ip_gre.c

linux 内核源代码

	nf_reset(skb);

	IPTUNNEL_XMIT();
	tunnel->recursion--;
	return 0;

tx_error_icmp:
	dst_link_failure(skb);

tx_error:
	stats->tx_errors++;
	dev_kfree_skb(skb);
	tunnel->recursion--;
	return 0;
}

static int
ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
{
	int err = 0;
	struct ip_tunnel_parm p;
	struct ip_tunnel *t;

	switch (cmd) {
	case SIOCGETTUNNEL:
		t = NULL;
		if (dev == ipgre_fb_tunnel_dev) {
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
				err = -EFAULT;
				break;
			}
			t = ipgre_tunnel_locate(&p, 0);
		}
		if (t == NULL)
			t = netdev_priv(dev);
		memcpy(&p, &t->parms, sizeof(p));
		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
			err = -EFAULT;
		break;

	case SIOCADDTUNNEL:
	case SIOCCHGTUNNEL:
		err = -EPERM;
		if (!capable(CAP_NET_ADMIN))
			goto done;

		err = -EFAULT;
		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
			goto done;

		err = -EINVAL;
		if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
		    ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)))
			goto done;
		if (p.iph.ttl)
			p.iph.frag_off |= htons(IP_DF);

		if (!(p.i_flags&GRE_KEY))
			p.i_key = 0;
		if (!(p.o_flags&GRE_KEY))
			p.o_key = 0;

		t = ipgre_tunnel_locate(&p, cmd == SIOCADDTUNNEL);

		if (dev != ipgre_fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
			if (t != NULL) {
				if (t->dev != dev) {
					err = -EEXIST;
					break;
				}
			} else {
				unsigned nflags=0;

				t = netdev_priv(dev);

				if (MULTICAST(p.iph.daddr))
					nflags = IFF_BROADCAST;
				else if (p.iph.daddr)
					nflags = IFF_POINTOPOINT;

				if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) {
					err = -EINVAL;
					break;
				}
				ipgre_tunnel_unlink(t);
				t->parms.iph.saddr = p.iph.saddr;
				t->parms.iph.daddr = p.iph.daddr;
				t->parms.i_key = p.i_key;
				t->parms.o_key = p.o_key;
				memcpy(dev->dev_addr, &p.iph.saddr, 4);
				memcpy(dev->broadcast, &p.iph.daddr, 4);
				ipgre_tunnel_link(t);
				netdev_state_change(dev);
			}
		}

		if (t) {
			err = 0;
			if (cmd == SIOCCHGTUNNEL) {
				t->parms.iph.ttl = p.iph.ttl;
				t->parms.iph.tos = p.iph.tos;
				t->parms.iph.frag_off = p.iph.frag_off;
			}
			if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
				err = -EFAULT;
		} else
			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
		break;

	case SIOCDELTUNNEL:
		err = -EPERM;
		if (!capable(CAP_NET_ADMIN))
			goto done;

		if (dev == ipgre_fb_tunnel_dev) {
			err = -EFAULT;
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
				goto done;
			err = -ENOENT;
			if ((t = ipgre_tunnel_locate(&p, 0)) == NULL)
				goto done;
			err = -EPERM;
			if (t == netdev_priv(ipgre_fb_tunnel_dev))
				goto done;
			dev = t->dev;
		}
		unregister_netdevice(dev);
		err = 0;
		break;

	default:
		err = -EINVAL;
	}

done:
	return err;
}

static struct net_device_stats *ipgre_tunnel_get_stats(struct net_device *dev)
{
	return &(((struct ip_tunnel*)netdev_priv(dev))->stat);
}

static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	if (new_mtu < 68 || new_mtu > 0xFFF8 - tunnel->hlen)
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}

/* Nice toy. Unfortunately, useless in real life :-)
   It allows to construct virtual multiprotocol broadcast "LAN"
   over the Internet, provided multicast routing is tuned.


   I have no idea was this bicycle invented before me,
   so that I had to set ARPHRD_IPGRE to a random value.
   I have an impression, that Cisco could make something similar,
   but this feature is apparently missing in IOS<=11.2(8).

