pppol2tp.c

来自「linux 内核源代码」· C语言 代码 · 共 2,472 行 · 第 1/5 页

/*****************************************************************************
 * 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 <[e-mail]>
 *		James Chapman ([e-mail])
 * Contributors:
 *		Michal Ostrowski <[e-mail]>
 *		Arnaldo Carvalho de Melo <[e-mail]>
 *		David S. Miller ([e-mail])
 *
 * 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/version.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 <net/net_namespace.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 */

	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 struct proto_ops pppol2tp_ops;
static LIST_HEAD(pppol2tp_tunnel_list);
static DEFINE_RWLOCK(pppol2tp_tunnel_list_lock);

/* 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;

	session = (struct pppol2tp_session *)(sk->sk_user_data);
	if (session == NULL)
		return NULL;

	BUG_ON(session->magic != L2TP_SESSION_MAGIC);

	return session;
}

static inline struct pppol2tp_tunnel *pppol2tp_sock_to_tunnel(struct sock *sk)
{
	struct pppol2tp_tunnel *tunnel;

	if (sk == NULL)
		return NULL;

	tunnel = (struct pppol2tp_tunnel *)(sk->sk_user_data);
	if (tunnel == NULL)
		return NULL;

	BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);

	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(&tunnel->hlist_lock);
	hlist_for_each_entry(session, walk, session_list, hlist) {
		if (session->tunnel_addr.s_session == session_id) {
			read_unlock(&tunnel->hlist_lock);
			return session;
		}
	}
	read_unlock(&tunnel->hlist_lock);

	return NULL;
}

/* Lookup a tunnel by id
 */
static struct pppol2tp_tunnel *pppol2tp_tunnel_find(u16 tunnel_id)
{
	struct pppol2tp_tunnel *tunnel = NULL;

	read_lock(&pppol2tp_tunnel_list_lock);
	list_for_each_entry(tunnel, &pppol2tp_tunnel_list, list) {
		if (tunnel->stats.tunnel_id == tunnel_id) {
			read_unlock(&pppol2tp_tunnel_list_lock);
			return tunnel;
		}
	}
	read_unlock(&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;
	u16 ns = PPPOL2TP_SKB_CB(skb)->ns;

	spin_lock(&session->reorder_q.lock);
	skb_queue_walk(&session->reorder_q, skbp) {
		if (PPPOL2TP_SKB_CB(skbp)->ns > ns) {
			__skb_insert(skb, skbp->prev, skbp, &session->reorder_q);
			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(&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 unlink it and return resources
	 * to its current owner (a socket receive buffer).
	 */
	skb_unlink(skb, &session->reorder_q);
	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);
		dst_release(skb->dst);
		skb->dst = NULL;
		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(&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);
			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;
			}
		}
		spin_unlock(&session->reorder_q.lock);
		pppol2tp_recv_dequeue_skb(session, skb);
		spin_lock(&session->reorder_q.lock);
	}

out:
	spin_unlock(&session->reorder_q.lock);
}

/* 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;