Merge tag 'nf-26-05-08' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following batch contains Netfilter fixes for net:

1) Allow initial x_tables table replacement without emitting an audit
   log message. Delay the register message until after hooks are wired up
   to avoid unnecessary unregister logs during error unwinding.

2) Fix a NULL dereference by allocating hook ops before adding the
   table to the per-netns list. Use `synchronize_rcu()` during error
   unwinding to ensure the table stops processing packets before
   teardown. Defer audit log register message until all operations
   succeed.

3) Refactor xtables to use a single `xt_unregister_table_pre_exit`
   function. Eliminate code duplication by centralizing table
   unregistration logic within the xtables core. ebtables cannot be
   changed due to incompatibility.

4) Unregister xtables templates before module removal. This prevents
   a race condition where userspace instantiates a new table after the
   pernet unreg removed the current table.

5) Add `xtables_unregister_table_exit` to fully unregister netfilter
   tables during module removal. Unlink the table from dying lists,
   then free hook operations.

6) Implement a two-stage removal scheme for ebtables following the
   x_tables pattern. Assign table->ops while holding the ebt mutex to
   prevent exposing partially-filled structures.

7) Fix ebtables module initialization race. Register the template last
   in table initialization functions. Prevent table instantiation before
   pernet operations are available.

8) Fix a race condition in x_tables module initialization. Ensure
   pernet ops are fully set up before exposing the table to userspace.

9) Fix a race condition in ebtables module initialization, similar to
   previous patch.

10) Restore propagation of helper to expected connection, this is a
    fix-for-recent-fix.

11) Validate that the expectation tuple and mask netlink attributes are
    present when adding expectation via nfqueue, this fixes a possible
    null-ptr-deref.

12) Fix possible rare memleak in the SIP helper in case helper has been
    detached from conntrack entry, from Li Xiasong.

13) Fix refcount leak in nft_ct when creating custom expectation, also
    from Li Xiason.

Patches 1-9 from Florian Westphal.

10) Restore propagation of helper to expected connection, this is a
    fix-for-recent-fix.

11) Check that tuple and mask netlink attributes are set when creating an
    expectation via nfqueue.

* tag 'nf-26-05-08' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  netfilter: nft_ct: fix missing expect put in obj eval
  netfilter: nf_conntrack_sip: get helper before allocating expectation
  netfilter: ctnetlink: check tuple and mask in expectations created via nfqueue
  netfilter: nf_conntrack_expect: restore helper propagation via expectation
  netfilter: bridge: eb_tables: close module init race
  netfilter: x_tables: close dangling table module init race
  netfilter: ebtables: close dangling table module init race
  netfilter: ebtables: move to two-stage removal scheme
  netfilter: x_tables: add and use xtables_unregister_table_exit
  netfilter: x_tables: unregister the templates first
  netfilter: x_tables: add and use xt_unregister_table_pre_exit
  netfilter: x_tables: allocate hook ops while under mutex
  netfilter: x_tables: allow initial table replace without emitting audit log message
====================

Link: https://patch.msgid.link/20260507234509.603182-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/netfilter/x_tables.h

@@ -305,9 +305,11 @@ struct xt_counters *xt_counters_alloc(unsigned int counters);
 
 struct xt_table *xt_register_table(struct net *net,
 				   const struct xt_table *table,
+				   const struct nf_hook_ops *template_ops,
 				   struct xt_table_info *bootstrap,
 				   struct xt_table_info *newinfo);
-void *xt_unregister_table(struct xt_table *table);
+void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name);
+struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name);
 
 struct xt_table_info *xt_replace_table(struct xt_table *table,
 				       unsigned int num_counters,

include/linux/netfilter_arp/arp_tables.h

@@ -53,7 +53,6 @@ int arpt_register_table(struct net *net, const struct xt_table *table,
 			const struct arpt_replace *repl,
 			const struct nf_hook_ops *ops);
 void arpt_unregister_table(struct net *net, const char *name);
-void arpt_unregister_table_pre_exit(struct net *net, const char *name);
 extern unsigned int arpt_do_table(void *priv, struct sk_buff *skb,
 				  const struct nf_hook_state *state);
 

include/linux/netfilter_ipv4/ip_tables.h

@@ -26,7 +26,6 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
 		       const struct ipt_replace *repl,
 		       const struct nf_hook_ops *ops);
 
-void ipt_unregister_table_pre_exit(struct net *net, const char *name);
 void ipt_unregister_table_exit(struct net *net, const char *name);
 
 /* Standard entry. */

include/linux/netfilter_ipv6/ip6_tables.h

@@ -27,7 +27,6 @@ extern void *ip6t_alloc_initial_table(const struct xt_table *);
 int ip6t_register_table(struct net *net, const struct xt_table *table,
 			const struct ip6t_replace *repl,
 			const struct nf_hook_ops *ops);
-void ip6t_unregister_table_pre_exit(struct net *net, const char *name);
 void ip6t_unregister_table_exit(struct net *net, const char *name);
 extern unsigned int ip6t_do_table(void *priv, struct sk_buff *skb,
 				  const struct nf_hook_state *state);

include/net/netfilter/nf_conntrack_expect.h

@@ -45,9 +45,12 @@ struct nf_conntrack_expect {
 	void (*expectfn)(struct nf_conn *new,
 			 struct nf_conntrack_expect *this);
 
-	/* Helper to assign to new connection */
+	/* Helper that created this expectation */
 	struct nf_conntrack_helper __rcu *helper;
 
+	/* Helper to assign to new connection */
+	struct nf_conntrack_helper __rcu *assign_helper;
+
 	/* The conntrack of the master connection */
 	struct nf_conn *master;
 

net/bridge/netfilter/ebtable_broute.c

@@ -112,24 +112,22 @@ static struct pernet_operations broute_net_ops = {
 
 static int __init ebtable_broute_init(void)
 {
-	int ret = ebt_register_template(&broute_table, broute_table_init);
+	int ret = register_pernet_subsys(&broute_net_ops);
 
 	if (ret)
 		return ret;
 
-	ret = register_pernet_subsys(&broute_net_ops);
-	if (ret) {
-		ebt_unregister_template(&broute_table);
-		return ret;
-	}
+	ret = ebt_register_template(&broute_table, broute_table_init);
+	if (ret)
+		unregister_pernet_subsys(&broute_net_ops);
 
-	return 0;
+	return ret;
 }
 
 static void __exit ebtable_broute_fini(void)
 {
-	unregister_pernet_subsys(&broute_net_ops);
 	ebt_unregister_template(&broute_table);
+	unregister_pernet_subsys(&broute_net_ops);
 }
 
 module_init(ebtable_broute_init);

net/bridge/netfilter/ebtable_filter.c

@@ -93,24 +93,22 @@ static struct pernet_operations frame_filter_net_ops = {
 
 static int __init ebtable_filter_init(void)
 {
-	int ret = ebt_register_template(&frame_filter, frame_filter_table_init);
+	int ret = register_pernet_subsys(&frame_filter_net_ops);
 
 	if (ret)
 		return ret;
 
-	ret = register_pernet_subsys(&frame_filter_net_ops);
-	if (ret) {
-		ebt_unregister_template(&frame_filter);
-		return ret;
-	}
+	ret = ebt_register_template(&frame_filter, frame_filter_table_init);
+	if (ret)
+		unregister_pernet_subsys(&frame_filter_net_ops);
 
-	return 0;
+	return ret;
 }
 
 static void __exit ebtable_filter_fini(void)
 {
-	unregister_pernet_subsys(&frame_filter_net_ops);
 	ebt_unregister_template(&frame_filter);
+	unregister_pernet_subsys(&frame_filter_net_ops);
 }
 
 module_init(ebtable_filter_init);

net/bridge/netfilter/ebtable_nat.c

@@ -93,24 +93,22 @@ static struct pernet_operations frame_nat_net_ops = {
 
 static int __init ebtable_nat_init(void)
 {
-	int ret = ebt_register_template(&frame_nat, frame_nat_table_init);
+	int ret = register_pernet_subsys(&frame_nat_net_ops);
 
 	if (ret)
 		return ret;
 
-	ret = register_pernet_subsys(&frame_nat_net_ops);
-	if (ret) {
-		ebt_unregister_template(&frame_nat);
-		return ret;
-	}
+	ret = ebt_register_template(&frame_nat, frame_nat_table_init);
+	if (ret)
+		unregister_pernet_subsys(&frame_nat_net_ops);
 
 	return ret;
 }
 
 static void __exit ebtable_nat_fini(void)
 {
-	unregister_pernet_subsys(&frame_nat_net_ops);
 	ebt_unregister_template(&frame_nat);
+	unregister_pernet_subsys(&frame_nat_net_ops);
 }
 
 module_init(ebtable_nat_init);

net/bridge/netfilter/ebtables.c

@@ -42,6 +42,7 @@
 
 struct ebt_pernet {
 	struct list_head tables;
+	struct list_head dead_tables;
 };
 
 struct ebt_template {
@@ -1162,11 +1163,6 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
 
 static void __ebt_unregister_table(struct net *net, struct ebt_table *table)
 {
-	mutex_lock(&ebt_mutex);
-	list_del(&table->list);
-	mutex_unlock(&ebt_mutex);
-	audit_log_nfcfg(table->name, AF_BRIDGE, table->private->nentries,
-			AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
 	EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size,
 			  ebt_cleanup_entry, net, NULL);
 	if (table->private->nentries)
@@ -1267,13 +1263,15 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
 	for (i = 0; i < num_ops; i++)
 		ops[i].priv = table;
 
-	list_add(&table->list, &ebt_net->tables);
-	mutex_unlock(&ebt_mutex);
-
 	table->ops = ops;
 	ret = nf_register_net_hooks(net, ops, num_ops);
-	if (ret)
+	if (ret) {
+		synchronize_rcu();
 		__ebt_unregister_table(net, table);
+	} else {
+		list_add(&table->list, &ebt_net->tables);
+	}
+	mutex_unlock(&ebt_mutex);
 
 	audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries,
 			AUDIT_XT_OP_REGISTER, GFP_KERNEL);
@@ -1339,7 +1337,7 @@ void ebt_unregister_template(const struct ebt_table *t)
 }
 EXPORT_SYMBOL(ebt_unregister_template);
 
-static struct ebt_table *__ebt_find_table(struct net *net, const char *name)
+void ebt_unregister_table_pre_exit(struct net *net, const char *name)
 {
 	struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id);
 	struct ebt_table *t;
@@ -1348,30 +1346,36 @@ static struct ebt_table *__ebt_find_table(struct net *net, const char *name)
 
 	list_for_each_entry(t, &ebt_net->tables, list) {
 		if (strcmp(t->name, name) == 0) {
+			list_move(&t->list, &ebt_net->dead_tables);
 			mutex_unlock(&ebt_mutex);
-			return t;
+			nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks));
+			return;
 		}
 	}
 
 	mutex_unlock(&ebt_mutex);
-	return NULL;
-}
-
-void ebt_unregister_table_pre_exit(struct net *net, const char *name)
-{
-	struct ebt_table *table = __ebt_find_table(net, name);
-
-	if (table)
-		nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks));
 }
 EXPORT_SYMBOL(ebt_unregister_table_pre_exit);
 
 void ebt_unregister_table(struct net *net, const char *name)
 {
-	struct ebt_table *table = __ebt_find_table(net, name);
+	struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id);
+	struct ebt_table *t;
 
-	if (table)
-		__ebt_unregister_table(net, table);
+	mutex_lock(&ebt_mutex);
+
+	list_for_each_entry(t, &ebt_net->dead_tables, list) {
+		if (strcmp(t->name, name) == 0) {
+			list_del(&t->list);
+			audit_log_nfcfg(t->name, AF_BRIDGE, t->private->nentries,
+					AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
+			__ebt_unregister_table(net, t);
+			mutex_unlock(&ebt_mutex);
+			return;
+		}
+	}
+
+	mutex_unlock(&ebt_mutex);
 }
 
 /* userspace just supplied us with counters */
@@ -2556,11 +2560,21 @@ static int __net_init ebt_pernet_init(struct net *net)
 	struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id);
 
 	INIT_LIST_HEAD(&ebt_net->tables);
+	INIT_LIST_HEAD(&ebt_net->dead_tables);
 	return 0;
 }
 
+static void __net_exit ebt_pernet_exit(struct net *net)
+{
+	struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id);
+
+	WARN_ON_ONCE(!list_empty(&ebt_net->tables));
+	WARN_ON_ONCE(!list_empty(&ebt_net->dead_tables));
+}
+
 static struct pernet_operations ebt_net_ops = {
 	.init = ebt_pernet_init,
+	.exit = ebt_pernet_exit,
 	.id   = &ebt_pernet_id,
 	.size = sizeof(struct ebt_pernet),
 };
@@ -2569,19 +2583,20 @@ static int __init ebtables_init(void)
 {
 	int ret;
 
-	ret = xt_register_target(&ebt_standard_target);
+	ret = register_pernet_subsys(&ebt_net_ops);
 	if (ret < 0)
 		return ret;
-	ret = nf_register_sockopt(&ebt_sockopts);
+
+	ret = xt_register_target(&ebt_standard_target);
 	if (ret < 0) {
-		xt_unregister_target(&ebt_standard_target);
+		unregister_pernet_subsys(&ebt_net_ops);
 		return ret;
 	}
 
