/*
* 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.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.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/if_vlan.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ip_tunnels.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/gre.h>
#include <net/dst_metadata.h>
#if IS_ENABLED(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 a good
solution, but it supposes maintaining new variable in ALL
skb, even if no tunneling is used.
Current solution: xmit_recursion breaks dead loops. This is a percpu
counter, since when we enter the first ndo_xmit(), cpu migration is
forbidden. We force an exit if this counter reaches RECURSION_LIMIT
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, ttl 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
rapidly 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. :-)
Alexey Kuznetsov.
*/
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
static int ipgre_net_id __read_mostly;
static int gre_tap_net_id __read_mostly;
static void ipgre_err(struct sk_buff *skb, u32 info,
const struct tnl_ptk_info *tpi)
{
/* 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.
Moreover, Cisco "wise men" put GRE key to the third word
in GRE header. It makes impossible maintaining even soft
state for keyed GRE tunnels with enabled checksum. Tell
them "thank you".
Well, I wonder, rfc1812 was written by Cisco employee,
what the hell these idiots break standards established
by themselves???
*/
struct net *net = dev_net(skb->dev);
struct ip_tunnel_net *itn;
const struct iphdr *iph;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
switch (type) {
default:
case ICMP_PARAMETERPROB:
return;
case ICMP_DEST_UNREACH: