/*
* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
* (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.
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/timer.h>
#include <linux/skbuff.h>
#include <linux/gfp.h>
#include <net/xfrm.h>
#include <linux/jhash.h>
#include <linux/rtnetlink.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_l3proto.h>
#include <net/netfilter/nf_nat_l4proto.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_helper.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <linux/netfilter/nf_nat.h>
static DEFINE_SPINLOCK(nf_nat_lock);
static DEFINE_MUTEX(nf_nat_proto_mutex);
static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO]
__read_mostly;
static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO]
__read_mostly;
inline const struct nf_nat_l3proto *
__nf_nat_l3proto_find(u8 family)
{
return rcu_dereference(nf_nat_l3protos[family]);
}
inline const struct nf_nat_l4proto *
__nf_nat_l4proto_find(u8 family, u8 protonum)
{
return rcu_dereference(nf_nat_l4protos[family][protonum]);
}
EXPORT_SYMBOL_GPL(__nf_nat_l4proto_find);
#ifdef CONFIG_XFRM
static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl)
{
const struct nf_nat_l3proto *l3proto;
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
enum ip_conntrack_dir dir;
unsigned long statusbit;
u8 family;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return;
family = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
rcu_read_lock();
l3proto = __nf_nat_l3proto_find(family);
if (l3proto == NULL)
goto out;
dir = CTINFO2DIR(ctinfo);
if (dir == IP_CT_DIR_ORIGINAL)
statusbit = IPS_DST_NAT;
else
statusbit = IPS_SRC_NAT;
l3proto->decode_session(skb, ct, dir, statusbit, fl);
out:
rcu_read_unlock();
}
int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family)
{
struct flowi fl;
unsigned int hh_len;
struct dst_entry *dst;
int err;
err = xfrm_decode_session(skb, &fl, family);
if (err < 0)
return err;
dst = skb_dst(skb);
if (dst->xfrm)
dst = ((struct xfrm_dst *)dst)->route;
dst_hold(dst);
dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0);
if (IS_ERR(dst))
return PTR_ERR(dst);
skb_dst_drop(skb);
skb_dst_set(skb, dst);
/* Change in oif may mean change in hh_len. */
hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL(nf_xfrm_me_harder);
#endif /* CONFIG_XFRM */
/* We keep an extra hash for each conntrack, for fast searching. */
static inline unsigned int
hash_by_src(const struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple)
{
unsigned int hash;
/* Original src, to ensure we map it consistently if poss. */
hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32),
tuple->dst.protonum ^ zone ^ nf_conntrack_hash_rnd);
return ((u64)hash * net->ct.nat_htable_size) >> 32;
}
/* Is this tuple already taken? (not by us) */
int
nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
const struct nf_conn *ignored_conntrack)
{
/* Conntrack tracking doesn't keep track of outgoing tuples; only
* incoming ones. NAT means they don't have a fixed mapping,
* so we invert the tuple and look for the incoming reply.
*
* We could keep a separate hash if this proves too slow.
*/
struct nf_conntrack_tuple reply;
nf_ct_invert_tuplepr(&reply, tuple);
return nf_conntrack_tuple_taken(&reply, ignored_conntrack);
}
EXPORT_SYMBOL(nf_nat_used_tuple);
/* If we source map this tuple so reply looks like reply_tuple, will
* that meet the constraints of range.
*/
static int in_range(const struct nf_nat_l3proto *l3proto,
const struct nf_nat_l4proto *l4proto,
const struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range)
{
/* If we are supposed to map IPs, then we must be in the
* range specified, otherwise let this drag us onto a new src IP.
*/
if (range->flags & NF_NAT_RANGE_MAP_IPS &&
!l3proto->in_range(tuple, range))
return 0;
if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) ||
l4proto->in_range(tuple, NF_NAT_MANIP_SRC,
&range->min_proto, &range->max_proto))
return 1;
return 0;
}
static inline int
same_src(const struct nf_conn *ct,
const struct nf_conntrack_tuple *tuple)
{
const struct nf_conntrack_tuple *t;
t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
return (t->dst.protonum == tuple->dst.protonum &&
nf_inet_addr_cmp(&t->src.u3, &tuple->src.u3) &&
t->src.u.all == tuple->src.u.all);
}
/* Only called for SRC manip */
static int
find_appropriate_src(struct net *net, u16 zone,
const struct nf_nat_l3proto *l3proto,
const struct nf_nat_l4proto *l4proto,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple *result,
const struct nf_nat_range *range)
{
unsigned int h = hash_by_src(net, zone, tuple);
const struct nf_conn_nat *nat;
const struct nf_conn *ct;
hlist_for_each_entry_rcu(nat, &net->ct.nat_bysource[h], bysource) {
ct = nat->ct;
if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) {
/* Copy source part from reply tuple. */
nf_ct_invert_tuplepr(result,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
result->dst = tuple->dst;
if (in_range(l3proto, l4proto, result, range))
return 1;
}
}
return 0;
}
/* For [FUTURE] fragmentation handling, we want the least-used
* src-ip/dst-ip/proto triple. Fairness doesn't come into it. Thus
* if the range specifies 1.2.3.4 ports 10000-10005 and 1.2.3.5 ports
* 1-65535, we don't do pro-rata allocation based on ports; we choose
* the ip with the lowest src-ip/dst-ip/proto usage.
*/
static void
find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
const struct nf_conn *ct,
enum nf_nat_manip_type maniptype)
{
union nf_inet_addr *var_ipp;
unsigned int i, max;
/* Host order */
u32 minip, maxip, j, dist;
bool full_range;
/* No IP mapping? Do nothing. */
if (!(range->flags & NF_NAT_RANGE_MAP_IPS))
return;
if (maniptype == NF_NAT_MANIP_SRC)
var_ipp = &tuple->src.u3;
else
var_ipp = &tuple->dst.u3;
/* Fast path: only one choice. */
if (nf_inet_addr_cmp(&range->min_addr, &range->max_addr)) {
*var_ipp = range->min_addr;
return;
}
if (nf_ct_l3num(ct) == NFPROTO_IPV4)
max = sizeof(var_ipp->ip) / sizeof(u32) - 1;
else
max = sizeof(var_ipp->ip6) / sizeof(u32) - 1;
/* Hashing source and destination IPs gives a fairly even
* spread in practice (if there are a small number of IPs
* involved, there usually aren't that many connections
* anyway). The consistency means that servers see the same
* client coming from the same IP (some Internet Banking sites
* like this), even across reboots.
*/
j = jhash2((u32 *)&tuple->src.u3, sizeof(tuple->src.u3) / sizeof(u32),
range->flags & NF_NAT_RANGE_PERSISTENT ?
0 : (__force u32)tuple->dst.u3.all[max] ^ zone);
full_range = false;
for (i = 0; i <= max; i++) {
/* If first bytes of the address are at the maximum, use the
* distance. Otherwise use the full range.
*/
if (!full_range) {
minip = ntohl((__force __be32)range->min_addr.all[i]);
maxip = ntohl((__force __be32)range->max_addr.all[i]);
dist = maxip - minip + 1;
} else {
minip = 0;
dist = ~0;
}
var_ipp->all[i] = (__force __u32)
htonl(minip + (