l2tp: Relocate pppol2tp driver to new net/l2tp directory

This patch moves the existing pppol2tp driver from drivers/net into a
new net/l2tp directory, which is where the upcoming L2TPv3 code will
live. The existing CONFIG_PPPOL2TP config option is left in its
current place to avoid "make oldconfig" issues when an existing
pppol2tp user takes this change. (This is the same approach used for
the pppoatm driver, which moved to net/atm.)

There are no code changes. The existing drivers/net/pppol2tp.c is
simply moved to net/l2tp.

Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 2685 insertions, 0 deletions

diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile
new file mode 100644
index 000000000000..9af41e898a04
--- /dev/null
+++ b/net/l2tp/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the L2TP.
+#
+
+obj-$(CONFIG_PPPOL2TP) += pppol2tp.o
diff --git a/net/l2tp/pppol2tp.c b/net/l2tp/pppol2tp.c
new file mode 100644
index 000000000000..449a9825200d
--- /dev/null
+++ b/net/l2tp/pppol2tp.c
@@ -0,0 +1,2680 @@
+/*****************************************************************************
+ * Linux PPP over L2TP (PPPoX/PPPoL2TP) Sockets
+ *
+ * PPPoX    --- Generic PPP encapsulation socket family
+ * PPPoL2TP --- PPP over L2TP (RFC 2661)
+ *
+ * Version:	1.0.0
+ *
+ * Authors:	Martijn van Oosterhout <kleptog@svana.org>
+ *		James Chapman (jchapman@katalix.com)
+ * Contributors:
+ *		Michal Ostrowski <mostrows@speakeasy.net>
+ *		Arnaldo Carvalho de Melo <acme@xconectiva.com.br>
+ *		David S. Miller (davem@redhat.com)
+ *
+ * License:
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ */
+
+/* This driver handles only L2TP data frames; control frames are handled by a
+ * userspace application.
+ *
+ * To send data in an L2TP session, userspace opens a PPPoL2TP socket and
+ * attaches it to a bound UDP socket with local tunnel_id / session_id and
+ * peer tunnel_id / session_id set. Data can then be sent or received using
+ * regular socket sendmsg() / recvmsg() calls. Kernel parameters of the socket
+ * can be read or modified using ioctl() or [gs]etsockopt() calls.
+ *
+ * When a PPPoL2TP socket is connected with local and peer session_id values
+ * zero, the socket is treated as a special tunnel management socket.
+ *
+ * Here's example userspace code to create a socket for sending/receiving data
+ * over an L2TP session:-
+ *
+ *	struct sockaddr_pppol2tp sax;
+ *	int fd;
+ *	int session_fd;
+ *
+ *	fd = socket(AF_PPPOX, SOCK_DGRAM, PX_PROTO_OL2TP);
+ *
+ *	sax.sa_family = AF_PPPOX;
+ *	sax.sa_protocol = PX_PROTO_OL2TP;
+ *	sax.pppol2tp.fd = tunnel_fd;	// bound UDP socket
+ *	sax.pppol2tp.addr.sin_addr.s_addr = addr->sin_addr.s_addr;
+ *	sax.pppol2tp.addr.sin_port = addr->sin_port;
+ *	sax.pppol2tp.addr.sin_family = AF_INET;
+ *	sax.pppol2tp.s_tunnel  = tunnel_id;
+ *	sax.pppol2tp.s_session = session_id;
+ *	sax.pppol2tp.d_tunnel  = peer_tunnel_id;
+ *	sax.pppol2tp.d_session = peer_session_id;
+ *
+ *	session_fd = connect(fd, (struct sockaddr *)&sax, sizeof(sax));
+ *
+ * A pppd plugin that allows PPP traffic to be carried over L2TP using
+ * this driver is available from the OpenL2TP project at
+ * http://openl2tp.sourceforge.net.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/list.h>
+#include <asm/uaccess.h>
+
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/jiffies.h>
+
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/if_pppox.h>
+#include <linux/if_pppol2tp.h>
+#include <net/sock.h>
+#include <linux/ppp_channel.h>
+#include <linux/ppp_defs.h>
+#include <linux/if_ppp.h>
+#include <linux/file.h>
+#include <linux/hash.h>
+#include <linux/sort.h>
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include <asm/byteorder.h>
+#include <asm/atomic.h>
+
+
+#define PPPOL2TP_DRV_VERSION	"V1.0"
+
+/* L2TP header constants */
+#define L2TP_HDRFLAG_T	   0x8000
+#define L2TP_HDRFLAG_L	   0x4000
+#define L2TP_HDRFLAG_S	   0x0800
+#define L2TP_HDRFLAG_O	   0x0200
+#define L2TP_HDRFLAG_P	   0x0100
+
+#define L2TP_HDR_VER_MASK  0x000F
+#define L2TP_HDR_VER	   0x0002
+
+/* Space for UDP, L2TP and PPP headers */
+#define PPPOL2TP_HEADER_OVERHEAD	40
+
+/* Just some random numbers */
+#define L2TP_TUNNEL_MAGIC	0x42114DDA
+#define L2TP_SESSION_MAGIC	0x0C04EB7D
+
+#define PPPOL2TP_HASH_BITS	4
+#define PPPOL2TP_HASH_SIZE	(1 << PPPOL2TP_HASH_BITS)
+
+/* Default trace flags */
+#define PPPOL2TP_DEFAULT_DEBUG_FLAGS	0
+
+#define PRINTK(_mask, _type, _lvl, _fmt, args...)			\
+	do {								\
+		if ((_mask) & (_type))					\
+			printk(_lvl "PPPOL2TP: " _fmt, ##args);		\
+	} while(0)
+
+/* Number of bytes to build transmit L2TP headers.
