Commit 58a317f1 authored by Patrick McHardy's avatar Patrick McHardy Committed by Pablo Neira Ayuso
Browse files

netfilter: ipv6: add IPv6 NAT support


Signed-off-by: default avatarPatrick McHardy <kaber@trash.net>
parent 2cf545e8
......@@ -147,6 +147,8 @@ enum ctattr_nat {
CTA_NAT_V4_MAXIP,
#define CTA_NAT_MAXIP CTA_NAT_V4_MAXIP
CTA_NAT_PROTO,
CTA_NAT_V6_MINIP,
CTA_NAT_V6_MAXIP,
__CTA_NAT_MAX
};
#define CTA_NAT_MAX (__CTA_NAT_MAX - 1)
......
......@@ -43,5 +43,10 @@ extern int nf_nat_icmp_reply_translation(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int hooknum);
extern int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
unsigned int hooknum,
unsigned int hdrlen);
#endif /* _NF_NAT_L3PROTO_H */
......@@ -51,6 +51,7 @@ extern const struct nf_nat_l4proto *__nf_nat_l4proto_find(u8 l3proto, u8 l4proto
extern const struct nf_nat_l4proto nf_nat_l4proto_tcp;
extern const struct nf_nat_l4proto nf_nat_l4proto_udp;
extern const struct nf_nat_l4proto nf_nat_l4proto_icmp;
extern const struct nf_nat_l4proto nf_nat_l4proto_icmpv6;
extern const struct nf_nat_l4proto nf_nat_l4proto_unknown;
extern bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
......
......@@ -42,6 +42,7 @@ struct netns_ipv6 {
#ifdef CONFIG_SECURITY
struct xt_table *ip6table_security;
#endif
struct xt_table *ip6table_nat;
#endif
struct rt6_info *ip6_null_entry;
struct rt6_statistics *rt6_stats;
......
......@@ -76,6 +76,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
return hash[0];
}
EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
#endif
#ifdef CONFIG_INET
......
......@@ -25,6 +25,18 @@ config NF_CONNTRACK_IPV6
To compile it as a module, choose M here. If unsure, say N.
config NF_NAT_IPV6
tristate "IPv6 NAT"
depends on NF_CONNTRACK_IPV6
depends on NETFILTER_ADVANCED
select NF_NAT
help
The IPv6 NAT option allows masquerading, port forwarding and other
forms of full Network Address Port Translation. It is controlled by
the `nat' table in ip6tables, see the man page for ip6tables(8).
To compile it as a module, choose M here. If unsure, say N.
config IP6_NF_IPTABLES
tristate "IP6 tables support (required for filtering)"
depends on INET && IPV6
......
......@@ -8,6 +8,7 @@ obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o
obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o
obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o
obj-$(CONFIG_NF_NAT_IPV6) += ip6table_nat.o
# objects for l3 independent conntrack
nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o
......@@ -15,6 +16,9 @@ nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o
# l3 independent conntrack
obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_defrag_ipv6.o
nf_nat_ipv6-y := nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
# defrag
nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
......
/*
* Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Based on Rusty Russell's IPv4 NAT code. Development of IPv6 NAT
* funded by Astaro.
*/
#include <linux/module.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <linux/ipv6.h>
#include <net/ipv6.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
static const struct xt_table nf_nat_ipv6_table = {
.name = "nat",
.valid_hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_POST_ROUTING) |
(1 << NF_INET_LOCAL_OUT) |
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
.af = NFPROTO_IPV6,
};
static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
{
/* Force range to this IP; let proto decide mapping for
* per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
*/
struct nf_nat_range range;
range.flags = 0;
pr_debug("Allocating NULL binding for %p (%pI6)\n", ct,
HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
&ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip6 :
&ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip6);
return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
}
static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
const struct net_device *in,
const struct net_device *out,
struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
unsigned int ret;
ret = ip6t_do_table(skb, hooknum, in, out, net->ipv6.ip6table_nat);
if (ret == NF_ACCEPT) {
if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
ret = alloc_null_binding(ct, hooknum);
}
return ret;
}
static unsigned int
nf_nat_ipv6_fn(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
__be16 frag_off;
int hdrlen;
u8 nexthdr;
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
* have dropped it. Hence it's the user's responsibilty to
* packet filter it out, or implement conntrack/NAT for that
* protocol. 8) --RR
*/
if (!ct)
return NF_ACCEPT;
/* Don't try to NAT if this packet is not conntracked */
if (nf_ct_is_untracked(ct))
return NF_ACCEPT;
nat = nfct_nat(ct);
if (!nat) {
/* NAT module was loaded late. */
if (nf_ct_is_confirmed(ct))
return NF_ACCEPT;
nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
if (nat == NULL) {
pr_debug("failed to add NAT extension\n");
return NF_ACCEPT;
}
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
nexthdr = ipv6_hdr(skb)->nexthdr;
hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
&nexthdr, &frag_off);
if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
hooknum, hdrlen))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
* or local packets.
