2005-04-16 16:20:36 -06:00
|
|
|
/*
|
2007-02-09 07:24:47 -07:00
|
|
|
* Linux NET3: IP/IP protocol decoder.
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* Authors:
|
|
|
|
* Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95
|
|
|
|
*
|
|
|
|
* Fixes:
|
|
|
|
* Alan Cox : Merged and made usable non modular (its so tiny its silly as
|
|
|
|
* a module taking up 2 pages).
|
|
|
|
* Alan Cox : Fixed bug with 1.3.18 and IPIP not working (now needs to set skb->h.iph)
|
|
|
|
* to keep ip_forward happy.
|
|
|
|
* Alan Cox : More fixes for 1.3.21, and firewall fix. Maybe this will work soon 8).
|
|
|
|
* Kai Schulte : Fixed #defines for IP_FIREWALL->FIREWALL
|
|
|
|
* David Woodhouse : Perform some basic ICMP handling.
|
|
|
|
* IPIP Routing without decapsulation.
|
|
|
|
* Carlos Picoto : GRE over IP support
|
|
|
|
* Alexey Kuznetsov: Reworked. Really, now it is truncated version of ipv4/ip_gre.c.
|
|
|
|
* I do not want to merge them together.
|
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* tunnel.c: an IP tunnel driver
|
|
|
|
|
|
|
|
The purpose of this driver is to provide an IP tunnel through
|
|
|
|
which you can tunnel network traffic transparently across subnets.
|
|
|
|
|
|
|
|
This was written by looking at Nick Holloway's dummy driver
|
|
|
|
Thanks for the great code!
|
|
|
|
|
|
|
|
-Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95
|
2007-02-09 07:24:47 -07:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
Minor tweaks:
|
|
|
|
Cleaned up the code a little and added some pre-1.3.0 tweaks.
|
|
|
|
dev->hard_header/hard_header_len changed to use no headers.
|
|
|
|
Comments/bracketing tweaked.
|
|
|
|
Made the tunnels use dev->name not tunnel: when error reporting.
|
|
|
|
Added tx_dropped stat
|
2007-02-09 07:24:47 -07:00
|
|
|
|
2008-10-13 20:01:08 -06:00
|
|
|
-Alan Cox (alan@lxorguk.ukuu.org.uk) 21 March 95
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
Reworked:
|
|
|
|
Changed to tunnel to destination gateway in addition to the
|
|
|
|
tunnel's pointopoint address
|
|
|
|
Almost completely rewritten
|
|
|
|
Note: There is currently no firewall or ICMP handling done.
|
|
|
|
|
|
|
|
-Sam Lantinga (slouken@cs.ucdavis.edu) 02/13/96
|
2007-02-09 07:24:47 -07:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
|
|
|
|
|
|
|
/* Things I wish I had known when writing the tunnel driver:
|
|
|
|
|
|
|
|
When the tunnel_xmit() function is called, the skb contains the
|
|
|
|
packet to be sent (plus a great deal of extra info), and dev
|
|
|
|
contains the tunnel device that _we_ are.
|
|
|
|
|
|
|
|
When we are passed a packet, we are expected to fill in the
|
|
|
|
source address with our source IP address.
|
|
|
|
|
|
|
|
What is the proper way to allocate, copy and free a buffer?
|
|
|
|
After you allocate it, it is a "0 length" chunk of memory
|
|
|
|
starting at zero. If you want to add headers to the buffer
|
|
|
|
later, you'll have to call "skb_reserve(skb, amount)" with
|
|
|
|
the amount of memory you want reserved. Then, you call
|
|
|
|
"skb_put(skb, amount)" with the amount of space you want in
|
|
|
|
the buffer. skb_put() returns a pointer to the top (#0) of
|
|
|
|
that buffer. skb->len is set to the amount of space you have
|
|
|
|
"allocated" with skb_put(). You can then write up to skb->len
|
|
|
|
bytes to that buffer. If you need more, you can call skb_put()
|
|
|
|
again with the additional amount of space you need. You can
|
2007-02-09 07:24:47 -07:00
|
|
|
find out how much more space you can allocate by calling
|
2005-04-16 16:20:36 -06:00
|
|
|
"skb_tailroom(skb)".
|
|
|
|
Now, to add header space, call "skb_push(skb, header_len)".
|
|
|
|
This creates space at the beginning of the buffer and returns
|
|
|
|
a pointer to this new space. If later you need to strip a
|
|
|
|
header from a buffer, call "skb_pull(skb, header_len)".