+ * Unfortunately the size is different depending on whether sequence numbers
+ * are enabled.
+ */
+#define PPPOL2TP_L2TP_HDR_SIZE_SEQ		10
+#define PPPOL2TP_L2TP_HDR_SIZE_NOSEQ		6
+
+struct pppol2tp_tunnel;
+
+/* Describes a session. It is the sk_user_data field in the PPPoL2TP
+ * socket. Contains information to determine incoming packets and transmit
+ * outgoing ones.
+ */
+struct pppol2tp_session
+{
+	int			magic;		/* should be
+						 * L2TP_SESSION_MAGIC */
+	int			owner;		/* pid that opened the socket */
+
+	struct sock		*sock;		/* Pointer to the session
+						 * PPPoX socket */
+	struct sock		*tunnel_sock;	/* Pointer to the tunnel UDP
+						 * socket */
+
+	struct pppol2tp_addr	tunnel_addr;	/* Description of tunnel */
+
+	struct pppol2tp_tunnel	*tunnel;	/* back pointer to tunnel
+						 * context */
+
+	char			name[20];	/* "sess xxxxx/yyyyy", where
+						 * x=tunnel_id, y=session_id */
+	int			mtu;
+	int			mru;
+	int			flags;		/* accessed by PPPIOCGFLAGS.
+						 * Unused. */
+	unsigned		recv_seq:1;	/* expect receive packets with
+						 * sequence numbers? */
+	unsigned		send_seq:1;	/* send packets with sequence
+						 * numbers? */
+	unsigned		lns_mode:1;	/* behave as LNS? LAC enables
+						 * sequence numbers under
+						 * control of LNS. */
+	int			debug;		/* bitmask of debug message
+						 * categories */
+	int			reorder_timeout; /* configured reorder timeout
+						  * (in jiffies) */
+	u16			nr;		/* session NR state (receive) */
+	u16			ns;		/* session NR state (send) */
+	struct sk_buff_head	reorder_q;	/* receive reorder queue */
+	struct pppol2tp_ioc_stats stats;
+	struct hlist_node	hlist;		/* Hash list node */
+};
+
+/* The sk_user_data field of the tunnel's UDP socket. It contains info to track
+ * all the associated sessions so incoming packets can be sorted out
+ */
+struct pppol2tp_tunnel
+{
+	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
+	rwlock_t		hlist_lock;	/* protect session_hlist */
+	struct hlist_head	session_hlist[PPPOL2TP_HASH_SIZE];
+						/* hashed list of sessions,
+						 * hashed by id */
+	int			debug;		/* bitmask of debug message
+						 * categories */
+	char			name[12];	/* "tunl xxxxx" */
+	struct pppol2tp_ioc_stats stats;
+
+	void (*old_sk_destruct)(struct sock *);
+
+	struct sock		*sock;		/* Parent socket */
+	struct list_head	list;		/* Keep a list of all open
+						 * prepared sockets */
+	struct net		*pppol2tp_net;	/* the net we belong to */
+
+	atomic_t		ref_count;
+};
+
+/* Private data stored for received packets in the skb.
+ */
+struct pppol2tp_skb_cb {
+	u16			ns;
+	u16			nr;
+	u16			has_seq;
+	u16			length;
+	unsigned long		expires;
+};
+
+#define PPPOL2TP_SKB_CB(skb)	((struct pppol2tp_skb_cb *) &skb->cb[sizeof(struct inet_skb_parm)])
+
+static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb);
+static void pppol2tp_tunnel_free(struct pppol2tp_tunnel *tunnel);
+
+static atomic_t pppol2tp_tunnel_count;
+static atomic_t pppol2tp_session_count;
+static struct ppp_channel_ops pppol2tp_chan_ops = { pppol2tp_xmit , NULL };
+static const struct proto_ops pppol2tp_ops;
+
+/* per-net private data for this module */
+static int pppol2tp_net_id __read_mostly;
+struct pppol2tp_net {
+	struct list_head pppol2tp_tunnel_list;
+	rwlock_t pppol2tp_tunnel_list_lock;
+};
+
+static inline struct pppol2tp_net *pppol2tp_pernet(struct net *net)
+{
+	BUG_ON(!net);
+
+	return net_generic(net, pppol2tp_net_id);
+}
+
+/* Helpers to obtain tunnel/session contexts from sockets.
