linux/net/ipv6/ip6_tunnel.c

1505 lines
35 KiB
C
Raw Normal View History

/*
* IPv6 tunneling device
* Linux INET6 implementation
*
* Authors:
* Ville Nuorvala <vnuorval@tcs.hut.fi>
* Yasuyuki Kozakai <kozakai@linux-ipv6.org>
*
* Based on:
* linux/net/ipv6/sit.c and linux/net/ipv4/ipip.c
*
* RFC 2473
*
* 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/module.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/sockios.h>
#include <linux/icmp.h>
#include <linux/if.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/if_tunnel.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/route.h>
#include <linux/rtnetlink.h>
#include <linux/netfilter_ipv6.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 08:04:11 +00:00
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <asm/atomic.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
MODULE_AUTHOR("Ville Nuorvala");
MODULE_DESCRIPTION("IPv6 tunneling device");
MODULE_LICENSE("GPL");
#define IPV6_TLV_TEL_DST_SIZE 8
#ifdef IP6_TNL_DEBUG
#define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__)
#else
#define IP6_TNL_TRACE(x...) do {;} while(0)
#endif
#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
#define IPV6_TCLASS_SHIFT 20
#define HASH_SIZE 32
#define HASH(addr) ((__force u32)((addr)->s6_addr32[0] ^ (addr)->s6_addr32[1] ^ \
(addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \
(HASH_SIZE - 1))
static void ip6_tnl_dev_init(struct net_device *dev);
static void ip6_tnl_dev_setup(struct net_device *dev);
static int ip6_tnl_net_id __read_mostly;
struct ip6_tnl_net {
/* the IPv6 tunnel fallback device */
struct net_device *fb_tnl_dev;
/* lists for storing tunnels in use */
struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE];
struct ip6_tnl __rcu *tnls_wc[1];
struct ip6_tnl __rcu **tnls[2];
};
/*
* Locking : hash tables are protected by RCU and RTNL
*/
static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
{
struct dst_entry *dst = t->dst_cache;
if (dst && dst->obsolete &&
dst->ops->check(dst, t->dst_cookie) == NULL) {
t->dst_cache = NULL;
dst_release(dst);
return NULL;
}
return dst;
}
static inline void ip6_tnl_dst_reset(struct ip6_tnl *t)
{
dst_release(t->dst_cache);
t->dst_cache = NULL;
}
static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *) dst;
t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
dst_release(t->dst_cache);
t->dst_cache = dst;
}
/**
* ip6_tnl_lookup - fetch tunnel matching the end-point addresses
* @remote: the address of the tunnel exit-point
* @local: the address of the tunnel entry-point
*
* Return:
* tunnel matching given end-points if found,
* else fallback tunnel if its device is up,
* else %NULL
**/
#define for_each_ip6_tunnel_rcu(start) \
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
static struct ip6_tnl *
ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
{
unsigned int h0 = HASH(remote);
unsigned int h1 = HASH(local);
struct ip6_tnl *t;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[h0 ^ h1]) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_equal(remote, &t->parms.raddr) &&
(t->dev->flags & IFF_UP))
return t;
}
t = rcu_dereference(ip6n->tnls_wc[0]);
if (t && (t->dev->flags & IFF_UP))
return t;
return NULL;
}
/**
* ip6_tnl_bucket - get head of list matching given tunnel parameters
* @p: parameters containing tunnel end-points
*
* Description:
* ip6_tnl_bucket() returns the head of the list matching the
* &struct in6_addr entries laddr and raddr in @p.
*
* Return: head of IPv6 tunnel list
**/
static struct ip6_tnl __rcu **
ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p)
{
struct in6_addr *remote = &p->raddr;
struct in6_addr *local = &p->laddr;
unsigned h = 0;
int prio = 0;
if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) {
prio = 1;
h = HASH(remote) ^ HASH(local);
}
return &ip6n->tnls[prio][h];
}
/**
* ip6_tnl_link - add tunnel to hash table
* @t: tunnel to be added
**/
static void
ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms);
rcu_assign_pointer(t->next , rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
/**
* ip6_tnl_unlink - remove tunnel from hash table
* @t: tunnel to be removed
**/
static void
ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
struct ip6_tnl __rcu **tp;
struct ip6_tnl *iter;
for (tp = ip6_tnl_bucket(ip6n, &t->parms);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
if (t == iter) {
rcu_assign_pointer(*tp, t->next);
break;
}
}
}
/**
* ip6_tnl_create() - create a new tunnel
* @p: tunnel parameters
* @pt: pointer to new tunnel
*
* Description:
* Create tunnel matching given parameters.
*
* Return:
* created tunnel or NULL
**/
static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p)
{
struct net_device *dev;
struct ip6_tnl *t;
char name[IFNAMSIZ];
int err;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (p->name[0])
strlcpy(name, p->name, IFNAMSIZ);
else
sprintf(name, "ip6tnl%%d");
dev = alloc_netdev(sizeof (*t), name, ip6_tnl_dev_setup);
if (dev == NULL)
goto failed;
dev_net_set(dev, net);
if (strchr(name, '%')) {
if (dev_alloc_name(dev, name) < 0)
goto failed_free;
}
t = netdev_priv(dev);
t->parms = *p;
ip6_tnl_dev_init(dev);
if ((err = register_netdevice(dev)) < 0)
goto failed_free;
dev_hold(dev);
ip6_tnl_link(ip6n, t);
return t;
failed_free:
free_netdev(dev);
failed:
return NULL;
}
/**
* ip6_tnl_locate - find or create tunnel matching given parameters
* @p: tunnel parameters
* @create: != 0 if allowed to create new tunnel if no match found
*
* Description:
* ip6_tnl_locate() first tries to locate an existing tunnel
* based on @parms. If this is unsuccessful, but @create is set a new
* tunnel device is created and registered for use.
*
* Return:
* matching tunnel or NULL
**/
static struct ip6_tnl *ip6_tnl_locate(struct net *net,
struct ip6_tnl_parm *p, int create)
{
struct in6_addr *remote = &p->raddr;
struct in6_addr *local = &p->laddr;
struct ip6_tnl __rcu **tp;
struct ip6_tnl *t;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
for (tp = ip6_tnl_bucket(ip6n, p);
(t = rtnl_dereference(*tp)) != NULL;
tp = &t->next) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_equal(remote, &t->parms.raddr))
return t;
}
if (!create)
return NULL;
return ip6_tnl_create(net, p);
}
/**
* ip6_tnl_dev_uninit - tunnel device uninitializer
* @dev: the device to be destroyed
*
* Description:
* ip6_tnl_dev_uninit() removes tunnel from its list
**/
static void
ip6_tnl_dev_uninit(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev == ip6n->fb_tnl_dev)
rcu_assign_pointer(ip6n->tnls_wc[0], NULL);
else
ip6_tnl_unlink(ip6n, t);
ip6_tnl_dst_reset(t);
dev_put(dev);
}
/**
* parse_tvl_tnl_enc_lim - handle encapsulation limit option
* @skb: received socket buffer
*
* Return:
* 0 if none was found,
* else index to encapsulation limit
**/
static __u16
parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw)
{
struct ipv6hdr *ipv6h = (struct ipv6hdr *) raw;
__u8 nexthdr = ipv6h->nexthdr;
__u16 off = sizeof (*ipv6h);
while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
__u16 optlen = 0;
struct ipv6_opt_hdr *hdr;
if (raw + off + sizeof (*hdr) > skb->data &&
!pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
break;
hdr = (struct ipv6_opt_hdr *) (raw + off);
if (nexthdr == NEXTHDR_FRAGMENT) {
struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
if (frag_hdr->frag_off)
break;
optlen = 8;
} else if (nexthdr == NEXTHDR_AUTH) {
optlen = (hdr->hdrlen + 2) << 2;
} else {
optlen = ipv6_optlen(hdr);
}
if (nexthdr == NEXTHDR_DEST) {
__u16 i = off + 2;
while (1) {
struct ipv6_tlv_tnl_enc_lim *tel;
/* No more room for encapsulation limit */
if (i + sizeof (*tel) > off + optlen)
break;
tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i];
/* return index of option if found and valid */
if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
tel->length == 1)
return i;
/* else jump to next option */
if (tel->type)
i += tel->length + 2;
else
i++;
}
}
nexthdr = hdr->nexthdr;
off += optlen;
}
return 0;
}
/**
* ip6_tnl_err - tunnel error handler
*
* Description:
* ip6_tnl_err() should handle errors in the tunnel according
* to the specifications in RFC 2473.
**/
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:12:13 +00:00
static int
ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
u8 *type, u8 *code, int *msg, __u32 *info, int offset)
{
struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data;
struct ip6_tnl *t;
int rel_msg = 0;
u8 rel_type = ICMPV6_DEST_UNREACH;
u8 rel_code = ICMPV6_ADDR_UNREACH;
__u32 rel_info = 0;
__u16 len;
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:12:13 +00:00
int err = -ENOENT;
/* If the packet doesn't contain the original IPv6 header we are
in trouble since we might need the source address for further
processing of the error. */
rcu_read_lock();
if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr,
&ipv6h->saddr)) == NULL)
goto out;
if (t->parms.proto != ipproto && t->parms.proto != 0)
goto out;
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:12:13 +00:00
err = 0;
switch (*type) {
__u32 teli;
struct ipv6_tlv_tnl_enc_lim *tel;
__u32 mtu;
case ICMPV6_DEST_UNREACH:
if (net_ratelimit())
printk(KERN_WARNING
"%s: Path to destination invalid "
"or inactive!\n", t->parms.name);
rel_msg = 1;
break;
case ICMPV6_TIME_EXCEED:
if ((*code) == ICMPV6_EXC_HOPLIMIT) {
if (net_ratelimit())
printk(KERN_WARNING
"%s: Too small hop limit or "
"routing loop in tunnel!\n",
t->parms.name);
rel_msg = 1;
}
break;
case ICMPV6_PARAMPROB:
teli = 0;
if ((*code) == ICMPV6_HDR_FIELD)
teli = parse_tlv_tnl_enc_lim(skb, skb->data);
if (teli && teli == *info - 2) {
tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
if (tel->encap_limit == 0) {
if (net_ratelimit())
printk(KERN_WARNING
"%s: Too small encapsulation "
"limit or routing loop in "
"tunnel!\n", t->parms.name);
rel_msg = 1;
}
} else if (net_ratelimit()) {
printk(KERN_WARNING
"%s: Recipient unable to parse tunneled "
"packet!\n ", t->parms.name);
}
break;
case ICMPV6_PKT_TOOBIG:
mtu = *info - offset;
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
t->dev->mtu = mtu;
if ((len = sizeof (*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) {
rel_type = ICMPV6_PKT_TOOBIG;
rel_code = 0;
rel_info = mtu;
rel_msg = 1;
}
break;
}
*type = rel_type;
*code = rel_code;
*info = rel_info;
*msg = rel_msg;
out:
rcu_read_unlock();
return err;
}
static int
ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
int rel_msg = 0;
u8 rel_type = type;
u8 rel_code = code;
__u32 rel_info = ntohl(info);
int err;
struct sk_buff *skb2;
struct iphdr *eiph;
struct flowi fl;
struct rtable *rt;
err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code,
&rel_msg, &rel_info, offset);
if (err < 0)
return err;
if (rel_msg == 0)
return 0;
switch (rel_type) {
case ICMPV6_DEST_UNREACH:
if (rel_code != ICMPV6_ADDR_UNREACH)
return 0;
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_HOST_UNREACH;
break;
case ICMPV6_PKT_TOOBIG:
if (rel_code != 0)
return 0;
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_FRAG_NEEDED;
break;
default:
return 0;
}
if (!pskb_may_pull(skb, offset + sizeof(struct iphdr)))
return 0;
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
return 0;
skb_dst_drop(skb2);
skb_pull(skb2, offset);
skb_reset_network_header(skb2);
eiph = ip_hdr(skb2);
/* Try to guess incoming interface */
memset(&fl, 0, sizeof(fl));
fl.fl4_dst = eiph->saddr;
fl.fl4_tos = RT_TOS(eiph->tos);
fl.proto = IPPROTO_IPIP;
if (ip_route_output_key(dev_net(skb->dev), &rt, &fl))
goto out;
skb2->dev = rt->dst.dev;
/* route "incoming" packet */
if (rt->rt_flags & RTCF_LOCAL) {
ip_rt_put(rt);
rt = NULL;
fl.fl4_dst = eiph->daddr;
fl.fl4_src = eiph->saddr;
fl.fl4_tos = eiph->tos;
if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) ||
rt->dst.dev->type != ARPHRD_TUNNEL) {
ip_rt_put(rt);
goto out;
}
skb_dst_set(skb2, (struct dst_entry *)rt);
} else {
ip_rt_put(rt);
if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
skb2->dev) ||
skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
goto out;
}
/* change mtu on this route */
if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) {
if (rel_info > dst_mtu(skb_dst(skb2)))
goto out;
skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info);
}
icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
out:
kfree_skb(skb2);
return 0;
}
static int
ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
int rel_msg = 0;
u8 rel_type = type;
u8 rel_code = code;
__u32 rel_info = ntohl(info);
int err;
err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code,
&rel_msg, &rel_info, offset);
if (err < 0)
return err;
if (rel_msg && pskb_may_pull(skb, offset + sizeof(struct ipv6hdr))) {
struct rt6_info *rt;
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
return 0;
skb_dst_drop(skb2);
skb_pull(skb2, offset);
skb_reset_network_header(skb2);
/* Try to guess incoming interface */
rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr,
NULL, 0, 0);
if (rt && rt->rt6i_dev)
skb2->dev = rt->rt6i_dev;
icmpv6_send(skb2, rel_type, rel_code, rel_info);
if (rt)
dst_release(&rt->dst);
kfree_skb(skb2);
}
return 0;
}
static void ip4ip6_dscp_ecn_decapsulate(struct ip6_tnl *t,
struct ipv6hdr *ipv6h,
struct sk_buff *skb)
{
__u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK;
if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield);
if (INET_ECN_is_ce(dsfield))
IP_ECN_set_ce(ip_hdr(skb));
}
static void ip6ip6_dscp_ecn_decapsulate(struct ip6_tnl *t,
struct ipv6hdr *ipv6h,
struct sk_buff *skb)
{
if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb));
if (INET_ECN_is_ce(ipv6_get_dsfield(ipv6h)))
IP6_ECN_set_ce(ipv6_hdr(skb));
}
/* called with rcu_read_lock() */
static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t)
{
struct ip6_tnl_parm *p = &t->parms;
int ret = 0;
struct net *net = dev_net(t->dev);
if (p->flags & IP6_TNL_F_CAP_RCV) {
struct net_device *ldev = NULL;
if (p->link)
ldev = dev_get_by_index_rcu(net, p->link);
if ((ipv6_addr_is_multicast(&p->laddr) ||
likely(ipv6_chk_addr(net, &p->laddr, ldev, 0))) &&
likely(!ipv6_chk_addr(net, &p->raddr, NULL, 0)))
ret = 1;
}
return ret;
}
/**
* ip6_tnl_rcv - decapsulate IPv6 packet and retransmit it locally
* @skb: received socket buffer
* @protocol: ethernet protocol ID
* @dscp_ecn_decapsulate: the function to decapsulate DSCP code and ECN
*
* Return: 0
**/
static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
__u8 ipproto,
void (*dscp_ecn_decapsulate)(struct ip6_tnl *t,
