remarkable-linux/net/ipv4/netfilter/iptable_nat.c
Florian Westphal b9e69e1273 netfilter: xtables: don't hook tables by default
delay hook registration until the table is being requested inside a
namespace.

Historically, a particular table (iptables mangle, ip6tables filter, etc)
was registered on module load.

When netns support was added to iptables only the ip/ip6tables ruleset was
made namespace aware, not the actual hook points.

This means f.e. that when ipt_filter table/module is loaded on a system,
then each namespace on that system has an (empty) iptables filter ruleset.

In other words, if a namespace sends a packet, such skb is 'caught' by
netfilter machinery and fed to hooking points for that table (i.e. INPUT,
FORWARD, etc).

Thanks to Eric Biederman, hooks are no longer global, but per namespace.

This means that we can avoid allocation of empty ruleset in a namespace and
defer hook registration until we need the functionality.

We register a tables hook entry points ONLY in the initial namespace.
When an iptables get/setockopt is issued inside a given namespace, we check
if the table is found in the per-namespace list.

If not, we attempt to find it in the initial namespace, and, if found,
create an empty default table in the requesting namespace and register the
needed hooks.

Hook points are destroyed only once namespace is deleted, there is no
'usage count' (it makes no sense since there is no 'remove table' operation
in xtables api).

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2016-03-02 20:05:24 +01:00

152 lines
3.7 KiB
C

/* (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/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/ip.h>
#include <net/ip.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>
static int __net_init iptable_nat_table_init(struct net *net);
static const struct xt_table nf_nat_ipv4_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_IPV4,
.table_init = iptable_nat_table_init,
};
static unsigned int iptable_nat_do_chain(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct)
{
return ipt_do_table(skb, state, state->net->ipv4.nat_table);
}
static unsigned int iptable_nat_ipv4_fn(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
return nf_nat_ipv4_fn(priv, skb, state, iptable_nat_do_chain);
}
static unsigned int iptable_nat_ipv4_in(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
return nf_nat_ipv4_in(priv, skb, state, iptable_nat_do_chain);
}
static unsigned int iptable_nat_ipv4_out(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
return nf_nat_ipv4_out(priv, skb, state, iptable_nat_do_chain);
}
static unsigned int iptable_nat_ipv4_local_fn(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
return nf_nat_ipv4_local_fn(priv, skb, state, iptable_nat_do_chain);
}
static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
/* Before packet filtering, change destination */
{
.hook = iptable_nat_ipv4_in,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_NAT_DST,
},
/* After packet filtering, change source */
{
.hook = iptable_nat_ipv4_out,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP_PRI_NAT_SRC,
},
/* Before packet filtering, change destination */
{
.hook = iptable_nat_ipv4_local_fn,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_NAT_DST,
},
/* After packet filtering, change source */
{
.hook = iptable_nat_ipv4_fn,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_NAT_SRC,
},
};
static int __net_init iptable_nat_table_init(struct net *net)
{
struct ipt_replace *repl;
int ret;
if (net->ipv4.nat_table)
return 0;
repl = ipt_alloc_initial_table(&nf_nat_ipv4_table);
if (repl == NULL)
return -ENOMEM;
ret = ipt_register_table(net, &nf_nat_ipv4_table, repl,
nf_nat_ipv4_ops, &net->ipv4.nat_table);
kfree(repl);
return ret;
}
static void __net_exit iptable_nat_net_exit(struct net *net)
{
if (!net->ipv4.nat_table)
return;
ipt_unregister_table(net, net->ipv4.nat_table, nf_nat_ipv4_ops);
net->ipv4.nat_table = NULL;
}
static struct pernet_operations iptable_nat_net_ops = {
.exit = iptable_nat_net_exit,
};
static int __init iptable_nat_init(void)
{
int ret = register_pernet_subsys(&iptable_nat_net_ops);
if (ret)
return ret;
ret = iptable_nat_table_init(&init_net);
if (ret)
unregister_pernet_subsys(&iptable_nat_net_ops);
return ret;
}
static void __exit iptable_nat_exit(void)
{
unregister_pernet_subsys(&iptable_nat_net_ops);
}
module_init(iptable_nat_init);
module_exit(iptable_nat_exit);
MODULE_LICENSE("GPL");