+ */
+static inline struct pppol2tp_session *pppol2tp_sock_to_session(struct sock *sk)
+{
+	struct pppol2tp_session *session;
+
+	if (sk == NULL)
+		return NULL;
+
+	sock_hold(sk);
+	session = (struct pppol2tp_session *)(sk->sk_user_data);
+	if (session == NULL) {
+		sock_put(sk);
+		goto out;
+	}
+
+	BUG_ON(session->magic != L2TP_SESSION_MAGIC);
+out:
+	return session;
+}
+
+static inline struct pppol2tp_tunnel *pppol2tp_sock_to_tunnel(struct sock *sk)
+{
+	struct pppol2tp_tunnel *tunnel;
+
+	if (sk == NULL)
+		return NULL;
+
+	sock_hold(sk);
+	tunnel = (struct pppol2tp_tunnel *)(sk->sk_user_data);
+	if (tunnel == NULL) {
+		sock_put(sk);
+		goto out;
+	}
+
+	BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
+out:
+	return tunnel;
+}
+
+/* Tunnel reference counts. Incremented per session that is added to
+ * the tunnel.
+ */
+static inline void pppol2tp_tunnel_inc_refcount(struct pppol2tp_tunnel *tunnel)
+{
+	atomic_inc(&tunnel->ref_count);
+}
+
+static inline void pppol2tp_tunnel_dec_refcount(struct pppol2tp_tunnel *tunnel)
+{
+	if (atomic_dec_and_test(&tunnel->ref_count))
+		pppol2tp_tunnel_free(tunnel);
+}
+
+/* Session hash list.
+ * The session_id SHOULD be random according to RFC2661, but several
+ * L2TP implementations (Cisco and Microsoft) use incrementing
+ * session_ids.  So we do a real hash on the session_id, rather than a
+ * simple bitmask.
+ */
+static inline struct hlist_head *
+pppol2tp_session_id_hash(struct pppol2tp_tunnel *tunnel, u16 session_id)
+{
+	unsigned long hash_val = (unsigned long) session_id;
+	return &tunnel->session_hlist[hash_long(hash_val, PPPOL2TP_HASH_BITS)];
+}
+
+/* Lookup a session by id
+ */
+static struct pppol2tp_session *
+pppol2tp_session_find(struct pppol2tp_tunnel *tunnel, u16 session_id)
+{
+	struct hlist_head *session_list =
+		pppol2tp_session_id_hash(tunnel, session_id);
+	struct pppol2tp_session *session;
+	struct hlist_node *walk;
+
+	read_lock_bh(&tunnel->hlist_lock);
+	hlist_for_each_entry(session, walk, session_list, hlist) {
+		if (session->tunnel_addr.s_session == session_id) {
+			read_unlock_bh(&tunnel->hlist_lock);
+			return session;
+		}
+	}
+	read_unlock_bh(&tunnel->hlist_lock);
+
+	return NULL;
+}
+
+/* Lookup a tunnel by id
+ */
+static struct pppol2tp_tunnel *pppol2tp_tunnel_find(struct net *net, u16 tunnel_id)
+{
+	struct pppol2tp_tunnel *tunnel;
+	struct pppol2tp_net *pn = pppol2tp_pernet(net);
+
+	read_lock_bh(&pn->pppol2tp_tunnel_list_lock);
+	list_for_each_entry(tunnel, &pn->pppol2tp_tunnel_list, list) {
+		if (tunnel->stats.tunnel_id == tunnel_id) {
+			read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
+			return tunnel;
+		}
+	}
+	read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
+
+	return NULL;
+}
+
+/*****************************************************************************
+ * Receive data handling
+ *****************************************************************************/
+
+/* Queue a skb in order. We come here only if the skb has an L2TP sequence
+ * number.
+ */
+static void pppol2tp_recv_queue_skb(struct pppol2tp_session *session, struct sk_buff *skb)
+{
+	struct sk_buff *skbp;
+	struct sk_buff *tmp;
+	u16 ns = PPPOL2TP_SKB_CB(skb)->ns;
+
+	spin_lock_bh(&session->reorder_q.lock);
+	skb_queue_walk_safe(&session->reorder_q, skbp, tmp) {
+		if (PPPOL2TP_SKB_CB(skbp)->ns > ns) {
+			__skb_queue_before(&session->reorder_q, skbp, skb);
+			PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+			       "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n",
+			       session->name, ns, PPPOL2TP_SKB_CB(skbp)->ns,
+			       skb_queue_len(&session->reorder_q));
+			session->stats.rx_oos_packets++;
+			goto out;
+		}
+	}
+
+	__skb_queue_tail(&session->reorder_q, skb);
+
+out:
+	spin_unlock_bh(&session->reorder_q.lock);
+}
+
+/* Dequeue a single skb.
