ip6_tunnel.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 1,163 行 · 第 1/2 页

/*
 *	IPv6 over IPv6 tunnel device
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Ville Nuorvala		<[e-mail]>	
 *
 *	$Id$
 *
 *      Based on:
 *      linux/net/ipv6/sit.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/config.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/sockios.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/ip.h>
#include <net/ipv6.h>
#include <net/protocol.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-in-IPv6 tunnel");
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 HASH_SIZE  32

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

static int ip6ip6_fb_tnl_dev_init(struct net_device *dev);
static int ip6ip6_tnl_dev_init(struct net_device *dev);
static void ip6ip6_tnl_dev_setup(struct net_device *dev);

/* the IPv6 tunnel fallback device */
static struct net_device *ip6ip6_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 rwlock_t ip6ip6_lock = RW_LOCK_UNLOCKED;

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;
		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;
}

/**
 * ip6ip6_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 *
ip6ip6_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_cmp(local, &t->parms.laddr) &&
		    !ipv6_addr_cmp(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;
}

/**
 * ip6ip6_bucket - get head of list matching given tunnel parameters
 *   @p: parameters containing tunnel end-points 
 *
 * Description:
 *   ip6ip6_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 **
ip6ip6_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];
}

/**
 * ip6ip6_tnl_link - add tunnel to hash table
 *   @t: tunnel to be added
 **/

static void
ip6ip6_tnl_link(struct ip6_tnl *t)
{
	struct ip6_tnl **tp = ip6ip6_bucket(&t->parms);

	write_lock_bh(&ip6ip6_lock);
	t->next = *tp;
	write_unlock_bh(&ip6ip6_lock);
	*tp = t;
}

/**
 * ip6ip6_tnl_unlink - remove tunnel from hash table
 *   @t: tunnel to be removed
 **/

static void
ip6ip6_tnl_unlink(struct ip6_tnl *t)
{
	struct ip6_tnl **tp;

	for (tp = ip6ip6_bucket(&t->parms); *tp; tp = &(*tp)->next) {
		if (t == *tp) {
			write_lock_bh(&ip6ip6_lock);
			*tp = t->next;
			write_unlock_bh(&ip6ip6_lock);
			break;
		}
	}
}

/**
 * ip6_tnl_create() - create a new tunnel
 *   @p: tunnel parameters
 *   @pt: pointer to new tunnel
 *
 * Description:
 *   Create tunnel matching given parameters.
 * 
 * Return: 
 *   0 on success
 **/

static int
ip6_tnl_create(struct ip6_tnl_parm *p, struct ip6_tnl **pt)
{
	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(name) == NULL)
				break;
		}
		if (i == IP6_TNL_MAX) 
			return -ENOBUFS;
	}
	dev = alloc_netdev(sizeof (*t), name, ip6ip6_tnl_dev_setup);
	if (dev == NULL)
		return -ENOMEM;

	t = dev->priv;
	dev->init = ip6ip6_tnl_dev_init;
	t->parms = *p;

	if ((err = register_netdevice(dev)) < 0) {
		free_netdev(dev);
		return err;
	}
	dev_hold(dev);

	ip6ip6_tnl_link(t);
	*pt = t;
	return 0;
}

/**
 * ip6ip6_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:
 *   ip6ip6_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:
 *   0 if tunnel located or created,
 *   -EINVAL if parameters incorrect,
 *   -ENODEV if no matching tunnel available
 **/

static int
ip6ip6_tnl_locate(struct ip6_tnl_parm *p, struct ip6_tnl **pt, int create)
{
	struct in6_addr *remote = &p->raddr;
	struct in6_addr *local = &p->laddr;
	struct ip6_tnl *t;

	if (p->proto != IPPROTO_IPV6)
		return -EINVAL;

	for (t = *ip6ip6_bucket(p); t; t = t->next) {
		if (!ipv6_addr_cmp(local, &t->parms.laddr) &&
		    !ipv6_addr_cmp(remote, &t->parms.raddr)) {
			*pt = t;
			return (create ? -EEXIST : 0);
		}
	}
	if (!create)
		return -ENODEV;
	
	return ip6_tnl_create(p, pt);
}

/**
 * ip6ip6_tnl_dev_uninit - tunnel device uninitializer
 *   @dev: the device to be destroyed
 *   
 * Description:
 *   ip6ip6_tnl_dev_uninit() removes tunnel from its list
 **/

static void
ip6ip6_tnl_dev_uninit(struct net_device *dev)
{
	struct ip6_tnl *t = dev->priv;

	if (dev == ip6ip6_fb_tnl_dev) {
		write_lock_bh(&ip6ip6_lock);
		tnls_wc[0] = NULL;
		write_unlock_bh(&ip6ip6_lock);
	} else {
		ip6ip6_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;
}

