1 files changed, 116 insertions, 134 deletions

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 04635e88e8e..369a9822488 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -9,6 +9,8 @@
  *	2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/icmp.h>
 #include <linux/module.h>
 #include <linux/skbuff.h>
@@ -32,15 +34,8 @@ struct l2tp_ip_sock {
 	/* inet_sock has to be the first member of l2tp_ip_sock */
 	struct inet_sock	inet;
 
-	__u32			conn_id;
-	__u32			peer_conn_id;
-
-	__u64			tx_packets;
-	__u64			tx_bytes;
-	__u64			tx_errors;
-	__u64			rx_packets;
-	__u64			rx_bytes;
-	__u64			rx_errors;
+	u32			conn_id;
+	u32			peer_conn_id;
 };
 
 static DEFINE_RWLOCK(l2tp_ip_lock);
@@ -54,10 +49,9 @@ static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk)
 
 static struct sock *__l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif, u32 tunnel_id)
 {
-	struct hlist_node *node;
 	struct sock *sk;
 
-	sk_for_each_bound(sk, node, &l2tp_ip_bind_table) {
+	sk_for_each_bound(sk, &l2tp_ip_bind_table) {
 		struct inet_sock *inet = inet_sk(sk);
 		struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk);
 
@@ -120,6 +114,7 @@ static inline struct sock *l2tp_ip_bind_lookup(struct net *net, __be32 laddr, in
  */
 static int l2tp_ip_recv(struct sk_buff *skb)
 {
+	struct net *net = dev_net(skb->dev);
 	struct sock *sk;
 	u32 session_id;
 	u32 tunnel_id;
@@ -127,7 +122,6 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	struct l2tp_session *session;
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
-	int offset;
 
 	/* Point to L2TP header */
 	optr = ptr = skb->data;
@@ -148,7 +142,7 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	}
 
 	/* Ok, this is a data packet. Lookup the session. */
-	session = l2tp_session_find(&init_net, NULL, session_id);
+	session = l2tp_session_find(net, NULL, session_id);
 	if (session == NULL)
 		goto discard;
 
@@ -162,14 +156,8 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
-		printk(KERN_DEBUG "%s: ip recv: ", tunnel->name);
-
-		offset = 0;
-		do {
-			printk(" %02X", ptr[offset]);
-		} while (++offset < length);
-
-		printk("\n");
+		pr_debug("%s: ip recv\n", tunnel->name);
+		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
 
 	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook);
@@ -185,14 +173,14 @@ pass_up:
 		goto discard;
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
-	tunnel = l2tp_tunnel_find(&init_net, tunnel_id);
+	tunnel = l2tp_tunnel_find(net, tunnel_id);
 	if (tunnel != NULL)
 		sk = tunnel->sock;
 	else {
 		struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
 
 		read_lock_bh(&l2tp_ip_lock);
-		sk = __l2tp_ip_bind_lookup(&init_net, iph->daddr, 0, tunnel_id);
+		sk = __l2tp_ip_bind_lookup(net, iph->daddr, 0, tunnel_id);
 		read_unlock_bh(&l2tp_ip_lock);
 	}
 
@@ -232,7 +220,7 @@ static void l2tp_ip_close(struct sock *sk, long timeout)
 {
 	write_lock_bh(&l2tp_ip_lock);
 	hlist_del_init(&sk->sk_bind_node);
-	hlist_del_init(&sk->sk_node);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip_lock);
 	sk_common_release(sk);
 }
@@ -240,10 +228,16 @@ static void l2tp_ip_close(struct sock *sk, long timeout)
 static void l2tp_ip_destroy_sock(struct sock *sk)
 {
 	struct sk_buff *skb;
+	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
 
 	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
 		kfree_skb(skb);
 
+	if (tunnel) {
+		l2tp_tunnel_closeall(tunnel);
+		sock_put(sk);
+	}
+
 	sk_refcnt_debug_dec(sk);
 }
 