-	ret = register_pernet_subsys(&ebt_net_ops);
+	ret = nf_register_sockopt(&ebt_sockopts);
 	if (ret < 0) {
-		nf_unregister_sockopt(&ebt_sockopts);
 		xt_unregister_target(&ebt_standard_target);
+		unregister_pernet_subsys(&ebt_net_ops);
 		return ret;
 	}
 

net/ipv4/netfilter/arp_tables.c

@@ -1501,13 +1501,11 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
 
 static void __arpt_unregister_table(struct net *net, struct xt_table *table)
 {
-	struct xt_table_info *private;
-	void *loc_cpu_entry;
+	struct xt_table_info *private = table->private;
 	struct module *table_owner = table->me;
+	void *loc_cpu_entry;
 	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)
@@ -1515,6 +1513,7 @@ static void __arpt_unregister_table(struct net *net, struct xt_table *table)
 	if (private->number > private->initial_entries)
 		module_put(table_owner);
 	xt_free_table_info(private);
+	kfree(table);
 }
 
 int arpt_register_table(struct net *net,
@@ -1522,13 +1521,11 @@ int arpt_register_table(struct net *net,
 			const struct arpt_replace *repl,
 			const struct nf_hook_ops *template_ops)
 {
-	struct nf_hook_ops *ops;
-	unsigned int num_ops;
-	int ret, i;
-	struct xt_table_info *newinfo;
 	struct xt_table_info bootstrap = {0};
-	void *loc_cpu_entry;
+	struct xt_table_info *newinfo;
 	struct xt_table *new_table;
+	void *loc_cpu_entry;
+	int ret;
 
 	newinfo = xt_alloc_table_info(repl->size);
 	if (!newinfo)
@@ -1543,7 +1540,7 @@ int arpt_register_table(struct net *net,
 		return ret;
 	}
 
-	new_table = xt_register_table(net, table, &bootstrap, newinfo);
+	new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo);
 	if (IS_ERR(new_table)) {
 		struct arpt_entry *iter;
 
@@ -1553,46 +1550,12 @@ int arpt_register_table(struct net *net,
 		return PTR_ERR(new_table);
 	}
 
-	num_ops = hweight32(table->valid_hooks);
-	if (num_ops == 0) {
-		ret = -EINVAL;
-		goto out_free;
-	}
-
-	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
-	if (!ops) {
-		ret = -ENOMEM;
-		goto out_free;
-	}
-
-	for (i = 0; i < num_ops; i++)
-		ops[i].priv = new_table;
-
-	new_table->ops = ops;
-
-	ret = nf_register_net_hooks(net, ops, num_ops);
-	if (ret != 0)
-		goto out_free;
-
-	return ret;
-
-out_free:
-	__arpt_unregister_table(net, new_table);
 	return ret;
 }
 
-void arpt_unregister_table_pre_exit(struct net *net, const char *name)
-{
-	struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name);
-
-	if (table)
-		nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks));
-}
-EXPORT_SYMBOL(arpt_unregister_table_pre_exit);
-
 void arpt_unregister_table(struct net *net, const char *name)
 {
-	struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name);
+	struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_ARP, name);
 
 	if (table)
 		__arpt_unregister_table(net, table);

net/ipv4/netfilter/arptable_filter.c

@@ -43,7 +43,7 @@ static int arptable_filter_table_init(struct net *net)
 
 static void __net_exit arptable_filter_net_pre_exit(struct net *net)
 {
-	arpt_unregister_table_pre_exit(net, "filter");
+	xt_unregister_table_pre_exit(net, NFPROTO_ARP, "filter");
 }
 
 static void __net_exit arptable_filter_net_exit(struct net *net)
@@ -58,32 +58,33 @@ static struct pernet_operations arptable_filter_net_ops = {
 
 static int __init arptable_filter_init(void)
 {
-	int ret = xt_register_template(&packet_filter,
-				       arptable_filter_table_init);
-
-	if (ret < 0)
-		return ret;
+	int ret;
 
 	arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arpt_do_table);
-	if (IS_ERR(arpfilter_ops)) {
-		xt_unregister_template(&packet_filter);
+	if (IS_ERR(arpfilter_ops))
 		return PTR_ERR(arpfilter_ops);
-	}
 
 	ret = register_pernet_subsys(&arptable_filter_net_ops);
+	if (ret < 0)
+		goto err_free;
+
+	ret = xt_register_template(&packet_filter,
+				   arptable_filter_table_init);
 	if (ret < 0) {
-		xt_unregister_template(&packet_filter);
-		kfree(arpfilter_ops);
-		return ret;
+		unregister_pernet_subsys(&arptable_filter_net_ops);
+		goto err_free;
 	}
 
+	return 0;
+err_free:
+	kfree(arpfilter_ops);
 	return ret;
 }
 
 static void __exit arptable_filter_fini(void)
 {
-	unregister_pernet_subsys(&arptable_filter_net_ops);
 	xt_unregister_template(&packet_filter);
+	unregister_pernet_subsys(&arptable_filter_net_ops);
 	kfree(arpfilter_ops);
 }
 

net/ipv4/netfilter/ip_tables.c

@@ -1704,12 +1704,10 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 
 static void __ipt_unregister_table(struct net *net, struct xt_table *table)
 {
-	struct xt_table_info *private;
-	void *loc_cpu_entry;
+	struct xt_table_info *private = table->private;
 	struct module *table_owner = table->me;
 	struct ipt_entry *iter;
-
-	private = xt_unregister_table(table);
+	void *loc_cpu_entry;
 
 	/* Decrease module usage counts and free resources */
 	loc_cpu_entry = private->entries;
@@ -1718,19 +1716,18 @@ static void __ipt_unregister_table(struct net *net, struct xt_table *table)
 	if (private->number > private->initial_entries)
 		module_put(table_owner);
 	xt_free_table_info(private);
+	kfree(table);
 }
 
 int ipt_register_table(struct net *net, const struct xt_table *table,
 		       const struct ipt_replace *repl,
 		       const struct nf_hook_ops *template_ops)
 {
-	struct nf_hook_ops *ops;
-	unsigned int num_ops;
-	int ret, i;
-	struct xt_table_info *newinfo;
 	struct xt_table_info bootstrap = {0};
-	void *loc_cpu_entry;
+	struct xt_table_info *newinfo;
 	struct xt_table *new_table;
+	void *loc_cpu_entry;
+	int ret;
 
 	newinfo = xt_alloc_table_info(repl->size);
 	if (!newinfo)
@@ -1745,7 +1742,7 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
 		return ret;
 	}
 
-	new_table = xt_register_table(net, table, &bootstrap, newinfo);
+	new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo);
 	if (IS_ERR(new_table)) {
 		struct ipt_entry *iter;
 
@@ -1755,51 +1752,12 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
 		return PTR_ERR(new_table);
 	}
 
-	/* No template? No need to do anything. This is used by 'nat' table, it registers
-	 * with the nat core instead of the netfilter core.
-	 */
-	if (!template_ops)
-		return 0;
-
-	num_ops = hweight32(table->valid_hooks);
-	if (num_ops == 0) {
-		ret = -EINVAL;
-		goto out_free;
-	}
-
-	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
-	if (!ops) {
-		ret = -ENOMEM;
-		goto out_free;
-	}
-
-	for (i = 0; i < num_ops; i++)
-		ops[i].priv = new_table;
-
-	new_table->ops = ops;
-
-	ret = nf_register_net_hooks(net, ops, num_ops);
-	if (ret != 0)
-		goto out_free;
-
 	return ret;
-
-out_free:
-	__ipt_unregister_table(net, new_table);
-	return ret;
-}
-
-void ipt_unregister_table_pre_exit(struct net *net, const char *name)
-{
-	struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name);
-
-	if (table)
-		nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks));
 }
 
 void ipt_unregister_table_exit(struct net *net, const char *name)
 {
-	struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name);
+	struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV4, name);
 
 	if (table)
 		__ipt_unregister_table(net, table);
@@ -1887,7 +1845,6 @@ static void __exit ip_tables_fini(void)
 }
 
