pppoe.c

linux 内核源代码

/** -*- linux-c -*- ***********************************************************
 * Linux PPP over Ethernet (PPPoX/PPPoE) Sockets
 *
 * PPPoX --- Generic PPP encapsulation socket family
 * PPPoE --- PPP over Ethernet (RFC 2516)
 *
 *
 * Version:	0.7.0
 *
 * 070228 :	Fix to allow multiple sessions with same remote MAC and same
 *		session id by including the local device ifindex in the
 *		tuple identifying a session. This also ensures packets can't
 *		be injected into a session from interfaces other than the one
 *		specified by userspace. Florian Zumbiehl <[e-mail]>
 *		(Oh, BTW, this one is YYMMDD, in case you were wondering ...)
 * 220102 :	Fix module use count on failure in pppoe_create, pppox_sk -acme
 * 030700 :	Fixed connect logic to allow for disconnect.
 * 270700 :	Fixed potential SMP problems; we must protect against
 *		simultaneous invocation of ppp_input
 *		and ppp_unregister_channel.
 * 040800 :	Respect reference count mechanisms on net-devices.
 * 200800 :	fix kfree(skb) in pppoe_rcv (acme)
 *		Module reference count is decremented in the right spot now,
 *		guards against sock_put not actually freeing the sk
 *		in pppoe_release.
 * 051000 :	Initialization cleanup.
 * 111100 :	Fix recvmsg.
 * 050101 :	Fix PADT procesing.
 * 140501 :	Use pppoe_rcv_core to handle all backlog. (Alexey)
 * 170701 :	Do not lock_sock with rwlock held. (DaveM)
 *		Ignore discovery frames if user has socket
 *		locked. (DaveM)
 *		Ignore return value of dev_queue_xmit in __pppoe_xmit
 *		or else we may kfree an SKB twice. (DaveM)
 * 190701 :	When doing copies of skb's in __pppoe_xmit, always delete
 *		the original skb that was passed in on success, never on
 *		failure.  Delete the copy of the skb on failure to avoid
 *		a memory leak.
 * 081001 :	Misc. cleanup (licence string, non-blocking, prevent
 *		reference of device on close).
 * 121301 :	New ppp channels interface; cannot unregister a channel
 *		from interrupts.  Thus, we mark the socket as a ZOMBIE
 *		and do the unregistration later.
 * 081002 :	seq_file support for proc stuff -acme
 * 111602 :	Merge all 2.4 fixes into 2.5/2.6 tree.  Label 2.5/2.6
 *		as version 0.7.  Spacing cleanup.
 * Author:	Michal Ostrowski <[e-mail]>
 * Contributors:
 * 		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.
 *
 */

#include <linux/string.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/net.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/if_ether.h>
#include <linux/if_pppox.h>
#include <linux/ppp_channel.h>
#include <linux/ppp_defs.h>
#include <linux/if_ppp.h>
#include <linux/notifier.h>
#include <linux/file.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>

#include <net/net_namespace.h>
#include <net/sock.h>

#include <asm/uaccess.h>

#define PPPOE_HASH_BITS 4
#define PPPOE_HASH_SIZE (1<<PPPOE_HASH_BITS)

static struct ppp_channel_ops pppoe_chan_ops;

static int pppoe_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
static int pppoe_xmit(struct ppp_channel *chan, struct sk_buff *skb);
static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb);

static const struct proto_ops pppoe_ops;
static DEFINE_RWLOCK(pppoe_hash_lock);

static struct ppp_channel_ops pppoe_chan_ops;

static inline int cmp_2_addr(struct pppoe_addr *a, struct pppoe_addr *b)
{
	return (a->sid == b->sid &&
		(memcmp(a->remote, b->remote, ETH_ALEN) == 0));
}

static inline int cmp_addr(struct pppoe_addr *a, __be16 sid, char *addr)
{
	return (a->sid == sid &&
		(memcmp(a->remote,addr,ETH_ALEN) == 0));
}

#if 8%PPPOE_HASH_BITS
#error 8 must be a multiple of PPPOE_HASH_BITS
#endif

static int hash_item(__be16 sid, unsigned char *addr)
{
	unsigned char hash = 0;
	unsigned int i;

	for (i = 0 ; i < ETH_ALEN ; i++) {
		hash ^= addr[i];
	}
	for (i = 0 ; i < sizeof(sid_t)*8 ; i += 8 ){
		hash ^= (__force __u32)sid>>i;
	}
	for (i = 8 ; (i>>=1) >= PPPOE_HASH_BITS ; ) {
		hash ^= hash>>i;
	}

	return hash & ( PPPOE_HASH_SIZE - 1 );
}

/* zeroed because its in .bss */
static struct pppox_sock *item_hash_table[PPPOE_HASH_SIZE];

/**********************************************************************
 *
 *  Set/get/delete/rehash items  (internal versions)
 *
 **********************************************************************/
static struct pppox_sock *__get_item(__be16 sid, unsigned char *addr, int ifindex)
{
	int hash = hash_item(sid, addr);
	struct pppox_sock *ret;

	ret = item_hash_table[hash];

	while (ret && !(cmp_addr(&ret->pppoe_pa, sid, addr) && ret->pppoe_ifindex == ifindex))
		ret = ret->next;

	return ret;
}

static int __set_item(struct pppox_sock *po)
{
	int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote);
	struct pppox_sock *ret;

	ret = item_hash_table[hash];
	while (ret) {
		if (cmp_2_addr(&ret->pppoe_pa, &po->pppoe_pa) && ret->pppoe_ifindex == po->pppoe_ifindex)
			return -EALREADY;

		ret = ret->next;
	}

	po->next = item_hash_table[hash];
	item_hash_table[hash] = po;

	return 0;
}

static struct pppox_sock *__delete_item(__be16 sid, char *addr, int ifindex)
{
	int hash = hash_item(sid, addr);
	struct pppox_sock *ret, **src;

	ret = item_hash_table[hash];
	src = &item_hash_table[hash];

	while (ret) {
		if (cmp_addr(&ret->pppoe_pa, sid, addr) && ret->pppoe_ifindex == ifindex) {
			*src = ret->next;
			break;
		}

		src = &ret->next;
		ret = ret->next;
	}

	return ret;
}

/**********************************************************************
 *
 *  Set/get/delete/rehash items
 *
 **********************************************************************/
static inline struct pppox_sock *get_item(__be16 sid,
					 unsigned char *addr, int ifindex)
{
	struct pppox_sock *po;

	read_lock_bh(&pppoe_hash_lock);
	po = __get_item(sid, addr, ifindex);
	if (po)
		sock_hold(sk_pppox(po));
	read_unlock_bh(&pppoe_hash_lock);

	return po;
}

static inline struct pppox_sock *get_item_by_addr(struct sockaddr_pppox *sp)
{
	struct net_device *dev;
	int ifindex;

	dev = dev_get_by_name(&init_net, sp->sa_addr.pppoe.dev);
	if(!dev)
		return NULL;
	ifindex = dev->ifindex;
	dev_put(dev);
	return get_item(sp->sa_addr.pppoe.sid, sp->sa_addr.pppoe.remote, ifindex);
}

static inline struct pppox_sock *delete_item(__be16 sid, char *addr, int ifindex)
{
	struct pppox_sock *ret;

	write_lock_bh(&pppoe_hash_lock);
	ret = __delete_item(sid, addr, ifindex);
	write_unlock_bh(&pppoe_hash_lock);

	return ret;
}



/***************************************************************************
 *
 *  Handler for device events.
 *  Certain device events require that sockets be unconnected.
 *
 **************************************************************************/

static void pppoe_flush_dev(struct net_device *dev)
{
	int hash;
	BUG_ON(dev == NULL);

	write_lock_bh(&pppoe_hash_lock);
	for (hash = 0; hash < PPPOE_HASH_SIZE; hash++) {
		struct pppox_sock *po = item_hash_table[hash];

		while (po != NULL) {
			struct sock *sk = sk_pppox(po);
			if (po->pppoe_dev != dev) {
				po = po->next;
				continue;
			}
			po->pppoe_dev = NULL;
			dev_put(dev);


