netfilter: x_tables: never register tables by default

For historical reasons x_tables still register tables by default in the
initial namespace.
Only newly created net namespaces add the hook on demand.

This means that the init_net always pays hook cost, even if no filtering
rules are added (e.g. only used inside a single netns).

Note that the hooks are added even when 'iptables -L' is called.
This is because there is no way to tell 'iptables -A' and 'iptables -L'
apart at kernel level.

The only solution would be to register the table, but delay hook
registration until the first rule gets added (or policy gets changed).

That however means that counters are not hooked either, so 'iptables -L'
would always show 0-counters even when traffic is flowing which might be
unexpected.

This keeps table and hook registration consistent with what is already done
in non-init netns: first iptables(-save) invocation registers both table
and hooks.

This applies the same solution adopted for ebtables.
All tables register a template that contains the l3 family, the name
and a constructor function that is called when the initial table has to
be added.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

5 files changed, 56 insertions, 51 deletions

diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index bb784ea7bbd3..727ee8097012 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -19,15 +19,12 @@ MODULE_DESCRIPTION("ip6tables filter table");
 			    (1 << NF_INET_FORWARD) | \
 			    (1 << NF_INET_LOCAL_OUT))
 
-static int __net_init ip6table_filter_table_init(struct net *net);
-
 static const struct xt_table packet_filter = {
 	.name		= "filter",
 	.valid_hooks	= FILTER_VALID_HOOKS,
 	.me		= THIS_MODULE,
 	.af		= NFPROTO_IPV6,
 	.priority	= NF_IP6_PRI_FILTER,
-	.table_init	= ip6table_filter_table_init,
 };
 
 /* The work comes in here from netfilter.c. */
@@ -44,7 +41,7 @@ static struct nf_hook_ops *filter_ops __read_mostly;
 static bool forward = true;
 module_param(forward, bool, 0000);
 
-static int __net_init ip6table_filter_table_init(struct net *net)
+static int ip6table_filter_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	int err;
@@ -63,7 +60,7 @@ static int __net_init ip6table_filter_table_init(struct net *net)
 
 static int __net_init ip6table_filter_net_init(struct net *net)
 {
-	if (net == &init_net || !forward)
+	if (!forward)
 		return ip6table_filter_table_init(net);
 
 	return 0;
@@ -87,15 +84,24 @@ static struct pernet_operations ip6table_filter_net_ops = {
 
 static int __init ip6table_filter_init(void)
 {
-	int ret;
+	int ret = xt_register_template(&packet_filter,
+					ip6table_filter_table_init);
+
+	if (ret < 0)
+		return ret;
 
 	filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook);
-	if (IS_ERR(filter_ops))
+	if (IS_ERR(filter_ops)) {
+		xt_unregister_template(&packet_filter);
 		return PTR_ERR(filter_ops);
+	}
 
 	ret = register_pernet_subsys(&ip6table_filter_net_ops);
-	if (ret < 0)
+	if (ret < 0) {
+		xt_unregister_template(&packet_filter);
 		kfree(filter_ops);
+		return ret;
+	}
 
 	return ret;
 }
@@ -103,6 +109,7 @@ static int __init ip6table_filter_init(void)
 static void __exit ip6table_filter_fini(void)
 {
 	unregister_pernet_subsys(&ip6table_filter_net_ops);
+	xt_unregister_template(&packet_filter);
 	kfree(filter_ops);
 }
 
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index c76cffd63041..9b518ce37d6a 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -20,15 +20,12 @@ MODULE_DESCRIPTION("ip6tables mangle table");
 			    (1 << NF_INET_LOCAL_OUT) | \
 			    (1 << NF_INET_POST_ROUTING))
 
