1 files changed, 133 insertions, 83 deletions

diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index eecc64e138de..8b8fc2337960 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -30,6 +30,9 @@
 #include <net/xfrm.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
 
 #include "l2tp_core.h"
 
@@ -41,7 +44,6 @@ struct l2tp_eth {
 	struct net_device	*dev;
 	struct sock		*tunnel_sock;
 	struct l2tp_session	*session;
-	struct list_head	list;
 	atomic_long_t		tx_bytes;
 	atomic_long_t		tx_packets;
 	atomic_long_t		tx_dropped;
@@ -52,20 +54,9 @@ struct l2tp_eth {
 
 /* via l2tp_session_priv() */
 struct l2tp_eth_sess {
-	struct net_device	*dev;
+	struct net_device __rcu *dev;
 };
 
-/* per-net private data for this module */
-static unsigned int l2tp_eth_net_id;
-struct l2tp_eth_net {
-	struct list_head l2tp_eth_dev_list;
-	spinlock_t l2tp_eth_lock;
-};
-
-static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net)
-{
-	return net_generic(net, l2tp_eth_net_id);
-}
 
 static int l2tp_eth_dev_init(struct net_device *dev)
 {
@@ -82,12 +73,13 @@ static int l2tp_eth_dev_init(struct net_device *dev)
 static void l2tp_eth_dev_uninit(struct net_device *dev)
 {
 	struct l2tp_eth *priv = netdev_priv(dev);
-	struct l2tp_eth_net *pn = l2tp_eth_pernet(dev_net(dev));
+	struct l2tp_eth_sess *spriv;
 
-	spin_lock(&pn->l2tp_eth_lock);
-	list_del_init(&priv->list);
-	spin_unlock(&pn->l2tp_eth_lock);
-	dev_put(dev);
+	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)
@@ -141,8 +133,8 @@ 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;
@@ -166,16 +158,25 @@ 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);
 }
 
@@ -186,11 +187,15 @@ 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();
 		}
 	}
 }
@@ -200,35 +205,89 @@ 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
 
-static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
+static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
+				struct l2tp_session *session,
+				struct net_device *dev)
+{
+	unsigned int overhead = 0;
+	struct dst_entry *dst;
+	u32 l3_overhead = 0;
+
+	/* if the encap is UDP, account for UDP header size */
+	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
+		overhead += sizeof(struct udphdr);
+		dev->needed_headroom += sizeof(struct udphdr);
+	}
+	if (session->mtu != 0) {
+		dev->mtu = session->mtu;
+		dev->needed_headroom += session->hdr_len;
+		return;
+	}
+	lock_sock(tunnel->sock);
+	l3_overhead = kernel_sock_ip_overhead(tunnel->sock);
+	release_sock(tunnel->sock);
+	if (l3_overhead == 0) {
+		/* L3 Overhead couldn't be identified, this could be
+		 * because tunnel->sock was NULL or the socket's
+		 * address family was not IPv4 or IPv6,
+		 * dev mtu stays at 1500.
+		 */
+		return;
+	}
+	/* Adjust MTU, factor overhead - underlay L3, overlay L2 hdr
+	 * UDP overhead, if any, was already factored in above.
+	 */
+	overhead += session->hdr_len + ETH_HLEN + l3_overhead;
+
+	/* If PMTU discovery was enabled, use discovered MTU on L2TP device */
+	dst = sk_dst_get(tunnel->sock);
+	if (dst) {
+		/* dst_mtu will use PMTU if found, else fallback to intf MTU */
+		u32 pmtu = dst_mtu(dst);
+
+		if (pmtu != 0)
+			dev->mtu = pmtu;
+		dst_release(dst);
+	}
+	session->mtu = dev->mtu - overhead;
+	dev->mtu = session->mtu;
+	dev->needed_headroom += session->hdr_len;
+}
+
+static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
+			   u32 session_id, u32 peer_session_id,
+			   struct l2tp_session_cfg *cfg)
 {
 	struct net_device *dev;
 	char name[IFNAMSIZ];
-	struct l2tp_tunnel *tunnel;
 	struct l2tp_session *session;
 	struct l2tp_eth *priv;
 	struct l2tp_eth_sess *spriv;
 	int rc;
-	struct l2tp_eth_net *pn;
-
-	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (!tunnel) {
-		rc = -ENODEV;
-		goto out;
-	}
 
