sit.c

嵌入式系统设计与实验教材二源码linux内核移植与编译

/*
 *	IPv6 over IPv4 tunnel device - Simple Internet Transition (SIT)
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>	
 *	Alexey Kuznetsov	<[e-mail]>
 *
 *	$Id: sit.c,v 1.53 2001/09/25 05:09:53 davem Exp $
 *
 *	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.
 *
 *	Changes:
 * Roger Venning <[e-mail]>:	6to4 support
 * Nate Thompson <[e-mail]>:		6to4 support
 */

#define __NO_VERSION__
#include <linux/config.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmp.h>
#include <asm/uaccess.h>
#include <linux/init.h>
#include <linux/netfilter_ipv4.h>

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

#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/inet_ecn.h>

/*
   This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c

   For comments look at net/ipv4/ip_gre.c --ANK
 */

#define HASH_SIZE  16
#define HASH(addr) ((addr^(addr>>4))&0xF)

static int ipip6_fb_tunnel_init(struct net_device *dev);
static int ipip6_tunnel_init(struct net_device *dev);

static struct net_device ipip6_fb_tunnel_dev = {
	"sit0", 0x0, 0x0, 0x0, 0x0, 0, 0, 0, 0, 0, NULL, ipip6_fb_tunnel_init,
};

static struct ip_tunnel ipip6_fb_tunnel = {
	NULL, &ipip6_fb_tunnel_dev, {0, }, 0, 0, 0, 0, 0, 0, 0, {"sit0", }
};

static struct ip_tunnel *tunnels_r_l[HASH_SIZE];
static struct ip_tunnel *tunnels_r[HASH_SIZE];
static struct ip_tunnel *tunnels_l[HASH_SIZE];
static struct ip_tunnel *tunnels_wc[1];
static struct ip_tunnel **tunnels[4] = { tunnels_wc, tunnels_l, tunnels_r, tunnels_r_l };

static rwlock_t ipip6_lock = RW_LOCK_UNLOCKED;

static struct ip_tunnel * ipip6_tunnel_lookup(u32 remote, u32 local)
{
	unsigned h0 = HASH(remote);
	unsigned h1 = HASH(local);
	struct ip_tunnel *t;

	for (t = tunnels_r_l[h0^h1]; t; t = t->next) {
		if (local == t->parms.iph.saddr &&
		    remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
			return t;
	}
	for (t = tunnels_r[h0]; t; t = t->next) {
		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
			return t;
	}
	for (t = tunnels_l[h1]; t; t = t->next) {
		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
			return t;
	}
	if ((t = tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP))
		return t;
	return NULL;
}

static struct ip_tunnel ** ipip6_bucket(struct ip_tunnel *t)
{
	u32 remote = t->parms.iph.daddr;
	u32 local = t->parms.iph.saddr;
	unsigned h = 0;
	int prio = 0;

	if (remote) {
		prio |= 2;
		h ^= HASH(remote);
	}
	if (local) {
		prio |= 1;
		h ^= HASH(local);
	}
	return &tunnels[prio][h];
}

static void ipip6_tunnel_unlink(struct ip_tunnel *t)
{
	struct ip_tunnel **tp;

	for (tp = ipip6_bucket(t); *tp; tp = &(*tp)->next) {
		if (t == *tp) {
			write_lock_bh(&ipip6_lock);
			*tp = t->next;
			write_unlock_bh(&ipip6_lock);
			break;
		}
	}
}

static void ipip6_tunnel_link(struct ip_tunnel *t)
{
	struct ip_tunnel **tp = ipip6_bucket(t);

	write_lock_bh(&ipip6_lock);
	t->next = *tp;
	write_unlock_bh(&ipip6_lock);
	*tp = t;
}

struct ip_tunnel * ipip6_tunnel_locate(struct ip_tunnel_parm *parms, int create)
{
	u32 remote = parms->iph.daddr;
	u32 local = parms->iph.saddr;
	struct ip_tunnel *t, **tp, *nt;
	struct net_device *dev;
	unsigned h = 0;
	int prio = 0;

	if (remote) {
		prio |= 2;
		h ^= HASH(remote);
	}
	if (local) {
		prio |= 1;
		h ^= HASH(local);
	}
	for (tp = &tunnels[prio][h]; (t = *tp) != NULL; tp = &t->next) {
		if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)
			return t;
	}
	if (!create)
		return NULL;