|
|
|
|
skb_headroom() will return how much space is left at the top
|
|
|
|
of the buffer (before the main data). Remember, this headroom
|
|
|
|
space must be reserved before the skb_put() function is called.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
This version of net/ipv4/ipip.c is cloned of net/ipv4/ip_gre.c
|
|
|
|
|
|
|
|
For comments look at net/ipv4/ip_gre.c --ANK
|
|
|
|
*/
|
|
|
|
|
2007-02-09 07:24:47 -07:00
|
|
|
|
2006-01-11 13:17:47 -07:00
|
|
|
#include <linux/capability.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/kernel.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
|
|
|
#include <linux/slab.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
#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/netfilter_ipv4.h>
|
2006-01-05 17:35:42 -07:00
|
|
|
#include <linux/if_ether.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
#include <net/sock.h>
|
|
|
|
#include <net/ip.h>
|
|
|
|
#include <net/icmp.h>
|
|
|
|
#include <net/ipip.h>
|
|
|
|
#include <net/inet_ecn.h>
|
|
|
|
#include <net/xfrm.h>
|
2008-04-16 02:03:13 -06:00
|
|
|
#include <net/net_namespace.h>
|
|
|
|
#include <net/netns/generic.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
#define HASH_SIZE 16
|
2006-11-08 01:23:14 -07:00
|
|
|
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-11-17 03:42:49 -07:00
|
|
|
static int ipip_net_id __read_mostly;
|
2008-04-16 02:03:13 -06:00
|
|
|
struct ipip_net {
|
2010-09-15 05:07:24 -06:00
|
|
|
struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
|
|
|
|
struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
|
|
|
|
struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
|
|
|
|
struct ip_tunnel __rcu *tunnels_wc[1];
|
|
|
|
struct ip_tunnel __rcu **tunnels[4];
|
2008-04-16 02:05:32 -06:00
|
|
|
|
2008-04-16 02:04:13 -06:00
|
|
|
struct net_device *fb_tunnel_dev;
|
2008-04-16 02:03:13 -06:00
|
|
|
};
|
|
|
|
|
2010-09-26 18:35:50 -06:00
|
|
|
static int ipip_tunnel_init(struct net_device *dev);
|
2005-04-16 16:20:36 -06:00
|
|
|
static void ipip_tunnel_setup(struct net_device *dev);
|
2010-09-26 18:35:50 -06:00
|
|
|
static void ipip_dev_free(struct net_device *dev);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-10-22 23:42:02 -06:00
|
|
|
/*
|
2010-09-15 05:07:24 -06:00
|
|
|
* Locking : hash tables are protected by RCU and RTNL
|
2009-10-22 23:42:02 -06:00
|
|
|
*/
|
|
|
|
|
|
|
|
#define for_each_ip_tunnel_rcu(start) \
|
|
|
|
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2010-09-26 18:35:50 -06:00
|
|
|
/* often modified stats are per cpu, other are shared (netdev->stats) */
|
|
|
|
struct pcpu_tstats {
|
2012-04-12 00:31:16 -06:00
|
|
|
u64 rx_packets;
|
|
|
|
u64 rx_bytes;
|
|
|
|
u64 tx_packets;
|
|
|
|
u64 tx_bytes;
|
|
|
|
struct u64_stats_sync syncp;
|
|
|
|
};
|
2010-09-26 18:35:50 -06:00
|
|
|
|
2012-04-12 00:31:16 -06:00
|
|
|
static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev,
|
|
|
|
struct rtnl_link_stats64 *tot)
|
2010-09-26 18:35:50 -06:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for_each_possible_cpu(i) {
|
|
|
|
const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
|
2012-04-12 00:31:16 -06:00
|
|
|
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
|
|
|
|
unsigned int start;
|
|
|
|
|
|
|
|
do {
|
|
|
|
start = u64_stats_fetch_begin_bh(&tstats->syncp);
|
|
|
|
rx_packets = tstats->rx_packets;
|
|
|
|
tx_packets = tstats->tx_packets;
|
|
|
|
rx_bytes = tstats->rx_bytes;
|
|
|
|
tx_bytes = tstats->tx_bytes;
|
|
|
|
} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
|
|
|
|
|
|
|
|
tot->rx_packets += rx_packets;
|
|
|
|
tot->tx_packets += tx_packets;
|
|
|
|
tot->rx_bytes += rx_bytes;
|
|
|
|
tot->tx_bytes += tx_bytes;
|
2010-09-26 18:35:50 -06:00
|
|
|
}
|
2012-04-12 00:31:16 -06:00
|
|
|
|
|
|
|
tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
|
|
|
|
tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
|
|
|
|
tot->tx_dropped = dev->stats.tx_dropped;
|
|
|
|
tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
|
|
|
|
tot->tx_errors = dev->stats.tx_errors;
|
|
|
|
tot->collisions = dev->stats.collisions;
|
|
|
|
|
|
|
|
return tot;
|
2010-09-26 18:35:50 -06:00
|
|
|
}
|
|
|
|
|
2012-04-14 19:34:41 -06:00
|
|
|
static struct ip_tunnel *ipip_tunnel_lookup(struct net *net,
|
2008-04-16 02:04:35 -06:00
|
|
|
__be32 remote, __be32 local)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2010-09-15 05:07:24 -06:00
|
|
|
unsigned int h0 = HASH(remote);
|
|
|
|
unsigned int h1 = HASH(local);
|
2005-04-16 16:20:36 -06:00
|
|
|
struct ip_tunnel *t;
|
2008-04-16 02:05:32 -06:00
|
|
|
struct ipip_net *ipn = net_generic(net, ipip_net_id);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-10-22 23:42:02 -06:00
|
|
|
for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1])
|
2005-04-16 16:20:36 -06:00
|
|
|
if (local == t->parms.iph.saddr &&
|
|
|
|
remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
|
|
|
|
return t;
|
2009-10-22 23:42:02 -06:00
|
|
|
|
|
|
|
for_each_ip_tunnel_rcu(ipn->tunnels_r[h0])
|
2005-04-16 16:20:36 -06:00
|
|
|
if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
|
|
|
|
return t;
|
2009-10-22 23:42:02 -06:00
|
|
|
|
|
|
|
for_each_ip_tunnel_rcu(ipn->tunnels_l[h1])
|
2005-04-16 16:20:36 -06:00
|
|
|
if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
|
|
|
|
return t;
|
2009-10-22 23:42:02 -06:00
|
|
|
|
|
|
|
t = rcu_dereference(ipn->tunnels_wc[0]);
|
|
|
|
if (t && (t->dev->flags&IFF_UP))
|
2005-04-16 16:20:36 -06:00
|
|
|
return t;
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2010-09-15 05:07:24 -06:00
|
|
|
static struct ip_tunnel __rcu **__ipip_bucket(struct ipip_net *ipn,
|
2008-04-16 02:04:35 -06:00
|
|
|
struct ip_tunnel_parm *parms)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2007-04-24 05:44:47 -06:00
|
|
|
__be32 remote = parms->iph.daddr;
|
|
|
|
__be32 local = parms->iph.saddr;
|
2010-09-15 05:07:24 -06:00
|
|
|
unsigned int h = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
int prio = 0;
|
|
|
|
|
|
|
|
if (remote) {
|
|
|
|
prio |= 2;
|
|
|
|
h ^= HASH(remote);
|
|
|
|
}
|
|
|
|
if (local) {
|
|
|
|
prio |= 1;
|
|
|
|
h ^= HASH(local);
|
|
|
|
}
|
2008-04-16 02:05:32 -06:00
|
|
|
return &ipn->tunnels[prio][h];
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2010-09-15 05:07:24 -06:00
|
|
|
static inline struct ip_tunnel __rcu **ipip_bucket(struct ipip_net *ipn,
|
2008-04-16 02:04:35 -06:00
|
|
|
struct ip_tunnel *t)
|
2007-04-24 05:44:47 -06:00
|
|
|
{
|
2008-04-16 02:04:35 -06:00
|
|
|
return __ipip_bucket(ipn, &t->parms);
|
2007-04-24 05:44:47 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-04-16 02:04:35 -06:00
|
|
|
static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2010-09-15 05:07:24 -06:00
|
|
|
struct ip_tunnel __rcu **tp;
|
|
|
|
struct ip_tunnel *iter;
|
|
|
|
|
|
|
|
for (tp = ipip_bucket(ipn, t);
|
|
|
|
(iter = rtnl_dereference(*tp)) != NULL;
|
|
|
|
tp = &iter->next) {
|
|
|
|
if (t == iter) {
|
2012-01-11 21:41:32 -07:00
|
|
|
rcu_assign_pointer(*tp, t->next);
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-04-16 02:04:35 -06:00
|
|
|
static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2010-09-15 05:07:24 -06:00
|
|
|
struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2012-01-11 21:41:32 -07:00
|
|
|
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
|
|
|
|
rcu_assign_pointer(*tp, t);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2012-04-14 19:34:41 -06:00
|
|
|
static struct ip_tunnel *ipip_tunnel_locate(struct net *net,
|
2008-04-16 02:04:35 -06:00
|
|
|
struct ip_tunnel_parm *parms, int create)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2006-11-08 01:23:14 -07:00
|
|
|
__be32 remote = parms->iph.daddr;
|
|
|
|
__be32 local = parms->iph.saddr;
|
2010-09-15 05:07:24 -06:00
|
|
|
struct ip_tunnel *t, *nt;
|
|
|
|
struct ip_tunnel __rcu **tp;
|
2005-04-16 16:20:36 -06:00
|
|
|
struct net_device *dev;
|
|
|
|
char name[IFNAMSIZ];
|
2008-04-16 02:04:35 -06:00
|
|
|
struct ipip_net *ipn = net_generic(net, ipip_net_id);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2010-09-15 05:07:24 -06:00
|
|
|
for (tp = __ipip_bucket(ipn, parms);
|
|
|
|
(t = rtnl_dereference(*tp)) != NULL;
|
|
|
|
tp = &t->next) {
|
2005-04-16 16:20:36 -06:00
|
|
|
if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)
|
|
|
|
return t;
|
|
|
|
}
|
|
|
|
if (!create)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (parms->name[0])
|
|
|
|
strlcpy(name, parms->name, IFNAMSIZ);
|
2008-02-23 21:19:20 -07:00
|
|
|
else
|
2010-09-26 18:35:50 -06:00
|
|
|
strcpy(name, "tunl%d");
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
dev = alloc_netdev(sizeof(*t), name, ipip_tunnel_setup);
|
|
|
|
if (dev == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
2008-04-16 02:06:18 -06:00
|
|
|
dev_net_set(dev, net);
|
|
|
|
|
2006-01-08 23:05:26 -07:00
|
|
|
nt = netdev_priv(dev);
|
2005-04-16 16:20:36 -06:00
|
|
|
nt->parms = *parms;
|
|
|
|
|
2010-09-26 18:35:50 -06:00
|
|
|
if (ipip_tunnel_init(dev) < 0)
|
|
|
|
goto failed_free;
|
2008-11-20 21:33:21 -07:00
|
|
|
|
[INET]: Don't create tunnels with '%' in name.
Four tunnel drivers (ip_gre, ipip, ip6_tunnel and sit) can receive a
pre-defined name for a device from the userspace. Since these drivers
call the register_netdevice() (rtnl_lock, is held), which does _not_
generate the device's name, this name may contain a '%' character.
Not sure how bad is this to have a device with a '%' in its name, but
all the other places either use the register_netdev(), which call the
dev_alloc_name(), or explicitly call the dev_alloc_name() before
registering, i.e. do not allow for such names.
This had to be prior to the commit 34cc7b, but I forgot to number the
patches and this one got lost, sorry.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-27 00:51:04 -07:00
|
|
|
if (register_netdevice(dev) < 0)
|
|
|
|
goto failed_free;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2011-12-07 17:46:21 -07:00
|
|
|
strcpy(nt->parms.name, dev->name);
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
dev_hold(dev);
|
2008-04-16 02:04:35 -06:00
|
|
|
ipip_tunnel_link(ipn, nt);
|
2005-04-16 16:20:36 -06:00
|
|
|
return nt;
|
|
|
|
|
[INET]: Don't create tunnels with '%' in name.
Four tunnel drivers (ip_gre, ipip, ip6_tunnel and sit) can receive a
pre-defined name for a device from the userspace. Since these drivers
call the register_netdevice() (rtnl_lock, is held), which does _not_
generate the device's name, this name may contain a '%' character.
Not sure how bad is this to have a device with a '%' in its name, but
all the other places either use the register_netdev(), which call the
dev_alloc_name(), or explicitly call the dev_alloc_name() before
registering, i.e. do not allow for such names.
This had to be prior to the commit 34cc7b, but I forgot to number the
patches and this one got lost, sorry.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-27 00:51:04 -07:00
|
|
|
failed_free:
|
2010-09-26 18:35:50 -06:00
|
|
|
ipip_dev_free(dev);
|
2005-04-16 16:20:36 -06:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2010-09-15 05:07:24 -06:00
|
|
|
/* called with RTNL */
|
2005-04-16 16:20:36 -06:00
|
|
|
static void ipip_tunnel_uninit(struct net_device *dev)
|
|
|
|
{
|
2008-04-16 02:04:13 -06:00
|
|
|
struct net *net = dev_net(dev);
|
|
|
|
struct ipip_net *ipn = net_generic(net, ipip_net_id);
|
|
|
|
|
2010-09-15 05:07:24 -06:00
|
|
|
if (dev == ipn->fb_tunnel_dev)
|
2011-08-01 10:19:00 -06:00
|
|
|
RCU_INIT_POINTER(ipn->tunnels_wc[0], NULL);
|
2010-09-15 05:07:24 -06:00
|
|
|
else
|
2008-04-16 02:04:35 -06:00
|
|
|
ipip_tunnel_unlink(ipn, netdev_priv(dev));
|
2005-04-16 16:20:36 -06:00
|
|
|
dev_put(dev);
|
|
|
|
}
|
|
|
|
|
2006-03-28 02:12:13 -07:00
|
|
|
static int ipip_err(struct sk_buff *skb, u32 info)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
|
2008-05-21 18:47:54 -06:00
|
|
|
/* All the routers (except for Linux) return only
|
2005-04-16 16:20:36 -06:00
|
|
|
8 bytes of packet payload. It means, that precise relaying of
|
|
|
|
ICMP in the real Internet is absolutely infeasible.
|
|
|
|
*/
|
2011-04-21 22:53:02 -06:00
|
|
|
const struct iphdr *iph = (const struct iphdr *)skb->data;
|
2007-03-13 11:43:18 -06:00
|
|
|
const int type = icmp_hdr(skb)->type;
|
|
|
|
const int code = icmp_hdr(skb)->code;
|
2005-04-16 16:20:36 -06:00
|
|
|
struct ip_tunnel *t;
|
2006-03-28 02:12:13 -07:00
|
|
|
int err;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
switch (type) {
|
|
|
|
default:
|
|
|
|
case ICMP_PARAMETERPROB:
|
2006-03-28 02:12:13 -07:00
|
|
|
return 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
case ICMP_DEST_UNREACH:
|
|
|
|
switch (code) {
|
|
|
|
case ICMP_SR_FAILED:
|
|
|
|
case ICMP_PORT_UNREACH:
|
|
|
|
/* Impossible event. */
|
2006-03-28 02:12:13 -07:00
|
|
|
return 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
case ICMP_FRAG_NEEDED:
|
|
|
|
/* Soft state for pmtu is maintained by IP core. */
|
2006-03-28 02:12:13 -07:00
|
|
|
return 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
default:
|
|
|
|
/* All others are translated to HOST_UNREACH.
|
|
|
|
rfc2003 contains "deep thoughts" about NET_UNREACH,
|
|
|
|
I believe they are just ether pollution. --ANK
|
|
|
|
*/
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case ICMP_TIME_EXCEEDED:
|
|
|
|
if (code != ICMP_EXC_TTL)
|
2006-03-28 02:12:13 -07:00
|
|
|
return 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2006-03-28 02:12:13 -07:00
|
|
|
err = -ENOENT;
|
|
|
|
|
2009-10-22 23:42:02 -06:00
|
|
|
rcu_read_lock();
|
2008-04-16 02:05:03 -06:00
|
|
|
t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (t == NULL || t->parms.iph.daddr == 0)
|
|
|
|
goto out;
|
2006-03-28 02:12:13 -07:00
|
|
|
|
|
|
|
err = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
|
|
|
|
goto out;
|
|
|
|
|
2009-02-25 00:36:47 -07:00
|
|
|
if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
|
2005-04-16 16:20:36 -06:00
|
|
|
t->err_count++;
|
|
|
|
else
|
|
|
|
t->err_count = 1;
|
|
|
|
t->err_time = jiffies;
|
|
|
|
out:
|
2009-10-22 23:42:02 -06:00
|
|
|
rcu_read_unlock();
|
2006-03-28 02:12:13 -07:00
|
|
|
return err;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2007-04-20 23:47:35 -06:00
|
|
|
static inline void ipip_ecn_decapsulate(const struct iphdr *outer_iph,
|
|
|
|
struct sk_buff *skb)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2007-04-20 23:47:35 -06:00
|
|
|
struct iphdr *inner_iph = ip_hdr(skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (INET_ECN_is_ce(outer_iph->tos))
|
|
|
|
IP_ECN_set_ce(inner_iph);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ipip_rcv(struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
struct ip_tunnel *tunnel;
|
2007-04-20 23:47:35 -06:00
|
|
|
const struct iphdr *iph = ip_hdr(skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-10-22 23:42:02 -06:00
|
|
|
rcu_read_lock();
|
2010-09-26 18:35:50 -06:00
|
|
|
tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
|
|
|
|
if (tunnel != NULL) {
|
|
|
|
struct pcpu_tstats *tstats;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
|
2009-10-22 23:42:02 -06:00
|
|
|
rcu_read_unlock();
|
2005-04-16 16:20:36 -06:00
|
|
|
kfree_skb(skb);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
secpath_reset(skb);
|
|
|
|
|
2007-04-10 22:21:55 -06:00
|
|
|
skb->mac_header = skb->network_header;
|
2007-04-10 21:45:18 -06:00
|
|
|
skb_reset_network_header(skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
skb->protocol = htons(ETH_P_IP);
|
|
|
|
skb->pkt_type = PACKET_HOST;
|
|
|
|
|
2010-09-26 18:35:50 -06:00
|
|
|
tstats = this_cpu_ptr(tunnel->dev->tstats);
|
2012-04-12 00:31:16 -06:00
|
|
|
u64_stats_update_begin(&tstats->syncp);
|
2010-09-26 18:35:50 -06:00
|
|
|
tstats->rx_packets++;
|
|
|
|
tstats->rx_bytes += skb->len;
|
2012-04-12 00:31:16 -06:00
|
|
|
u64_stats_update_end(&tstats->syncp);
|
2010-09-26 18:35:50 -06:00
|
|
|
|
|
|
|
__skb_tunnel_rx(skb, tunnel->dev);
|
2010-05-17 23:36:55 -06:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
ipip_ecn_decapsulate(iph, skb);
|
2010-09-19 18:12:11 -06:00
|
|
|
|
2010-09-30 15:06:55 -06:00
|
|
|
netif_rx(skb);
|
2010-09-19 18:12:11 -06:00
|
|
|
|
2009-10-22 23:42:02 -06:00
|
|
|
rcu_read_unlock();
|
2005-04-16 16:20:36 -06:00
|
|
|
return 0;
|
|
|
|
}
|
2009-10-22 23:42:02 -06:00
|
|
|
rcu_read_unlock();
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This function assumes it is being called from dev_queue_xmit()
|
|
|
|
* and that skb is filled properly by that function.
