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>

include/linux/netfilter/x_tables.h

@@ -200,6 +200,9 @@ struct xt_table {
 	u_int8_t af;		/* address/protocol family */
 	int priority;		/* hook order */
 
+	/* called when table is needed in the given netns */
+	int (*table_init)(struct net *net);
+
 	/* A unique name... */
 	const char name[XT_TABLE_MAXNAMELEN];
 };
@@ -408,8 +411,7 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)
 	return cnt;
 }
 
-struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *);
-void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *);
+struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
 
 #ifdef CONFIG_COMPAT
 #include <net/compat.h>

net/ipv4/netfilter/arp_tables.c

@@ -1780,6 +1780,24 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
 	return ret;
 }
 
+static void __arpt_unregister_table(struct xt_table *table)
+{
+	struct xt_table_info *private;
+	void *loc_cpu_entry;
+	struct module *table_owner = table->me;
+	struct arpt_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);
+	if (private->number > private->initial_entries)
+		module_put(table_owner);
+	xt_free_table_info(private);
+}
+
 int arpt_register_table(struct net *net,
 			const struct xt_table *table,
 			const struct arpt_replace *repl,
@@ -1810,8 +1828,15 @@ int arpt_register_table(struct net *net,
 		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) {
+		__arpt_unregister_table(new_table);
+		*res = NULL;
+	}
+
 	return ret;
 
 out_free:
@@ -1822,20 +1847,8 @@ int arpt_register_table(struct net *net,
 void arpt_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 arpt_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);
-	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));
+	__arpt_unregister_table(table);
 }
 
 /* The built-in targets: standard (NULL) and error. */

net/ipv4/netfilter/arptable_filter.c

@@ -17,12 +17,15 @@ MODULE_DESCRIPTION("arptables filter table");
 #define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \
 			   (1 << NF_ARP_FORWARD))
 
+static int __net_init arptable_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_ARP,
 	.priority	= NF_IP_PRI_FILTER,
+	.table_init	= arptable_filter_table_init,
 };
 
 /* The work comes in here from netfilter.c */
@@ -35,11 +38,14 @@ arptable_filter_hook(void *priv, struct sk_buff *skb,
 
 static struct nf_hook_ops *arpfilter_ops __read_mostly;
 
-static int __net_init arptable_filter_net_init(struct net *net)
+static int __net_init arptable_filter_table_init(struct net *net)
 {
 	struct arpt_replace *repl;
 	int err;
 
+	if (net->ipv4.arptable_filter)
+		return 0;
+
 	repl = arpt_alloc_initial_table(&packet_filter);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -51,11 +57,13 @@ static int __net_init arptable_filter_net_init(struct net *net)
 
 static void __net_exit arptable_filter_net_exit(struct net *net)
 {
+	if (!net->ipv4.arptable_filter)
+		return;
 	arpt_unregister_table(net, net->ipv4.arptable_filter, arpfilter_ops);
+	net->ipv4.arptable_filter = NULL;
 }
 
 static struct pernet_operations arptable_filter_net_ops = {
-	.init = arptable_filter_net_init,
 	.exit = arptable_filter_net_exit,
 };
 
@@ -63,26 +71,23 @@ static int __init arptable_filter_init(void)
 {
 	int ret;
 
+	arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arptable_filter_hook);
+	if (IS_ERR(arpfilter_ops))
+		return PTR_ERR(arpfilter_ops);
+
 	ret = register_pernet_subsys(&arptable_filter_net_ops);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(arpfilter_ops);
 		return ret;
-
-	arpfilter_ops = xt_hook_link(&packet_filter, arptable_filter_hook);
-	if (IS_ERR(arpfilter_ops)) {
-		ret = PTR_ERR(arpfilter_ops);
-		goto cleanup_table;
 	}
-	return ret;
 
-cleanup_table:
-	unregister_pernet_subsys(&arptable_filter_net_ops);
 	return ret;
 }
 
 static void __exit arptable_filter_fini(void)
 {
-	xt_hook_unlink(&packet_filter, arpfilter_ops);
 	unregister_pernet_subsys(&arptable_filter_net_ops);
+	kfree(arpfilter_ops);
 }
 
 module_init(arptable_filter_init);

net/ipv4/netfilter/ip_tables.c

@@ -2062,6 +2062,24 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	return ret;
 }
 