 EXPORT_SYMBOL(ipt_register_table);
-EXPORT_SYMBOL(ipt_unregister_table_pre_exit);
 EXPORT_SYMBOL(ipt_unregister_table_exit);
 EXPORT_SYMBOL(ipt_do_table);
 module_init(ip_tables_init);

net/ipv4/netfilter/iptable_filter.c

@@ -61,7 +61,7 @@ static int __net_init iptable_filter_net_init(struct net *net)
 
 static void __net_exit iptable_filter_net_pre_exit(struct net *net)
 {
-	ipt_unregister_table_pre_exit(net, "filter");
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "filter");
 }
 
 static void __net_exit iptable_filter_net_exit(struct net *net)
@@ -77,32 +77,33 @@ static struct pernet_operations iptable_filter_net_ops = {
 
 static int __init iptable_filter_init(void)
 {
-	int ret = xt_register_template(&packet_filter,
-				       iptable_filter_table_init);
-
-	if (ret < 0)
-		return ret;
+	int ret;
 
 	filter_ops = xt_hook_ops_alloc(&packet_filter, ipt_do_table);
-	if (IS_ERR(filter_ops)) {
-		xt_unregister_template(&packet_filter);
+	if (IS_ERR(filter_ops))
 		return PTR_ERR(filter_ops);
-	}
 
 	ret = register_pernet_subsys(&iptable_filter_net_ops);
+	if (ret < 0)
+		goto err_free;
+
+	ret = xt_register_template(&packet_filter,
+				   iptable_filter_table_init);
 	if (ret < 0) {
-		xt_unregister_template(&packet_filter);
-		kfree(filter_ops);
-		return ret;
+		unregister_pernet_subsys(&iptable_filter_net_ops);
+		goto err_free;
 	}
 
 	return 0;
+err_free:
+	kfree(filter_ops);
+	return ret;
 }
 
 static void __exit iptable_filter_fini(void)
 {
-	unregister_pernet_subsys(&iptable_filter_net_ops);
 	xt_unregister_template(&packet_filter);
+	unregister_pernet_subsys(&iptable_filter_net_ops);
 	kfree(filter_ops);
 }
 

net/ipv4/netfilter/iptable_mangle.c

@@ -96,7 +96,7 @@ static int iptable_mangle_table_init(struct net *net)
 
 static void __net_exit iptable_mangle_net_pre_exit(struct net *net)
 {
-	ipt_unregister_table_pre_exit(net, "mangle");
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "mangle");
 }
 
 static void __net_exit iptable_mangle_net_exit(struct net *net)
@@ -111,32 +111,33 @@ static struct pernet_operations iptable_mangle_net_ops = {
 
 static int __init iptable_mangle_init(void)
 {
-	int ret = xt_register_template(&packet_mangler,
-				       iptable_mangle_table_init);
-	if (ret < 0)
-		return ret;
+	int ret;
 
 	mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook);
-	if (IS_ERR(mangle_ops)) {
-		xt_unregister_template(&packet_mangler);
-		ret = PTR_ERR(mangle_ops);
-		return ret;
-	}
+	if (IS_ERR(mangle_ops))
+		return PTR_ERR(mangle_ops);
 
 	ret = register_pernet_subsys(&iptable_mangle_net_ops);
+	if (ret < 0)
+		goto err_free;
+
+	ret = xt_register_template(&packet_mangler,
+				   iptable_mangle_table_init);
 	if (ret < 0) {
-		xt_unregister_template(&packet_mangler);
-		kfree(mangle_ops);
-		return ret;
+		unregister_pernet_subsys(&iptable_mangle_net_ops);
+		goto err_free;
 	}
 
+	return 0;
+err_free:
+	kfree(mangle_ops);
 	return ret;
 }
 
 static void __exit iptable_mangle_fini(void)
 {
-	unregister_pernet_subsys(&iptable_mangle_net_ops);
 	xt_unregister_template(&packet_mangler);
+	unregister_pernet_subsys(&iptable_mangle_net_ops);
 	kfree(mangle_ops);
 }
 

net/ipv4/netfilter/iptable_nat.c

@@ -119,8 +119,11 @@ static int iptable_nat_table_init(struct net *net)
 	}
 
 	ret = ipt_nat_register_lookups(net);
-	if (ret < 0)
+	if (ret < 0) {
+		xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat");
+		synchronize_rcu();
 		ipt_unregister_table_exit(net, "nat");
+	}
 
 	kfree(repl);
 	return ret;
@@ -129,6 +132,7 @@ static int iptable_nat_table_init(struct net *net)
 static void __net_exit iptable_nat_net_pre_exit(struct net *net)
 {
 	ipt_nat_unregister_lookups(net);
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat");
 }
 
 static void __net_exit iptable_nat_net_exit(struct net *net)

net/ipv4/netfilter/iptable_raw.c

@@ -53,7 +53,7 @@ static int iptable_raw_table_init(struct net *net)
 
 static void __net_exit iptable_raw_net_pre_exit(struct net *net)
 {
-	ipt_unregister_table_pre_exit(net, "raw");
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "raw");
 }
 
 static void __net_exit iptable_raw_net_exit(struct net *net)
@@ -77,32 +77,32 @@ static int __init iptable_raw_init(void)
 		pr_info("Enabling raw table before defrag\n");
 	}
 
-	ret = xt_register_template(table,
-				   iptable_raw_table_init);
-	if (ret < 0)
-		return ret;
-
 	rawtable_ops = xt_hook_ops_alloc(table, ipt_do_table);
-	if (IS_ERR(rawtable_ops)) {
-		xt_unregister_template(table);
+	if (IS_ERR(rawtable_ops))
 		return PTR_ERR(rawtable_ops);
-	}
 
 	ret = register_pernet_subsys(&iptable_raw_net_ops);
+	if (ret < 0)
+		goto err_free;
+
+	ret = xt_register_template(table,
+				   iptable_raw_table_init);
 	if (ret < 0) {
-		xt_unregister_template(table);
-		kfree(rawtable_ops);
-		return ret;
+		unregister_pernet_subsys(&iptable_raw_net_ops);
+		goto err_free;
 	}
 
+	return 0;
+err_free:
+	kfree(rawtable_ops);
 	return ret;
 }
 
 static void __exit iptable_raw_fini(void)
 {
+	xt_unregister_template(&packet_raw);
 	unregister_pernet_subsys(&iptable_raw_net_ops);
 	kfree(rawtable_ops);
-	xt_unregister_template(&packet_raw);
 }
 
 module_init(iptable_raw_init);

net/ipv4/netfilter/iptable_security.c

@@ -50,7 +50,7 @@ static int iptable_security_table_init(struct net *net)
 
 static void __net_exit iptable_security_net_pre_exit(struct net *net)
 {
-	ipt_unregister_table_pre_exit(net, "security");
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "security");
 }
 
 static void __net_exit iptable_security_net_exit(struct net *net)
@@ -65,33 +65,34 @@ static struct pernet_operations iptable_security_net_ops = {
 
 static int __init iptable_security_init(void)
 {
-	int ret = xt_register_template(&security_table,
-				       iptable_security_table_init);
-
-	if (ret < 0)
-		return ret;
+	int ret;
 
 	sectbl_ops = xt_hook_ops_alloc(&security_table, ipt_do_table);
-	if (IS_ERR(sectbl_ops)) {
-		xt_unregister_template(&security_table);
+	if (IS_ERR(sectbl_ops))
 		return PTR_ERR(sectbl_ops);
-	}
 
 	ret = register_pernet_subsys(&iptable_security_net_ops);
+	if (ret < 0)
+		goto err_free;
+
+	ret = xt_register_template(&security_table,
+				   iptable_security_table_init);
 	if (ret < 0) {
-		xt_unregister_template(&security_table);
-		kfree(sectbl_ops);
-		return ret;
+		unregister_pernet_subsys(&iptable_security_net_ops);
+		goto err_free;
 	}
 