 	if (cfg->ifname) {
 		dev = dev_get_by_name(net, cfg->ifname);
 		if (dev) {
 			dev_put(dev);
 			rc = -EEXIST;
-			goto out;
+			goto err;
 		}
 		strlcpy(name, cfg->ifname, IFNAMSIZ);
 	} else
@@ -238,26 +297,22 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
 				      peer_session_id, cfg);
 	if (IS_ERR(session)) {
 		rc = PTR_ERR(session);
-		goto out;
+		goto err;
 	}
 
 	dev = alloc_netdev(sizeof(*priv), name, NET_NAME_UNKNOWN,
 			   l2tp_eth_dev_setup);
 	if (!dev) {
 		rc = -ENOMEM;
-		goto out_del_session;
+		goto err_sess;
 	}
 
 	dev_net_set(dev, net);
-	if (session->mtu == 0)
-		session->mtu = dev->mtu - session->hdr_len;
-	dev->mtu = session->mtu;
-	dev->needed_headroom += session->hdr_len;
+	l2tp_eth_adjust_mtu(tunnel, session, dev);
 
 	priv = netdev_priv(dev);
 	priv->dev = dev;
 	priv->session = session;
-	INIT_LIST_HEAD(&priv->list);
 
 	priv->tunnel_sock = tunnel->sock;
 	session->recv_skb = l2tp_eth_dev_recv;
@@ -267,48 +322,50 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
 #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);
 
-	__module_get(THIS_MODULE);
-	/* Must be done after register_netdev() */
-	strlcpy(session->ifname, dev->name, IFNAMSIZ);
+	rtnl_lock();
 
-	dev_hold(dev);
-	pn = l2tp_eth_pernet(dev_net(dev));
-	spin_lock(&pn->l2tp_eth_lock);
-	list_add(&priv->list, &pn->l2tp_eth_dev_list);
-	spin_unlock(&pn->l2tp_eth_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;
+	}
 
-	return 0;
+	rc = register_netdevice(dev);
+	if (rc < 0) {
+		rtnl_unlock();
+		l2tp_session_delete(session);
+		l2tp_session_dec_refcount(session);
+		free_netdev(dev);
 
-out_del_dev:
-	free_netdev(dev);
-	spriv->dev = NULL;
-out_del_session:
-	l2tp_session_delete(session);
-out:
-	return rc;
-}
+		return rc;
+	}
 
-static __net_init int l2tp_eth_init_net(struct net *net)
-{
-	struct l2tp_eth_net *pn = net_generic(net, l2tp_eth_net_id);
+	strlcpy(session->ifname, dev->name, IFNAMSIZ);
+	rcu_assign_pointer(spriv->dev, dev);
+
+	rtnl_unlock();
 
-	INIT_LIST_HEAD(&pn->l2tp_eth_dev_list);
-	spin_lock_init(&pn->l2tp_eth_lock);
+	l2tp_session_dec_refcount(session);
+
+	__module_get(THIS_MODULE);
 
 	return 0;
-}
 
-static struct pernet_operations l2tp_eth_net_ops = {
-	.init = l2tp_eth_init_net,
-	.id   = &l2tp_eth_net_id,
-	.size = sizeof(struct l2tp_eth_net),
-};
+err_sess_dev:
+	l2tp_session_dec_refcount(session);
+	free_netdev(dev);
+err_sess:
+	kfree(session);
+err:
+	return rc;
+}
 
 
 static const struct l2tp_nl_cmd_ops l2tp_eth_nl_cmd_ops = {
@@ -323,25 +380,18 @@ static int __init l2tp_eth_init(void)
 
 	err = l2tp_nl_register_ops(L2TP_PWTYPE_ETH, &l2tp_eth_nl_cmd_ops);
 	if (err)
-		goto out;
-
-	err = register_pernet_device(&l2tp_eth_net_ops);
-	if (err)
-		goto out_unreg;
+		goto err;
 
 	pr_info("L2TP ethernet pseudowire support (L2TPv3)\n");
 
 	return 0;
 
-out_unreg:
-	l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
-out:
+err:
 	return err;
 }
 
 static void __exit l2tp_eth_exit(void)
 {
-	unregister_pernet_device(&l2tp_eth_net_ops);
 	l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
 }