struct ipv6hdr *ipv6h,
struct sk_buff *skb))
{
struct ip6_tnl *t;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
rcu_read_lock();
if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr,
&ipv6h->daddr)) != NULL) {
if (t->parms.proto != ipproto && t->parms.proto != 0) {
rcu_read_unlock();
goto discard;
}
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
rcu_read_unlock();
goto discard;
}
if (!ip6_tnl_rcv_ctl(t)) {
t->dev->stats.rx_dropped++;
rcu_read_unlock();
goto discard;
}
secpath_reset(skb);
skb->mac_header = skb->network_header;
skb_reset_network_header(skb);
skb->protocol = htons(protocol);
skb->pkt_type = PACKET_HOST;
memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
skb_tunnel_rx(skb, t->dev);
dscp_ecn_decapsulate(t, ipv6h, skb);
if (netif_rx(skb) == NET_RX_DROP)
t->dev->stats.rx_dropped++;
rcu_read_unlock();
return 0;
}
rcu_read_unlock();
return 1;
discard:
kfree_skb(skb);
return 0;
}
static int ip4ip6_rcv(struct sk_buff *skb)
{
return ip6_tnl_rcv(skb, ETH_P_IP, IPPROTO_IPIP,
ip4ip6_dscp_ecn_decapsulate);
}
static int ip6ip6_rcv(struct sk_buff *skb)
{
return ip6_tnl_rcv(skb, ETH_P_IPV6, IPPROTO_IPV6,
ip6ip6_dscp_ecn_decapsulate);
}
struct ipv6_tel_txoption {
struct ipv6_txoptions ops;
__u8 dst_opt[8];
};
static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit)
{
memset(opt, 0, sizeof(struct ipv6_tel_txoption));
opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT;
opt->dst_opt[3] = 1;
opt->dst_opt[4] = encap_limit;
opt->dst_opt[5] = IPV6_TLV_PADN;
opt->dst_opt[6] = 1;
opt->ops.dst0opt = (struct ipv6_opt_hdr *) opt->dst_opt;
opt->ops.opt_nflen = 8;
}
/**
* ip6_tnl_addr_conflict - compare packet addresses to tunnel's own
* @t: the outgoing tunnel device
* @hdr: IPv6 header from the incoming packet
*
* Description:
* Avoid trivial tunneling loop by checking that tunnel exit-point
* doesn't match source of incoming packet.
*
* Return:
* 1 if conflict,
* 0 else
**/
static inline int
ip6_tnl_addr_conflict(struct ip6_tnl *t, struct ipv6hdr *hdr)
{
return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
}
static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
{
struct ip6_tnl_parm *p = &t->parms;
int ret = 0;
struct net *net = dev_net(t->dev);
if (p->flags & IP6_TNL_F_CAP_XMIT) {
struct net_device *ldev = NULL;
rcu_read_lock();
if (p->link)
ldev = dev_get_by_index_rcu(net, p->link);
if (unlikely(!ipv6_chk_addr(net, &p->laddr, ldev, 0)))
printk(KERN_WARNING
"%s xmit: Local address not yet configured!\n",
p->name);
else if (!ipv6_addr_is_multicast(&p->raddr) &&
unlikely(ipv6_chk_addr(net, &p->raddr, NULL, 0)))
printk(KERN_WARNING
"%s xmit: Routing loop! "
"Remote address found on this node!\n",
p->name);
else
ret = 1;
rcu_read_unlock();
}
return ret;
}
/**
* ip6_tnl_xmit2 - encapsulate packet and send
* @skb: the outgoing socket buffer
* @dev: the outgoing tunnel device
* @dsfield: dscp code for outer header
* @fl: flow of tunneled packet
* @encap_limit: encapsulation limit
* @pmtu: Path MTU is stored if packet is too big
*
* Description:
* Build new header and do some sanity checks on the packet before sending
* it.
*
* Return:
* 0 on success
* -1 fail
* %-EMSGSIZE message too big. return mtu in this case.
**/
static int ip6_tnl_xmit2(struct sk_buff *skb,
struct net_device *dev,
__u8 dsfield,
struct flowi *fl,
int encap_limit,
__u32 *pmtu)
{
struct net *net = dev_net(dev);
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->dev->stats;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct ipv6_tel_txoption opt;
struct dst_entry *dst;
struct net_device *tdev;
int mtu;
unsigned int max_headroom = sizeof(struct ipv6hdr);
u8 proto;
int err = -1;
int pkt_len;
if ((dst = ip6_tnl_dst_check(t)) != NULL)
dst_hold(dst);
else {
dst = ip6_route_output(net, NULL, fl);
if (dst->error || xfrm_lookup(net, &dst, fl, NULL, 0) < 0)
goto tx_err_link_failure;
}
tdev = dst->dev;
if (tdev == dev) {
stats->collisions++;
if (net_ratelimit())
printk(KERN_WARNING
"%s: Local routing loop detected!\n",
t->parms.name);
goto tx_err_dst_release;
}
mtu = dst_mtu(dst) - sizeof (*ipv6h);
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (skb->len > mtu) {
*pmtu = mtu;
err = -EMSGSIZE;
goto tx_err_dst_release;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom += LL_RESERVED_SPACE(tdev);
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb;
if (!(new_skb = skb_realloc_headroom(skb, max_headroom)))
goto tx_err_dst_release;
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
kfree_skb(skb);
skb = new_skb;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst_clone(dst));
skb->transport_header = skb->network_header;
proto = fl->proto;
if (encap_limit >= 0) {
init_tel_txopt(&opt, encap_limit);
ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
*(__be32*)ipv6h = fl->fl6_flowlabel | htonl(0x60000000);
dsfield = INET_ECN_encapsulate(0, dsfield);
ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = proto;
ipv6_addr_copy(&ipv6h->saddr, &fl->fl6_src);
ipv6_addr_copy(&ipv6h->daddr, &fl->fl6_dst);
nf_reset(skb);
pkt_len = skb->len;
err = ip6_local_out(skb);
if (net_xmit_eval(err) == 0) {
stats->tx_bytes += pkt_len;
stats->tx_packets++;
} else {
stats->tx_errors++;
stats->tx_aborted_errors++;
}
ip6_tnl_dst_store(t, dst);
return 0;
tx_err_link_failure:
stats->tx_carrier_errors++;
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
return err;
}
static inline int
ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct iphdr *iph = ip_hdr(skb);
int encap_limit = -1;
struct flowi fl;
__u8 dsfield;
__u32 mtu;
int err;
if ((t->parms.proto != IPPROTO_IPIP && t->parms.proto != 0) ||
!ip6_tnl_xmit_ctl(t))
return -1;
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_IPIP;
dsfield = ipv4_get_dsfield(iph);
if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
fl.fl6_flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
& IPV6_TCLASS_MASK;
err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
if (err != 0) {
/* XXX: send ICMP error even if DF is not set. */
if (err == -EMSGSIZE)
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
return -1;
}
return 0;
}
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);
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);
return -1;
}
return 0;
}
static netdev_tx_t
ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->dev->stats;
int ret;
switch (skb->protocol) {
case htons(ETH_P_IP):
ret = ip4ip6_tnl_xmit(skb, dev);
break;
case htons(ETH_P_IPV6):
ret = ip6ip6_tnl_xmit(skb, dev);