/**
 * ip6ip6_err - tunnel error handler
 *
 * Description:
 *   ip6ip6_err() should handle errors in the tunnel according
 *   to the specifications in RFC 2473.
 **/

static void 
ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
	   int type, int code, int offset, __u32 info)
{
	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;

	/* 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(&ip6ip6_lock);
	if ((t = ip6ip6_tnl_lookup(&ipv6h->daddr, &ipv6h->saddr)) == NULL)
		goto out;

	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:
		/* ignore if parameter problem not caused by a tunnel
		   encapsulation limit sub-option */
		if (code != ICMPV6_HDR_FIELD) {
			break;
		}
		teli = parse_tlv_tnl_enc_lim(skb, skb->data);

		if (teli && teli == ntohl(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;
			}
		}
		break;
	case ICMPV6_PKT_TOOBIG:
		mtu = ntohl(info) - offset;
		if (mtu < IPV6_MIN_MTU)
			mtu = IPV6_MIN_MTU;
		t->dev->mtu = mtu;

		if ((len = sizeof (*ipv6h) + ipv6h->payload_len) > mtu) {
			rel_type = ICMPV6_PKT_TOOBIG;
			rel_code = 0;
			rel_info = mtu;
			rel_msg = 1;
		}
		break;
	}
	if (rel_msg &&  pskb_may_pull(skb, offset + sizeof (*ipv6h))) {
		struct rt6_info *rt;
		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
		if (!skb2)
			goto out;

		dst_release(skb2->dst);
		skb2->dst = NULL;
		skb_pull(skb2, offset);
		skb2->nh.raw = skb2->data;

		/* Try to guess incoming interface */
		rt = rt6_lookup(&skb2->nh.ipv6h->saddr, NULL, 0, 0);

		if (rt && rt->rt6i_dev)
			skb2->dev = rt->rt6i_dev;

		icmpv6_send(skb2, rel_type, rel_code, rel_info, skb2->dev);

		if (rt)
			dst_release(&rt->u.dst);

		kfree_skb(skb2);
	}
out:
	read_unlock(&ip6ip6_lock);
}

static inline void ip6ip6_ecn_decapsulate(struct ipv6hdr *outer_iph,
					  struct sk_buff *skb)
{
	struct ipv6hdr *inner_iph = skb->nh.ipv6h;

	if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
		IP6_ECN_set_ce(inner_iph);
}

/**
 * ip6ip6_rcv - decapsulate IPv6 packet and retransmit it locally
 *   @skb: received socket buffer
 *
 * Return: 0
 **/

static int 
ip6ip6_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
{
	struct sk_buff *skb = *pskb;
	struct ipv6hdr *ipv6h;
	struct ip6_tnl *t;

	if (!pskb_may_pull(skb, sizeof (*ipv6h)))
		goto discard;

	ipv6h = skb->nh.ipv6h;

	read_lock(&ip6ip6_lock);

	if ((t = ip6ip6_tnl_lookup(&ipv6h->saddr, &ipv6h->daddr)) != NULL) {
		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
			kfree_skb(skb);
			return 0;
		}

		if (!(t->parms.flags & IP6_TNL_F_CAP_RCV)) {
			t->stat.rx_dropped++;
			read_unlock(&ip6ip6_lock);
			goto discard;
		}
		secpath_reset(skb);
		skb->mac.raw = skb->nh.raw;
		skb->nh.raw = skb->data;
		skb->protocol = htons(ETH_P_IPV6);
		skb->pkt_type = PACKET_HOST;
		memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
		skb->dev = t->dev;
		dst_release(skb->dst);
		skb->dst = NULL;
		if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
			ipv6_copy_dscp(ipv6h, skb->nh.ipv6h);
		ip6ip6_ecn_decapsulate(ipv6h, skb);
		t->stat.rx_packets++;
		t->stat.rx_bytes += skb->len;
		netif_rx(skb);
		read_unlock(&ip6ip6_lock);
		return 0;
	}
	read_unlock(&ip6ip6_lock);
	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev);
discard:
	return 1;
}

static inline struct ipv6_txoptions *create_tel(__u8 encap_limit)
{
	struct ipv6_tlv_tnl_enc_lim *tel;
	struct ipv6_txoptions *opt;
	__u8 *raw;

	int opt_len = sizeof(*opt) + 8;

	if (!(opt = kmalloc(opt_len, GFP_ATOMIC))) {
		return NULL;
	}
	memset(opt, 0, opt_len);
	opt->tot_len = opt_len;
	opt->dst0opt = (struct ipv6_opt_hdr *) (opt + 1);
	opt->opt_nflen = 8;

	tel = (struct ipv6_tlv_tnl_enc_lim *) (opt->dst0opt + 1);
	tel->type = IPV6_TLV_TNL_ENCAP_LIMIT;
	tel->length = 1;
	tel->encap_limit = encap_limit;

	raw = (__u8 *) opt->dst0opt;
	raw[5] = IPV6_TLV_PADN;