1 files changed, 161 insertions, 74 deletions

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1a9f3723c13..d36875f3427 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -101,6 +101,7 @@ struct l2tp_skb_cb {
 
 static atomic_t l2tp_tunnel_count;
 static atomic_t l2tp_session_count;
+static struct workqueue_struct *l2tp_wq;
 
 /* per-net private data for this module */
 static unsigned int l2tp_net_id;
@@ -122,7 +123,6 @@ static inline struct l2tp_net *l2tp_pernet(struct net *net)
 	return net_generic(net, l2tp_net_id);
 }
 
-
 /* Tunnel reference counts. Incremented per session that is added to
  * the tunnel.
  */
@@ -168,6 +168,51 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id)
 
 }
 
+/* Lookup the tunnel socket, possibly involving the fs code if the socket is
+ * owned by userspace.  A struct sock returned from this function must be
+ * released using l2tp_tunnel_sock_put once you're done with it.
+ */
+struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel)
+{
+	int err = 0;
+	struct socket *sock = NULL;
+	struct sock *sk = NULL;
+
+	if (!tunnel)
+		goto out;
+
+	if (tunnel->fd >= 0) {
+		/* Socket is owned by userspace, who might be in the process
+		 * of closing it.  Look the socket up using the fd to ensure
+		 * consistency.
+		 */
+		sock = sockfd_lookup(tunnel->fd, &err);
+		if (sock)
+			sk = sock->sk;
+	} else {
+		/* Socket is owned by kernelspace */
+		sk = tunnel->sock;
+	}
+
+out:
+	return sk;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_lookup);
+
+/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */
+void l2tp_tunnel_sock_put(struct sock *sk)
+{
+	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
+	if (tunnel) {
+		if (tunnel->fd >= 0) {
+			/* Socket is owned by userspace */
+			sockfd_put(sk->sk_socket);
+		}
+		sock_put(sk);
+	}
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put);
+
 /* Lookup a session by id in the global session list
  */
 static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id)
@@ -176,10 +221,9 @@ static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id)
 	struct hlist_head *session_list =
 		l2tp_session_id_hash_2(pn, session_id);
 	struct l2tp_session *session;
-	struct hlist_node *walk;
 
 	rcu_read_lock_bh();
-	hlist_for_each_entry_rcu(session, walk, session_list, global_hlist) {
+	hlist_for_each_entry_rcu(session, session_list, global_hlist) {
 		if (session->session_id == session_id) {
 			rcu_read_unlock_bh();
 			return session;
@@ -208,7 +252,6 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn
 {
 	struct hlist_head *session_list;
 	struct l2tp_session *session;
-	struct hlist_node *walk;
 
 	/* In L2TPv3, session_ids are unique over all tunnels and we
 	 * sometimes need to look them up before we know the
@@ -219,7 +262,7 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn
 
 	session_list = l2tp_session_id_hash(tunnel, session_id);
 	read_lock_bh(&tunnel->hlist_lock);
-	hlist_for_each_entry(session, walk, session_list, hlist) {
+	hlist_for_each_entry(session, session_list, hlist) {
 		if (session->session_id == session_id) {
 			read_unlock_bh(&tunnel->hlist_lock);
 			return session;
@@ -234,13 +277,12 @@ EXPORT_SYMBOL_GPL(l2tp_session_find);
 struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
 {
 	int hash;
-	struct hlist_node *walk;
 	struct l2tp_session *session;
 	int count = 0;
 
 	read_lock_bh(&tunnel->hlist_lock);
 	for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
-		hlist_for_each_entry(session, walk, &tunnel->session_hlist[hash], hlist) {
+		hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
 			if (++count > nth) {
 				read_unlock_bh(&tunnel->hlist_lock);
 				return session;
@@ -261,12 +303,11 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);
 	int hash;
-	struct hlist_node *walk;
 	struct l2tp_session *session;
 
 	rcu_read_lock_bh();
 	for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) {
-		hlist_for_each_entry_rcu(session, walk, &pn->l2tp_session_hlist[hash], global_hlist) {
+		hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) {
 			if (!strcmp(session->ifname, ifname)) {
 				rcu_read_unlock_bh();
 				return session;
@@ -1123,8 +1164,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 	struct udphdr *uh;
 	struct inet_sock *inet;
 	__wsum csum;
-	int old_headroom;
-	int new_headroom;
 	int headroom;
 	int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
 	int udp_len;
@@ -1136,16 +1175,12 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 	 */
 	headroom = NET_SKB_PAD + sizeof(struct iphdr) +
 		uhlen + hdr_len;
-	old_headroom = skb_headroom(skb);
 	if (skb_cow_head(skb, headroom)) {
 		kfree_skb(skb);
 		return NET_XMIT_DROP;
 	}
 
