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>

6 files changed, 137 insertions, 85 deletions

diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 052d744..84f9baf 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -2071,6 +2071,24 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	return ret;
 }
 
+static void __ip6t_unregister_table(struct net *net, struct xt_table *table)
+{
+	struct xt_table_info *private;
+	void *loc_cpu_entry;
+	struct module *table_owner = table->me;
+	struct ip6t_entry *iter;
+
+	private = xt_unregister_table(table);
+
+	/* Decrease module usage counts and free resources */
+	loc_cpu_entry = private->entries;
+	xt_entry_foreach(iter, loc_cpu_entry, private->size)
+		cleanup_entry(iter, net);
+	if (private->number > private->initial_entries)
+		module_put(table_owner);
+	xt_free_table_info(private);
+}
+
 int ip6t_register_table(struct net *net, const struct xt_table *table,
 			const struct ip6t_replace *repl,
 			const struct nf_hook_ops *ops,
@@ -2099,7 +2117,15 @@ int ip6t_register_table(struct net *net, const struct xt_table *table,
 		goto out_free;
 	}
 
+	/* set res now, will see skbs right after nf_register_net_hooks */
 	WRITE_ONCE(*res, new_table);
+
+	ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
+	if (ret != 0) {
+		__ip6t_unregister_table(net, new_table);
+		*res = NULL;
+	}
+
 	return ret;
 
 out_free:
@@ -2110,20 +2136,8 @@ out_free:
 void ip6t_unregister_table(struct net *net, struct xt_table *table,
 			   const struct nf_hook_ops *ops)
 {
-	struct xt_table_info *private;
-	void *loc_cpu_entry;
-	struct module *table_owner = table->me;
-	struct ip6t_entry *iter;
-
-	private = xt_unregister_table(table);
-
-	/* Decrease module usage counts and free resources */
-	loc_cpu_entry = private->entries;
-	xt_entry_foreach(iter, loc_cpu_entry, private->size)
-		cleanup_entry(iter, net);
-	if (private->number > private->initial_entries)
-		module_put(table_owner);
-	xt_free_table_info(private);
+	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+	__ip6t_unregister_table(net, table);
 }
 
 /* Returns 1 if the type and code is matched by the range, 0 otherwise */
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index d191d54..1343077 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -22,12 +22,15 @@ 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. */
@@ -44,11 +47,14 @@ static struct nf_hook_ops *filter_ops __read_mostly;
 static bool forward = true;
 module_param(forward, bool, 0000);
 
-static int __net_init ip6table_filter_net_init(struct net *net)
+static int __net_init ip6table_filter_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	int err;
 
+	if (net->ipv6.ip6table_filter)
+		return 0;
+
 	repl = ip6t_alloc_initial_table(&packet_filter);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -62,9 +68,20 @@ static int __net_init ip6table_filter_net_init(struct net *net)
 	return err;
 }
 
+static int __net_init ip6table_filter_net_init(struct net *net)
+{
+	if (net == &init_net || !forward)
+		return ip6table_filter_table_init(net);
+
+	return 0;
+}
+
 static void __net_exit ip6table_filter_net_exit(struct net *net)
 {
+	if (!net->ipv6.ip6table_filter)
+		return;
 	ip6t_unregister_table(net, net->ipv6.ip6table_filter, filter_ops);
+	net->ipv6.ip6table_filter = NULL;
 }
 
 static struct pernet_operations ip6table_filter_net_ops = {
@@ -76,28 +93,21 @@ static int __init ip6table_filter_init(void)
 {
 	int ret;
 
+	filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook);
+	if (IS_ERR(filter_ops))
+		return PTR_ERR(filter_ops);
+
 	ret = register_pernet_subsys(&ip6table_filter_net_ops);
 	if (ret < 0)
-		return ret;
-
-	/* Register hooks */
-	filter_ops = xt_hook_link(&packet_filter, ip6table_filter_hook);
-	if (IS_ERR(filter_ops)) {
-		ret = PTR_ERR(filter_ops);
-		goto cleanup_table;
-	}
+		kfree(filter_ops);
 
 	return ret;
-
- cleanup_table:
-	unregister_pernet_subsys(&ip6table_filter_net_ops);
-	return ret;
 }
 
 static void __exit ip6table_filter_fini(void)
 {
-	xt_hook_unlink(&packet_filter, filter_ops);
 	unregister_pernet_subsys(&ip6table_filter_net_ops);
+	kfree(filter_ops);
 }
 
 module_init(ip6table_filter_init);
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index fe43d08..cb2b288 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -23,12 +23,15 @@ 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
@@ -88,11 +91,14 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb,
 }
 
 static struct nf_hook_ops *mangle_ops __read_mostly;
-static int __net_init ip6table_mangle_net_init(struct net *net)
+static int __net_init ip6table_mangle_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	int ret;
 