	MOD_INC_USE_COUNT;
	dev = kmalloc(sizeof(*dev) + sizeof(*t), GFP_KERNEL);
	if (dev == NULL) {
		MOD_DEC_USE_COUNT;
		return NULL;
	}
	memset(dev, 0, sizeof(*dev) + sizeof(*t));
	dev->priv = (void*)(dev+1);
	nt = (struct ip_tunnel*)dev->priv;
	nt->dev = dev;
	dev->init = ipip6_tunnel_init;
	dev->features |= NETIF_F_DYNALLOC;
	memcpy(&nt->parms, parms, sizeof(*parms));
	nt->parms.name[IFNAMSIZ-1] = '\0';
	strcpy(dev->name, nt->parms.name);
	if (dev->name[0] == 0) {
		int i;
		for (i=1; i<100; i++) {
			sprintf(dev->name, "sit%d", i);
			if (__dev_get_by_name(dev->name) == NULL)
				break;
		}
		if (i==100)
			goto failed;
		memcpy(nt->parms.name, dev->name, IFNAMSIZ);
	}
	if (register_netdevice(dev) < 0)
		goto failed;

	dev_hold(dev);
	ipip6_tunnel_link(nt);
	/* Do not decrement MOD_USE_COUNT here. */
	return nt;

failed:
	kfree(dev);
	MOD_DEC_USE_COUNT;
	return NULL;
}

static void ipip6_tunnel_destructor(struct net_device *dev)
{
	if (dev != &ipip6_fb_tunnel_dev) {
		MOD_DEC_USE_COUNT;
	}
}

static void ipip6_tunnel_uninit(struct net_device *dev)
{
	if (dev == &ipip6_fb_tunnel_dev) {
		write_lock_bh(&ipip6_lock);
		tunnels_wc[0] = NULL;
		write_unlock_bh(&ipip6_lock);
		dev_put(dev);
	} else {
		ipip6_tunnel_unlink((struct ip_tunnel*)dev->priv);
		dev_put(dev);
	}
}


void ipip6_err(struct sk_buff *skb, u32 info)
{
#ifndef I_WISH_WORLD_WERE_PERFECT

/* It is not :-( All the routers (except for Linux) return only
   8 bytes of packet payload. It means, that precise relaying of
   ICMP in the real Internet is absolutely infeasible.
 */
	struct iphdr *iph = (struct iphdr*)skb->data;
	int type = skb->h.icmph->type;
	int code = skb->h.icmph->code;
	struct ip_tunnel *t;

	switch (type) {
	default:
	case ICMP_PARAMETERPROB:
		return;

	case ICMP_DEST_UNREACH:
		switch (code) {
		case ICMP_SR_FAILED:
		case ICMP_PORT_UNREACH:
			/* Impossible event. */
			return;
		case ICMP_FRAG_NEEDED:
			/* Soft state for pmtu is maintained by IP core. */
			return;
		default:
			/* All others are translated to HOST_UNREACH.
			   rfc2003 contains "deep thoughts" about NET_UNREACH,
			   I believe they are just ether pollution. --ANK
			 */
			break;
		}
		break;
	case ICMP_TIME_EXCEEDED:
		if (code != ICMP_EXC_TTL)
			return;
		break;
	}

	read_lock(&ipip6_lock);
	t = ipip6_tunnel_lookup(iph->daddr, iph->saddr);
	if (t == NULL || t->parms.iph.daddr == 0)
		goto out;
	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
		goto out;

	if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
		t->err_count++;
	else
		t->err_count = 1;
	t->err_time = jiffies;
out:
	read_unlock(&ipip6_lock);
	return;
#else
	struct iphdr *iph = (struct iphdr*)dp;
	int hlen = iph->ihl<<2;
	struct ipv6hdr *iph6;
	int type = skb->h.icmph->type;
	int code = skb->h.icmph->code;
	int rel_type = 0;
	int rel_code = 0;
	int rel_info = 0;
	struct sk_buff *skb2;
	struct rt6_info *rt6i;

	if (len < hlen + sizeof(struct ipv6hdr))
		return;
	iph6 = (struct ipv6hdr*)(dp + hlen);

	switch (type) {
	default:
		return;
	case ICMP_PARAMETERPROB:
		if (skb->h.icmph->un.gateway < hlen)
			return;

		/* So... This guy found something strange INSIDE encapsulated
		   packet. Well, he is fool, but what can we do ?
		 */
		rel_type = ICMPV6_PARAMPROB;
		rel_info = skb->h.icmph->un.gateway - hlen;
		break;

	case ICMP_DEST_UNREACH:
		switch (code) {
		case ICMP_SR_FAILED:
		case ICMP_PORT_UNREACH:
			/* Impossible event. */
			return;
		case ICMP_FRAG_NEEDED:
			/* Too complicated case ... */
			return;
		default:
			/* All others are translated to HOST_UNREACH.
			   rfc2003 contains "deep thoughts" about NET_UNREACH,
			   I believe, it is just ether pollution. --ANK
			 */
			rel_type = ICMPV6_DEST_UNREACH;
			rel_code = ICMPV6_ADDR_UNREACH;
			break;
		}
		break;
	case ICMP_TIME_EXCEEDED:
		if (code != ICMP_EXC_TTL)
			return;
		rel_type = ICMPV6_TIME_EXCEED;
		rel_code = ICMPV6_EXC_HOPLIMIT;
		break;
	}

	/* Prepare fake skb to feed it to icmpv6_send */
	skb2 = skb_clone(skb, GFP_ATOMIC);
	if (skb2 == NULL)
		return;
	dst_release(skb2->dst);
	skb2->dst = NULL;
	skb_pull(skb2, skb->data - (u8*)iph6);
	skb2->nh.raw = skb2->data;

	/* Try to guess incoming interface */
	rt6i = rt6_lookup(&iph6->saddr, NULL, NULL, 0);
	if (rt6i && rt6i->rt6i_dev) {
		skb2->dev = rt6i->rt6i_dev;

		rt6i = rt6_lookup(&iph6->daddr, &iph6->saddr, NULL, 0);

		if (rt6i && rt6i->rt6i_dev && rt6i->rt6i_dev->type == ARPHRD_SIT) {
			struct ip_tunnel * t = (struct ip_tunnel*)rt6i->rt6i_dev->priv;
			if (rel_type == ICMPV6_TIME_EXCEED && t->parms.iph.ttl) {
				rel_type = ICMPV6_DEST_UNREACH;
				rel_code = ICMPV6_ADDR_UNREACH;
			}
			icmpv6_send(skb2, rel_type, rel_code, rel_info, skb2->dev);
		}
	}
	kfree_skb(skb2);
	return;
#endif
}

static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
{
	if (INET_ECN_is_ce(iph->tos) &&
	    INET_ECN_is_not_ce(ip6_get_dsfield(skb->nh.ipv6h)))
		IP6_ECN_set_ce(skb->nh.ipv6h);
}

int ipip6_rcv(struct sk_buff *skb)
{
	struct iphdr *iph;
	struct ip_tunnel *tunnel;

	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
		goto out;

	iph = skb->nh.iph;

	read_lock(&ipip6_lock);
	if ((tunnel = ipip6_tunnel_lookup(iph->saddr, iph->daddr)) != NULL) {
		skb->mac.raw = skb->nh.raw;
		skb->nh.raw = skb->data;
		memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
		skb->protocol = __constant_htons(ETH_P_IPV6);
		skb->pkt_type = PACKET_HOST;
		tunnel->stat.rx_packets++;
		tunnel->stat.rx_bytes += skb->len;
		skb->dev = tunnel->dev;
		dst_release(skb->dst);
		skb->dst = NULL;
#ifdef CONFIG_NETFILTER
		nf_conntrack_put(skb->nfct);
		skb->nfct = NULL;
#ifdef CONFIG_NETFILTER_DEBUG
		skb->nf_debug = 0;
#endif
#endif
		ipip6_ecn_decapsulate(iph, skb);
		netif_rx(skb);
		read_unlock(&ipip6_lock);
		return 0;
	}

	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0);
	kfree_skb(skb);
	read_unlock(&ipip6_lock);
out:
	return 0;
}

/* Need this wrapper because NF_HOOK takes the function address */
static inline int do_ip_send(struct sk_buff *skb)
{
	return ip_send(skb);
}