*/
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
if (ret != NF_ACCEPT)
return ret;
} else
pr_debug("Already setup manip %s for ct %p\n",
maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
break;
default:
/* ESTABLISHED */
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == IP_CT_ESTABLISHED_REPLY);
}
return nf_nat_packet(ct, ctinfo, hooknum, skb);
}
static unsigned int
nf_nat_ipv6_in(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
unsigned int ret;
struct in6_addr daddr = ipv6_hdr(skb)->daddr;
ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
if (ret != NF_DROP && ret != NF_STOLEN &&
ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
skb_dst_drop(skb);
return ret;
}
static unsigned int
nf_nat_ipv6_out(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
#ifdef CONFIG_XFRM
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
#endif
unsigned int ret;
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct ipv6hdr))
return NF_ACCEPT;
ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
#ifdef CONFIG_XFRM
if (ret != NF_DROP && ret != NF_STOLEN &&
!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
(ct = nf_ct_get(skb, &ctinfo)) != NULL) {
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3) ||
(ct->tuplehash[dir].tuple.src.u.all !=
ct->tuplehash[!dir].tuple.dst.u.all))
if (nf_xfrm_me_harder(skb, AF_INET6) < 0)
ret = NF_DROP;
}
#endif
return ret;
}
static unsigned int
nf_nat_ipv6_local_fn(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
unsigned int ret;
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct ipv6hdr))
return NF_ACCEPT;
ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
if (ret != NF_DROP && ret != NF_STOLEN &&
(ct = nf_ct_get(skb, &ctinfo)) != NULL) {
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
&ct->tuplehash[!dir].tuple.src.u3)) {
if (ip6_route_me_harder(skb))
ret = NF_DROP;
}
#ifdef CONFIG_XFRM
else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
ct->tuplehash[dir].tuple.dst.u.all !=
ct->tuplehash[!dir].tuple.src.u.all)
if (nf_xfrm_me_harder(skb, AF_INET6))
ret = NF_DROP;
#endif
}
return ret;
}
static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
/* Before packet filtering, change destination */
{
.hook = nf_nat_ipv6_in,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP6_PRI_NAT_DST,
},
/* After packet filtering, change source */
{
.hook = nf_nat_ipv6_out,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP6_PRI_NAT_SRC,
},
/* Before packet filtering, change destination */
{
.hook = nf_nat_ipv6_local_fn,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP6_PRI_NAT_DST,
},
/* After packet filtering, change source */
{
.hook = nf_nat_ipv6_fn,
.owner = THIS_MODULE,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP6_PRI_NAT_SRC,
},
};
static int __net_init ip6table_nat_net_init(struct net *net)
{
struct ip6t_replace *repl;
repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table);
if (repl == NULL)
return -ENOMEM;
net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl);
kfree(repl);
if (IS_ERR(net->ipv6.ip6table_nat))
return PTR_ERR(net->ipv6.ip6table_nat);
return 0;
}
static void __net_exit ip6table_nat_net_exit(struct net *net)
{
ip6t_unregister_table(net, net->ipv6.ip6table_nat);
}
static struct pernet_operations ip6table_nat_net_ops = {
.init = ip6table_nat_net_init,
.exit = ip6table_nat_net_exit,
};
static int __init ip6table_nat_init(void)
{
int err;
err = register_pernet_subsys(&ip6table_nat_net_ops);
if (err < 0)
goto err1;
err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
if (err < 0)
goto err2;
return 0;
err2:
unregister_pernet_subsys(&ip6table_nat_net_ops);
err1:
return err;
}
static void __exit ip6table_nat_exit(void)
{
nf_unregister_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
unregister_pernet_subsys(&ip6table_nat_net_ops);
}
module_init(ip6table_nat_init);
module_exit(ip6table_nat_exit);
MODULE_LICENSE("GPL");
......@@ -28,6 +28,7 @@
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
#include <net/netfilter/nf_nat_helper.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <net/netfilter/nf_log.h>
......@@ -142,6 +143,36 @@ static unsigned int ipv6_confirm(unsigned int hooknum,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
unsigned char pnum = ipv6_hdr(skb)->nexthdr;
int protoff;
__be16 frag_off;
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
goto out;
protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
&frag_off);
if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
pr_debug("proto header not found\n");
goto out;
}
/* adjust seqs for loopback traffic only in outgoing direction */
if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
!nf_is_loopback_packet(skb)) {
typeof(nf_nat_seq_adjust_hook) seq_adjust;
seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
if (!seq_adjust ||
!seq_adjust(skb, ct, ctinfo, protoff)) {
NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
return NF_DROP;
}
}
out:
/* We've seen it coming out the other side: confirm it */
return nf_conntrack_confirm(skb);
}
......@@ -170,12 +201,14 @@ static unsigned int __ipv6_conntrack_in(struct net *net,
}
/* Conntrack helpers need the entire reassembled packet in the
* POST_ROUTING hook.