+	if (net->ipv6.ip6table_mangle)
+		return 0;
+
 	repl = ip6t_alloc_initial_table(&packet_mangler);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -104,11 +110,14 @@ static int __net_init ip6table_mangle_net_init(struct net *net)
 
 static void __net_exit ip6table_mangle_net_exit(struct net *net)
 {
+	if (!net->ipv6.ip6table_mangle)
+		return;
+
 	ip6t_unregister_table(net, net->ipv6.ip6table_mangle, mangle_ops);
+	net->ipv6.ip6table_mangle = NULL;
 }
 
 static struct pernet_operations ip6table_mangle_net_ops = {
-	.init = ip6table_mangle_net_init,
 	.exit = ip6table_mangle_net_exit,
 };
 
@@ -116,28 +125,28 @@ static int __init ip6table_mangle_init(void)
 {
 	int ret;
 
+	mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook);
+	if (IS_ERR(mangle_ops))
+		return PTR_ERR(mangle_ops);
+
 	ret = register_pernet_subsys(&ip6table_mangle_net_ops);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(mangle_ops);
 		return ret;
-
-	/* Register hooks */
-	mangle_ops = xt_hook_link(&packet_mangler, ip6table_mangle_hook);
-	if (IS_ERR(mangle_ops)) {
-		ret = PTR_ERR(mangle_ops);
-		goto cleanup_table;
 	}
 
-	return ret;
-
- cleanup_table:
-	unregister_pernet_subsys(&ip6table_mangle_net_ops);
+	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)
 {
-	xt_hook_unlink(&packet_mangler, mangle_ops);
 	unregister_pernet_subsys(&ip6table_mangle_net_ops);
+	kfree(mangle_ops);
 }
 
 module_init(ip6table_mangle_init);
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 7f9740e..7d2bd94 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -20,6 +20,8 @@
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_l3proto.h>
 
+static int __net_init ip6table_nat_table_init(struct net *net);
+
 static const struct xt_table nf_nat_ipv6_table = {
 	.name		= "nat",
 	.valid_hooks	= (1 << NF_INET_PRE_ROUTING) |
@@ -28,6 +30,7 @@ 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,
@@ -97,11 +100,14 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 };
 
-static int __net_init ip6table_nat_net_init(struct net *net)
+static int __net_init ip6table_nat_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	int ret;
 
+	if (net->ipv6.ip6table_nat)
+		return 0;
+
 	repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -113,36 +119,31 @@ static int __net_init ip6table_nat_net_init(struct net *net)
 
 static void __net_exit ip6table_nat_net_exit(struct net *net)
 {
+	if (!net->ipv6.ip6table_nat)
+		return;
 	ip6t_unregister_table(net, net->ipv6.ip6table_nat, nf_nat_ipv6_ops);
+	net->ipv6.ip6table_nat = NULL;
 }
 
 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;
+	int ret = register_pernet_subsys(&ip6table_nat_net_ops);
 
-	err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
-	if (err < 0)
-		goto err2;
-	return 0;
+	if (ret)
+		return ret;
 
-err2:
-	unregister_pernet_subsys(&ip6table_nat_net_ops);
-err1:
-	return err;
+	ret = ip6table_nat_table_init(&init_net);
+	if (ret)
+		unregister_pernet_subsys(&ip6table_nat_net_ops);
+	return ret;
 }
 
 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);
 }
 
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 5fac433..d4bc564 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -9,12 +9,15 @@
 
 #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 const struct xt_table packet_raw = {
 	.name = "raw",
 	.valid_hooks = RAW_VALID_HOOKS,
 	.me = THIS_MODULE,
 	.af = NFPROTO_IPV6,
 	.priority = NF_IP6_PRI_RAW,
+	.table_init = ip6table_raw_table_init,
 };
 