   I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks
   with broadcast 224.66.66.66. If you have access to mbone, play with me :-)

   ping -t 255 224.66.66.66

   If nobody answers, mbone does not work.

   ip tunnel add Universe mode gre remote 224.66.66.66 local <Your_real_addr> ttl 255
   ip addr add 10.66.66.<somewhat>/24 dev Universe
   ifconfig Universe up
   ifconfig Universe add fe80::<Your_real_addr>/10
   ifconfig Universe add fec0:6666:6666::<Your_real_addr>/96
   ftp 10.66.66.66
   ...
   ftp fec0:6666:6666::193.233.7.65
   ...

 */

static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
			unsigned short type,
			const void *daddr, const void *saddr, unsigned len)
{
	struct ip_tunnel *t = netdev_priv(dev);
	struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen);
	__be16 *p = (__be16*)(iph+1);

	memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
	p[0]		= t->parms.o_flags;
	p[1]		= htons(type);

	/*
	 *	Set the source hardware address.
	 */

	if (saddr)
		memcpy(&iph->saddr, saddr, 4);

	if (daddr) {
		memcpy(&iph->daddr, daddr, 4);
		return t->hlen;
	}
	if (iph->daddr && !MULTICAST(iph->daddr))
		return t->hlen;

	return -t->hlen;
}

static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
{
	struct iphdr *iph = (struct iphdr*) skb_mac_header(skb);
	memcpy(haddr, &iph->saddr, 4);
	return 4;
}

static const struct header_ops ipgre_header_ops = {
	.create	= ipgre_header,
	.parse	= ipgre_header_parse,
};

#ifdef CONFIG_NET_IPGRE_BROADCAST
static int ipgre_open(struct net_device *dev)
{
	struct ip_tunnel *t = netdev_priv(dev);

	if (MULTICAST(t->parms.iph.daddr)) {
		struct flowi fl = { .oif = t->parms.link,
				    .nl_u = { .ip4_u =
					      { .daddr = t->parms.iph.daddr,
						.saddr = t->parms.iph.saddr,
						.tos = RT_TOS(t->parms.iph.tos) } },
				    .proto = IPPROTO_GRE };
		struct rtable *rt;
		if (ip_route_output_key(&rt, &fl))
			return -EADDRNOTAVAIL;
		dev = rt->u.dst.dev;
		ip_rt_put(rt);
		if (__in_dev_get_rtnl(dev) == NULL)
			return -EADDRNOTAVAIL;
		t->mlink = dev->ifindex;
		ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr);
	}
	return 0;
}

static int ipgre_close(struct net_device *dev)
{
	struct ip_tunnel *t = netdev_priv(dev);
	if (MULTICAST(t->parms.iph.daddr) && t->mlink) {
		struct in_device *in_dev = inetdev_by_index(t->mlink);
		if (in_dev) {
			ip_mc_dec_group(in_dev, t->parms.iph.daddr);
			in_dev_put(in_dev);
		}
	}
	return 0;
}

#endif

static void ipgre_tunnel_setup(struct net_device *dev)
{
	dev->uninit		= ipgre_tunnel_uninit;
	dev->destructor 	= free_netdev;
	dev->hard_start_xmit	= ipgre_tunnel_xmit;
	dev->get_stats		= ipgre_tunnel_get_stats;
	dev->do_ioctl		= ipgre_tunnel_ioctl;
	dev->change_mtu		= ipgre_tunnel_change_mtu;

	dev->type		= ARPHRD_IPGRE;
	dev->hard_header_len 	= LL_MAX_HEADER + sizeof(struct iphdr) + 4;
	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr) - 4;
	dev->flags		= IFF_NOARP;
	dev->iflink		= 0;
	dev->addr_len		= 4;
}

static int ipgre_tunnel_init(struct net_device *dev)
{
	struct net_device *tdev = NULL;
	struct ip_tunnel *tunnel;
	struct iphdr *iph;
	int hlen = LL_MAX_HEADER;
	int mtu = ETH_DATA_LEN;
	int addend = sizeof(struct iphdr) + 4;

	tunnel = netdev_priv(dev);
	iph = &tunnel->parms.iph;

	tunnel->dev = dev;
	strcpy(tunnel->parms.name, dev->name);