-	new_headroom = skb_headroom(skb);
 	skb_orphan(skb);
-	skb->truesize += new_headroom - old_headroom;
-
 	/* Setup L2TP header */
 	session->build_header(session, __skb_push(skb, hdr_len));
 
@@ -1232,6 +1267,7 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
 static void l2tp_tunnel_destruct(struct sock *sk)
 {
 	struct l2tp_tunnel *tunnel;
+	struct l2tp_net *pn;
 
 	tunnel = sk->sk_user_data;
 	if (tunnel == NULL)
@@ -1239,9 +1275,8 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 
 	l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name);
 
-	/* Close all sessions */
-	l2tp_tunnel_closeall(tunnel);
 
+	/* Disable udp encapsulation */
 	switch (tunnel->encap) {
 	case L2TP_ENCAPTYPE_UDP:
 		/* No longer an encapsulation socket. See net/ipv4/udp.c */
@@ -1253,17 +1288,23 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 	}
 
 	/* Remove hooks into tunnel socket */
-	tunnel->sock = NULL;
 	sk->sk_destruct = tunnel->old_sk_destruct;
 	sk->sk_user_data = NULL;
+	tunnel->sock = NULL;
 
-	/* Call the original destructor */
-	if (sk->sk_destruct)
-		(*sk->sk_destruct)(sk);
+	/* Remove the tunnel struct from the tunnel list */
+	pn = l2tp_pernet(tunnel->l2tp_net);
+	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
+	list_del_rcu(&tunnel->list);
+	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+	atomic_dec(&l2tp_tunnel_count);
 
-	/* We're finished with the socket */
+	l2tp_tunnel_closeall(tunnel);
 	l2tp_tunnel_dec_refcount(tunnel);
 
+	/* Call the original destructor */
+	if (sk->sk_destruct)
+		(*sk->sk_destruct)(sk);
 end:
 	return;
 }
@@ -1337,48 +1378,77 @@ again:
  */
 static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel)
 {
-	struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
-
 	BUG_ON(atomic_read(&tunnel->ref_count) != 0);
 	BUG_ON(tunnel->sock != NULL);
-
 	l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: free...\n", tunnel->name);
-
-	/* Remove from tunnel list */
-	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
-	list_del_rcu(&tunnel->list);
 	kfree_rcu(tunnel, rcu);
-	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+}
 
-	atomic_dec(&l2tp_tunnel_count);
+/* Workqueue tunnel deletion function */
+static void l2tp_tunnel_del_work(struct work_struct *work)
+{
+	struct l2tp_tunnel *tunnel = NULL;
+	struct socket *sock = NULL;
+	struct sock *sk = NULL;
+
+	tunnel = container_of(work, struct l2tp_tunnel, del_work);
+	sk = l2tp_tunnel_sock_lookup(tunnel);
+	if (!sk)
+		return;
+
+	sock = sk->sk_socket;
+	BUG_ON(!sock);
+
+	/* If the tunnel socket was created directly by the kernel, use the
+	 * sk_* API to release the socket now.  Otherwise go through the
+	 * inet_* layer to shut the socket down, and let userspace close it.
+	 * In either case the tunnel resources are freed in the socket
+	 * destructor when the tunnel socket goes away.
+	 */
+	if (sock->file == NULL) {
+		kernel_sock_shutdown(sock, SHUT_RDWR);
+		sk_release_kernel(sk);
+	} else {
+		inet_shutdown(sock, 2);
+	}
+
+	l2tp_tunnel_sock_put(sk);
 }
 