+	return 0;
+err_free:
+	kfree(sectbl_ops);
 	return ret;
 }
 
 static void __exit iptable_security_fini(void)
 {
+	xt_unregister_template(&security_table);
 	unregister_pernet_subsys(&iptable_security_net_ops);
 	kfree(sectbl_ops);
-	xt_unregister_template(&security_table);
 }
 
 module_init(iptable_security_init);

net/ipv6/netfilter/ip6_tables.c

@@ -1713,12 +1713,10 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 
 static void __ip6t_unregister_table(struct net *net, struct xt_table *table)
 {
-	struct xt_table_info *private;
-	void *loc_cpu_entry;
+	struct xt_table_info *private = table->private;
 	struct module *table_owner = table->me;
 	struct ip6t_entry *iter;
-
-	private = xt_unregister_table(table);
+	void *loc_cpu_entry;
 
 	/* Decrease module usage counts and free resources */
 	loc_cpu_entry = private->entries;
@@ -1727,19 +1725,18 @@ static void __ip6t_unregister_table(struct net *net, struct xt_table *table)
 	if (private->number > private->initial_entries)
 		module_put(table_owner);
 	xt_free_table_info(private);
+	kfree(table);
 }
 
 int ip6t_register_table(struct net *net, const struct xt_table *table,
 			const struct ip6t_replace *repl,
 			const struct nf_hook_ops *template_ops)
 {
-	struct nf_hook_ops *ops;
-	unsigned int num_ops;
-	int ret, i;
-	struct xt_table_info *newinfo;
 	struct xt_table_info bootstrap = {0};
-	void *loc_cpu_entry;
+	struct xt_table_info *newinfo;
 	struct xt_table *new_table;
+	void *loc_cpu_entry;
+	int ret;
 
 	newinfo = xt_alloc_table_info(repl->size);
 	if (!newinfo)
@@ -1754,7 +1751,7 @@ int ip6t_register_table(struct net *net, const struct xt_table *table,
 		return ret;
 	}
 
-	new_table = xt_register_table(net, table, &bootstrap, newinfo);
+	new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo);
 	if (IS_ERR(new_table)) {
 		struct ip6t_entry *iter;
 
@@ -1764,48 +1761,12 @@ int ip6t_register_table(struct net *net, const struct xt_table *table,
 		return PTR_ERR(new_table);
 	}
 
-	if (!template_ops)
-		return 0;
-
-	num_ops = hweight32(table->valid_hooks);
-	if (num_ops == 0) {
-		ret = -EINVAL;
-		goto out_free;
-	}
-
-	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
-	if (!ops) {
-		ret = -ENOMEM;
-		goto out_free;
-	}
-
-	for (i = 0; i < num_ops; i++)
-		ops[i].priv = new_table;
-
-	new_table->ops = ops;
-
-	ret = nf_register_net_hooks(net, ops, num_ops);
-	if (ret != 0)
-		goto out_free;
-
 	return ret;
-
-out_free:
-	__ip6t_unregister_table(net, new_table);
-	return ret;
-}
-
-void ip6t_unregister_table_pre_exit(struct net *net, const char *name)
-{
-	struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name);
-
-	if (table)
-		nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks));
 }
 
 void ip6t_unregister_table_exit(struct net *net, const char *name)
 {
-	struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name);
+	struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV6, name);
 
 	if (table)
 		__ip6t_unregister_table(net, table);
@@ -1894,7 +1855,6 @@ static void __exit ip6_tables_fini(void)
 }
 
 EXPORT_SYMBOL(ip6t_register_table);
-EXPORT_SYMBOL(ip6t_unregister_table_pre_exit);
 EXPORT_SYMBOL(ip6t_unregister_table_exit);
 EXPORT_SYMBOL(ip6t_do_table);
 

net/ipv6/netfilter/ip6table_filter.c

@@ -60,7 +60,7 @@ static int __net_init ip6table_filter_net_init(struct net *net)
 
 static void __net_exit ip6table_filter_net_pre_exit(struct net *net)
 {
-	ip6t_unregister_table_pre_exit(net, "filter");
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "filter");
 }
 
 static void __net_exit ip6table_filter_net_exit(struct net *net)
@@ -76,32 +76,32 @@ static struct pernet_operations ip6table_filter_net_ops = {
 
 static int __init ip6table_filter_init(void)
 {
-	int ret = xt_register_template(&packet_filter,
-					ip6table_filter_table_init);
-
-	if (ret < 0)
-		return ret;
+	int ret;
 
 	filter_ops = xt_hook_ops_alloc(&packet_filter, ip6t_do_table);
-	if (IS_ERR(filter_ops)) {
-		xt_unregister_template(&packet_filter);
+	if (IS_ERR(filter_ops))
 		return PTR_ERR(filter_ops);
-	}
 
 	ret = register_pernet_subsys(&ip6table_filter_net_ops);
+	if (ret < 0)
+		goto err_free;
+
+	ret = xt_register_template(&packet_filter, ip6table_filter_table_init);
 	if (ret < 0) {
-		xt_unregister_template(&packet_filter);
-		kfree(filter_ops);
-		return ret;
+		unregister_pernet_subsys(&ip6table_filter_net_ops);
+		goto err_free;
 	}
 
+	return 0;
+err_free:
+	kfree(filter_ops);
 	return ret;
 }
 
 static void __exit ip6table_filter_fini(void)
 {
-	unregister_pernet_subsys(&ip6table_filter_net_ops);
 	xt_unregister_template(&packet_filter);
+	unregister_pernet_subsys(&ip6table_filter_net_ops);
 	kfree(filter_ops);
 }
 

net/ipv6/netfilter/ip6table_mangle.c

@@ -89,7 +89,7 @@ static int ip6table_mangle_table_init(struct net *net)
 
 static void __net_exit ip6table_mangle_net_pre_exit(struct net *net)
 {
-	ip6t_unregister_table_pre_exit(net, "mangle");
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "mangle");
 }
 
 static void __net_exit ip6table_mangle_net_exit(struct net *net)
@@ -104,32 +104,33 @@ static struct pernet_operations ip6table_mangle_net_ops = {
 
 static int __init ip6table_mangle_init(void)
 {
-	int ret = xt_register_template(&packet_mangler,
-				       ip6table_mangle_table_init);
-
-	if (ret < 0)
-		return ret;
+	int ret;
 
 	mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook);
-	if (IS_ERR(mangle_ops)) {
-		xt_unregister_template(&packet_mangler);
+	if (IS_ERR(mangle_ops))
 		return PTR_ERR(mangle_ops);
-	}
 
 	ret = register_pernet_subsys(&ip6table_mangle_net_ops);
+	if (ret < 0)
+		goto err_free;
+
+	ret = xt_register_template(&packet_mangler,
+				   ip6table_mangle_table_init);
 	if (ret < 0) {
-		xt_unregister_template(&packet_mangler);
-		kfree(mangle_ops);
-		return ret;
+		unregister_pernet_subsys(&ip6table_mangle_net_ops);
+		goto err_free;
 	}
 