@@ -251,12 +245,21 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *) uaddr;
-	int ret = -EINVAL;
+	struct net *net = sock_net(sk);
+	int ret;
 	int chk_addr_ret;
 
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		return -EINVAL;
+	if (addr_len < sizeof(struct sockaddr_l2tpip))
+		return -EINVAL;
+	if (addr->l2tp_family != AF_INET)
+		return -EINVAL;
+
 	ret = -EADDRINUSE;
 	read_lock_bh(&l2tp_ip_lock);
-	if (__l2tp_ip_bind_lookup(&init_net, addr->l2tp_addr.s_addr, sk->sk_bound_dev_if, addr->l2tp_conn_id))
+	if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr,
+				  sk->sk_bound_dev_if, addr->l2tp_conn_id))
 		goto out_in_use;
 
 	read_unlock_bh(&l2tp_ip_lock);
@@ -265,13 +268,14 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip))
 		goto out;
 
-	chk_addr_ret = inet_addr_type(&init_net, addr->l2tp_addr.s_addr);
+	chk_addr_ret = inet_addr_type(net, addr->l2tp_addr.s_addr);
 	ret = -EADDRNOTAVAIL;
 	if (addr->l2tp_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
 	    chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
 		goto out;
 
-	inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr;
+	if (addr->l2tp_addr.s_addr)
+		inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr;
 	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
 		inet->inet_saddr = 0;  /* Use device */
 	sk_dst_reset(sk);
@@ -283,6 +287,8 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip_lock);
 	ret = 0;
+	sock_reset_flag(sk, SOCK_ZAPPED);
+
 out:
 	release_sock(sk);
 
@@ -296,68 +302,43 @@ out_in_use:
 
 static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
-	int rc;
-	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr;
-	struct rtable *rt;
-	__be32 saddr;
-	int oif;
-
-	rc = -EINVAL;
-	if (addr_len < sizeof(*lsa))
-		goto out;
-
-	rc = -EAFNOSUPPORT;
-	if (lsa->l2tp_family != AF_INET)
-		goto out;
+	int rc;
 
-	sk_dst_reset(sk);
+	if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */
+		return -EINVAL;
 
-	oif = sk->sk_bound_dev_if;
-	saddr = inet->inet_saddr;
+	if (addr_len < sizeof(*lsa))
+		return -EINVAL;
 
-	rc = -EINVAL;
 	if (ipv4_is_multicast(lsa->l2tp_addr.s_addr))
-		goto out;
+		return -EINVAL;
 
-	rc = ip_route_connect(&rt, lsa->l2tp_addr.s_addr, saddr,
-			      RT_CONN_FLAGS(sk), oif,
-			      IPPROTO_L2TP,
-			      0, 0, sk, 1);
-	if (rc) {
-		if (rc == -ENETUNREACH)
-			IP_INC_STATS_BH(&init_net, IPSTATS_MIB_OUTNOROUTES);
-		goto out;
-	}
+	rc = ip4_datagram_connect(sk, uaddr, addr_len);
+	if (rc < 0)
+		return rc;
 
-	rc = -ENETUNREACH;
-	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
-		ip_rt_put(rt);
-		goto out;
-	}
+	lock_sock(sk);
 
 	l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;
 
-	if (!inet->inet_saddr)
-		inet->inet_saddr = rt->rt_src;
-	if (!inet->inet_rcv_saddr)
-		inet->inet_rcv_saddr = rt->rt_src;
-	inet->inet_daddr = rt->rt_dst;
-	sk->sk_state = TCP_ESTABLISHED;
-	inet->inet_id = jiffies;
-
-	sk_dst_set(sk, &rt->dst);
-
 	write_lock_bh(&l2tp_ip_lock);
 	hlist_del_init(&sk->sk_bind_node);
 	sk_add_bind_node(sk, &l2tp_ip_bind_table);
 	write_unlock_bh(&l2tp_ip_lock);
 