 /* Create a socket for the tunnel, if one isn't set up by
  * userspace. This is used for static tunnels where there is no
  * managing L2TP daemon.
+ *
+ * Since we don't want these sockets to keep a namespace alive by
+ * themselves, we drop the socket's namespace refcount after creation.
+ * These sockets are freed when the namespace exits using the pernet
+ * exit hook.
  */
-static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct socket **sockp)
+static int l2tp_tunnel_sock_create(struct net *net,
+				u32 tunnel_id,
+				u32 peer_tunnel_id,
+				struct l2tp_tunnel_cfg *cfg,
+				struct socket **sockp)
 {
 	int err = -EINVAL;
-	struct sockaddr_in udp_addr;
+	struct socket *sock = NULL;
+	struct sockaddr_in udp_addr = {0};
+	struct sockaddr_l2tpip ip_addr = {0};
 #if IS_ENABLED(CONFIG_IPV6)
-	struct sockaddr_in6 udp6_addr;
-	struct sockaddr_l2tpip6 ip6_addr;
+	struct sockaddr_in6 udp6_addr = {0};
+	struct sockaddr_l2tpip6 ip6_addr = {0};
 #endif
-	struct sockaddr_l2tpip ip_addr;
-	struct socket *sock = NULL;
 
 	switch (cfg->encap) {
 	case L2TP_ENCAPTYPE_UDP:
 #if IS_ENABLED(CONFIG_IPV6)
 		if (cfg->local_ip6 && cfg->peer_ip6) {
-			err = sock_create(AF_INET6, SOCK_DGRAM, 0, sockp);
+			err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock);
 			if (err < 0)
 				goto out;
 
-			sock = *sockp;
+			sk_change_net(sock->sk, net);
 
-			memset(&udp6_addr, 0, sizeof(udp6_addr));
 			udp6_addr.sin6_family = AF_INET6;
 			memcpy(&udp6_addr.sin6_addr, cfg->local_ip6,
 			       sizeof(udp6_addr.sin6_addr));
@@ -1400,13 +1470,12 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t
 		} else
 #endif
 		{
-			err = sock_create(AF_INET, SOCK_DGRAM, 0, sockp);
+			err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock);
 			if (err < 0)
 				goto out;
 
-			sock = *sockp;
+			sk_change_net(sock->sk, net);
 
-			memset(&udp_addr, 0, sizeof(udp_addr));
 			udp_addr.sin_family = AF_INET;
 			udp_addr.sin_addr = cfg->local_ip;
 			udp_addr.sin_port = htons(cfg->local_udp_port);
@@ -1433,14 +1502,13 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t
 	case L2TP_ENCAPTYPE_IP:
 #if IS_ENABLED(CONFIG_IPV6)
 		if (cfg->local_ip6 && cfg->peer_ip6) {
-			err = sock_create(AF_INET6, SOCK_DGRAM, IPPROTO_L2TP,
-					  sockp);
+			err = sock_create_kern(AF_INET6, SOCK_DGRAM,
+					  IPPROTO_L2TP, &sock);
 			if (err < 0)
 				goto out;
 
-			sock = *sockp;
+			sk_change_net(sock->sk, net);
 
-			memset(&ip6_addr, 0, sizeof(ip6_addr));
 			ip6_addr.l2tp_family = AF_INET6;
 			memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6,
 			       sizeof(ip6_addr.l2tp_addr));
@@ -1462,14 +1530,13 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t
 		} else
 #endif
 		{
-			err = sock_create(AF_INET, SOCK_DGRAM, IPPROTO_L2TP,
-					  sockp);
+			err = sock_create_kern(AF_INET, SOCK_DGRAM,
+					  IPPROTO_L2TP, &sock);
 			if (err < 0)
 				goto out;
 
-			sock = *sockp;
+			sk_change_net(sock->sk, net);
 
-			memset(&ip_addr, 0, sizeof(ip_addr));
 			ip_addr.l2tp_family = AF_INET;
 			ip_addr.l2tp_addr = cfg->local_ip;
 			ip_addr.l2tp_conn_id = tunnel_id;
@@ -1493,8 +1560,10 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t
 	}
 
 out:
+	*sockp = sock;
 	if ((err < 0) && sock) {
-		sock_release(sock);
+		kernel_sock_shutdown(sock, SHUT_RDWR);
+		sk_release_kernel(sock->sk);
 		*sockp = NULL;
 	}
 