	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);

	/* Guess output device to choose reasonable mtu and hard_header_len */

	if (iph->daddr) {
		struct flowi fl = { .oif = tunnel->parms.link,
				    .nl_u = { .ip4_u =
					      { .daddr = iph->daddr,
						.saddr = iph->saddr,
						.tos = RT_TOS(iph->tos) } },
				    .proto = IPPROTO_GRE };
		struct rtable *rt;
		if (!ip_route_output_key(&rt, &fl)) {
			tdev = rt->u.dst.dev;
			ip_rt_put(rt);
		}

		dev->flags |= IFF_POINTOPOINT;

#ifdef CONFIG_NET_IPGRE_BROADCAST
		if (MULTICAST(iph->daddr)) {
			if (!iph->saddr)
				return -EINVAL;
			dev->flags = IFF_BROADCAST;
			dev->header_ops = &ipgre_header_ops;
			dev->open = ipgre_open;
			dev->stop = ipgre_close;
		}
#endif
	} else {
		dev->header_ops = &ipgre_header_ops;
	}

	if (!tdev && tunnel->parms.link)
		tdev = __dev_get_by_index(&init_net, tunnel->parms.link);

	if (tdev) {
		hlen = tdev->hard_header_len;
		mtu = tdev->mtu;
	}
	dev->iflink = tunnel->parms.link;

	/* Precalculate GRE options length */
	if (tunnel->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
		if (tunnel->parms.o_flags&GRE_CSUM)
			addend += 4;
		if (tunnel->parms.o_flags&GRE_KEY)
			addend += 4;
		if (tunnel->parms.o_flags&GRE_SEQ)
			addend += 4;
	}
	dev->hard_header_len = hlen + addend;
	dev->mtu = mtu - addend;
	tunnel->hlen = addend;
	return 0;
}

static int __init ipgre_fb_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr *iph = &tunnel->parms.iph;

	tunnel->dev = dev;
	strcpy(tunnel->parms.name, dev->name);

	iph->version		= 4;
	iph->protocol		= IPPROTO_GRE;
	iph->ihl		= 5;
	tunnel->hlen		= sizeof(struct iphdr) + 4;

	dev_hold(dev);
	tunnels_wc[0]		= tunnel;
	return 0;
}


static struct net_protocol ipgre_protocol = {
	.handler	=	ipgre_rcv,
	.err_handler	=	ipgre_err,
};


/*
 *	And now the modules code and kernel interface.
 */

static int __init ipgre_init(void)
{
	int err;

	printk(KERN_INFO "GRE over IPv4 tunneling driver\n");

	if (inet_add_protocol(&ipgre_protocol, IPPROTO_GRE) < 0) {
		printk(KERN_INFO "ipgre init: can't add protocol\n");
		return -EAGAIN;
	}

	ipgre_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
					   ipgre_tunnel_setup);
	if (!ipgre_fb_tunnel_dev) {
		err = -ENOMEM;
		goto err1;
	}

	ipgre_fb_tunnel_dev->init = ipgre_fb_tunnel_init;

	if ((err = register_netdev(ipgre_fb_tunnel_dev)))
		goto err2;
out:
	return err;
err2:
	free_netdev(ipgre_fb_tunnel_dev);
err1:
	inet_del_protocol(&ipgre_protocol, IPPROTO_GRE);
	goto out;
}

static void __exit ipgre_destroy_tunnels(void)
{
	int prio;

	for (prio = 0; prio < 4; prio++) {
		int h;
		for (h = 0; h < HASH_SIZE; h++) {
			struct ip_tunnel *t;
			while ((t = tunnels[prio][h]) != NULL)
				unregister_netdevice(t->dev);
		}
	}
}

static void __exit ipgre_fini(void)
{
	if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0)
		printk(KERN_INFO "ipgre close: can't remove protocol\n");

	rtnl_lock();
	ipgre_destroy_tunnels();
	rtnl_unlock();
}

module_init(ipgre_init);
module_exit(ipgre_fini);
MODULE_LICENSE("GPL");