* POST_ROUTING hook. In case of unconfirmed connections NAT
* might reassign a helper, so the entire packet is also
* required.
*/
ct = nf_ct_get(reasm, &ctinfo);
if (ct != NULL && !nf_ct_is_untracked(ct)) {
help = nfct_help(ct);
if (help && help->helper) {
if ((help && help->helper) || !nf_ct_is_confirmed(ct)) {
nf_conntrack_get_reasm(skb);
NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
(struct net_device *)in,
......
/*
* Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Development of IPv6 NAT funded by Astaro.
*/
#include <linux/types.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/ipv6.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
#include <net/secure_seq.h>
#include <net/checksum.h>
#include <net/ip6_route.h>
#include <net/ipv6.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
#include <net/netfilter/nf_nat_l4proto.h>
static const struct nf_nat_l3proto nf_nat_l3proto_ipv6;
#ifdef CONFIG_XFRM
static void nf_nat_ipv6_decode_session(struct sk_buff *skb,
const struct nf_conn *ct,
enum ip_conntrack_dir dir,
unsigned long statusbit,
struct flowi *fl)
{
const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple;
struct flowi6 *fl6 = &fl->u.ip6;
if (ct->status & statusbit) {
fl6->daddr = t->dst.u3.in6;
if (t->dst.protonum == IPPROTO_TCP ||
t->dst.protonum == IPPROTO_UDP ||
t->dst.protonum == IPPROTO_UDPLITE ||
t->dst.protonum == IPPROTO_DCCP ||
t->dst.protonum == IPPROTO_SCTP)
fl6->fl6_dport = t->dst.u.all;
}
statusbit ^= IPS_NAT_MASK;
if (ct->status & statusbit) {
fl6->saddr = t->src.u3.in6;
if (t->dst.protonum == IPPROTO_TCP ||
t->dst.protonum == IPPROTO_UDP ||
t->dst.protonum == IPPROTO_UDPLITE ||
t->dst.protonum == IPPROTO_DCCP ||
t->dst.protonum == IPPROTO_SCTP)
fl6->fl6_sport = t->src.u.all;
}
}
#endif
static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t,
const struct nf_nat_range *range)
{
return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 &&
ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0;
}
static u32 nf_nat_ipv6_secure_port(const struct nf_conntrack_tuple *t,
__be16 dport)
{
return secure_ipv6_port_ephemeral(t->src.u3.ip6, t->dst.u3.ip6, dport);
}
static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
unsigned int iphdroff,
const struct nf_nat_l4proto *l4proto,
const struct nf_conntrack_tuple *target,
enum nf_nat_manip_type maniptype)
{
struct ipv6hdr *ipv6h;
__be16 frag_off;
int hdroff;
u8 nexthdr;
if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h)))
return false;
ipv6h = (void *)skb->data + iphdroff;
nexthdr = ipv6h->nexthdr;
hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h),
&nexthdr, &frag_off);
if (hdroff < 0)
goto manip_addr;
if ((frag_off & htons(~0x7)) == 0 &&
!l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff,
target, maniptype))
return false;
manip_addr:
if (maniptype == NF_NAT_MANIP_SRC)
ipv6h->saddr = target->src.u3.in6;
else
ipv6h->daddr = target->dst.u3.in6;
return true;
}
static void nf_nat_ipv6_csum_update(struct sk_buff *skb,
unsigned int iphdroff, __sum16 *check,
const struct nf_conntrack_tuple *t,
enum nf_nat_manip_type maniptype)
{
const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff);
const struct in6_addr *oldip, *newip;
if (maniptype == NF_NAT_MANIP_SRC) {
oldip = &ipv6h->saddr;
newip = &t->src.u3.in6;
} else {
oldip = &ipv6h->daddr;
newip = &t->dst.u3.in6;
}
inet_proto_csum_replace16(check, skb, oldip->s6_addr32,
newip->s6_addr32, 1);
}
static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb,
u8 proto, void *data, __sum16 *check,
int datalen, int oldlen)
{
const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
if (skb->ip_summed != CHECKSUM_PARTIAL) {
if (!(rt->rt6i_flags & RTF_LOCAL) &&
(!skb->dev || skb->dev->features & NETIF_F_V6_CSUM)) {
skb->ip_summed = CHECKSUM_PARTIAL;