-static int __net_init ip6table_mangle_table_init(struct net *net);
-
 static const struct xt_table packet_mangler = {
 	.name		= "mangle",
 	.valid_hooks	= MANGLE_VALID_HOOKS,
 	.me		= THIS_MODULE,
 	.af		= NFPROTO_IPV6,
 	.priority	= NF_IP6_PRI_MANGLE,
-	.table_init	= ip6table_mangle_table_init,
 };
 
 static unsigned int
@@ -76,7 +73,7 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb,
 }
 
 static struct nf_hook_ops *mangle_ops __read_mostly;
-static int __net_init ip6table_mangle_table_init(struct net *net)
+static int ip6table_mangle_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	int ret;
@@ -106,29 +103,32 @@ static struct pernet_operations ip6table_mangle_net_ops = {
 
 static int __init ip6table_mangle_init(void)
 {
-	int ret;
+	int ret = xt_register_template(&packet_mangler,
+				       ip6table_mangle_table_init);
+
+	if (ret < 0)
+		return ret;
 
 	mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook);
-	if (IS_ERR(mangle_ops))
+	if (IS_ERR(mangle_ops)) {
+		xt_unregister_template(&packet_mangler);
 		return PTR_ERR(mangle_ops);
+	}
 
 	ret = register_pernet_subsys(&ip6table_mangle_net_ops);
 	if (ret < 0) {
+		xt_unregister_template(&packet_mangler);
 		kfree(mangle_ops);
 		return ret;
 	}
 
-	ret = ip6table_mangle_table_init(&init_net);
-	if (ret) {
-		unregister_pernet_subsys(&ip6table_mangle_net_ops);
-		kfree(mangle_ops);
-	}
 	return ret;
 }
 
 static void __exit ip6table_mangle_fini(void)
 {
 	unregister_pernet_subsys(&ip6table_mangle_net_ops);
+	xt_unregister_template(&packet_mangler);
 	kfree(mangle_ops);
 }
 
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index b0292251e655..921c1723a01e 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -19,8 +19,6 @@ struct ip6table_nat_pernet {
 	struct nf_hook_ops *nf_nat_ops;
 };
 
-static int __net_init ip6table_nat_table_init(struct net *net);
-
 static unsigned int ip6table_nat_net_id __read_mostly;
 
 static const struct xt_table nf_nat_ipv6_table = {
@@ -31,7 +29,6 @@ static const struct xt_table nf_nat_ipv6_table = {
 			  (1 << NF_INET_LOCAL_IN),
 	.me		= THIS_MODULE,
 	.af		= NFPROTO_IPV6,
-	.table_init	= ip6table_nat_table_init,
 };
 
 static unsigned int ip6table_nat_do_chain(void *priv,
@@ -115,7 +112,7 @@ static void ip6t_nat_unregister_lookups(struct net *net)
 	kfree(ops);
 }
 
-static int __net_init ip6table_nat_table_init(struct net *net)
+static int ip6table_nat_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	int ret;
@@ -157,20 +154,23 @@ static struct pernet_operations ip6table_nat_net_ops = {
 
 static int __init ip6table_nat_init(void)
 {
-	int ret = register_pernet_subsys(&ip6table_nat_net_ops);
+	int ret = xt_register_template(&nf_nat_ipv6_table,
+				       ip6table_nat_table_init);
 
-	if (ret)
+	if (ret < 0)
 		return ret;
 
-	ret = ip6table_nat_table_init(&init_net);
+	ret = register_pernet_subsys(&ip6table_nat_net_ops);
 	if (ret)
-		unregister_pernet_subsys(&ip6table_nat_net_ops);
+		xt_unregister_template(&nf_nat_ipv6_table);
+
 	return ret;
 }
 
 static void __exit ip6table_nat_exit(void)
 {
 	unregister_pernet_subsys(&ip6table_nat_net_ops);
+	xt_unregister_template(&nf_nat_ipv6_table);
 }
 
 module_init(ip6table_nat_init);
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index f63c106c521e..4f2a04af71d3 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -11,8 +11,6 @@
 
 #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT))
 
-static int __net_init ip6table_raw_table_init(struct net *net);
-
 static bool raw_before_defrag __read_mostly;
 MODULE_PARM_DESC(raw_before_defrag, "Enable raw table before defrag");
 module_param(raw_before_defrag, bool, 0000);
@@ -23,7 +21,6 @@ static const struct xt_table packet_raw = {
 	.me = THIS_MODULE,
 	.af = NFPROTO_IPV6,
 	.priority = NF_IP6_PRI_RAW,
-	.table_init = ip6table_raw_table_init,
 };
 
 static const struct xt_table packet_raw_before_defrag = {
@@ -32,7 +29,6 @@ static const struct xt_table packet_raw_before_defrag = {
 	.me = THIS_MODULE,
 	.af = NFPROTO_IPV6,
 	.priority = NF_IP6_PRI_RAW_BEFORE_DEFRAG,
-	.table_init = ip6table_raw_table_init,
 };
 