+ */
+static void pppol2tp_recv_dequeue_skb(struct pppol2tp_session *session, struct sk_buff *skb)
+{
+	struct pppol2tp_tunnel *tunnel = session->tunnel;
+	int length = PPPOL2TP_SKB_CB(skb)->length;
+	struct sock *session_sock = NULL;
+
+	/* We're about to requeue the skb, so return resources
+	 * to its current owner (a socket receive buffer).
+	 */
+	skb_orphan(skb);
+
+	tunnel->stats.rx_packets++;
+	tunnel->stats.rx_bytes += length;
+	session->stats.rx_packets++;
+	session->stats.rx_bytes += length;
+
+	if (PPPOL2TP_SKB_CB(skb)->has_seq) {
+		/* Bump our Nr */
+		session->nr++;
+		PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+		       "%s: updated nr to %hu\n", session->name, session->nr);
+	}
+
+	/* If the socket is bound, send it in to PPP's input queue. Otherwise
+	 * queue it on the session socket.
+	 */
+	session_sock = session->sock;
+	if (session_sock->sk_state & PPPOX_BOUND) {
+		struct pppox_sock *po;
+		PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+		       "%s: recv %d byte data frame, passing to ppp\n",
+		       session->name, length);
+
+		/* We need to forget all info related to the L2TP packet
+		 * gathered in the skb as we are going to reuse the same
+		 * skb for the inner packet.
+		 * Namely we need to:
+		 * - reset xfrm (IPSec) information as it applies to
+		 *   the outer L2TP packet and not to the inner one
+		 * - release the dst to force a route lookup on the inner
+		 *   IP packet since skb->dst currently points to the dst
+		 *   of the UDP tunnel
+		 * - reset netfilter information as it doesn't apply
+		 *   to the inner packet either
+		 */
+		secpath_reset(skb);
+		skb_dst_drop(skb);
+		nf_reset(skb);
+
+		po = pppox_sk(session_sock);
+		ppp_input(&po->chan, skb);
+	} else {
+		PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
+		       "%s: socket not bound\n", session->name);
+
+		/* Not bound. Nothing we can do, so discard. */
+		session->stats.rx_errors++;
+		kfree_skb(skb);
+	}
+
+	sock_put(session->sock);
+}
+
+/* Dequeue skbs from the session's reorder_q, subject to packet order.
+ * Skbs that have been in the queue for too long are simply discarded.
+ */
+static void pppol2tp_recv_dequeue(struct pppol2tp_session *session)
+{
+	struct sk_buff *skb;
+	struct sk_buff *tmp;
+
+	/* If the pkt at the head of the queue has the nr that we
+	 * expect to send up next, dequeue it and any other
+	 * in-sequence packets behind it.
+	 */
+	spin_lock_bh(&session->reorder_q.lock);
+	skb_queue_walk_safe(&session->reorder_q, skb, tmp) {
+		if (time_after(jiffies, PPPOL2TP_SKB_CB(skb)->expires)) {
+			session->stats.rx_seq_discards++;
+			session->stats.rx_errors++;
+			PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+			       "%s: oos pkt %hu len %d discarded (too old), "
+			       "waiting for %hu, reorder_q_len=%d\n",
+			       session->name, PPPOL2TP_SKB_CB(skb)->ns,
+			       PPPOL2TP_SKB_CB(skb)->length, session->nr,
+			       skb_queue_len(&session->reorder_q));
+			__skb_unlink(skb, &session->reorder_q);
+			kfree_skb(skb);
+			sock_put(session->sock);
+			continue;
+		}
+
+		if (PPPOL2TP_SKB_CB(skb)->has_seq) {
+			if (PPPOL2TP_SKB_CB(skb)->ns != session->nr) {
+				PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+				       "%s: holding oos pkt %hu len %d, "
+				       "waiting for %hu, reorder_q_len=%d\n",
+				       session->name, PPPOL2TP_SKB_CB(skb)->ns,
+				       PPPOL2TP_SKB_CB(skb)->length, session->nr,
+				       skb_queue_len(&session->reorder_q));
+				goto out;
+			}
+		}
+		__skb_unlink(skb, &session->reorder_q);
+
+		/* Process the skb. We release the queue lock while we
+		 * do so to let other contexts process the queue.