|
|
|
|
*/
|
|
|
|
|
2009-08-31 13:50:41 -06:00
|
|
|
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2006-01-08 23:05:26 -07:00
|
|
|
struct ip_tunnel *tunnel = netdev_priv(dev);
|
2010-09-26 18:35:50 -06:00
|
|
|
struct pcpu_tstats *tstats;
|
2011-04-21 22:53:02 -06:00
|
|
|
const struct iphdr *tiph = &tunnel->parms.iph;
|
2005-04-16 16:20:36 -06:00
|
|
|
u8 tos = tunnel->parms.iph.tos;
|
2006-11-08 01:23:14 -07:00
|
|
|
__be16 df = tiph->frag_off;
|
2005-04-16 16:20:36 -06:00
|
|
|
struct rtable *rt; /* Route to the other host */
|
2010-09-26 18:35:50 -06:00
|
|
|
struct net_device *tdev; /* Device to other host */
|
2011-04-21 22:53:02 -06:00
|
|
|
const struct iphdr *old_iph = ip_hdr(skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
struct iphdr *iph; /* Our new IP header */
|
2007-10-23 22:07:32 -06:00
|
|
|
unsigned int max_headroom; /* The extra header space needed */
|
2006-11-08 01:23:14 -07:00
|
|
|
__be32 dst = tiph->daddr;
|
2011-05-03 21:25:42 -06:00
|
|
|
struct flowi4 fl4;
|
2005-04-16 16:20:36 -06:00
|
|
|
int mtu;
|
|
|
|
|
|
|
|
if (skb->protocol != htons(ETH_P_IP))
|
|
|
|
goto tx_error;
|
|
|
|
|
2010-09-26 18:35:50 -06:00
|
|
|
if (tos & 1)
|
2005-04-16 16:20:36 -06:00
|
|
|
tos = old_iph->tos;
|
|
|
|
|
|
|
|
if (!dst) {
|
|
|
|
/* NBMA tunnel */
|
2009-06-01 23:14:27 -06:00
|
|
|
if ((rt = skb_rtable(skb)) == NULL) {
|
2010-09-26 18:35:50 -06:00
|
|
|
dev->stats.tx_fifo_errors++;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto tx_error;
|
|
|
|
}
|
2012-01-24 16:18:05 -07:00
|
|
|
dst = rt->rt_gateway;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2011-05-03 21:25:42 -06:00
|
|
|
rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
|
2011-03-11 22:00:52 -07:00
|
|
|
dst, tiph->saddr,
|
|
|
|
0, 0,
|
|
|
|
IPPROTO_IPIP, RT_TOS(tos),
|
|
|
|
tunnel->parms.link);
|
|
|
|
if (IS_ERR(rt)) {
|
|
|
|
dev->stats.tx_carrier_errors++;
|
|
|
|
goto tx_error_icmp;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
2010-06-11 00:31:35 -06:00
|
|
|
tdev = rt->dst.dev;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (tdev == dev) {
|
|
|
|
ip_rt_put(rt);
|
2010-09-26 18:35:50 -06:00
|
|
|
dev->stats.collisions++;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto tx_error;
|
|
|
|
}
|
|
|
|
|
2009-11-06 03:37:41 -07:00
|
|
|
df |= old_iph->frag_off & htons(IP_DF);
|
|
|
|
|
|
|
|
if (df) {
|
2010-06-11 00:31:35 -06:00
|
|
|
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-11-06 03:37:41 -07:00
|
|
|
if (mtu < 68) {
|
2010-09-26 18:35:50 -06:00
|
|
|
dev->stats.collisions++;
|
2009-11-06 03:37:41 -07:00
|
|
|
ip_rt_put(rt);
|
|
|
|
goto tx_error;
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-11-06 03:37:41 -07:00
|
|
|
if (skb_dst(skb))
|
|
|
|
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-11-06 03:37:41 -07:00
|
|
|
if ((old_iph->frag_off & htons(IP_DF)) &&
|
|
|
|
mtu < ntohs(old_iph->tot_len)) {
|
|
|
|
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
|
|
|
|
htonl(mtu));
|
|
|
|
ip_rt_put(rt);
|
|
|
|
goto tx_error;
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
if (tunnel->err_count > 0) {
|
2009-02-25 00:36:47 -07:00
|
|
|
if (time_before(jiffies,
|
|
|
|
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
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));
|
|
|
|
|
2007-07-09 16:33:40 -06:00
|
|
|
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
|
|
|
|
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
|
2005-04-16 16:20:36 -06:00
|
|
|
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
|
|
|
|
if (!new_skb) {
|
|
|
|
ip_rt_put(rt);
|
2010-09-26 18:35:50 -06:00
|
|
|
dev->stats.tx_dropped++;
|
2005-04-16 16:20:36 -06:00
|
|
|
dev_kfree_skb(skb);
|
2009-06-23 00:03:08 -06:00
|
|
|
return NETDEV_TX_OK;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
if (skb->sk)
|
|
|
|
skb_set_owner_w(new_skb, skb->sk);
|
|
|
|
dev_kfree_skb(skb);
|
|
|
|
skb = new_skb;
|
2007-04-20 23:47:35 -06:00
|
|
|
old_iph = ip_hdr(skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2007-04-10 22:21:55 -06:00
|
|
|
skb->transport_header = skb->network_header;
|
2007-04-10 21:46:21 -06:00
|
|
|
skb_push(skb, sizeof(struct iphdr));
|
|
|
|
skb_reset_network_header(skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
|
2006-02-15 16:10:22 -07:00
|
|
|
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
|
|
|
|
IPSKB_REROUTED);
|
2009-06-01 23:19:30 -06:00
|
|
|
skb_dst_drop(skb);
|
2010-06-11 00:31:35 -06:00
|
|
|
skb_dst_set(skb, &rt->dst);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Push down and install the IPIP header.