-	rc = 0;
-out:
+	release_sock(sk);
 	return rc;
 }
 
+static int l2tp_ip_disconnect(struct sock *sk, int flags)
+{
+	if (sock_flag(sk, SOCK_ZAPPED))
+		return 0;
+
+	return udp_disconnect(sk, flags);
+}
+
 static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr,
 			   int *uaddr_len, int peer)
 {
@@ -388,11 +369,6 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
-	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
-		goto drop;
-
-	nf_reset(skb);
-
 	/* Charge it to the socket, dropping if the queue is full. */
 	rc = sock_queue_rcv_skb(sk, skb);
 	if (rc < 0)
@@ -401,7 +377,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
 	return 0;
 
 drop:
-	IP_INC_STATS(&init_net, IPSTATS_MIB_INDISCARDS);
+	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
 	kfree_skb(skb);
 	return -1;
 }
@@ -413,31 +389,36 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 {
 	struct sk_buff *skb;
 	int rc;
-	struct l2tp_ip_sock *lsa = l2tp_ip_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
-	struct ip_options *opt = inet->opt;
 	struct rtable *rt = NULL;
+	struct flowi4 *fl4;
 	int connected = 0;
 	__be32 daddr;
 
+	lock_sock(sk);
+
+	rc = -ENOTCONN;
 	if (sock_flag(sk, SOCK_DEAD))
-		return -ENOTCONN;
+		goto out;
 
 	/* Get and verify the address. */
 	if (msg->msg_name) {
-		struct sockaddr_l2tpip *lip = (struct sockaddr_l2tpip *) msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_l2tpip *, lip, msg->msg_name);
+		rc = -EINVAL;
 		if (msg->msg_namelen < sizeof(*lip))
-			return -EINVAL;
+			goto out;
 
 		if (lip->l2tp_family != AF_INET) {
+			rc = -EAFNOSUPPORT;
 			if (lip->l2tp_family != AF_UNSPEC)
-				return -EAFNOSUPPORT;
+				goto out;
 		}
 
 		daddr = lip->l2tp_addr.s_addr;
 	} else {
+		rc = -EDESTADDRREQ;
 		if (sk->sk_state != TCP_ESTABLISHED)
-			return -EDESTADDRREQ;
+			goto out;
 
 		daddr = inet->inet_daddr;
 		connected = 1;
@@ -466,73 +447,77 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		goto error;
 	}
 
+	fl4 = &inet->cork.fl.u.ip4;
 	if (connected)
 		rt = (struct rtable *) __sk_dst_check(sk, 0);
 
+	rcu_read_lock();
 	if (rt == NULL) {
+		const struct ip_options_rcu *inet_opt;
+
+		inet_opt = rcu_dereference(inet->inet_opt);
+
 		/* Use correct destination address if we have options. */
-		if (opt && opt->srr)
-			daddr = opt->faddr;
-
-		{
-			struct flowi fl = { .oif = sk->sk_bound_dev_if,
-					    .fl4_dst = daddr,
-					    .fl4_src = inet->inet_saddr,
-					    .fl4_tos = RT_CONN_FLAGS(sk),
-					    .proto = sk->sk_protocol,
-					    .flags = inet_sk_flowi_flags(sk),
-					    .fl_ip_sport = inet->inet_sport,
-					    .fl_ip_dport = inet->inet_dport };
-
-			/* If this fails, retransmit mechanism of transport layer will
-			 * keep trying until route appears or the connection times
-			 * itself out.
-			 */
-			security_sk_classify_flow(sk, &fl);
-			if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0))
-				goto no_route;
+		if (inet_opt && inet_opt->opt.srr)
+			daddr = inet_opt->opt.faddr;
+
+		/* If this fails, retransmit mechanism of transport layer will
+		 * keep trying until route appears or the connection times
+		 * itself out.
+		 */
+		rt = ip_route_output_ports(sock_net(sk), fl4, sk,
+					   daddr, inet->inet_saddr,
+					   inet->inet_dport, inet->inet_sport,
+					   sk->sk_protocol, RT_CONN_FLAGS(sk),
+					   sk->sk_bound_dev_if);
+		if (IS_ERR(rt))
+			goto no_route;
+		if (connected) {
+			sk_setup_caps(sk, &rt->dst);
+		} else {
+			skb_dst_set(skb, &rt->dst);
+			goto xmit;
 		}
-		sk_setup_caps(sk, &rt->dst);
 	}
-	skb_dst_set(skb, dst_clone(&rt->dst));
 
+	/* We dont need to clone dst here, it is guaranteed to not disappear.
+	 *  __dev_xmit_skb() might force a refcount if needed.
+	 */
+	skb_dst_set_noref(skb, &rt->dst);
+
+xmit:
 	/* Queue the packet to IP for output */
-	rc = ip_queue_xmit(skb);
+	rc = ip_queue_xmit(sk, skb, &inet->cork.fl);
+	rcu_read_unlock();
 
 error:
-	/* Update stats */
-	if (rc >= 0) {
-		lsa->tx_packets++;
-		lsa->tx_bytes += len;
+	if (rc >= 0)
 		rc = len;
-	} else {
-		lsa->tx_errors++;
-	}
 
+out:
+	release_sock(sk);
 	return rc;
 
 no_route:
+	rcu_read_unlock();
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
 	kfree_skb(skb);
-	return -EHOSTUNREACH;
+	rc = -EHOSTUNREACH;
+	goto out;
 }
 
 static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			   size_t len, int noblock, int flags, int *addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
-	struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk);
 	size_t copied = 0;
 	int err = -EOPNOTSUPP;
-	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct sk_buff *skb;
 
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
 		goto out;
@@ -555,6 +540,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		sin->sin_port = 0;
 		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
 		ip_cmsg_recv(msg, skb);
@@ -563,15 +549,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 done:
 	skb_free_datagram(sk, skb);
 out:
-	if (err) {
-		lsk->rx_errors++;
-		return err;
-	}
-
-	lsk->rx_packets++;
-	lsk->rx_bytes += copied;
-
-	return copied;
+	return err ? err : copied;
 }
 
 static struct proto l2tp_ip_prot = {
@@ -581,7 +559,7 @@ static struct proto l2tp_ip_prot = {
 	.close		   = l2tp_ip_close,
 	.bind		   = l2tp_ip_bind,
 	.connect	   = l2tp_ip_connect,
-	.disconnect	   = udp_disconnect,
+	.disconnect	   = l2tp_ip_disconnect,
 	.ioctl		   = udp_ioctl,
 	.destroy	   = l2tp_ip_destroy_sock,
 	.setsockopt	   = ip_setsockopt,
@@ -628,18 +606,18 @@ static struct inet_protosw l2tp_ip_protosw = {
 	.protocol	= IPPROTO_L2TP,
 	.prot		= &l2tp_ip_prot,
 	.ops		= &l2tp_ip_ops,
-	.no_check	= 0,
 };
 
 static struct net_protocol l2tp_ip_protocol __read_mostly = {
 	.handler	= l2tp_ip_recv,
+	.netns_ok	= 1,
 };
 
 static int __init l2tp_ip_init(void)
 {
 	int err;
 
-	printk(KERN_INFO "L2TP IP encapsulation support (L2TPv3)\n");
+	pr_info("L2TP IP encapsulation support (L2TPv3)\n");
 
 	err = proto_register(&l2tp_ip_prot, 1);
 	if (err != 0)
@@ -672,4 +650,8 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
 MODULE_DESCRIPTION("L2TP over IP");
 MODULE_VERSION("1.0");
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, SOCK_DGRAM, IPPROTO_L2TP);
+
+/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like
+ * enums
+ */
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP);