ip6_tunnel.c

linux 内核源代码

/*
 *	IPv6 tunneling device
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Ville Nuorvala		<[e-mail]>
 *	Yasuyuki Kozakai	<[e-mail]>
 *
 *	$Id$
 *
 *      Based on:
 *      linux/net/ipv6/sit.c and linux/net/ipv4/ipip.c
 *
 *      RFC 2473
 *
 *	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/module.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/sockios.h>
#include <linux/icmp.h>
#include <linux/if.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/if_tunnel.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/route.h>
#include <linux/rtnetlink.h>
#include <linux/netfilter_ipv6.h>

#include <asm/uaccess.h>
#include <asm/atomic.h>

#include <net/icmp.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>

MODULE_AUTHOR("Ville Nuorvala");
MODULE_DESCRIPTION("IPv6 tunneling device");
MODULE_LICENSE("GPL");

#define IPV6_TLV_TEL_DST_SIZE 8

#ifdef IP6_TNL_DEBUG
#define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __FUNCTION__)
#else
#define IP6_TNL_TRACE(x...) do {;} while(0)
#endif

#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
#define IPV6_TCLASS_SHIFT 20

#define HASH_SIZE  32

#define HASH(addr) ((__force u32)((addr)->s6_addr32[0] ^ (addr)->s6_addr32[1] ^ \
		     (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \
		    (HASH_SIZE - 1))

static int ip6_fb_tnl_dev_init(struct net_device *dev);
static int ip6_tnl_dev_init(struct net_device *dev);
static void ip6_tnl_dev_setup(struct net_device *dev);

/* the IPv6 tunnel fallback device */
static struct net_device *ip6_fb_tnl_dev;


/* lists for storing tunnels in use */
static struct ip6_tnl *tnls_r_l[HASH_SIZE];
static struct ip6_tnl *tnls_wc[1];
static struct ip6_tnl **tnls[2] = { tnls_wc, tnls_r_l };

/* lock for the tunnel lists */
static DEFINE_RWLOCK(ip6_tnl_lock);

static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
{
	struct dst_entry *dst = t->dst_cache;

	if (dst && dst->obsolete &&
	    dst->ops->check(dst, t->dst_cookie) == NULL) {
		t->dst_cache = NULL;
		dst_release(dst);
		return NULL;
	}

	return dst;
}

static inline void ip6_tnl_dst_reset(struct ip6_tnl *t)
{
	dst_release(t->dst_cache);
	t->dst_cache = NULL;
}

static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
{
	struct rt6_info *rt = (struct rt6_info *) dst;
	t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
	dst_release(t->dst_cache);
	t->dst_cache = dst;
}

/**
 * ip6_tnl_lookup - fetch tunnel matching the end-point addresses
 *   @remote: the address of the tunnel exit-point
 *   @local: the address of the tunnel entry-point
 *
 * Return:
 *   tunnel matching given end-points if found,
 *   else fallback tunnel if its device is up,
 *   else %NULL
 **/

static struct ip6_tnl *
ip6_tnl_lookup(struct in6_addr *remote, struct in6_addr *local)
{
	unsigned h0 = HASH(remote);
	unsigned h1 = HASH(local);
	struct ip6_tnl *t;

	for (t = tnls_r_l[h0 ^ h1]; t; t = t->next) {
		if (ipv6_addr_equal(local, &t->parms.laddr) &&
		    ipv6_addr_equal(remote, &t->parms.raddr) &&
		    (t->dev->flags & IFF_UP))
			return t;
	}
	if ((t = tnls_wc[0]) != NULL && (t->dev->flags & IFF_UP))
		return t;

	return NULL;
}

/**
 * ip6_tnl_bucket - get head of list matching given tunnel parameters
 *   @p: parameters containing tunnel end-points
 *
 * Description:
 *   ip6_tnl_bucket() returns the head of the list matching the
 *   &struct in6_addr entries laddr and raddr in @p.
 *
 * Return: head of IPv6 tunnel list
 **/

static struct ip6_tnl **
ip6_tnl_bucket(struct ip6_tnl_parm *p)
{
	struct in6_addr *remote = &p->raddr;
	struct in6_addr *local = &p->laddr;
	unsigned h = 0;
	int prio = 0;

	if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) {
		prio = 1;
		h = HASH(remote) ^ HASH(local);
	}
	return &tnls[prio][h];
}

/**
 * ip6_tnl_link - add tunnel to hash table
 *   @t: tunnel to be added
 **/

static void
ip6_tnl_link(struct ip6_tnl *t)
{
	struct ip6_tnl **tp = ip6_tnl_bucket(&t->parms);

	t->next = *tp;
	write_lock_bh(&ip6_tnl_lock);
	*tp = t;
	write_unlock_bh(&ip6_tnl_lock);
}

/**
 * ip6_tnl_unlink - remove tunnel from hash table
 *   @t: tunnel to be removed
 **/

static void
ip6_tnl_unlink(struct ip6_tnl *t)
{
	struct ip6_tnl **tp;

	for (tp = ip6_tnl_bucket(&t->parms); *tp; tp = &(*tp)->next) {
		if (t == *tp) {
			write_lock_bh(&ip6_tnl_lock);
			*tp = t->next;
			write_unlock_bh(&ip6_tnl_lock);
			break;
		}
	}
}

/**
 * ip6_tnl_create() - create a new tunnel
 *   @p: tunnel parameters
 *   @pt: pointer to new tunnel
 *
 * Description:
 *   Create tunnel matching given parameters.
 *
 * Return:
 *   created tunnel or NULL
 **/

static struct ip6_tnl *ip6_tnl_create(struct ip6_tnl_parm *p)
{
	struct net_device *dev;
	struct ip6_tnl *t;
	char name[IFNAMSIZ];
	int err;

	if (p->name[0]) {
		strlcpy(name, p->name, IFNAMSIZ);
	} else {
		int i;
		for (i = 1; i < IP6_TNL_MAX; i++) {
			sprintf(name, "ip6tnl%d", i);
			if (__dev_get_by_name(&init_net, name) == NULL)
				break;
		}
		if (i == IP6_TNL_MAX)
			goto failed;
	}
	dev = alloc_netdev(sizeof (*t), name, ip6_tnl_dev_setup);
	if (dev == NULL)
		goto failed;

	t = netdev_priv(dev);
	dev->init = ip6_tnl_dev_init;
	t->parms = *p;

	if ((err = register_netdevice(dev)) < 0) {
		free_netdev(dev);
		goto failed;
	}
	dev_hold(dev);
	ip6_tnl_link(t);
	return t;
failed:
	return NULL;
}

/**
 * ip6_tnl_locate - find or create tunnel matching given parameters
 *   @p: tunnel parameters
 *   @create: != 0 if allowed to create new tunnel if no match found
 *
 * Description:
 *   ip6_tnl_locate() first tries to locate an existing tunnel
 *   based on @parms. If this is unsuccessful, but @create is set a new
 *   tunnel device is created and registered for use.
 *
 * Return:
 *   matching tunnel or NULL
 **/

static struct ip6_tnl *ip6_tnl_locate(struct ip6_tnl_parm *p, int create)
{
	struct in6_addr *remote = &p->raddr;
	struct in6_addr *local = &p->laddr;
	struct ip6_tnl *t;

	for (t = *ip6_tnl_bucket(p); t; t = t->next) {
		if (ipv6_addr_equal(local, &t->parms.laddr) &&
		    ipv6_addr_equal(remote, &t->parms.raddr))
			return t;
	}
	if (!create)
		return NULL;
	return ip6_tnl_create(p);
}

/**
 * ip6_tnl_dev_uninit - tunnel device uninitializer
 *   @dev: the device to be destroyed
 *
 * Description:
 *   ip6_tnl_dev_uninit() removes tunnel from its list
 **/

static void
ip6_tnl_dev_uninit(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);

	if (dev == ip6_fb_tnl_dev) {
		write_lock_bh(&ip6_tnl_lock);
		tnls_wc[0] = NULL;
		write_unlock_bh(&ip6_tnl_lock);
	} else {
		ip6_tnl_unlink(t);
	}
	ip6_tnl_dst_reset(t);
	dev_put(dev);
}

