sit.c

linux 内核源代码

	struct net_device *tdev;			/* Device to other host */
	struct iphdr  *iph;			/* Our new IP header */
	unsigned int max_headroom;		/* The extra header space needed */
	__be32 dst = tiph->daddr;
	int    mtu;
	struct in6_addr *addr6;
	int addr_type;

	if (tunnel->recursion++) {
		tunnel->stat.collisions++;
		goto tx_error;
	}

	if (skb->protocol != htons(ETH_P_IPV6))
		goto tx_error;

	if (!dst)
		dst = try_6to4(&iph6->daddr);

	if (!dst) {
		struct neighbour *neigh = NULL;

		if (skb->dst)
			neigh = skb->dst->neighbour;

		if (neigh == NULL) {
			if (net_ratelimit())
				printk(KERN_DEBUG "sit: nexthop == NULL\n");
			goto tx_error;
		}

		addr6 = (struct in6_addr*)&neigh->primary_key;
		addr_type = ipv6_addr_type(addr6);

		if (addr_type == IPV6_ADDR_ANY) {
			addr6 = &ipv6_hdr(skb)->daddr;
			addr_type = ipv6_addr_type(addr6);
		}

		if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
			goto tx_error_icmp;

		dst = addr6->s6_addr32[3];
	}

	{
		struct flowi fl = { .nl_u = { .ip4_u =
					      { .daddr = dst,
						.saddr = tiph->saddr,
						.tos = RT_TOS(tos) } },
				    .oif = tunnel->parms.link,
				    .proto = IPPROTO_IPV6 };
		if (ip_route_output_key(&rt, &fl)) {
			tunnel->stat.tx_carrier_errors++;
			goto tx_error_icmp;
		}
	}
	if (rt->rt_type != RTN_UNICAST) {
		ip_rt_put(rt);
		tunnel->stat.tx_carrier_errors++;
		goto tx_error_icmp;
	}
	tdev = rt->u.dst.dev;

	if (tdev == dev) {
		ip_rt_put(rt);
		tunnel->stat.collisions++;
		goto tx_error;
	}

	if (tiph->frag_off)
		mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
	else
		mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;

	if (mtu < 68) {
		tunnel->stat.collisions++;
		ip_rt_put(rt);
		goto tx_error;
	}
	if (mtu < IPV6_MIN_MTU)
		mtu = IPV6_MIN_MTU;
	if (tunnel->parms.iph.daddr && skb->dst)
		skb->dst->ops->update_pmtu(skb->dst, mtu);

	if (skb->len > mtu) {
		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
		ip_rt_put(rt);
		goto tx_error;
	}

	if (tunnel->err_count > 0) {
		if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
			tunnel->err_count--;
			dst_link_failure(skb);
		} else
			tunnel->err_count = 0;
	}

	/*
	 * Okay, now see if we can stuff it in the buffer as-is.
	 */
	max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);

	if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
		if (!new_skb) {
			ip_rt_put(rt);
			stats->tx_dropped++;
			dev_kfree_skb(skb);
			tunnel->recursion--;
			return 0;
		}
		if (skb->sk)
			skb_set_owner_w(new_skb, skb->sk);
		dev_kfree_skb(skb);
		skb = new_skb;
		iph6 = ipv6_hdr(skb);
	}

	skb->transport_header = skb->network_header;
	skb_push(skb, sizeof(struct iphdr));
	skb_reset_network_header(skb);
	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
	IPCB(skb)->flags = 0;
	dst_release(skb->dst);
	skb->dst = &rt->u.dst;

	/*
	 *	Push down and install the IPIP header.
	 */

	iph 			=	ip_hdr(skb);
	iph->version		=	4;
	iph->ihl		=	sizeof(struct iphdr)>>2;
	if (mtu > IPV6_MIN_MTU)
		iph->frag_off	=	htons(IP_DF);
	else
		iph->frag_off	=	0;

	iph->protocol		=	IPPROTO_IPV6;
	iph->tos		=	INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
	iph->daddr		=	rt->rt_dst;
	iph->saddr		=	rt->rt_src;

	if ((iph->ttl = tiph->ttl) == 0)
		iph->ttl	=	iph6->hop_limit;