 /* The work comes in here from netfilter.c. */
@@ -45,7 +41,7 @@ ip6table_raw_hook(void *priv, struct sk_buff *skb,
 
 static struct nf_hook_ops *rawtable_ops __read_mostly;
 
-static int __net_init ip6table_raw_table_init(struct net *net)
+static int ip6table_raw_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	const struct xt_table *table = &packet_raw;
@@ -79,37 +75,39 @@ static struct pernet_operations ip6table_raw_net_ops = {
 
 static int __init ip6table_raw_init(void)
 {
-	int ret;
 	const struct xt_table *table = &packet_raw;
+	int ret;
 
 	if (raw_before_defrag) {
 		table = &packet_raw_before_defrag;
-
 		pr_info("Enabling raw table before defrag\n");
 	}
 
+	ret = xt_register_template(table, ip6table_raw_table_init);
+	if (ret < 0)
+		return ret;
+
 	/* Register hooks */
 	rawtable_ops = xt_hook_ops_alloc(table, ip6table_raw_hook);
-	if (IS_ERR(rawtable_ops))
+	if (IS_ERR(rawtable_ops)) {
+		xt_unregister_template(table);
 		return PTR_ERR(rawtable_ops);
+	}
 
 	ret = register_pernet_subsys(&ip6table_raw_net_ops);
 	if (ret < 0) {
 		kfree(rawtable_ops);
+		xt_unregister_template(table);
 		return ret;
 	}
 
-	ret = ip6table_raw_table_init(&init_net);
-	if (ret) {
-		unregister_pernet_subsys(&ip6table_raw_net_ops);
-		kfree(rawtable_ops);
-	}
 	return ret;
 }
 
 static void __exit ip6table_raw_fini(void)
 {
 	unregister_pernet_subsys(&ip6table_raw_net_ops);
+	xt_unregister_template(&packet_raw);
 	kfree(rawtable_ops);
 }
 
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index 8dc335cf450b..931674034d8b 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -24,15 +24,12 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules");
 				(1 << NF_INET_FORWARD) | \
 				(1 << NF_INET_LOCAL_OUT)
 
-static int __net_init ip6table_security_table_init(struct net *net);
-
 static const struct xt_table security_table = {
 	.name		= "security",
 	.valid_hooks	= SECURITY_VALID_HOOKS,
 	.me		= THIS_MODULE,
 	.af		= NFPROTO_IPV6,
 	.priority	= NF_IP6_PRI_SECURITY,
-	.table_init     = ip6table_security_table_init,
 };
 
 static unsigned int
@@ -44,7 +41,7 @@ ip6table_security_hook(void *priv, struct sk_buff *skb,
 
 static struct nf_hook_ops *sectbl_ops __read_mostly;
 
-static int __net_init ip6table_security_table_init(struct net *net)
+static int ip6table_security_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	int ret;
@@ -74,29 +71,32 @@ static struct pernet_operations ip6table_security_net_ops = {
 
 static int __init ip6table_security_init(void)
 {
-	int ret;
+	int ret = xt_register_template(&security_table,
+				       ip6table_security_table_init);
+
+	if (ret < 0)
+		return ret;
 
 	sectbl_ops = xt_hook_ops_alloc(&security_table, ip6table_security_hook);
-	if (IS_ERR(sectbl_ops))
+	if (IS_ERR(sectbl_ops)) {
+		xt_unregister_template(&security_table);
 		return PTR_ERR(sectbl_ops);
+	}
 
 	ret = register_pernet_subsys(&ip6table_security_net_ops);
 	if (ret < 0) {
 		kfree(sectbl_ops);
+		xt_unregister_template(&security_table);
 		return ret;
 	}
 
-	ret = ip6table_security_table_init(&init_net);
-	if (ret) {
-		unregister_pernet_subsys(&ip6table_security_net_ops);
-		kfree(sectbl_ops);
-	}
 	return ret;
 }
 
 static void __exit ip6table_security_fini(void)
 {
 	unregister_pernet_subsys(&ip6table_security_net_ops);
+	xt_unregister_template(&security_table);
 	kfree(sectbl_ops);
 }