ip6_tunnel.c

linux 内核源代码

}

static inline int
ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
	int encap_limit = -1;
	__u16 offset;
	struct flowi fl;
	__u8 dsfield;
	__u32 mtu;
	int err;

	if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
	    !ip6_tnl_xmit_ctl(t) || ip6_tnl_addr_conflict(t, ipv6h))
		return -1;

	offset = parse_tlv_tnl_enc_lim(skb, skb_network_header(skb));
	if (offset > 0) {
		struct ipv6_tlv_tnl_enc_lim *tel;
		tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
		if (tel->encap_limit == 0) {
			icmpv6_send(skb, ICMPV6_PARAMPROB,
				    ICMPV6_HDR_FIELD, offset + 2, skb->dev);
			return -1;
		}
		encap_limit = tel->encap_limit - 1;
	} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
		encap_limit = t->parms.encap_limit;

	memcpy(&fl, &t->fl, sizeof (fl));
	fl.proto = IPPROTO_IPV6;

	dsfield = ipv6_get_dsfield(ipv6h);
	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
		fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL))
		fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);

	err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
	if (err != 0) {
		if (err == -EMSGSIZE)
			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
		return -1;
	}

	return 0;
}

static int
ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct net_device_stats *stats = &t->stat;
	int ret;

	if (t->recursion++) {
		t->stat.collisions++;
		goto tx_err;
	}

	switch (skb->protocol) {
	case __constant_htons(ETH_P_IP):
		ret = ip4ip6_tnl_xmit(skb, dev);
		break;
	case __constant_htons(ETH_P_IPV6):
		ret = ip6ip6_tnl_xmit(skb, dev);
		break;
	default:
		goto tx_err;
	}

	if (ret < 0)
		goto tx_err;

	t->recursion--;
	return 0;

tx_err:
	stats->tx_errors++;
	stats->tx_dropped++;
	kfree_skb(skb);
	t->recursion--;
	return 0;
}

static void ip6_tnl_set_cap(struct ip6_tnl *t)
{
	struct ip6_tnl_parm *p = &t->parms;
	int ltype = ipv6_addr_type(&p->laddr);
	int rtype = ipv6_addr_type(&p->raddr);

	p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV);

	if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) &&
	    rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) &&
	    !((ltype|rtype) & IPV6_ADDR_LOOPBACK) &&
	    (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) {
		if (ltype&IPV6_ADDR_UNICAST)
			p->flags |= IP6_TNL_F_CAP_XMIT;
		if (rtype&IPV6_ADDR_UNICAST)
			p->flags |= IP6_TNL_F_CAP_RCV;
	}
}

static void ip6_tnl_link_config(struct ip6_tnl *t)
{
	struct net_device *dev = t->dev;
	struct ip6_tnl_parm *p = &t->parms;
	struct flowi *fl = &t->fl;

	memcpy(&dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
	memcpy(&dev->broadcast, &p->raddr, sizeof(struct in6_addr));

	/* Set up flowi template */
	ipv6_addr_copy(&fl->fl6_src, &p->laddr);
	ipv6_addr_copy(&fl->fl6_dst, &p->raddr);
	fl->oif = p->link;
	fl->fl6_flowlabel = 0;

	if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS))
		fl->fl6_flowlabel |= IPV6_TCLASS_MASK & p->flowinfo;
	if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL))
		fl->fl6_flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo;

	ip6_tnl_set_cap(t);

	if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV)
		dev->flags |= IFF_POINTOPOINT;
	else
		dev->flags &= ~IFF_POINTOPOINT;

	dev->iflink = p->link;

	if (p->flags & IP6_TNL_F_CAP_XMIT) {
		int strict = (ipv6_addr_type(&p->raddr) &
			      (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));

		struct rt6_info *rt = rt6_lookup(&p->raddr, &p->laddr,
						 p->link, strict);

		if (rt == NULL)
			return;

		if (rt->rt6i_dev) {
			dev->hard_header_len = rt->rt6i_dev->hard_header_len +
				sizeof (struct ipv6hdr);

			dev->mtu = rt->rt6i_dev->mtu - sizeof (struct ipv6hdr);

			if (dev->mtu < IPV6_MIN_MTU)
				dev->mtu = IPV6_MIN_MTU;
		}
		dst_release(&rt->u.dst);
	}
}

