ip_gre.c

/*
 *	Linux NET3:	GRE over IP protocol decoder.
 *
 *	Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.ru)
 *
 *	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/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/mroute.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/if_ether.h>

#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ipip.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>

#ifdef CONFIG_IPV6
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#endif

/*
   Problems & solutions
   --------------------

   1. The most important issue is detecting local dead loops.
   They would cause complete host lockup in transmit, which
   would be "resolved" by stack overflow or, if queueing is enabled,
   with infinite looping in net_bh.

   We cannot track such dead loops during route installation,
   it is infeasible task. The most general solutions would be
   to keep skb->encapsulation counter (sort of local ttl),
   and silently drop packet when it expires. It is the best
   solution, but it supposes maintaing new variable in ALL
   skb, even if no tunneling is used.

   Current solution: t->recursion lock breaks dead loops. It looks
   like dev->tbusy flag, but I preferred new variable, because
   the semantics is different. One day, when hard_start_xmit
   will be multithreaded we will have to use skb->encapsulation.



   2. Networking dead loops would not kill routers, but would really
   kill network. IP hop limit plays role of "t->recursion" in this case,
   if we copy it from packet being encapsulated to upper header.
   It is very good solution, but it introduces two problems:

   - Routing protocols, using packets with ttl=1 (OSPF, RIP2),
     do not work over tunnels.
   - traceroute does not work. I planned to relay ICMP from tunnel,
     so that this problem would be solved and traceroute output
     would even more informative. This idea appeared to be wrong:
     only Linux complies to rfc1812 now (yes, guys, Linux is the only
     true router now :-)), all routers (at least, in neighbourhood of mine)
     return only 8 bytes of payload. It is the end.

   Hence, if we want that OSPF worked or traceroute said something reasonable,
   we should search for another solution.

   One of them is to parse packet trying to detect inner encapsulation
   made by our node. It is difficult or even impossible, especially,
   taking into account fragmentation. TO be short, tt is not solution at all.

   Current solution: The solution was UNEXPECTEDLY SIMPLE.
   We force DF flag on tunnels with preconfigured hop limit,
   that is ALL. :-) Well, it does not remove the problem completely,
   but exponential growth of network traffic is changed to linear
   (branches, that exceed pmtu are pruned) and tunnel mtu
   fastly degrades to value <68, where looping stops.
   Yes, it is not good if there exists a router in the loop,
   which does not force DF, even when encapsulating packets have DF set.
   But it is not our problem! Nobody could accuse us, we made
   all that we could make. Even if it is your gated who injected
   fatal route to network, even if it were you who configured
   fatal static route: you are innocent. :-)



   3. Really, ipv4/ipip.c, ipv4/ip_gre.c and ipv6/sit.c contain
   practically identical code. It would be good to glue them
   together, but it is not very evident, how to make them modular.
   sit is integral part of IPv6, ipip and gre are naturally modular.
   We could extract common parts (hash table, ioctl etc)
   to a separate module (ip_tunnel.c).

   Alexey Kuznetsov.
 */

static int ipgre_tunnel_init(struct net_device *dev);
static void ipgre_tunnel_setup(struct net_device *dev);

/* Fallback tunnel: no source, no destination, no key, no options */

static int ipgre_fb_tunnel_init(struct net_device *dev);

static struct net_device *ipgre_fb_tunnel_dev;

/* Tunnel hash table */

/*
   4 hash tables:

   3: (remote,local)
   2: (remote,*)
   1: (*,local)
   0: (*,*)

   We require exact key match i.e. if a key is present in packet
   it will match only tunnel with the same key; if it is not present,
   it will match only keyless tunnel.

   All keysless packets, if not matched configured keyless tunnels
   will match fallback tunnel.
 */

#define HASH_SIZE  16
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)

static struct ip_tunnel *tunnels[4][HASH_SIZE];

#define tunnels_r_l	(tunnels[3])
#define tunnels_r	(tunnels[2])
#define tunnels_l	(tunnels[1])
#define tunnels_wc	(tunnels[0])

static DEFINE_RWLOCK(ipgre_lock);

/* Given src, dst and key, find appropriate for input tunnel. */

static struct ip_tunnel * ipgre_tunnel_lookup(__be32 remote, __be32 local, __be32 key)
{
	unsigned h0 = HASH(remote);
	unsigned h1 = HASH(key);
	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) {
			if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
				return t;
		}
	}
	for (t = tunnels_r[h0^h1]; t; t = t->next) {
		if (remote == t->parms.iph.daddr) {
			if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
				return t;
		}
	}
	for (t = tunnels_l[h1]; t; t = t->next) {
		if (local == t->parms.iph.saddr ||
		     (local == t->parms.iph.daddr && MULTICAST(local))) {
			if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
				return t;
		}
	}
	for (t = tunnels_wc[h1]; t; t = t->next) {
		if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
			return t;
	}

	if (ipgre_fb_tunnel_dev->flags&IFF_UP)
		return netdev_priv(ipgre_fb_tunnel_dev);
	return NULL;
}

static struct ip_tunnel **ipgre_bucket(struct ip_tunnel *t)
{
	__be32 remote = t->parms.iph.daddr;
	__be32 local = t->parms.iph.saddr;
	__be32 key = t->parms.i_key;
	unsigned h = HASH(key);
	int prio = 0;