+	return 0;
+err_free:
+	kfree(mangle_ops);
 	return ret;
 }
 
 static void __exit ip6table_mangle_fini(void)
 {
-	unregister_pernet_subsys(&ip6table_mangle_net_ops);
 	xt_unregister_template(&packet_mangler);
+	unregister_pernet_subsys(&ip6table_mangle_net_ops);
 	kfree(mangle_ops);
 }
 

net/ipv6/netfilter/ip6table_nat.c

@@ -121,8 +121,11 @@ static int ip6table_nat_table_init(struct net *net)
 	}
 
 	ret = ip6t_nat_register_lookups(net);
-	if (ret < 0)
+	if (ret < 0) {
+		xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat");
+		synchronize_rcu();
 		ip6t_unregister_table_exit(net, "nat");
+	}
 
 	kfree(repl);
 	return ret;
@@ -131,6 +134,7 @@ static int ip6table_nat_table_init(struct net *net)
 static void __net_exit ip6table_nat_net_pre_exit(struct net *net)
 {
 	ip6t_nat_unregister_lookups(net);
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat");
 }
 
 static void __net_exit ip6table_nat_net_exit(struct net *net)

net/ipv6/netfilter/ip6table_raw.c

@@ -52,7 +52,7 @@ static int ip6table_raw_table_init(struct net *net)
 
 static void __net_exit ip6table_raw_net_pre_exit(struct net *net)
 {
-	ip6t_unregister_table_pre_exit(net, "raw");
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "raw");
 }
 
 static void __net_exit ip6table_raw_net_exit(struct net *net)
@@ -75,31 +75,31 @@ static int __init ip6table_raw_init(void)
 		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, ip6t_do_table);
-	if (IS_ERR(rawtable_ops)) {
-		xt_unregister_template(table);
+	if (IS_ERR(rawtable_ops))
 		return PTR_ERR(rawtable_ops);
-	}
 
 	ret = register_pernet_subsys(&ip6table_raw_net_ops);
+	if (ret < 0)
+		goto err_free;
+
+	ret = xt_register_template(table, ip6table_raw_table_init);
 	if (ret < 0) {
-		kfree(rawtable_ops);
-		xt_unregister_template(table);
-		return ret;
+		unregister_pernet_subsys(&ip6table_raw_net_ops);
+		goto err_free;
 	}
 
+	return 0;
+err_free:
+	kfree(rawtable_ops);
 	return ret;
 }
 
 static void __exit ip6table_raw_fini(void)
 {
-	unregister_pernet_subsys(&ip6table_raw_net_ops);
 	xt_unregister_template(&packet_raw);
+	unregister_pernet_subsys(&ip6table_raw_net_ops);
 	kfree(rawtable_ops);
 }
 

net/ipv6/netfilter/ip6table_security.c

@@ -49,7 +49,7 @@ static int ip6table_security_table_init(struct net *net)
 
 static void __net_exit ip6table_security_net_pre_exit(struct net *net)
 {
-	ip6t_unregister_table_pre_exit(net, "security");
+	xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "security");
 }
 
 static void __net_exit ip6table_security_net_exit(struct net *net)
@@ -64,32 +64,33 @@ static struct pernet_operations ip6table_security_net_ops = {
 
 static int __init ip6table_security_init(void)
 {
-	int ret = xt_register_template(&security_table,
-				       ip6table_security_table_init);
-
-	if (ret < 0)
-		return ret;
+	int ret;
 
 	sectbl_ops = xt_hook_ops_alloc(&security_table, ip6t_do_table);
-	if (IS_ERR(sectbl_ops)) {
-		xt_unregister_template(&security_table);
+	if (IS_ERR(sectbl_ops))
 		return PTR_ERR(sectbl_ops);
-	}
 
 	ret = register_pernet_subsys(&ip6table_security_net_ops);
+	if (ret < 0)
+		goto err_free;
+
+	ret = xt_register_template(&security_table,
+				   ip6table_security_table_init);
 	if (ret < 0) {
-		kfree(sectbl_ops);
-		xt_unregister_template(&security_table);
-		return ret;
+		unregister_pernet_subsys(&ip6table_security_net_ops);
+		goto err_free;
 	}
 
+	return 0;
+err_free:
+	kfree(sectbl_ops);
 	return ret;
 }
 
 static void __exit ip6table_security_fini(void)
 {
-	unregister_pernet_subsys(&ip6table_security_net_ops);
 	xt_unregister_template(&security_table);
+	unregister_pernet_subsys(&ip6table_security_net_ops);
 	kfree(sectbl_ops);
 }
 

net/netfilter/nf_conntrack_broadcast.c

@@ -72,6 +72,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb,
 	exp->flags                = NF_CT_EXPECT_PERMANENT;
 	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
 	rcu_assign_pointer(exp->helper, helper);
+	rcu_assign_pointer(exp->assign_helper, NULL);
 	write_pnet(&exp->net, net);
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	exp->zone = ct->zone;

net/netfilter/nf_conntrack_core.c

@@ -1811,14 +1811,17 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 		spin_lock_bh(&nf_conntrack_expect_lock);
 		exp = nf_ct_find_expectation(net, zone, tuple, !tmpl || nf_ct_is_confirmed(tmpl));
 		if (exp) {
+			struct nf_conntrack_helper *assign_helper;
+
 			/* Welcome, Mr. Bond.  We've been expecting you... */
 			__set_bit(IPS_EXPECTED_BIT, &ct->status);
 			/* exp->master safe, refcnt bumped in nf_ct_find_expectation */
 			ct->master = exp->master;
-			if (exp->helper) {
+			assign_helper = rcu_dereference(exp->assign_helper);
+			if (assign_helper) {
 				help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
 				if (help)
-					rcu_assign_pointer(help->helper, exp->helper);
+					rcu_assign_pointer(help->helper, assign_helper);
 			}
 