+		 */
+		spin_unlock_bh(&session->reorder_q.lock);
+		pppol2tp_recv_dequeue_skb(session, skb);
+		spin_lock_bh(&session->reorder_q.lock);
+	}
+
+out:
+	spin_unlock_bh(&session->reorder_q.lock);
+}
+
+static inline int pppol2tp_verify_udp_checksum(struct sock *sk,
+					       struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_hdr(skb);
+	u16 ulen = ntohs(uh->len);
+	struct inet_sock *inet;
+	__wsum psum;
+
+	if (sk->sk_no_check || skb_csum_unnecessary(skb) || !uh->check)
+		return 0;
+
+	inet = inet_sk(sk);
+	psum = csum_tcpudp_nofold(inet->inet_saddr, inet->inet_daddr, ulen,
+				  IPPROTO_UDP, 0);
+
+	if ((skb->ip_summed == CHECKSUM_COMPLETE) &&
+	    !csum_fold(csum_add(psum, skb->csum)))
+		return 0;
+
+	skb->csum = psum;
+
+	return __skb_checksum_complete(skb);
+}
+
+/* Internal receive frame. Do the real work of receiving an L2TP data frame
+ * here. The skb is not on a list when we get here.
+ * Returns 0 if the packet was a data packet and was successfully passed on.
+ * Returns 1 if the packet was not a good data packet and could not be
+ * forwarded.  All such packets are passed up to userspace to deal with.
+ */
+static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb)
+{
+	struct pppol2tp_session *session = NULL;
+	struct pppol2tp_tunnel *tunnel;
+	unsigned char *ptr, *optr;
+	u16 hdrflags;
+	u16 tunnel_id, session_id;
+	int length;
+	int offset;
+
+	tunnel = pppol2tp_sock_to_tunnel(sock);
+	if (tunnel == NULL)
+		goto no_tunnel;
+
+	if (tunnel->sock && pppol2tp_verify_udp_checksum(tunnel->sock, skb))
+		goto discard_bad_csum;
+
+	/* UDP always verifies the packet length. */
+	__skb_pull(skb, sizeof(struct udphdr));
+
+	/* Short packet? */
+	if (!pskb_may_pull(skb, 12)) {
+		PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
+		       "%s: recv short packet (len=%d)\n", tunnel->name, skb->len);
+		goto error;
+	}
+
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
+
+	/* Get L2TP header flags */
+	hdrflags = ntohs(*(__be16*)ptr);
+
+	/* Trace packet contents, if enabled */
+	if (tunnel->debug & PPPOL2TP_MSG_DATA) {
+		length = min(16u, skb->len);
+		if (!pskb_may_pull(skb, length))
+			goto error;
+
+		printk(KERN_DEBUG "%s: recv: ", tunnel->name);
+
+		offset = 0;
+		do {
+			printk(" %02X", ptr[offset]);
+		} while (++offset < length);
+
+		printk("\n");
+	}
+
+	/* Get length of L2TP packet */
+	length = skb->len;
+
+	/* If type is control packet, it is handled by userspace. */
+	if (hdrflags & L2TP_HDRFLAG_T) {
+		PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+		       "%s: recv control packet, len=%d\n", tunnel->name, length);
+		goto error;
+	}
+
+	/* Skip flags */
+	ptr += 2;
+
+	/* If length is present, skip it */
+	if (hdrflags & L2TP_HDRFLAG_L)
+		ptr += 2;
+
+	/* Extract tunnel and session ID */
+	tunnel_id = ntohs(*(__be16 *) ptr);
+	ptr += 2;
+	session_id = ntohs(*(__be16 *) ptr);
+	ptr += 2;
+
+	/* Find the session context */
+	session = pppol2tp_session_find(tunnel, session_id);
+	if (!session) {
+		/* Not found? Pass to userspace to deal with */
+		PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
+		       "%s: no socket found (%hu/%hu). Passing up.\n",
+		       tunnel->name, tunnel_id, session_id);
+		goto error;
+	}
+	sock_hold(session->sock);
+
+	/* The ref count on the socket was increased by the above call since
+	 * we now hold a pointer to the session. Take care to do sock_put()
+	 * when exiting this function from now on...
+	 */
+
+	/* Handle the optional sequence numbers.  If we are the LAC,
+	 * enable/disable sequence numbers under the control of the LNS.  If
+	 * no sequence numbers present but we were expecting them, discard
+	 * frame.
+	 */
+	if (hdrflags & L2TP_HDRFLAG_S) {
+		u16 ns, nr;
+		ns = ntohs(*(__be16 *) ptr);
+		ptr += 2;
+		nr = ntohs(*(__be16 *) ptr);
+		ptr += 2;
+
+		/* Received a packet with sequence numbers. If we're the LNS,
+		 * check if we sre sending sequence numbers and if not,
+		 * configure it so.
+		 */
+		if ((!session->lns_mode) && (!session->send_seq)) {
+			PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_INFO,
+			       "%s: requested to enable seq numbers by LNS\n",
+			       session->name);
+			session->send_seq = -1;
+		}
+
+		/* Store L2TP info in the skb */
+		PPPOL2TP_SKB_CB(skb)->ns = ns;
+		PPPOL2TP_SKB_CB(skb)->nr = nr;
+		PPPOL2TP_SKB_CB(skb)->has_seq = 1;
+
+		PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+		       "%s: recv data ns=%hu, nr=%hu, session nr=%hu\n",
+		       session->name, ns, nr, session->nr);
+	} else {
+		/* No sequence numbers.