			/* We always grab the socket lock, followed by the
			 * pppoe_hash_lock, in that order.  Since we should
			 * hold the sock lock while doing any unbinding,
			 * we need to release the lock we're holding.
			 * Hold a reference to the sock so it doesn't disappear
			 * as we're jumping between locks.
			 */

			sock_hold(sk);

			write_unlock_bh(&pppoe_hash_lock);
			lock_sock(sk);

			if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) {
				pppox_unbind_sock(sk);
				sk->sk_state = PPPOX_ZOMBIE;
				sk->sk_state_change(sk);
			}

			release_sock(sk);
			sock_put(sk);

			/* Restart scan at the beginning of this hash chain.
			 * While the lock was dropped the chain contents may
			 * have changed.
			 */
			write_lock_bh(&pppoe_hash_lock);
			po = item_hash_table[hash];
		}
	}
	write_unlock_bh(&pppoe_hash_lock);
}

static int pppoe_device_event(struct notifier_block *this,
			      unsigned long event, void *ptr)
{
	struct net_device *dev = (struct net_device *) ptr;

	if (dev->nd_net != &init_net)
		return NOTIFY_DONE;

	/* Only look at sockets that are using this specific device. */
	switch (event) {
	case NETDEV_CHANGEMTU:
		/* A change in mtu is a bad thing, requiring
		 * LCP re-negotiation.
		 */

	case NETDEV_GOING_DOWN:
	case NETDEV_DOWN:
		/* Find every socket on this device and kill it. */
		pppoe_flush_dev(dev);
		break;

	default:
		break;
	};

	return NOTIFY_DONE;
}


static struct notifier_block pppoe_notifier = {
	.notifier_call = pppoe_device_event,
};


/************************************************************************
 *
 * Do the real work of receiving a PPPoE Session frame.
 *
 ***********************************************************************/
static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
{
	struct pppox_sock *po = pppox_sk(sk);
	struct pppox_sock *relay_po;

	if (sk->sk_state & PPPOX_BOUND) {
		struct pppoe_hdr *ph = pppoe_hdr(skb);
		int len = ntohs(ph->length);
		skb_pull_rcsum(skb, sizeof(struct pppoe_hdr));
		if (pskb_trim_rcsum(skb, len))
			goto abort_kfree;

		ppp_input(&po->chan, skb);
	} else if (sk->sk_state & PPPOX_RELAY) {
		relay_po = get_item_by_addr(&po->pppoe_relay);

		if (relay_po == NULL)
			goto abort_kfree;

		if ((sk_pppox(relay_po)->sk_state & PPPOX_CONNECTED) == 0)
			goto abort_put;

		skb_pull(skb, sizeof(struct pppoe_hdr));
		if (!__pppoe_xmit(sk_pppox(relay_po), skb))
			goto abort_put;
	} else {
		if (sock_queue_rcv_skb(sk, skb))
			goto abort_kfree;
	}

	return NET_RX_SUCCESS;

abort_put:
	sock_put(sk_pppox(relay_po));

abort_kfree:
	kfree_skb(skb);
	return NET_RX_DROP;
}

/************************************************************************
 *
 * Receive wrapper called in BH context.
 *
 ***********************************************************************/
static int pppoe_rcv(struct sk_buff *skb,
		     struct net_device *dev,
		     struct packet_type *pt,
		     struct net_device *orig_dev)

{
	struct pppoe_hdr *ph;
	struct pppox_sock *po;

	if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
		goto out;

	if (dev->nd_net != &init_net)
		goto drop;

	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
		goto drop;

	ph = pppoe_hdr(skb);

	po = get_item(ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
	if (po != NULL)
		return sk_receive_skb(sk_pppox(po), skb, 0);
drop:
	kfree_skb(skb);
out:
	return NET_RX_DROP;
}