 /* The work comes in here from netfilter.c. */
@@ -27,11 +30,14 @@ ip6table_raw_hook(void *priv, struct sk_buff *skb,
 
 static struct nf_hook_ops *rawtable_ops __read_mostly;
 
-static int __net_init ip6table_raw_net_init(struct net *net)
+static int __net_init ip6table_raw_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	int ret;
 
+	if (net->ipv6.ip6table_raw)
+		return 0;
+
 	repl = ip6t_alloc_initial_table(&packet_raw);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -43,11 +49,13 @@ static int __net_init ip6table_raw_net_init(struct net *net)
 
 static void __net_exit ip6table_raw_net_exit(struct net *net)
 {
+	if (!net->ipv6.ip6table_raw)
+		return;
 	ip6t_unregister_table(net, net->ipv6.ip6table_raw, rawtable_ops);
+	net->ipv6.ip6table_raw = NULL;
 }
 
 static struct pernet_operations ip6table_raw_net_ops = {
-	.init = ip6table_raw_net_init,
 	.exit = ip6table_raw_net_exit,
 };
 
@@ -55,28 +63,29 @@ static int __init ip6table_raw_init(void)
 {
 	int ret;
 
+	/* Register hooks */
+	rawtable_ops = xt_hook_ops_alloc(&packet_raw, ip6table_raw_hook);
+	if (IS_ERR(rawtable_ops))
+		return PTR_ERR(rawtable_ops);
+
 	ret = register_pernet_subsys(&ip6table_raw_net_ops);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(rawtable_ops);
 		return ret;
-
-	/* Register hooks */
-	rawtable_ops = xt_hook_link(&packet_raw, ip6table_raw_hook);
-	if (IS_ERR(rawtable_ops)) {
-		ret = PTR_ERR(rawtable_ops);
-		goto cleanup_table;
 	}
 
-	return ret;
-
- cleanup_table:
-	unregister_pernet_subsys(&ip6table_raw_net_ops);
+	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)
 {
-	xt_hook_unlink(&packet_raw, rawtable_ops);
 	unregister_pernet_subsys(&ip6table_raw_net_ops);
+	kfree(rawtable_ops);
 }
 
 module_init(ip6table_raw_init);
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index cf58745..cf26ccb 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -27,12 +27,15 @@ 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
@@ -44,11 +47,14 @@ ip6table_security_hook(void *priv, struct sk_buff *skb,
 
 static struct nf_hook_ops *sectbl_ops __read_mostly;
 
-static int __net_init ip6table_security_net_init(struct net *net)
+static int __net_init ip6table_security_table_init(struct net *net)
 {
 	struct ip6t_replace *repl;
 	int ret;
 
+	if (net->ipv6.ip6table_security)
+		return 0;
+
 	repl = ip6t_alloc_initial_table(&security_table);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -60,11 +66,13 @@ static int __net_init ip6table_security_net_init(struct net *net)
 
 static void __net_exit ip6table_security_net_exit(struct net *net)
 {
+	if (!net->ipv6.ip6table_security)
+		return;
 	ip6t_unregister_table(net, net->ipv6.ip6table_security, sectbl_ops);
+	net->ipv6.ip6table_security = NULL;
 }
 
 static struct pernet_operations ip6table_security_net_ops = {
-	.init = ip6table_security_net_init,
 	.exit = ip6table_security_net_exit,
 };
 
@@ -72,27 +80,28 @@ static int __init ip6table_security_init(void)
 {
 	int ret;
 
+	sectbl_ops = xt_hook_ops_alloc(&security_table, ip6table_security_hook);
+	if (IS_ERR(sectbl_ops))
+		return PTR_ERR(sectbl_ops);
+
 	ret = register_pernet_subsys(&ip6table_security_net_ops);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(sectbl_ops);
 		return ret;
-
-	sectbl_ops = xt_hook_link(&security_table, ip6table_security_hook);
-	if (IS_ERR(sectbl_ops)) {
-		ret = PTR_ERR(sectbl_ops);
-		goto cleanup_table;
 	}
 
-	return ret;
-
-cleanup_table:
-	unregister_pernet_subsys(&ip6table_security_net_ops);
+	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)
 {
-	xt_hook_unlink(&security_table, sectbl_ops);
 	unregister_pernet_subsys(&ip6table_security_net_ops);
+	kfree(sectbl_ops);
 }
 
 module_init(ip6table_security_init);