+		 * If user has configured mandatory sequence numbers, discard.
+		 */
+		if (session->recv_seq) {
+			PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_WARNING,
+			       "%s: recv data has no seq numbers when required. "
+			       "Discarding\n", session->name);
+			session->stats.rx_seq_discards++;
+			goto discard;
+		}
+
+		/* If we're the LAC and we're sending sequence numbers, the
+		 * LNS has requested that we no longer send sequence numbers.
+		 * If we're the LNS and we're sending sequence numbers, the
+		 * LAC is broken. Discard the frame.
+		 */
+		if ((!session->lns_mode) && (session->send_seq)) {
+			PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_INFO,
+			       "%s: requested to disable seq numbers by LNS\n",
+			       session->name);
+			session->send_seq = 0;
+		} else if (session->send_seq) {
+			PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_WARNING,
+			       "%s: recv data has no seq numbers when required. "
+			       "Discarding\n", session->name);
+			session->stats.rx_seq_discards++;
+			goto discard;
+		}
+
+		/* Store L2TP info in the skb */
+		PPPOL2TP_SKB_CB(skb)->has_seq = 0;
+	}
+
+	/* If offset bit set, skip it. */
+	if (hdrflags & L2TP_HDRFLAG_O) {
+		offset = ntohs(*(__be16 *)ptr);
+		ptr += 2 + offset;
+	}
+
+	offset = ptr - optr;
+	if (!pskb_may_pull(skb, offset))
+		goto discard;
+
+	__skb_pull(skb, offset);
+
+	/* Skip PPP header, if present.	 In testing, Microsoft L2TP clients
+	 * don't send the PPP header (PPP header compression enabled), but
+	 * other clients can include the header. So we cope with both cases
+	 * here. The PPP header is always FF03 when using L2TP.
+	 *
+	 * Note that skb->data[] isn't dereferenced from a u16 ptr here since
+	 * the field may be unaligned.
+	 */
+	if (!pskb_may_pull(skb, 2))
+		goto discard;
+
+	if ((skb->data[0] == 0xff) && (skb->data[1] == 0x03))
+		skb_pull(skb, 2);
+
+	/* Prepare skb for adding to the session's reorder_q.  Hold
+	 * packets for max reorder_timeout or 1 second if not
+	 * reordering.
+	 */
+	PPPOL2TP_SKB_CB(skb)->length = length;
+	PPPOL2TP_SKB_CB(skb)->expires = jiffies +
+		(session->reorder_timeout ? session->reorder_timeout : HZ);
+
+	/* Add packet to the session's receive queue. Reordering is done here, if
+	 * enabled. Saved L2TP protocol info is stored in skb->sb[].
+	 */
+	if (PPPOL2TP_SKB_CB(skb)->has_seq) {
+		if (session->reorder_timeout != 0) {
+			/* Packet reordering enabled. Add skb to session's
+			 * reorder queue, in order of ns.
+			 */
+			pppol2tp_recv_queue_skb(session, skb);
+		} else {
+			/* Packet reordering disabled. Discard out-of-sequence
+			 * packets
+			 */
+			if (PPPOL2TP_SKB_CB(skb)->ns != session->nr) {
+				session->stats.rx_seq_discards++;
+				PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+				       "%s: oos pkt %hu len %d discarded, "
+				       "waiting for %hu, reorder_q_len=%d\n",
+				       session->name, PPPOL2TP_SKB_CB(skb)->ns,
+				       PPPOL2TP_SKB_CB(skb)->length, session->nr,
+				       skb_queue_len(&session->reorder_q));
+				goto discard;
+			}
+			skb_queue_tail(&session->reorder_q, skb);
+		}
+	} else {
+		/* No sequence numbers. Add the skb to the tail of the
+		 * reorder queue. This ensures that it will be
+		 * delivered after all previous sequenced skbs.
+		 */
+		skb_queue_tail(&session->reorder_q, skb);
+	}
+
+	/* Try to dequeue as many skbs from reorder_q as we can. */
+	pppol2tp_recv_dequeue(session);
+	sock_put(sock);
+
+	return 0;
+
+discard:
+	session->stats.rx_errors++;
+	kfree_skb(skb);
+	sock_put(session->sock);
+	sock_put(sock);
+
+	return 0;
+
+discard_bad_csum:
+	LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name);
+	UDP_INC_STATS_USER(&init_net, UDP_MIB_INERRORS, 0);
+	tunnel->stats.rx_errors++;
+	kfree_skb(skb);
+	sock_put(sock);
+
+	return 0;
+
+error:
+	/* Put UDP header back */
+	__skb_push(skb, sizeof(struct udphdr));
+	sock_put(sock);
+
+no_tunnel:
+	return 1;
+}
+
+/* UDP encapsulation receive handler. See net/ipv4/udp.c.