+static void __ipt_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 ipt_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 ipt_register_table(struct net *net, const struct xt_table *table,
 		       const struct ipt_replace *repl,
 		       const struct nf_hook_ops *ops, struct xt_table **res)
@@ -2089,7 +2107,15 @@ int ipt_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) {
+		__ipt_unregister_table(net, new_table);
+		*res = NULL;
+	}
+
 	return ret;
 
 out_free:
@@ -2100,20 +2126,8 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
 void ipt_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 ipt_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));
+	__ipt_unregister_table(net, table);
 }
 
 /* Returns 1 if the type and code is matched by the range, 0 otherwise */

net/ipv4/netfilter/iptable_filter.c

@@ -23,6 +23,7 @@ MODULE_DESCRIPTION("iptables filter table");
 #define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \
 			    (1 << NF_INET_FORWARD) | \
 			    (1 << NF_INET_LOCAL_OUT))
+static int __net_init iptable_filter_table_init(struct net *net);
 
 static const struct xt_table packet_filter = {
 	.name		= "filter",
@@ -30,6 +31,7 @@ static const struct xt_table packet_filter = {
 	.me		= THIS_MODULE,
 	.af		= NFPROTO_IPV4,
 	.priority	= NF_IP_PRI_FILTER,
+	.table_init	= iptable_filter_table_init,
 };
 
 static unsigned int
@@ -48,14 +50,17 @@ iptable_filter_hook(void *priv, struct sk_buff *skb,
 static struct nf_hook_ops *filter_ops __read_mostly;
 
 /* Default to forward because I got too much mail already. */
-static bool forward = true;
+static bool forward __read_mostly = true;
 module_param(forward, bool, 0000);
 
-static int __net_init iptable_filter_net_init(struct net *net)
+static int __net_init iptable_filter_table_init(struct net *net)
 {
 	struct ipt_replace *repl;
 	int err;
 
+	if (net->ipv4.iptable_filter)
+		return 0;
+
 	repl = ipt_alloc_initial_table(&packet_filter);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -69,9 +74,20 @@ static int __net_init iptable_filter_net_init(struct net *net)
 	return err;
 }
 
+static int __net_init iptable_filter_net_init(struct net *net)
+{
+	if (net == &init_net || !forward)
+		return iptable_filter_table_init(net);
+
+	return 0;
+}
+
 static void __net_exit iptable_filter_net_exit(struct net *net)
 {
+	if (!net->ipv4.iptable_filter)
+		return;
 	ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops);
+	net->ipv4.iptable_filter = NULL;
 }
 
 static struct pernet_operations iptable_filter_net_ops = {
@@ -83,24 +99,21 @@ static int __init iptable_filter_init(void)
 {
 	int ret;
 
+	filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook);
+	if (IS_ERR(filter_ops))
+		return PTR_ERR(filter_ops);
+
 	ret = register_pernet_subsys(&iptable_filter_net_ops);
 	if (ret < 0)
-		return ret;
-
-	/* Register hooks */
-	filter_ops = xt_hook_link(&packet_filter, iptable_filter_hook);
-	if (IS_ERR(filter_ops)) {
-		ret = PTR_ERR(filter_ops);
-		unregister_pernet_subsys(&iptable_filter_net_ops);
-	}
+		kfree(filter_ops);
 
 	return ret;
 }
 
 static void __exit iptable_filter_fini(void)
 {
-	xt_hook_unlink(&packet_filter, filter_ops);
 	unregister_pernet_subsys(&iptable_filter_net_ops);
+	kfree(filter_ops);
 }
 
 module_init(iptable_filter_init);

net/ipv4/netfilter/iptable_mangle.c

@@ -28,12 +28,15 @@ MODULE_DESCRIPTION("iptables mangle table");
 			    (1 << NF_INET_LOCAL_OUT) | \
 			    (1 << NF_INET_POST_ROUTING))
 
+static int __net_init iptable_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_IPV4,
 	.priority	= NF_IP_PRI_MANGLE,
+	.table_init	= iptable_mangle_table_init,
 };
 
 static unsigned int
@@ -92,12 +95,14 @@ iptable_mangle_hook(void *priv,
 }
 
 static struct nf_hook_ops *mangle_ops __read_mostly;
-
-static int __net_init iptable_mangle_net_init(struct net *net)
+static int __net_init iptable_mangle_table_init(struct net *net)
 {
 	struct ipt_replace *repl;
 	int ret;
 
+	if (net->ipv4.iptable_mangle)
+		return 0;
+
 	repl = ipt_alloc_initial_table(&packet_mangler);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -109,11 +114,13 @@ static int __net_init iptable_mangle_net_init(struct net *net)
 
 static void __net_exit iptable_mangle_net_exit(struct net *net)
 {
+	if (!net->ipv4.iptable_mangle)
+		return;
 	ipt_unregister_table(net, net->ipv4.iptable_mangle, mangle_ops);
+	net->ipv4.iptable_mangle = NULL;
 }
 
 static struct pernet_operations iptable_mangle_net_ops = {
-	.init = iptable_mangle_net_init,
 	.exit = iptable_mangle_net_exit,
 };
 
@@ -121,15 +128,22 @@ static int __init iptable_mangle_init(void)
 {
 	int ret;
 
+	mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook);
+	if (IS_ERR(mangle_ops)) {
+		ret = PTR_ERR(mangle_ops);
+		return ret;
+	}
+
 	ret = register_pernet_subsys(&iptable_mangle_net_ops);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(mangle_ops);
 		return ret;
+	}
 
-	/* Register hooks */
-	mangle_ops = xt_hook_link(&packet_mangler, iptable_mangle_hook);
-	if (IS_ERR(mangle_ops)) {
-		ret = PTR_ERR(mangle_ops);
+	ret = iptable_mangle_table_init(&init_net);
+	if (ret) {
 		unregister_pernet_subsys(&iptable_mangle_net_ops);
+		kfree(mangle_ops);
 	}
 
 	return ret;
@@ -137,8 +151,8 @@ static int __init iptable_mangle_init(void)
 
 static void __exit iptable_mangle_fini(void)
 {
-	xt_hook_unlink(&packet_mangler, mangle_ops);
 	unregister_pernet_subsys(&iptable_mangle_net_ops);
+	kfree(mangle_ops);
 }
 
 module_init(iptable_mangle_init);

net/ipv4/netfilter/iptable_nat.c

@@ -18,6 +18,8 @@
 #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) |
@@ -26,6 +28,7 @@ static const struct xt_table nf_nat_ipv4_table = {
 			  (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,
@@ -95,11 +98,14 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 };
 
-static int __net_init iptable_nat_net_init(struct net *net)
+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;
@@ -111,36 +117,31 @@ static int __net_init iptable_nat_net_init(struct net *net)
 
 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 = {
-	.init	= iptable_nat_net_init,
 	.exit	= iptable_nat_net_exit,
 };
 
 static int __init iptable_nat_init(void)
 {
-	int err;
-
-	err = register_pernet_subsys(&iptable_nat_net_ops);
-	if (err < 0)
-		goto err1;
+	int ret = register_pernet_subsys(&iptable_nat_net_ops);
 
-	err = nf_register_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
-	if (err < 0)
-		goto err2;
-	return 0;
+	if (ret)
+		return ret;
 
-err2:
+	ret = iptable_nat_table_init(&init_net);
+	if (ret)
 		unregister_pernet_subsys(&iptable_nat_net_ops);
-err1:
-	return err;
+	return ret;
 }
 
 static void __exit iptable_nat_exit(void)
 {
-	nf_unregister_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
 	unregister_pernet_subsys(&iptable_nat_net_ops);
 }
 

net/ipv4/netfilter/iptable_raw.c

@@ -10,12 +10,15 @@
 
 #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT))
 
+static int __net_init iptable_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_IPV4,
 	.priority = NF_IP_PRI_RAW,
+	.table_init = iptable_raw_table_init,
 };
 
 /* The work comes in here from netfilter.c. */
@@ -34,11 +37,14 @@ iptable_raw_hook(void *priv, struct sk_buff *skb,
 
 static struct nf_hook_ops *rawtable_ops __read_mostly;
 
-static int __net_init iptable_raw_net_init(struct net *net)
+static int __net_init iptable_raw_table_init(struct net *net)
 {
 	struct ipt_replace *repl;
 	int ret;
 
+	if (net->ipv4.iptable_raw)
+		return 0;
+
 	repl = ipt_alloc_initial_table(&packet_raw);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -50,11 +56,13 @@ static int __net_init iptable_raw_net_init(struct net *net)
 
 static void __net_exit iptable_raw_net_exit(struct net *net)
 {
+	if (!net->ipv4.iptable_raw)
+		return;
 	ipt_unregister_table(net, net->ipv4.iptable_raw, rawtable_ops);
+	net->ipv4.iptable_raw = NULL;
 }
 
 static struct pernet_operations iptable_raw_net_ops = {
-	.init = iptable_raw_net_init,
 	.exit = iptable_raw_net_exit,
 };
 
@@ -62,15 +70,20 @@ static int __init iptable_raw_init(void)
 {
 	int ret;
 
+	rawtable_ops = xt_hook_ops_alloc(&packet_raw, iptable_raw_hook);
+	if (IS_ERR(rawtable_ops))
+		return PTR_ERR(rawtable_ops);
+
 	ret = register_pernet_subsys(&iptable_raw_net_ops);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(rawtable_ops);
 		return ret;
+	}
 
-	/* Register hooks */
-	rawtable_ops = xt_hook_link(&packet_raw, iptable_raw_hook);
-	if (IS_ERR(rawtable_ops)) {
-		ret = PTR_ERR(rawtable_ops);
+	ret = iptable_raw_table_init(&init_net);
+	if (ret) {
 		unregister_pernet_subsys(&iptable_raw_net_ops);
+		kfree(rawtable_ops);
 	}
 
 	return ret;
@@ -78,8 +91,8 @@ static int __init iptable_raw_init(void)
 
 static void __exit iptable_raw_fini(void)
 {
-	xt_hook_unlink(&packet_raw, rawtable_ops);
 	unregister_pernet_subsys(&iptable_raw_net_ops);
+	kfree(rawtable_ops);
 }
 
 module_init(iptable_raw_init);

net/ipv4/netfilter/iptable_security.c

@@ -28,12 +28,15 @@ MODULE_DESCRIPTION("iptables security table, for MAC rules");
 				(1 << NF_INET_FORWARD) | \
 				(1 << NF_INET_LOCAL_OUT)
 
+static int __net_init iptable_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_IPV4,
 	.priority	= NF_IP_PRI_SECURITY,
+	.table_init	= iptable_security_table_init,
 };
 
 static unsigned int
@@ -51,11 +54,14 @@ iptable_security_hook(void *priv, struct sk_buff *skb,
 
 static struct nf_hook_ops *sectbl_ops __read_mostly;
 
-static int __net_init iptable_security_net_init(struct net *net)
+static int __net_init iptable_security_table_init(struct net *net)
 {
 	struct ipt_replace *repl;
 	int ret;
 
+	if (net->ipv4.iptable_security)
+		return 0;
+
 	repl = ipt_alloc_initial_table(&security_table);
 	if (repl == NULL)
 		return -ENOMEM;
@@ -67,11 +73,14 @@ static int __net_init iptable_security_net_init(struct net *net)
 
 static void __net_exit iptable_security_net_exit(struct net *net)
 {
+	if (!net->ipv4.iptable_security)
+		return;
+
 	ipt_unregister_table(net, net->ipv4.iptable_security, sectbl_ops);
+	net->ipv4.iptable_security = NULL;
 }
 
 static struct pernet_operations iptable_security_net_ops = {
-	.init = iptable_security_net_init,
 	.exit = iptable_security_net_exit,
 };
 
@@ -79,27 +88,29 @@ static int __init iptable_security_init(void)
 {
 	int ret;
 
+	sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook);
+	if (IS_ERR(sectbl_ops))
+		return PTR_ERR(sectbl_ops);
+
 	ret = register_pernet_subsys(&iptable_security_net_ops);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(sectbl_ops);
 		return ret;
-
-	sectbl_ops = xt_hook_link(&security_table, iptable_security_hook);
-	if (IS_ERR(sectbl_ops)) {
-		ret = PTR_ERR(sectbl_ops);
-		goto cleanup_table;
 	}
 