@@ -1517,15 +1586,23 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	 * kernel socket.
 	 */
 	if (fd < 0) {
-		err = l2tp_tunnel_sock_create(tunnel_id, peer_tunnel_id, cfg, &sock);
+		err = l2tp_tunnel_sock_create(net, tunnel_id, peer_tunnel_id,
+				cfg, &sock);
 		if (err < 0)
 			goto err;
 	} else {
-		err = -EBADF;
 		sock = sockfd_lookup(fd, &err);
 		if (!sock) {
-			pr_err("tunl %hu: sockfd_lookup(fd=%d) returned %d\n",
+			pr_err("tunl %u: sockfd_lookup(fd=%d) returned %d\n",
 			       tunnel_id, fd, err);
+			err = -EBADF;
+			goto err;
+		}
+
+		/* Reject namespace mismatches */
+		if (!net_eq(sock_net(sock->sk), net)) {
+			pr_err("tunl %u: netns mismatch\n", tunnel_id);
+			err = -EINVAL;
 			goto err;
 		}
 	}
@@ -1607,10 +1684,14 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	tunnel->old_sk_destruct = sk->sk_destruct;
 	sk->sk_destruct = &l2tp_tunnel_destruct;
 	tunnel->sock = sk;
+	tunnel->fd = fd;
 	lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock");
 
 	sk->sk_allocation = GFP_ATOMIC;
 
+	/* Init delete workqueue struct */
+	INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work);
+
 	/* Add tunnel to our list */
 	INIT_LIST_HEAD(&tunnel->list);
 	atomic_inc(&l2tp_tunnel_count);
@@ -1642,25 +1723,7 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
  */
 int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
-	int err = 0;
-	struct socket *sock = tunnel->sock ? tunnel->sock->sk_socket : NULL;
-
-	/* Force the tunnel socket to close. This will eventually
-	 * cause the tunnel to be deleted via the normal socket close
-	 * mechanisms when userspace closes the tunnel socket.
-	 */
-	if (sock != NULL) {
-		err = inet_shutdown(sock, 2);
-
-		/* If the tunnel's socket was created by the kernel,
-		 * close the socket here since the socket was not
-		 * created by userspace.
-		 */
-		if (sock->file == NULL)
-			err = inet_release(sock);
-	}
-
-	return err;
+	return (false == queue_work(l2tp_wq, &tunnel->del_work));
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
@@ -1844,8 +1907,21 @@ static __net_init int l2tp_init_net(struct net *net)
 	return 0;
 }
 
+static __net_exit void l2tp_exit_net(struct net *net)
+{
+	struct l2tp_net *pn = l2tp_pernet(net);
+	struct l2tp_tunnel *tunnel = NULL;
+
+	rcu_read_lock_bh();
+	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
+		(void)l2tp_tunnel_delete(tunnel);
+	}
+	rcu_read_unlock_bh();
+}
+
 static struct pernet_operations l2tp_net_ops = {
 	.init = l2tp_init_net,
+	.exit = l2tp_exit_net,
 	.id   = &l2tp_net_id,
 	.size = sizeof(struct l2tp_net),
 };
@@ -1858,6 +1934,13 @@ static int __init l2tp_init(void)
 	if (rc)
 		goto out;
 
+	l2tp_wq = alloc_workqueue("l2tp", WQ_NON_REENTRANT | WQ_UNBOUND, 0);
+	if (!l2tp_wq) {
+		pr_err("alloc_workqueue failed\n");
+		rc = -ENOMEM;
+		goto out;
+	}
+
 	pr_info("L2TP core driver, %s\n", L2TP_DRV_VERSION);
 
 out:
@@ -1867,6 +1950,10 @@ out:
 static void __exit l2tp_exit(void)
 {
 	unregister_pernet_device(&l2tp_net_ops);
+	if (l2tp_wq) {
+		destroy_workqueue(l2tp_wq);
+		l2tp_wq = NULL;
+	}
 }
 
 module_init(l2tp_init);