+ * Return codes:
+ * 0 : success.
+ * <0: error
+ * >0: skb should be passed up to userspace as UDP.
+ */
+static int pppol2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct pppol2tp_tunnel *tunnel;
+
+	tunnel = pppol2tp_sock_to_tunnel(sk);
+	if (tunnel == NULL)
+		goto pass_up;
+
+	PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+	       "%s: received %d bytes\n", tunnel->name, skb->len);
+
+	if (pppol2tp_recv_core(sk, skb))
+		goto pass_up_put;
+
+	sock_put(sk);
+	return 0;
+
+pass_up_put:
+	sock_put(sk);
+pass_up:
+	return 1;
+}
+
+/* Receive message. This is the recvmsg for the PPPoL2TP socket.
+ */
+static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
+			    struct msghdr *msg, size_t len,
+			    int flags)
+{
+	int err;
+	struct sk_buff *skb;
+	struct sock *sk = sock->sk;
+
+	err = -EIO;
+	if (sk->sk_state & PPPOX_BOUND)
+		goto end;
+
+	msg->msg_namelen = 0;
+
+	err = 0;
+	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
+				flags & MSG_DONTWAIT, &err);
+	if (!skb)
+		goto end;
+
+	if (len > skb->len)
+		len = skb->len;
+	else if (len < skb->len)
+		msg->msg_flags |= MSG_TRUNC;
+
+	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
+	if (likely(err == 0))
+		err = len;
+
+	kfree_skb(skb);
+end:
+	return err;
+}
+
+/************************************************************************
+ * Transmit handling
+ ***********************************************************************/
+
+/* Tell how big L2TP headers are for a particular session. This
+ * depends on whether sequence numbers are being used.
+ */
+static inline int pppol2tp_l2tp_header_len(struct pppol2tp_session *session)
+{
+	if (session->send_seq)
+		return PPPOL2TP_L2TP_HDR_SIZE_SEQ;
+
+	return PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
+}
+
+/* Build an L2TP header for the session into the buffer provided.
+ */
+static void pppol2tp_build_l2tp_header(struct pppol2tp_session *session,
+				       void *buf)
+{
+	__be16 *bufp = buf;
+	u16 flags = L2TP_HDR_VER;
+
+	if (session->send_seq)
+		flags |= L2TP_HDRFLAG_S;
+
+	/* Setup L2TP header.
+	 * FIXME: Can this ever be unaligned? Is direct dereferencing of
+	 * 16-bit header fields safe here for all architectures?
+	 */
+	*bufp++ = htons(flags);
+	*bufp++ = htons(session->tunnel_addr.d_tunnel);
+	*bufp++ = htons(session->tunnel_addr.d_session);
+	if (session->send_seq) {
+		*bufp++ = htons(session->ns);
+		*bufp++ = 0;
+		session->ns++;
+		PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+		       "%s: updated ns to %hu\n", session->name, session->ns);
+	}
+}
+
+/* This is the sendmsg for the PPPoL2TP pppol2tp_session socket.  We come here
+ * when a user application does a sendmsg() on the session socket. L2TP and
+ * PPP headers must be inserted into the user's data.
+ */
+static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
+			    size_t total_len)
+{
+	static const unsigned char ppph[2] = { 0xff, 0x03 };
+	struct sock *sk = sock->sk;
+	struct inet_sock *inet;
+	__wsum csum;
+	struct sk_buff *skb;
+	int error;
+	int hdr_len;
+	struct pppol2tp_session *session;
+	struct pppol2tp_tunnel *tunnel;
+	struct udphdr *uh;
+	unsigned int len;
+	struct sock *sk_tun;
+	u16 udp_len;
+
+	error = -ENOTCONN;
+	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
+		goto error;
+
+	/* Get session and tunnel contexts */
+	error = -EBADF;
+	session = pppol2tp_sock_to_session(sk);
+	if (session == NULL)
+		goto error;
+
+	sk_tun = session->tunnel_sock;
+	tunnel = pppol2tp_sock_to_tunnel(sk_tun);
+	if (tunnel == NULL)
+		goto error_put_sess;
+
+	/* What header length is configured for this session? */
+	hdr_len = pppol2tp_l2tp_header_len(session);
+
+	/* Allocate a socket buffer */
+	error = -ENOMEM;
+	skb = sock_wmalloc(sk, NET_SKB_PAD + sizeof(struct iphdr) +
+			   sizeof(struct udphdr) + hdr_len +
+			   sizeof(ppph) + total_len,
+			   0, GFP_KERNEL);
+	if (!skb)
+		goto error_put_sess_tun;
+
+	/* Reserve space for headers. */
+	skb_reserve(skb, NET_SKB_PAD);
+	skb_reset_network_header(skb);
+	skb_reserve(skb, sizeof(struct iphdr));
+	skb_reset_transport_header(skb);
+
+	/* Build UDP header */
+	inet = inet_sk(sk_tun);