break;
default:
goto tx_err;
}
if (ret < 0)
goto tx_err;
return NETDEV_TX_OK;
tx_err:
stats->tx_errors++;
stats->tx_dropped++;
kfree_skb(skb);
return NETDEV_TX_OK;
}
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(dev_net(dev),
&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->dst);
}
}
/**
* ip6_tnl_change - update the tunnel parameters
* @t: tunnel to be changed
* @p: tunnel configuration parameters
*
* 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;
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
switch (cmd) {
case SIOCGETTUNNEL:
if (dev == ip6n->fb_tnl_dev) {
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) {
err = -EFAULT;
break;
}
t = ip6_tnl_locate(net, &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(net, &p, cmd == SIOCADDTUNNEL);
if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) {
if (t != NULL) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
} else
t = netdev_priv(dev);
ip6_tnl_unlink(ip6n, t);
err = ip6_tnl_change(t, &p);
ip6_tnl_link(ip6n, 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 == ip6n->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(net, &p, 0)) == NULL)
break;
err = -EPERM;
if (t->dev == ip6n->fb_tnl_dev)
break;
dev = t->dev;
}
err = 0;
unregister_netdevice(dev);
break;
default:
err = -EINVAL;
}
return err;
}
/**
* 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;
}
static const struct net_device_ops ip6_tnl_netdev_ops = {
.ndo_uninit = ip6_tnl_dev_uninit,
.ndo_start_xmit = ip6_tnl_xmit,
.ndo_do_ioctl = ip6_tnl_ioctl,
.ndo_change_mtu = ip6_tnl_change_mtu,
};
/**
* 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->netdev_ops = &ip6_tnl_netdev_ops;
dev->destructor = free_netdev;
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);
dev->features |= NETIF_F_NETNS_LOCAL;
}
/**
* 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 void 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);
}
/**
* ip6_fb_tnl_dev_init - initializer for fallback tunnel device
* @dev: fallback device
*
* Return: 0
**/
static void __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
ip6_tnl_dev_init_gen(dev);
t->parms.proto = IPPROTO_IPV6;
dev_hold(dev);
rcu_assign_pointer(ip6n->tnls_wc[0], t);
}
static struct xfrm6_tunnel ip4ip6_handler __read_mostly = {
.handler = ip4ip6_rcv,
.err_handler = ip4ip6_err,
.priority = 1,
};
static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
.handler = ip6ip6_rcv,
.err_handler = ip6ip6_err,
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:12:13 +00:00
.priority = 1,
};
static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
{
int h;
struct ip6_tnl *t;
LIST_HEAD(list);
for (h = 0; h < HASH_SIZE; h++) {
t = rtnl_dereference(ip6n->tnls_r_l[h]);
while (t != NULL) {
unregister_netdevice_queue(t->dev, &list);
t = rtnl_dereference(t->next);
}
}
t = rtnl_dereference(ip6n->tnls_wc[0]);
unregister_netdevice_queue(t->dev, &list);
unregister_netdevice_many(&list);
}
static int __net_init ip6_tnl_init_net(struct net *net)
{
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
int err;
ip6n->tnls[0] = ip6n->tnls_wc;
ip6n->tnls[1] = ip6n->tnls_r_l;
err = -ENOMEM;
ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0",
ip6_tnl_dev_setup);
if (!ip6n->fb_tnl_dev)
goto err_alloc_dev;
net: fix tunnels in netns after ndo_ changes dev_net_set() should be the very first thing after alloc_netdev(). "ndo_" changes turned simple assignment (which is OK to do before netns assignment) into quite non-trivial operation (which is not OK, init_net was used). This leads to incomplete initialisation of tunnel device in netns. BUG: unable to handle kernel NULL pointer dereference at 00000004 IP: [<c02efdb5>] ip6_tnl_exit_net+0x37/0x4f *pde = 00000000 Oops: 0000 [#1] PREEMPT DEBUG_PAGEALLOC last sysfs file: /sys/class/net/lo/operstate Pid: 10, comm: netns Not tainted (2.6.28-rc6 #1) EIP: 0060:[<c02efdb5>] EFLAGS: 00010246 CPU: 0 EIP is at ip6_tnl_exit_net+0x37/0x4f EAX: 00000000 EBX: 00000020 ECX: 00000000 EDX: 00000003 ESI: c5caef30 EDI: c782bbe8 EBP: c7909f50 ESP: c7909f48 DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068 Process netns (pid: 10, ti=c7908000 task=c7905780 task.ti=c7908000) Stack: c03e75e0 c7390bc8 c7909f60 c0245448 c7390bd8 c7390bf0 c7909fa8 c012577a 00000000 00000002 00000000 c0125736 c782bbe8 c7909f90 c0308fe3 c782bc04 c7390bd4 c0245406 c084b718 c04f0770 c03ad785 c782bbe8 c782bc04 c782bc0c Call Trace: [<c0245448>] ? cleanup_net+0x42/0x82 [<c012577a>] ? run_workqueue+0xd6/0x1ae [<c0125736>] ? run_workqueue+0x92/0x1ae [<c0308fe3>] ? schedule+0x275/0x285 [<c0245406>] ? cleanup_net+0x0/0x82 [<c0125ae1>] ? worker_thread+0x81/0x8d [<c0128344>] ? autoremove_wake_function+0x0/0x33 [<c0125a60>] ? worker_thread+0x0/0x8d [<c012815c>] ? kthread+0x39/0x5e [<c0128123>] ? kthread+0x0/0x5e [<c0103b9f>] ? kernel_thread_helper+0x7/0x10 Code: db e8 05 ff ff ff 89 c6 e8 dc 04 f6 ff eb 08 8b 40 04 e8 38 89 f5 ff 8b 44 9e 04 85 c0 75 f0 43 83 fb 20 75 f2 8b 86 84 00 00 00 <8b> 40 04 e8 1c 89 f5 ff e8 98 04 f6 ff 89 f0 e8 f8 63 e6 ff 5b EIP: [<c02efdb5>] ip6_tnl_exit_net+0x37/0x4f SS:ESP 0068:c7909f48 ---[ end trace 6c2f2328fccd3e0c ]--- Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-24 01:26:26 +00:00
dev_net_set(ip6n->fb_tnl_dev, net);
ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
err = register_netdev(ip6n->fb_tnl_dev);
if (err < 0)
goto err_register;
return 0;
err_register:
free_netdev(ip6n->fb_tnl_dev);
err_alloc_dev:
return err;
}
static void __net_exit ip6_tnl_exit_net(struct net *net)
{
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
rtnl_lock();
ip6_tnl_destroy_tunnels(ip6n);
rtnl_unlock();
}
static struct pernet_operations ip6_tnl_net_ops = {
.init = ip6_tnl_init_net,
.exit = ip6_tnl_exit_net,
.id = &ip6_tnl_net_id,
.size = sizeof(struct ip6_tnl_net),
};
/**
* ip6_tunnel_init - register protocol and reserve needed resources
*
* Return: 0 on success
**/
static int __init ip6_tunnel_init(void)
{
int err;
err = register_pernet_device(&ip6_tnl_net_ops);
if (err < 0)
goto out_pernet;
err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET);
if (err < 0) {
printk(KERN_ERR "ip6_tunnel init: can't register ip4ip6\n");
goto out_ip4ip6;
}
err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6);
if (err < 0) {
printk(KERN_ERR "ip6_tunnel init: can't register ip6ip6\n");
goto out_ip6ip6;
}
return 0;
out_ip6ip6:
xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET);
out_ip4ip6:
unregister_pernet_device(&ip6_tnl_net_ops);
out_pernet:
return err;
}
/**
* 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");
unregister_pernet_device(&ip6_tnl_net_ops);
}
module_init(ip6_tunnel_init);
module_exit(ip6_tunnel_cleanup);