-	return ret;
-
-cleanup_table:
+	ret = iptable_security_table_init(&init_net);
+	if (ret) {
 		unregister_pernet_subsys(&iptable_security_net_ops);
+		kfree(sectbl_ops);
+	}
+
 	return ret;
 }
 
 static void __exit iptable_security_fini(void)
 {
-	xt_hook_unlink(&security_table, sectbl_ops);
 	unregister_pernet_subsys(&iptable_security_net_ops);
+	kfree(sectbl_ops);
 }
 
 module_init(iptable_security_init);

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 @@ int ip6t_register_table(struct net *net, const struct xt_table *table,
 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 */

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);

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:
+	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);

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:
+	ret = ip6table_nat_table_init(&init_net);
+	if (ret)
 		unregister_pernet_subsys(&ip6table_nat_net_ops);
-err1:
-	return err;
+	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);
 }
 

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;
 
-	ret = register_pernet_subsys(&ip6table_raw_net_ops);
-	if (ret < 0)
-		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;
-	}
+	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) {
+		kfree(rawtable_ops);
 		return ret;
+	}
 
- cleanup_table:
+	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);

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:
+	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);

net/netfilter/x_tables.c

@@ -694,12 +694,45 @@ EXPORT_SYMBOL(xt_free_table_info);
 struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
 				    const char *name)
 {
-	struct xt_table *t;
+	struct xt_table *t, *found = NULL;
 
 	mutex_lock(&xt[af].mutex);
 	list_for_each_entry(t, &net->xt.tables[af], list)
 		if (strcmp(t->name, name) == 0 && try_module_get(t->me))
 			return t;
+
+	if (net == &init_net)
+		goto out;
+
+	/* Table doesn't exist in this netns, re-try init */
+	list_for_each_entry(t, &init_net.xt.tables[af], list) {
+		if (strcmp(t->name, name))
+			continue;
+		if (!try_module_get(t->me))
+			return NULL;
+
+		mutex_unlock(&xt[af].mutex);
+		if (t->table_init(net) != 0) {
+			module_put(t->me);
+			return NULL;
+		}
+
+		found = t;
+
+		mutex_lock(&xt[af].mutex);
+		break;
+	}
+
+	if (!found)
+		goto out;
+
+	/* and once again: */
+	list_for_each_entry(t, &net->xt.tables[af], list)
+		if (strcmp(t->name, name) == 0)
+			return t;
+
+	module_put(found->me);
+ out:
 	mutex_unlock(&xt[af].mutex);
 	return NULL;
 }
@@ -1170,20 +1203,20 @@ static const struct file_operations xt_target_ops = {
 #endif /* CONFIG_PROC_FS */
 
 /**
- * xt_hook_link - set up hooks for a new table
+ * xt_hook_ops_alloc - set up hooks for a new table
  * @table:	table with metadata needed to set up hooks
  * @fn:		Hook function
  *
- * This function will take care of creating and registering the necessary
- * Netfilter hooks for XT tables.
+ * This function will create the nf_hook_ops that the x_table needs
+ * to hand to xt_hook_link_net().
  */
-struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn)
+struct nf_hook_ops *
+xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn)
 {
 	unsigned int hook_mask = table->valid_hooks;
 	uint8_t i, num_hooks = hweight32(hook_mask);
 	uint8_t hooknum;
 	struct nf_hook_ops *ops;
-	int ret;
 
 	ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL);
 	if (ops == NULL)
@@ -1200,27 +1233,9 @@ struct nf_hook_ops *xt_hook_link(const struct xt_table *table, nf_hookfn *fn)
 		++i;
 	}
 
-	ret = nf_register_hooks(ops, num_hooks);
-	if (ret < 0) {
-		kfree(ops);
-		return ERR_PTR(ret);
-	}
-
 	return ops;
 }
-EXPORT_SYMBOL_GPL(xt_hook_link);
-
-/**
- * xt_hook_unlink - remove hooks for a table
- * @ops:	nf_hook_ops array as returned by nf_hook_link
- * @hook_mask:	the very same mask that was passed to nf_hook_link
- */
-void xt_hook_unlink(const struct xt_table *table, struct nf_hook_ops *ops)
-{
-	nf_unregister_hooks(ops, hweight32(table->valid_hooks));
-	kfree(ops);
-}
-EXPORT_SYMBOL_GPL(xt_hook_unlink);
+EXPORT_SYMBOL_GPL(xt_hook_ops_alloc);
 
 int xt_proto_init(struct net *net, u_int8_t af)
 {