/**
 * ip6_tnl_change - update the tunnel parameters
 *   @t: tunnel to be changed
 *   @p: tunnel configuration parameters
 *   @active: != 0 if tunnel is ready for use
 *
 * Description:
 *   ip6_tnl_change() updates the tunnel parameters
 **/

static int
ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p)
{
	ipv6_addr_copy(&t->parms.laddr, &p->laddr);
	ipv6_addr_copy(&t->parms.raddr, &p->raddr);
	t->parms.flags = p->flags;
	t->parms.hop_limit = p->hop_limit;
	t->parms.encap_limit = p->encap_limit;
	t->parms.flowinfo = p->flowinfo;
	t->parms.link = p->link;
	t->parms.proto = p->proto;
	ip6_tnl_dst_reset(t);
	ip6_tnl_link_config(t);
	return 0;
}

/**
 * ip6_tnl_ioctl - configure ipv6 tunnels from userspace
 *   @dev: virtual device associated with tunnel
 *   @ifr: parameters passed from userspace
 *   @cmd: command to be performed
 *
 * Description:
 *   ip6_tnl_ioctl() is used for managing IPv6 tunnels
 *   from userspace.
 *
 *   The possible commands are the following:
 *     %SIOCGETTUNNEL: get tunnel parameters for device
 *     %SIOCADDTUNNEL: add tunnel matching given tunnel parameters
 *     %SIOCCHGTUNNEL: change tunnel parameters to those given
 *     %SIOCDELTUNNEL: delete tunnel
 *
 *   The fallback device "ip6tnl0", created during module
 *   initialization, can be used for creating other tunnel devices.
 *
 * Return:
 *   0 on success,
 *   %-EFAULT if unable to copy data to or from userspace,
 *   %-EPERM if current process hasn't %CAP_NET_ADMIN set
 *   %-EINVAL if passed tunnel parameters are invalid,
 *   %-EEXIST if changing a tunnel's parameters would cause a conflict
 *   %-ENODEV if attempting to change or delete a nonexisting device
 **/

static int
ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
	int err = 0;
	struct ip6_tnl_parm p;
	struct ip6_tnl *t = NULL;

	switch (cmd) {
	case SIOCGETTUNNEL:
		if (dev == ip6_fb_tnl_dev) {
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) {
				err = -EFAULT;
				break;
			}
			t = ip6_tnl_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))
			break;
		err = -EFAULT;
		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p)))
			break;
		err = -EINVAL;
		if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP &&
		    p.proto != 0)
			break;
		t = ip6_tnl_locate(&p, cmd == SIOCADDTUNNEL);
		if (dev != ip6_fb_tnl_dev && cmd == SIOCCHGTUNNEL) {
			if (t != NULL) {
				if (t->dev != dev) {
					err = -EEXIST;
					break;
				}
			} else
				t = netdev_priv(dev);

			ip6_tnl_unlink(t);
			err = ip6_tnl_change(t, &p);
			ip6_tnl_link(t);
			netdev_state_change(dev);
		}
		if (t) {
			err = 0;
			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))
			break;

		if (dev == ip6_fb_tnl_dev) {
			err = -EFAULT;
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p)))
				break;
			err = -ENOENT;
			if ((t = ip6_tnl_locate(&p, 0)) == NULL)
				break;
			err = -EPERM;
			if (t->dev == ip6_fb_tnl_dev)
				break;
			dev = t->dev;
		}
		err = 0;
		unregister_netdevice(dev);
		break;
	default:
		err = -EINVAL;
	}
	return err;
}

/**
 * ip6_tnl_get_stats - return the stats for tunnel device
 *   @dev: virtual device associated with tunnel
 *
 * Return: stats for device
 **/

static struct net_device_stats *
ip6_tnl_get_stats(struct net_device *dev)
{
	return &(((struct ip6_tnl *)netdev_priv(dev))->stat);
}

/**
 * ip6_tnl_change_mtu - change mtu manually for tunnel device
 *   @dev: virtual device associated with tunnel
 *   @new_mtu: the new mtu
 *
 * Return:
 *   0 on success,
 *   %-EINVAL if mtu too small
 **/

static int
ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu < IPV6_MIN_MTU) {
		return -EINVAL;
	}
	dev->mtu = new_mtu;
	return 0;
}