/**
 * parse_tvl_tnl_enc_lim - handle encapsulation limit option
 *   @skb: received socket buffer
 *
 * Return:
 *   0 if none was found,
 *   else index to encapsulation limit
 **/

static __u16
parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw)
{
	struct ipv6hdr *ipv6h = (struct ipv6hdr *) raw;
	__u8 nexthdr = ipv6h->nexthdr;
	__u16 off = sizeof (*ipv6h);

	while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
		__u16 optlen = 0;
		struct ipv6_opt_hdr *hdr;
		if (raw + off + sizeof (*hdr) > skb->data &&
		    !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
			break;

		hdr = (struct ipv6_opt_hdr *) (raw + off);
		if (nexthdr == NEXTHDR_FRAGMENT) {
			struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
			if (frag_hdr->frag_off)
				break;
			optlen = 8;
		} else if (nexthdr == NEXTHDR_AUTH) {
			optlen = (hdr->hdrlen + 2) << 2;
		} else {
			optlen = ipv6_optlen(hdr);
		}
		if (nexthdr == NEXTHDR_DEST) {
			__u16 i = off + 2;
			while (1) {
				struct ipv6_tlv_tnl_enc_lim *tel;

				/* No more room for encapsulation limit */
				if (i + sizeof (*tel) > off + optlen)
					break;

				tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i];
				/* return index of option if found and valid */
				if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
				    tel->length == 1)
					return i;
				/* else jump to next option */
				if (tel->type)
					i += tel->length + 2;
				else
					i++;
			}
		}
		nexthdr = hdr->nexthdr;
		off += optlen;
	}
	return 0;
}

/**
 * ip6_tnl_err - tunnel error handler
 *
 * Description:
 *   ip6_tnl_err() should handle errors in the tunnel according
 *   to the specifications in RFC 2473.
 **/

static int
ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
	    int *type, int *code, int *msg, __u32 *info, int offset)
{
	struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data;
	struct ip6_tnl *t;
	int rel_msg = 0;
	int rel_type = ICMPV6_DEST_UNREACH;
	int rel_code = ICMPV6_ADDR_UNREACH;
	__u32 rel_info = 0;
	__u16 len;
	int err = -ENOENT;

	/* If the packet doesn't contain the original IPv6 header we are
	   in trouble since we might need the source address for further
	   processing of the error. */

	read_lock(&ip6_tnl_lock);
	if ((t = ip6_tnl_lookup(&ipv6h->daddr, &ipv6h->saddr)) == NULL)
		goto out;

	if (t->parms.proto != ipproto && t->parms.proto != 0)
		goto out;

	err = 0;

	switch (*type) {
		__u32 teli;
		struct ipv6_tlv_tnl_enc_lim *tel;
		__u32 mtu;
	case ICMPV6_DEST_UNREACH:
		if (net_ratelimit())
			printk(KERN_WARNING
			       "%s: Path to destination invalid "
			       "or inactive!\n", t->parms.name);
		rel_msg = 1;
		break;
	case ICMPV6_TIME_EXCEED:
		if ((*code) == ICMPV6_EXC_HOPLIMIT) {
			if (net_ratelimit())
				printk(KERN_WARNING
				       "%s: Too small hop limit or "
				       "routing loop in tunnel!\n",
				       t->parms.name);
			rel_msg = 1;
		}
		break;
	case ICMPV6_PARAMPROB:
		teli = 0;
		if ((*code) == ICMPV6_HDR_FIELD)
			teli = parse_tlv_tnl_enc_lim(skb, skb->data);

		if (teli && teli == *info - 2) {
			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
			if (tel->encap_limit == 0) {
				if (net_ratelimit())
					printk(KERN_WARNING
					       "%s: Too small encapsulation "
					       "limit or routing loop in "
					       "tunnel!\n", t->parms.name);
				rel_msg = 1;
			}
		} else if (net_ratelimit()) {
			printk(KERN_WARNING
			       "%s: Recipient unable to parse tunneled "
			       "packet!\n ", t->parms.name);
		}
		break;
	case ICMPV6_PKT_TOOBIG:
		mtu = *info - offset;
		if (mtu < IPV6_MIN_MTU)
			mtu = IPV6_MIN_MTU;
		t->dev->mtu = mtu;

		if ((len = sizeof (*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) {
			rel_type = ICMPV6_PKT_TOOBIG;
			rel_code = 0;
			rel_info = mtu;
			rel_msg = 1;
		}
		break;
	}

	*type = rel_type;
	*code = rel_code;
	*info = rel_info;
	*msg = rel_msg;

out:
	read_unlock(&ip6_tnl_lock);
	return err;
}

static int
ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
	   int type, int code, int offset, __be32 info)
{
	int rel_msg = 0;
	int rel_type = type;
	int rel_code = code;
	__u32 rel_info = ntohl(info);
	int err;
	struct sk_buff *skb2;