|
|
|
|
*/
|
|
|
|
|
2007-04-20 23:47:35 -06:00
|
|
|
iph = ip_hdr(skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
iph->version = 4;
|
|
|
|
iph->ihl = sizeof(struct iphdr)>>2;
|
|
|
|
iph->frag_off = df;
|
|
|
|
iph->protocol = IPPROTO_IPIP;
|
|
|
|
iph->tos = INET_ECN_encapsulate(tos, old_iph->tos);
|
2011-05-04 12:10:28 -06:00
|
|
|
iph->daddr = fl4.daddr;
|
|
|
|
iph->saddr = fl4.saddr;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if ((iph->ttl = tiph->ttl) == 0)
|
|
|
|
iph->ttl = old_iph->ttl;
|
|
|
|
|
|
|
|
nf_reset(skb);
|
2010-09-26 18:35:50 -06:00
|
|
|
tstats = this_cpu_ptr(dev->tstats);
|
|
|
|
__IPTUNNEL_XMIT(tstats, &dev->stats);
|
2009-06-23 00:03:08 -06:00
|
|
|
return NETDEV_TX_OK;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
tx_error_icmp:
|
|
|
|
dst_link_failure(skb);
|
|
|
|
tx_error:
|
2010-09-26 18:35:50 -06:00
|
|
|
dev->stats.tx_errors++;
|
2005-04-16 16:20:36 -06:00
|
|
|
dev_kfree_skb(skb);
|
2009-06-23 00:03:08 -06:00
|
|
|
return NETDEV_TX_OK;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2007-12-12 12:01:43 -07:00
|
|
|
static void ipip_tunnel_bind_dev(struct net_device *dev)
|
|
|
|
{
|
|
|
|
struct net_device *tdev = NULL;
|
|
|
|
struct ip_tunnel *tunnel;
|
2011-04-21 22:53:02 -06:00
|
|
|
const struct iphdr *iph;
|
2007-12-12 12:01:43 -07:00
|
|
|
|
|
|
|
tunnel = netdev_priv(dev);
|
|
|
|
iph = &tunnel->parms.iph;
|
|
|
|
|
|
|
|
if (iph->daddr) {
|
2011-05-03 21:25:42 -06:00
|
|
|
struct rtable *rt;
|
|
|
|
struct flowi4 fl4;
|
|
|
|
|
|
|
|
rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
|
|
|
|
iph->daddr, iph->saddr,
|
|
|
|
0, 0,
|
|
|
|
IPPROTO_IPIP,
|
|
|
|
RT_TOS(iph->tos),
|
|
|
|
tunnel->parms.link);
|
2011-03-02 15:31:35 -07:00
|
|
|
if (!IS_ERR(rt)) {
|
2010-06-11 00:31:35 -06:00
|
|
|
tdev = rt->dst.dev;
|
2007-12-12 12:01:43 -07:00
|
|
|
ip_rt_put(rt);
|
|
|
|
}
|
|
|
|
dev->flags |= IFF_POINTOPOINT;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!tdev && tunnel->parms.link)
|
2008-04-16 02:05:57 -06:00
|
|
|
tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
|
2007-12-12 12:01:43 -07:00
|
|
|
|
|
|
|
if (tdev) {
|
|
|
|
dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
|
|
|
|
dev->mtu = tdev->mtu - sizeof(struct iphdr);
|
|
|
|
}
|
|
|
|
dev->iflink = tunnel->parms.link;
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
static int
|
|
|
|
ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
|
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
struct ip_tunnel_parm p;
|
|
|
|
struct ip_tunnel *t;
|
2008-04-16 02:04:13 -06:00
|
|
|
struct net *net = dev_net(dev);
|
|
|
|
struct ipip_net *ipn = net_generic(net, ipip_net_id);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
switch (cmd) {
|
|
|
|
case SIOCGETTUNNEL:
|
|
|
|
t = NULL;
|
2008-04-16 02:04:13 -06:00
|
|
|
if (dev == ipn->fb_tunnel_dev) {
|
2005-04-16 16:20:36 -06:00
|
|
|
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
|
|
|
|
err = -EFAULT;
|
|
|
|
break;
|
|
|
|
}
|
2008-04-16 02:04:35 -06:00
|
|
|
t = ipip_tunnel_locate(net, &p, 0);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
if (t == NULL)
|
2006-01-08 23:05:26 -07:00
|
|
|
t = netdev_priv(dev);
|
2005-04-16 16:20:36 -06:00
|
|
|
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_IPIP ||
|
|
|
|
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
|
|
|
|
goto done;
|
|
|
|
if (p.iph.ttl)
|
|
|
|
p.iph.frag_off |= htons(IP_DF);
|
|
|
|
|
2008-04-16 02:04:35 -06:00
|
|
|
t = ipip_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-04-16 02:04:13 -06:00
|
|
|
if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
|
2005-04-16 16:20:36 -06:00
|
|
|
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;
|
|
|
|
}
|
2006-01-08 23:05:26 -07:00
|
|
|
t = netdev_priv(dev);
|
2008-04-16 02:04:35 -06:00
|
|
|
ipip_tunnel_unlink(ipn, t);
|
2010-10-26 23:43:53 -06:00
|
|
|
synchronize_net();
|
2005-04-16 16:20:36 -06:00
|
|
|
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);
|
2008-04-16 02:04:35 -06:00
|
|
|
ipip_tunnel_link(ipn, t);
|
2005-04-16 16:20:36 -06:00
|
|
|
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;
|
2007-12-12 12:01:43 -07:00
|
|
|
if (t->parms.link != p.link) {
|
|
|
|
t->parms.link = p.link;
|
|
|
|
ipip_tunnel_bind_dev(dev);
|
|
|
|
netdev_state_change(dev);
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
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;
|
|
|
|
|
2008-04-16 02:04:13 -06:00
|
|
|
if (dev == ipn->fb_tunnel_dev) {
|
2005-04-16 16:20:36 -06:00
|
|
|
err = -EFAULT;
|
|
|
|
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
|
|
|
|
goto done;
|
|
|
|
err = -ENOENT;
|
2008-04-16 02:04:35 -06:00
|
|
|
if ((t = ipip_tunnel_locate(net, &p, 0)) == NULL)
|
2005-04-16 16:20:36 -06:00
|
|
|
goto done;
|
|
|
|
err = -EPERM;
|
2008-04-16 02:04:13 -06:00
|
|
|
if (t->dev == ipn->fb_tunnel_dev)
|
2005-04-16 16:20:36 -06:00
|
|
|
goto done;
|
|
|
|
dev = t->dev;
|
|
|
|
}
|
2007-02-07 01:09:58 -07:00
|
|
|
unregister_netdevice(dev);
|
|
|
|
err = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
err = -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
done:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ipip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
|
|
|
|
{
|
|
|
|
if (new_mtu < 68 || new_mtu > 0xFFF8 - sizeof(struct iphdr))
|
|
|
|
return -EINVAL;
|
|
|
|
dev->mtu = new_mtu;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-11-20 21:33:21 -07:00
|
|
|
static const struct net_device_ops ipip_netdev_ops = {
|
|
|
|
.ndo_uninit = ipip_tunnel_uninit,
|
|
|
|
.ndo_start_xmit = ipip_tunnel_xmit,
|
|
|
|
.ndo_do_ioctl = ipip_tunnel_ioctl,
|
|
|
|
.ndo_change_mtu = ipip_tunnel_change_mtu,
|
2012-04-12 00:31:16 -06:00
|
|
|
.ndo_get_stats64 = ipip_get_stats64,
|
2008-11-20 21:33:21 -07:00
|
|
|
};
|
|
|
|
|
2010-09-26 18:35:50 -06:00
|
|
|
static void ipip_dev_free(struct net_device *dev)
|
|
|
|
{
|
|
|
|
free_percpu(dev->tstats);
|
|
|
|
free_netdev(dev);
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
static void ipip_tunnel_setup(struct net_device *dev)
|
|
|
|
{
|
2008-11-20 21:33:21 -07:00
|
|
|
dev->netdev_ops = &ipip_netdev_ops;
|
2010-09-26 18:35:50 -06:00
|
|
|
dev->destructor = ipip_dev_free;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
dev->type = ARPHRD_TUNNEL;
|
|
|
|
dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
|
2006-01-05 17:35:42 -07:00
|
|
|
dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr);
|
2005-04-16 16:20:36 -06:00
|
|
|
dev->flags = IFF_NOARP;
|
|
|
|
dev->iflink = 0;
|
|
|
|
dev->addr_len = 4;
|
2008-04-16 02:06:18 -06:00
|
|
|
dev->features |= NETIF_F_NETNS_LOCAL;
|
2010-09-27 18:17:17 -06:00
|
|
|
dev->features |= NETIF_F_LLTX;
|
2009-05-28 04:44:30 -06:00
|
|
|
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2010-09-26 18:35:50 -06:00
|
|
|
static int ipip_tunnel_init(struct net_device *dev)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2008-11-20 21:33:21 -07:00
|
|
|
struct ip_tunnel *tunnel = netdev_priv(dev);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
tunnel->dev = dev;
|
|
|
|
|
|
|
|
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
|
|
|
|
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
|
|
|
|
|
2007-12-12 12:01:43 -07:00
|
|
|
ipip_tunnel_bind_dev(dev);
|
2010-09-26 18:35:50 -06:00
|
|
|
|
|
|
|
dev->tstats = alloc_percpu(struct pcpu_tstats);
|
|
|
|
if (!dev->tstats)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
return 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2010-09-27 17:56:46 -06:00
|
|
|
static int __net_init ipip_fb_tunnel_init(struct net_device *dev)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2006-01-08 23:05:26 -07:00
|
|
|
struct ip_tunnel *tunnel = netdev_priv(dev);
|
2005-04-16 16:20:36 -06:00
|
|
|
struct iphdr *iph = &tunnel->parms.iph;
|
2008-04-16 02:05:32 -06:00
|
|
|
struct ipip_net *ipn = net_generic(dev_net(dev), ipip_net_id);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
tunnel->dev = dev;
|
|
|
|
strcpy(tunnel->parms.name, dev->name);
|
|
|
|
|
|
|
|
iph->version = 4;
|
|
|
|
iph->protocol = IPPROTO_IPIP;
|
|
|
|
iph->ihl = 5;
|
|
|
|
|
2010-09-27 17:56:46 -06:00
|
|
|
dev->tstats = alloc_percpu(struct pcpu_tstats);
|
|
|
|
if (!dev->tstats)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
dev_hold(dev);
|
2012-01-11 21:41:32 -07:00
|
|
|
rcu_assign_pointer(ipn->tunnels_wc[0], tunnel);
|
2010-09-27 17:56:46 -06:00
|
|
|
return 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2010-08-30 01:04:14 -06:00
|
|
|
static struct xfrm_tunnel ipip_handler __read_mostly = {
|
2005-04-16 16:20:36 -06:00
|
|
|
.handler = ipip_rcv,
|
|
|
|
.err_handler = ipip_err,
|
2006-03-28 02:12:13 -07:00
|
|
|
.priority = 1,
|
2005-04-16 16:20:36 -06:00
|
|
|
};
|
|
|
|
|
2009-02-22 01:02:08 -07:00
|
|
|
static const char banner[] __initconst =
|
2005-04-16 16:20:36 -06:00
|
|
|
KERN_INFO "IPv4 over IPv4 tunneling driver\n";
|
|
|
|
|
2009-10-27 01:06:59 -06:00
|
|
|
static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
|
2008-04-16 02:05:32 -06:00
|
|
|
{
|
|
|
|
int prio;
|
|
|
|
|
|
|
|
for (prio = 1; prio < 4; prio++) {
|
|
|
|
int h;
|
|
|
|
for (h = 0; h < HASH_SIZE; h++) {
|
2010-09-15 05:07:24 -06:00
|
|
|
struct ip_tunnel *t;
|
2009-10-27 01:06:59 -06:00
|
|
|
|
2010-09-15 05:07:24 -06:00
|
|
|
t = rtnl_dereference(ipn->tunnels[prio][h]);
|
2009-10-27 01:06:59 -06:00
|
|
|
while (t != NULL) {
|
|
|
|
unregister_netdevice_queue(t->dev, head);
|
2010-09-15 05:07:24 -06:00
|
|
|
t = rtnl_dereference(t->next);
|
2009-10-27 01:06:59 -06:00
|
|
|
}
|
2008-04-16 02:05:32 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2010-01-16 20:35:32 -07:00
|
|
|
static int __net_init ipip_init_net(struct net *net)
|
2008-04-16 02:03:13 -06:00
|
|
|
{
|
2009-11-29 08:46:14 -07:00
|
|
|
struct ipip_net *ipn = net_generic(net, ipip_net_id);
|
2011-12-07 17:46:21 -07:00
|
|
|
struct ip_tunnel *t;
|
2008-04-16 02:03:13 -06:00
|
|
|
int err;
|
|
|
|
|
2008-04-16 02:05:32 -06:00
|
|
|
ipn->tunnels[0] = ipn->tunnels_wc;
|
|
|
|
ipn->tunnels[1] = ipn->tunnels_l;
|
|
|
|
ipn->tunnels[2] = ipn->tunnels_r;
|
|
|
|
ipn->tunnels[3] = ipn->tunnels_r_l;
|
|
|
|
|
2008-04-16 02:04:13 -06:00
|
|
|
ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel),
|
|
|
|
"tunl0",
|
|
|
|
ipip_tunnel_setup);
|
|
|
|
if (!ipn->fb_tunnel_dev) {
|
|
|
|
err = -ENOMEM;
|
|
|
|
goto err_alloc_dev;
|
|
|
|
}
|
2008-11-23 18:26:26 -07:00
|
|
|
dev_net_set(ipn->fb_tunnel_dev, net);
|
2008-04-16 02:04:13 -06:00
|
|
|
|
2010-09-27 17:56:46 -06:00
|
|
|
err = ipip_fb_tunnel_init(ipn->fb_tunnel_dev);
|
|
|
|
if (err)
|
|
|
|
goto err_reg_dev;
|
2008-04-16 02:04:13 -06:00
|
|
|
|
|
|
|
if ((err = register_netdev(ipn->fb_tunnel_dev)))
|
|
|
|
goto err_reg_dev;
|
|
|
|
|
2011-12-07 17:46:21 -07:00
|
|
|
t = netdev_priv(ipn->fb_tunnel_dev);
|
|
|
|
|
|
|
|
strcpy(t->parms.name, ipn->fb_tunnel_dev->name);
|
2008-04-16 02:03:13 -06:00
|
|
|
return 0;
|
|
|
|
|
2008-04-16 02:04:13 -06:00
|
|
|
err_reg_dev:
|
2010-09-27 17:56:46 -06:00
|
|
|
ipip_dev_free(ipn->fb_tunnel_dev);
|
2008-04-16 02:04:13 -06:00
|
|
|
err_alloc_dev:
|
|
|
|
/* nothing */
|
2008-04-16 02:03:13 -06:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2010-01-16 20:35:32 -07:00
|
|
|
static void __net_exit ipip_exit_net(struct net *net)
|
2008-04-16 02:03:13 -06:00
|
|
|
{
|
2009-11-29 08:46:14 -07:00
|
|
|
struct ipip_net *ipn = net_generic(net, ipip_net_id);
|
2009-10-27 01:06:59 -06:00
|
|
|
LIST_HEAD(list);
|
2008-04-16 02:03:13 -06:00
|
|
|
|
2008-04-16 02:04:13 -06:00
|
|
|
rtnl_lock();
|
2009-10-27 01:06:59 -06:00
|
|
|
ipip_destroy_tunnels(ipn, &list);
|
|
|
|
unregister_netdevice_queue(ipn->fb_tunnel_dev, &list);
|
|
|
|
unregister_netdevice_many(&list);
|
2008-04-16 02:04:13 -06:00
|
|
|
rtnl_unlock();
|
2008-04-16 02:03:13 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static struct pernet_operations ipip_net_ops = {
|
|
|
|
.init = ipip_init_net,
|
|
|
|
.exit = ipip_exit_net,
|
2009-11-29 08:46:14 -07:00
|
|
|
.id = &ipip_net_id,
|
|
|
|
.size = sizeof(struct ipip_net),
|
2008-04-16 02:03:13 -06:00
|
|
|
};
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
static int __init ipip_init(void)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
|
|
|
|
printk(banner);
|
|
|
|
|
2010-02-16 02:05:04 -07:00
|
|
|
err = register_pernet_device(&ipip_net_ops);
|
|
|
|
if (err < 0)
|
|
|
|
return err;
|
|
|
|
err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
|
|
|
|
if (err < 0) {
|
|
|
|
unregister_pernet_device(&ipip_net_ops);
|
2012-03-11 12:36:11 -06:00
|
|
|
pr_info("%s: can't register tunnel\n", __func__);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit ipip_fini(void)
|
|
|
|
{
|
2007-02-13 13:54:47 -07:00
|
|
|
if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET))
|
2012-03-11 12:36:11 -06:00
|
|
|
pr_info("%s: can't deregister tunnel\n", __func__);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-11-29 08:46:14 -07:00
|
|
|
unregister_pernet_device(&ipip_net_ops);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
module_init(ipip_init);
|
|
|
|
module_exit(ipip_fini);
|
|
|
|
MODULE_LICENSE("GPL");
|
2011-03-01 14:33:13 -07:00
|
|
|
MODULE_ALIAS_NETDEV("tunl0");
|