/**
 * ip6_tnl_dev_setup - setup virtual tunnel device
 *   @dev: virtual device associated with tunnel
 *
 * Description:
 *   Initialize function pointers and device parameters
 **/

static void ip6_tnl_dev_setup(struct net_device *dev)
{
	dev->uninit = ip6_tnl_dev_uninit;
	dev->destructor = free_netdev;
	dev->hard_start_xmit = ip6_tnl_xmit;
	dev->get_stats = ip6_tnl_get_stats;
	dev->do_ioctl = ip6_tnl_ioctl;
	dev->change_mtu = ip6_tnl_change_mtu;

	dev->type = ARPHRD_TUNNEL6;
	dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr);
	dev->mtu = ETH_DATA_LEN - sizeof (struct ipv6hdr);
	dev->flags |= IFF_NOARP;
	dev->addr_len = sizeof(struct in6_addr);
}


/**
 * ip6_tnl_dev_init_gen - general initializer for all tunnel devices
 *   @dev: virtual device associated with tunnel
 **/

static inline void
ip6_tnl_dev_init_gen(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	t->dev = dev;
	strcpy(t->parms.name, dev->name);
}

/**
 * ip6_tnl_dev_init - initializer for all non fallback tunnel devices
 *   @dev: virtual device associated with tunnel
 **/

static int
ip6_tnl_dev_init(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	ip6_tnl_dev_init_gen(dev);
	ip6_tnl_link_config(t);
	return 0;
}

/**
 * ip6_fb_tnl_dev_init - initializer for fallback tunnel device
 *   @dev: fallback device
 *
 * Return: 0
 **/

static int
ip6_fb_tnl_dev_init(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	ip6_tnl_dev_init_gen(dev);
	t->parms.proto = IPPROTO_IPV6;
	dev_hold(dev);
	tnls_wc[0] = t;
	return 0;
}

static struct xfrm6_tunnel ip4ip6_handler = {
	.handler	= ip4ip6_rcv,
	.err_handler	= ip4ip6_err,
	.priority	=	1,
};

static struct xfrm6_tunnel ip6ip6_handler = {
	.handler	= ip6ip6_rcv,
	.err_handler	= ip6ip6_err,
	.priority	=	1,
};

/**
 * ip6_tunnel_init - register protocol and reserve needed resources
 *
 * Return: 0 on success
 **/

static int __init ip6_tunnel_init(void)
{
	int  err;

	if (xfrm6_tunnel_register(&ip4ip6_handler, AF_INET)) {
		printk(KERN_ERR "ip6_tunnel init: can't register ip4ip6\n");
		err = -EAGAIN;
		goto out;
	}

	if (xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6)) {
		printk(KERN_ERR "ip6_tunnel init: can't register ip6ip6\n");
		err = -EAGAIN;
		goto unreg_ip4ip6;
	}
	ip6_fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0",
				      ip6_tnl_dev_setup);

	if (!ip6_fb_tnl_dev) {
		err = -ENOMEM;
		goto fail;
	}
	ip6_fb_tnl_dev->init = ip6_fb_tnl_dev_init;

	if ((err = register_netdev(ip6_fb_tnl_dev))) {
		free_netdev(ip6_fb_tnl_dev);
		goto fail;
	}
	return 0;
fail:
	xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6);
unreg_ip4ip6:
	xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET);
out:
	return err;
}

static void __exit ip6_tnl_destroy_tunnels(void)
{
	int h;
	struct ip6_tnl *t;

	for (h = 0; h < HASH_SIZE; h++) {
		while ((t = tnls_r_l[h]) != NULL)
			unregister_netdevice(t->dev);
	}

	t = tnls_wc[0];
	unregister_netdevice(t->dev);
}

/**
 * ip6_tunnel_cleanup - free resources and unregister protocol
 **/

static void __exit ip6_tunnel_cleanup(void)
{
	if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET))
		printk(KERN_INFO "ip6_tunnel close: can't deregister ip4ip6\n");

	if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6))
		printk(KERN_INFO "ip6_tunnel close: can't deregister ip6ip6\n");

	rtnl_lock();
	ip6_tnl_destroy_tunnels();
	rtnl_unlock();
}

module_init(ip6_tunnel_init);
module_exit(ip6_tunnel_cleanup);