+	udp_len = hdr_len + sizeof(ppph) + total_len;
+	uh = (struct udphdr *) skb->data;
+	uh->source = inet->inet_sport;
+	uh->dest = inet->inet_dport;
+	uh->len = htons(udp_len);
+	uh->check = 0;
+	skb_put(skb, sizeof(struct udphdr));
+
+	/* Build L2TP header */
+	pppol2tp_build_l2tp_header(session, skb->data);
+	skb_put(skb, hdr_len);
+
+	/* Add PPP header */
+	skb->data[0] = ppph[0];
+	skb->data[1] = ppph[1];
+	skb_put(skb, 2);
+
+	/* Copy user data into skb */
+	error = memcpy_fromiovec(skb->data, m->msg_iov, total_len);
+	if (error < 0) {
+		kfree_skb(skb);
+		goto error_put_sess_tun;
+	}
+	skb_put(skb, total_len);
+
+	/* Calculate UDP checksum if configured to do so */
+	if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT)
+		skb->ip_summed = CHECKSUM_NONE;
+	else if (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) {
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		csum = skb_checksum(skb, 0, udp_len, 0);
+		uh->check = csum_tcpudp_magic(inet->inet_saddr,
+					      inet->inet_daddr,
+					      udp_len, IPPROTO_UDP, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+	} else {
+		skb->ip_summed = CHECKSUM_PARTIAL;
+		skb->csum_start = skb_transport_header(skb) - skb->head;
+		skb->csum_offset = offsetof(struct udphdr, check);
+		uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
+					       inet->inet_daddr,
+					       udp_len, IPPROTO_UDP, 0);
+	}
+
+	/* Debug */
+	if (session->send_seq)
+		PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+		       "%s: send %Zd bytes, ns=%hu\n", session->name,
+		       total_len, session->ns - 1);
+	else
+		PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+		       "%s: send %Zd bytes\n", session->name, total_len);
+
+	if (session->debug & PPPOL2TP_MSG_DATA) {
+		int i;
+		unsigned char *datap = skb->data;
+
+		printk(KERN_DEBUG "%s: xmit:", session->name);
+		for (i = 0; i < total_len; i++) {
+			printk(" %02X", *datap++);
+			if (i == 15) {
+				printk(" ...");
+				break;
+			}
+		}
+		printk("\n");
+	}
+
+	/* Queue the packet to IP for output */
+	len = skb->len;
+	error = ip_queue_xmit(skb, 1);
+
+	/* Update stats */
+	if (error >= 0) {
+		tunnel->stats.tx_packets++;
+		tunnel->stats.tx_bytes += len;
+		session->stats.tx_packets++;
+		session->stats.tx_bytes += len;
+	} else {
+		tunnel->stats.tx_errors++;
+		session->stats.tx_errors++;
+	}
+
+	return error;
+
+error_put_sess_tun:
+	sock_put(session->tunnel_sock);
+error_put_sess:
+	sock_put(sk);
+error:
+	return error;
+}
+
+/* Automatically called when the skb is freed.
+ */
+static void pppol2tp_sock_wfree(struct sk_buff *skb)
+{
+	sock_put(skb->sk);
+}
+
+/* For data skbs that we transmit, we associate with the tunnel socket
+ * but don't do accounting.
+ */
+static inline void pppol2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
+{
+	sock_hold(sk);
+	skb->sk = sk;
+	skb->destructor = pppol2tp_sock_wfree;
+}
+
+/* Transmit function called by generic PPP driver.  Sends PPP frame
+ * over PPPoL2TP socket.
+ *
+ * This is almost the same as pppol2tp_sendmsg(), but rather than
+ * being called with a msghdr from userspace, it is called with a skb
+ * from the kernel.
+ *
+ * The supplied skb from ppp doesn't have enough headroom for the
+ * insertion of L2TP, UDP and IP headers so we need to allocate more
+ * headroom in the skb. This will create a cloned skb. But we must be
+ * careful in the error case because the caller will expect to free
+ * the skb it supplied, not our cloned skb. So we take care to always
+ * leave the original skb unfreed if we return an error.
+ */
+static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+	static const u8 ppph[2] = { 0xff, 0x03 };
+	struct sock *sk = (struct sock *) chan->private;
+	struct sock *sk_tun;
+	int hdr_len;
+	u16 udp_len;
+	struct pppol2tp_session *session;
+	struct pppol2tp_tunnel *tunnel;
+	int rc;
+	int headroom;
+	int data_len = skb->len;
+	struct inet_sock *inet;
+	__wsum csum;
+	struct udphdr *uh;
+	unsigned int len;
+	int old_headroom;
+	int new_headroom;
+
+	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
+		goto abort;
+
+	/* Get session and tunnel con