	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
ipip6_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 == ipip6_fb_tunnel_dev) {
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
				err = -EFAULT;
				break;
			}
			t = ipip6_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_IPV6 ||
		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
			goto done;
		if (p.iph.ttl)
			p.iph.frag_off |= htons(IP_DF);

		t = ipip6_tunnel_locate(&p, cmd == SIOCADDTUNNEL);

		if (dev != ipip6_fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
			if (t != NULL) {
				if (t->dev != dev) {
					err = -EEXIST;
					break;
				}
			} else {
				if (((dev->flags&IFF_POINTOPOINT) && !p.iph.daddr) ||
				    (!(dev->flags&IFF_POINTOPOINT) && p.iph.daddr)) {
					err = -EINVAL;
					break;
				}
				t = netdev_priv(dev);
				ipip6_tunnel_unlink(t);
				t->parms.iph.saddr = p.iph.saddr;
				t->parms.iph.daddr = p.iph.daddr;
				memcpy(dev->dev_addr, &p.iph.saddr, 4);
				memcpy(dev->broadcast, &p.iph.daddr, 4);
				ipip6_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;
			}
			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 == ipip6_fb_tunnel_dev) {
			err = -EFAULT;
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
				goto done;
			err = -ENOENT;
			if ((t = ipip6_tunnel_locate(&p, 0)) == NULL)
				goto done;
			err = -EPERM;
			if (t == netdev_priv(ipip6_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 *ipip6_tunnel_get_stats(struct net_device *dev)
{
	return &(((struct ip_tunnel*)netdev_priv(dev))->stat);
}

static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - sizeof(struct iphdr))
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}

static void ipip6_tunnel_setup(struct net_device *dev)
{
	dev->uninit		= ipip6_tunnel_uninit;
	dev->destructor 	= free_netdev;
	dev->hard_start_xmit	= ipip6_tunnel_xmit;
	dev->get_stats		= ipip6_tunnel_get_stats;
	dev->do_ioctl		= ipip6_tunnel_ioctl;
	dev->change_mtu		= ipip6_tunnel_change_mtu;

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

static int ipip6_tunnel_init(struct net_device *dev)
{
	struct net_device *tdev = NULL;
	struct ip_tunnel *tunnel;
	struct iphdr *iph;

	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);

	if (iph->daddr) {
		struct flowi fl = { .nl_u = { .ip4_u =
					      { .daddr = iph->daddr,
						.saddr = iph->saddr,
						.tos = RT_TOS(iph->tos) } },
				    .oif = tunnel->parms.link,
				    .proto = IPPROTO_IPV6 };
		struct rtable *rt;
		if (!ip_route_output_key(&rt, &fl)) {
			tdev = rt->u.dst.dev;
			ip_rt_put(rt);
		}
		dev->flags |= IFF_POINTOPOINT;
	}

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

	if (tdev) {
		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
		dev->mtu = tdev->mtu - sizeof(struct iphdr);
		if (dev->mtu < IPV6_MIN_MTU)
			dev->mtu = IPV6_MIN_MTU;
	}
	dev->iflink = tunnel->parms.link;

	return 0;
}

static int __init ipip6_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_IPV6;
	iph->ihl		= 5;
	iph->ttl		= 64;

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

static struct xfrm_tunnel sit_handler = {
	.handler	=	ipip6_rcv,
	.err_handler	=	ipip6_err,
	.priority	=	1,
};

static void __exit sit_destroy_tunnels(void)
{
	int prio;

	for (prio = 1; 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 sit_cleanup(void)
{
	xfrm4_tunnel_deregister(&sit_handler, AF_INET6);

	rtnl_lock();
	sit_destroy_tunnels();
	unregister_netdevice(ipip6_fb_tunnel_dev);
	rtnl_unlock();
}

static int __init sit_init(void)
{
	int err;

	printk(KERN_INFO "IPv6 over IPv4 tunneling driver\n");

	if (xfrm4_tunnel_register(&sit_handler, AF_INET6) < 0) {
		printk(KERN_INFO "sit init: Can't add protocol\n");
		return -EAGAIN;
	}

	ipip6_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0",
					   ipip6_tunnel_setup);
	if (!ipip6_fb_tunnel_dev) {
		err = -ENOMEM;
		goto err1;
	}

	ipip6_fb_tunnel_dev->init = ipip6_fb_tunnel_init;

	if ((err =  register_netdev(ipip6_fb_tunnel_dev)))
		goto err2;

 out:
	return err;
 err2:
	free_netdev(ipip6_fb_tunnel_dev);
 err1:
	xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
	goto out;
}

module_init(sit_init);
module_exit(sit_cleanup);
MODULE_LICENSE("GPL");
MODULE_ALIAS("sit0");