 #ifdef CONFIG_NF_CONNTRACK_MARK

net/netfilter/nf_conntrack_expect.c

@@ -344,6 +344,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
 		helper = rcu_dereference(help->helper);
 
 	rcu_assign_pointer(exp->helper, helper);
+	rcu_assign_pointer(exp->assign_helper, NULL);
 	write_pnet(&exp->net, net);
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	exp->zone = ct->zone;

net/netfilter/nf_conntrack_h323_main.c

@@ -643,7 +643,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct,
 			  &ct->tuplehash[!dir].tuple.src.u3,
 			  &ct->tuplehash[!dir].tuple.dst.u3,
 			  IPPROTO_TCP, NULL, &port);
-	rcu_assign_pointer(exp->helper, &nf_conntrack_helper_h245);
+	rcu_assign_pointer(exp->assign_helper, &nf_conntrack_helper_h245);
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
 	if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -767,7 +767,7 @@ static int expect_callforwarding(struct sk_buff *skb,
 	nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_TCP, NULL, &port);
-	rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
 	if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -1234,7 +1234,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
 				&ct->tuplehash[!dir].tuple.src.u3 : NULL,
 			  &ct->tuplehash[!dir].tuple.dst.u3,
 			  IPPROTO_TCP, NULL, &port);
-	rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
 	exp->flags = NF_CT_EXPECT_PERMANENT;	/* Accept multiple calls */
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
@@ -1306,7 +1306,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
 	nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_UDP, NULL, &port);
-	rcu_assign_pointer(exp->helper, nf_conntrack_helper_ras);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_ras);
 
 	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect RAS ");
@@ -1523,7 +1523,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct,
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_TCP, NULL, &port);
 	exp->flags = NF_CT_EXPECT_PERMANENT;
-	rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
 
 	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect Q.931 ");
@@ -1577,7 +1577,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct,
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_TCP, NULL, &port);
 	exp->flags = NF_CT_EXPECT_PERMANENT;
-	rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
+	rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931);
 
 	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect Q.931 ");

net/netfilter/nf_conntrack_helper.c

@@ -400,6 +400,11 @@ static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data)
 
 	this = rcu_dereference_protected(exp->helper,
 					 lockdep_is_held(&nf_conntrack_expect_lock));
+	if (this == me)
+		return true;
+
+	this = rcu_dereference_protected(exp->assign_helper,
+					 lockdep_is_held(&nf_conntrack_expect_lock));
 	return this == me;
 }
 

net/netfilter/nf_conntrack_netlink.c

@@ -2634,6 +2634,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = {
 
 static struct nf_conntrack_expect *
 ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct,
+		       const struct nf_conntrack_helper *assign_helper,
 		       struct nf_conntrack_tuple *tuple,
 		       struct nf_conntrack_tuple *mask);
 
@@ -2860,6 +2861,7 @@ static int
 ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
 			     u32 portid, u32 report)
 {
+	struct nf_conntrack_helper *assign_helper = NULL;
 	struct nlattr *cda[CTA_EXPECT_MAX+1];
 	struct nf_conntrack_tuple tuple, mask;
 	struct nf_conntrack_expect *exp;
@@ -2870,13 +2872,26 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
 	if (err < 0)
 		return err;
 
+	if (!cda[CTA_EXPECT_TUPLE] || !cda[CTA_EXPECT_MASK])
+		return -EINVAL;
+
 	err = ctnetlink_glue_exp_parse((const struct nlattr * const *)cda,
 				       ct, &tuple, &mask);
 	if (err < 0)
 		return err;
 
+	if (cda[CTA_EXPECT_HELP_NAME]) {
+		const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
+
+		assign_helper = __nf_conntrack_helper_find(helpname,
+							   nf_ct_l3num(ct),
+							   tuple.dst.protonum);
+		if (!assign_helper)
+			return -EOPNOTSUPP;
+	}
+
 	exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct,
-				     &tuple, &mask);
+				     assign_helper, &tuple, &mask);
 	if (IS_ERR(exp))
 		return PTR_ERR(exp);
 
@@ -3515,6 +3530,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr,
 
 static struct nf_conntrack_expect *
 ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
+		       const struct nf_conntrack_helper *assign_helper,
 		       struct nf_conntrack_tuple *tuple,
 		       struct nf_conntrack_tuple *mask)
 {
@@ -3568,6 +3584,7 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 	exp->zone = ct->zone;
 #endif
 	rcu_assign_pointer(exp->helper, helper);
+	rcu_assign_pointer(exp->assign_helper, assign_helper);
 	exp->tuple = *tuple;
 	exp->mask.src.u3 = mask->src.u3;
 	exp->mask.src.u.all = mask->src.u.all;
@@ -3623,7 +3640,7 @@ ctnetlink_create_expect(struct net *net,
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
 	rcu_read_lock();
-	exp = ctnetlink_alloc_expect(cda, ct, &tuple, &mask);
+	exp = ctnetlink_alloc_expect(cda, ct, NULL, &tuple, &mask);
 	if (IS_ERR(exp)) {
 		err = PTR_ERR(exp);
 		goto err_rcu;

net/netfilter/nf_conntrack_sip.c

@@ -1366,6 +1366,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 		goto store_cseq;
 	}
 
+	helper = rcu_dereference(nfct_help(ct)->helper);
+	if (!helper)
+		return NF_DROP;
+
 	exp = nf_ct_expect_alloc(ct);
 	if (!exp) {
 		nf_ct_helper_log(skb, ct, "cannot alloc expectation");
@@ -1376,14 +1380,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 	if (sip_direct_signalling)
 		saddr = &ct->tuplehash[!dir].tuple.src.u3;
 
-	helper = rcu_dereference(nfct_help(ct)->helper);
-	if (!helper)
-		return NF_DROP;
-
 	nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct),
 			  saddr, &daddr, proto, NULL, &port);
 	exp->timeout.expires = sip_timeout * HZ;
-	rcu_assign_pointer(exp->helper, helper);
+	rcu_assign_pointer(exp->assign_helper, helper);
 	exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE;
 
 	hooks = rcu_dereference(nf_nat_sip_hooks);

net/netfilter/nft_ct.c

@@ -1334,6 +1334,8 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
 
 	if (nf_ct_expect_related(exp, 0) != 0)
 		regs->verdict.code = NF_DROP;
+
+	nf_ct_expect_put(exp);
 }
 
 static const struct nla_policy nft_ct_expect_policy[NFTA_CT_EXPECT_MAX + 1] = {

net/netfilter/x_tables.c

@@ -55,6 +55,9 @@ static struct list_head xt_templates[NFPROTO_NUMPROTO];
 
 struct xt_pernet {
 	struct list_head tables[NFPROTO_NUMPROTO];
+
+	/* stash area used during netns exit */
+	struct list_head dead_tables[NFPROTO_NUMPROTO];
 };
 
 struct compat_delta {
@@ -1472,11 +1475,9 @@ struct xt_counters *xt_counters_alloc(unsigned int counters)
 }
 EXPORT_SYMBOL(xt_counters_alloc);
 
-struct xt_table_info *
-xt_replace_table(struct xt_table *table,
-	      unsigned int num_counters,
-	      struct xt_table_info *newinfo,
-	      int *error)
+static struct xt_table_info *
+do_replace_table(struct xt_table *table, unsigned int num_counters,
+		 struct xt_table_info *newinfo, int *error)
 {
 	struct xt_table_info *private;
 	unsigned int cpu;
@@ -1531,30 +1532,54 @@ xt_replace_table(struct xt_table *table,
 		}
 	}
 
-	audit_log_nfcfg(table->name, table->af, private->number,
-			!private->number ? AUDIT_XT_OP_REGISTER :
-					   AUDIT_XT_OP_REPLACE,
-			GFP_KERNEL);
+	return private;
+}
+
+struct xt_table_info *
+xt_replace_table(struct xt_table *table, unsigned int num_counters,
+		 struct xt_table_info *newinfo,
+		 int *error)
+{
+	struct xt_table_info *private;
+
+	private = do_replace_table(table, num_counters, newinfo, error);
+	if (private)
+		audit_log_nfcfg(table->name, table->af, private->number,
+				AUDIT_XT_OP_REPLACE,
+				GFP_KERNEL);
+
 	return private;
 }
 EXPORT_SYMBOL_GPL(xt_replace_table);
 
 struct xt_table *xt_register_table(struct net *net,
 				   const struct xt_table *input_table,
+				   const struct nf_hook_ops *template_ops,
 				   struct xt_table_info *bootstrap,
 				   struct xt_table_info *newinfo)
 {
 	struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
+	struct xt_table *t, *table = NULL;
+	struct nf_hook_ops *ops = NULL;
 	struct xt_table_info *private;
-	struct xt_table *t, *table;
-	int ret;
+	unsigned int num_ops;
+	int ret = -EINVAL;
+
+	num_ops = hweight32(input_table->valid_hooks);
+	if (num_ops == 0)
+		goto out;
+
+	ret = -ENOMEM;
+	if (template_ops) {
+		ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
+		if (!ops)
+			goto out;
+	}
 
 	/* Don't add one object to multiple lists. */
 	table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL);
-	if (!table) {
-		ret = -ENOMEM;
+	if (!table)
 		goto out;
-	}
 
 	mutex_lock(&xt[table->af].mutex);
 	/* Don't autoload: we'd eat our tail... */
@@ -1568,7 +1593,7 @@ struct xt_table *xt_register_table(struct net *net,
 	/* Simplifies replace_table code. */
 	table->private = bootstrap;
 
-	if (!xt_replace_table(table, 0, newinfo, &ret))
+	if (!do_replace_table(table, 0, newinfo, &ret))
 		goto unlock;
 
 	private = table->private;
@@ -1577,34 +1602,122 @@ struct xt_table *xt_register_table(struct net *net,
 	/* save number of initial entries */
 	private->initial_entries = private->number;
 
+	if (ops) {
+		int i;
+
+		for (i = 0; i < num_ops; i++)
+			ops[i].priv = table;
+
+		ret = nf_register_net_hooks(net, ops, num_ops);
+		if (ret != 0) {
+			mutex_unlock(&xt[table->af].mutex);
+			/* nf_register_net_hooks() might have published a
+			 * base chain before internal error unwind.
+			 */
+			synchronize_rcu();
+			goto out;
+		}
+
+		table->ops = ops;
+	}
+
+	audit_log_nfcfg(table->name, table->af, private->number,
+			AUDIT_XT_OP_REGISTER, GFP_KERNEL);
+
 	list_add(&table->list, &xt_net->tables[table->af]);
 	mutex_unlock(&xt[table->af].mutex);
 	return table;
 
 unlock:
 	mutex_unlock(&xt[table->af].mutex);
-	kfree(table);
 out:
+	kfree(table);
+	kfree(ops);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(xt_register_table);
 
-void *xt_unregister_table(struct xt_table *table)
+/**
+ * xt_unregister_table_pre_exit - pre-shutdown unregister of a table
+ * @net: network namespace
+ * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6)
+ * @name: name of the table to unregister
+ *
+ * Unregisters the specified netfilter table from the given network namespace
+ * and also unregisters the hooks from netfilter core: no new packets will be
+ * processed.
+ *
+ * This must be called prior to xt_unregister_table_exit() from the pernet
+ * .pre_exit callback.  After this call, the table is no longer visible to
+ * the get/setsockopt path.  In case of rmmod, module exit path must have
+ * called xt_unregister_template() prior to unregistering pernet ops to
+ * prevent re-instantiation of the table.
+ *
+ * See also: xt_unregister_table_exit()
+ */
+void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name)
 {
-	struct xt_table_info *private;
+	struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
+	struct xt_table *t;
 
-	mutex_lock(&xt[table->af].mutex);
-	private = table->private;
-	list_del(&table->list);
-	mutex_unlock(&xt[table->af].mutex);
-	audit_log_nfcfg(table->name, table->af, private->number,
-			AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
-	kfree(table->ops);
-	kfree(table);
+	mutex_lock(&xt[af].mutex);
+	list_for_each_entry(t, &xt_net->tables[af], list) {
+		if (strcmp(t->name, name) == 0) {
+			list_move(&t->list, &xt_net->dead_tables[af]);
+			mutex_unlock(&xt[af].mutex);
 
-	return private;
+			if (t->ops) /* nat table registers with nat core, t->ops is NULL. */
+				nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks));
+			return;
+		}
+	}
+	mutex_unlock(&xt[af].mutex);
 }
-EXPORT_SYMBOL_GPL(xt_unregister_table);
+EXPORT_SYMBOL(xt_unregister_table_pre_exit);
+
+/**
+ * xt_unregister_table_exit - remove a table during namespace teardown
+ * @net: the network namespace from which to unregister the table
+ * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6)
+ * @name: name of the table to unregister
+ *
+ * Completes the unregister process for a table. This must be called from
+ * the pernet ops .exit callback. This is the second stage after
+ * xt_unregister_table_pre_exit().
+ *
+ * pair with xt_unregister_table_pre_exit() during namespace shutdown.
+ *
+ * Return: the unregistered table or NULL if the table was never
+ *         instantiated. The caller needs to kfree() the table after it
+ *         has removed the family specific matches/targets.
+ */
+struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name)
+{
+	struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
+	struct xt_table *table;
+
+	mutex_lock(&xt[af].mutex);
+	list_for_each_entry(table, &xt_net->dead_tables[af], list) {
+		struct nf_hook_ops *ops = NULL;
+
+		if (strcmp(table->name, name) != 0)
+			continue;
+
+		list_del(&table->list);
+
+		audit_log_nfcfg(table->name, table->af, table->private->number,
+				AUDIT_XT_OP_UNREGISTER, GFP_KERNEL);
+		swap(table->ops, ops);
+		mutex_unlock(&xt[af].mutex);
+
+		kfree(ops);
+		return table;
+	}
+	mutex_unlock(&xt[af].mutex);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(xt_unregister_table_exit);
 #endif
 
 #ifdef CONFIG_PROC_FS
@@ -2051,8 +2164,10 @@ static int __net_init xt_net_init(struct net *net)
 	struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
 	int i;
 
-	for (i = 0; i < NFPROTO_NUMPROTO; i++)
+	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
 		INIT_LIST_HEAD(&xt_net->tables[i]);
+		INIT_LIST_HEAD(&xt_net->dead_tables[i]);
+	}
 	return 0;
 }
 
@@ -2061,8 +2176,10 @@ static void __net_exit xt_net_exit(struct net *net)
 	struct xt_pernet *xt_net = net_generic(net, xt_pernet_id);
 	int i;
 
-	for (i = 0; i < NFPROTO_NUMPROTO; i++)
+	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
 		WARN_ON_ONCE(!list_empty(&xt_net->tables[i]));
+		WARN_ON_ONCE(!list_empty(&xt_net->dead_tables[i]));
+	}
 }
 
 static struct pernet_operations xt_net_ops = {