
-			unregister_netdev(dev);
-			spriv->dev = NULL;
+			unregister_netdevice(dev);
+			rtnl_unlock();
 			module_put(THIS_MODULE);
+		} else {
+			rtnl_unlock();
 		}
 	}
 }
@@ -189,9 +204,20 @@ static void l2tp_eth_show(struct seq_file *m, void *arg)
 {
 	struct l2tp_session *session = arg;
 	struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
-	struct net_device *dev = spriv->dev;
+	struct net_device *dev;
+
+	rcu_read_lock();
+	dev = rcu_dereference(spriv->dev);
+	if (!dev) {
+		rcu_read_unlock();
+		return;
+	}
+	dev_hold(dev);
+	rcu_read_unlock();
 
 	seq_printf(m, "   interface %s\n", dev->name);
+
+	dev_put(dev);
 }
 #endif
 
@@ -268,14 +294,14 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 				      peer_session_id, cfg);
 	if (IS_ERR(session)) {
 		rc = PTR_ERR(session);
-		goto out;
+		goto err;
 	}
 
 	dev = alloc_netdev(sizeof(*priv), name, name_assign_type,
 			   l2tp_eth_dev_setup);
 	if (!dev) {
 		rc = -ENOMEM;
-		goto out_del_session;
+		goto err_sess;
 	}
 
 	dev_net_set(dev, net);
@@ -284,10 +310,8 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 	l2tp_eth_adjust_mtu(tunnel, session, dev);
 
 	priv = netdev_priv(dev);
-	priv->dev = dev;
 	priv->session = session;
 
-	priv->tunnel_sock = tunnel->sock;
 	session->recv_skb = l2tp_eth_dev_recv;
 	session->session_close = l2tp_eth_delete;
 #if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
@@ -295,26 +319,48 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 #endif
 
 	spriv = l2tp_session_priv(session);
-	spriv->dev = dev;
 
-	rc = register_netdev(dev);
-	if (rc < 0)
-		goto out_del_dev;
+	l2tp_session_inc_refcount(session);
+
+	rtnl_lock();
+
+	/* Register both device and session while holding the rtnl lock. This
+	 * ensures that l2tp_eth_delete() will see that there's a device to
+	 * unregister, even if it happened to run before we assign spriv->dev.
+	 */
+	rc = l2tp_session_register(session, tunnel);
+	if (rc < 0) {
+		rtnl_unlock();
+		goto err_sess_dev;
+	}
+
+	rc = register_netdevice(dev);
+	if (rc < 0) {
+		rtnl_unlock();
+		l2tp_session_delete(session);
+		l2tp_session_dec_refcount(session);
+		free_netdev(dev);
+
+		return rc;
+	}
 
-	__module_get(THIS_MODULE);
-	/* Must be done after register_netdev() */
 	strlcpy(session->ifname, dev->name, IFNAMSIZ);
+	rcu_assign_pointer(spriv->dev, dev);
 
-	dev_hold(dev);
+	rtnl_unlock();
+
+	l2tp_session_dec_refcount(session);
+
+	__module_get(THIS_MODULE);
 
 	return 0;
 
-out_del_dev:
+err_sess_dev:
+	l2tp_session_dec_refcount(session);
 	free_netdev(dev);
-	spriv->dev = NULL;
-out_del_session:
-	l2tp_session_delete(session);
-out:
+err_sess:
+	kfree(session);
+err:
 	return rc;
 }