/************************************************************************
 *
 * Receive a PPPoE Discovery frame.
 * This is solely for detection of PADT frames
 *
 ***********************************************************************/
static int pppoe_disc_rcv(struct sk_buff *skb,
			  struct net_device *dev,
			  struct packet_type *pt,
			  struct net_device *orig_dev)

{
	struct pppoe_hdr *ph;
	struct pppox_sock *po;

	if (dev->nd_net != &init_net)
		goto abort;

	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
		goto abort;

	if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
		goto out;

	ph = pppoe_hdr(skb);
	if (ph->code != PADT_CODE)
		goto abort;

	po = get_item(ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
	if (po) {
		struct sock *sk = sk_pppox(po);

		bh_lock_sock(sk);

		/* If the user has locked the socket, just ignore
		 * the packet.  With the way two rcv protocols hook into
		 * one socket family type, we cannot (easily) distinguish
		 * what kind of SKB it is during backlog rcv.
		 */
		if (sock_owned_by_user(sk) == 0) {
			/* We're no longer connect at the PPPOE layer,
			 * and must wait for ppp channel to disconnect us.
			 */
			sk->sk_state = PPPOX_ZOMBIE;
		}

		bh_unlock_sock(sk);
		sock_put(sk);
	}

abort:
	kfree_skb(skb);
out:
	return NET_RX_SUCCESS; /* Lies... :-) */
}

static struct packet_type pppoes_ptype = {
	.type	= __constant_htons(ETH_P_PPP_SES),
	.func	= pppoe_rcv,
};

static struct packet_type pppoed_ptype = {
	.type	= __constant_htons(ETH_P_PPP_DISC),
	.func	= pppoe_disc_rcv,
};

static struct proto pppoe_sk_proto = {
	.name	  = "PPPOE",
	.owner	  = THIS_MODULE,
	.obj_size = sizeof(struct pppox_sock),
};

/***********************************************************************
 *
 * Initialize a new struct sock.
 *
 **********************************************************************/
static int pppoe_create(struct net *net, struct socket *sock)
{
	int error = -ENOMEM;
	struct sock *sk;

	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppoe_sk_proto);
	if (!sk)
		goto out;

	sock_init_data(sock, sk);

	sock->state = SS_UNCONNECTED;
	sock->ops   = &pppoe_ops;

	sk->sk_backlog_rcv = pppoe_rcv_core;
	sk->sk_state	   = PPPOX_NONE;
	sk->sk_type	   = SOCK_STREAM;
	sk->sk_family	   = PF_PPPOX;
	sk->sk_protocol	   = PX_PROTO_OE;

	error = 0;
out:	return error;
}

static int pppoe_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct pppox_sock *po;

	if (!sk)
		return 0;

	lock_sock(sk);
	if (sock_flag(sk, SOCK_DEAD)){
		release_sock(sk);
		return -EBADF;
	}

	pppox_unbind_sock(sk);

	/* Signal the death of the socket. */
	sk->sk_state = PPPOX_DEAD;


	/* Write lock on hash lock protects the entire "po" struct from
	 * concurrent updates via pppoe_flush_dev. The "po" struct should
	 * be considered part of the hash table contents, thus protected
	 * by the hash table lock */
	write_lock_bh(&pppoe_hash_lock);

	po = pppox_sk(sk);
	if (po->pppoe_pa.sid) {
		__delete_item(po->pppoe_pa.sid,
			      po->pppoe_pa.remote, po->pppoe_ifindex);
	}

	if (po->pppoe_dev) {
		dev_put(po->pppoe_dev);
		po->pppoe_dev = NULL;
	}

	write_unlock_bh(&pppoe_hash_lock);

	sock_orphan(sk);
	sock->sk = NULL;

	skb_queue_purge(&sk->sk_receive_queue);
	release_sock(sk);
	sock_put(sk);

	return 0;
}


static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
		  int sockaddr_len, int flags)
{
	struct sock *sk = sock->sk;
	struct net_device *dev;
	struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr;