Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains Netfilter updates for your net-next tree,
they are:

1) Remove useless debug message when deleting IPVS service, from
   Yannick Brosseau.

2) Get rid of compilation warning when CONFIG_PROC_FS is unset in
   several spots of the IPVS code, from Arnd Bergmann.

3) Add prandom_u32 support to nft_meta, from Florian Westphal.

4) Remove unused variable in xt_osf, from Sudip Mukherjee.

5) Don't calculate IP checksum twice from netfilter ipv4 defrag hook
   since fixing af_packet defragmentation issues, from Joe Stringer.

6) On-demand hook registration for iptables from netns. Instead of
   registering the hooks for every available netns whenever we need
   one of the support tables, we register this on the specific netns
   that needs it, patchset from Florian Westphal.

7) Add missing port range selection to nf_tables masquerading support.

BTW, just for the record, there is a typo in the description of
5f6c253ebe93b0 ("netfilter: bridge: register hooks only when bridge
interface is added") that refers to the cluster match as deprecated, but
it is actually the CLUSTERIP target (which registers hooks
inconditionally) the one that is scheduled for removal.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 180 insertions, 116 deletions

diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 99425cf2819b..84f9baf7aee8 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -2071,9 +2071,28 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	return ret;
 }
 
-struct xt_table *ip6t_register_table(struct net *net,
-				     const struct xt_table *table,
-				     const struct ip6t_replace *repl)
+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,
+			struct xt_table **res)
 {
 	int ret;
 	struct xt_table_info *newinfo;
@@ -2082,10 +2101,8 @@ struct xt_table *ip6t_register_table(struct net *net,
 	struct xt_table *new_table;
 
 	newinfo = xt_alloc_table_info(repl->size);
-	if (!newinfo) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!newinfo)
+		return -ENOMEM;
 
 	loc_cpu_entry = newinfo->entries;
 	memcpy(loc_cpu_entry, repl->entries, repl->size);
@@ -2099,30 +2116,28 @@ struct xt_table *ip6t_register_table(struct net *net,
 		ret = PTR_ERR(new_table);
 		goto out_free;
 	}
-	return new_table;
+
+	/* 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:
 	xt_free_table_info(newinfo);
-out:
-	return ERR_PTR(ret);
+	return ret;
 }
 
-void ip6t_unregister_table(struct net *net, 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 */
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index 8b277b983ca5..1343077dde93 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. */
@@ -44,9 +47,13 @@ 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)
@@ -55,15 +62,26 @@ static int __net_init ip6table_filter_net_init(struct net *net)
 	((struct ip6t_standard *)repl->entries)[1].target.verdict =
 		forward ? -NF_ACCEPT - 1 : -NF_DROP - 1;
 
-	net->ipv6.ip6table_filter =
-		ip6t_register_table(net, &packet_filter, repl);
+	err = ip6t_register_table(net, &packet_filter, repl, filter_ops,
+				  &net->ipv6.ip6table_filter);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv6.ip6table_filter);
+	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)
 {
-	ip6t_unregister_table(net, net->ipv6.ip6table_filter);
+	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 = {
@@ -75,28 +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 abe278b07932..cb2b28883252 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
@@ -88,26 +91,33 @@ 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;
-	net->ipv6.ip6table_mangle =
-		ip6t_register_table(net, &packet_mangler, repl);
+	ret = ip6t_register_table(net, &packet_mangler, repl, mangle_ops,
+				  &net->ipv6.ip6table_mangle);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv6.ip6table_mangle);
+	return ret;
 }
 
 static void __net_exit ip6table_mangle_net_exit(struct net *net)
 {
-	ip6t_unregister_table(net, net->ipv6.ip6table_mangle);
+	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,
 };
 
@@ -115,28 +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 de2a10a565f5..7d2bd940291f 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,
@@ -97,50 +100,50 @@ 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;
-	net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl);
+	ret = ip6t_register_table(net, &nf_nat_ipv6_table, repl,
+				  nf_nat_ipv6_ops, &net->ipv6.ip6table_nat);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv6.ip6table_nat);
+	return ret;
 }
 
 static void __net_exit ip6table_nat_net_exit(struct net *net)
 {
-	ip6t_unregister_table(net, net->ipv6.ip6table_nat);
+	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;
+	int ret = register_pernet_subsys(&ip6table_nat_net_ops);
 
-	err = register_pernet_subsys(&ip6table_nat_net_ops);
-	if (err < 0)
-		goto err1;
+	if (ret)
+		return ret;
 
-	err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
-	if (err < 0)
-		goto err2;
-	return 0;
-
-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 9021963565c3..d4bc56443dc1 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. */
@@ -27,26 +30,32 @@ 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;
-	net->ipv6.ip6table_raw =
-		ip6t_register_table(net, &packet_raw, repl);
+	ret = ip6t_register_table(net, &packet_raw, repl, rawtable_ops,
+				  &net->ipv6.ip6table_raw);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv6.ip6table_raw);
+	return ret;
 }
 
 static void __net_exit ip6table_raw_net_exit(struct net *net)
 {
-	ip6t_unregister_table(net, net->ipv6.ip6table_raw);
+	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,
 };
 
@@ -54,28 +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 0d856fedfeb0..cf26ccb04056 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
@@ -44,26 +47,32 @@ 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;
-	net->ipv6.ip6table_security =
-		ip6t_register_table(net, &security_table, repl);
+	ret = ip6t_register_table(net, &security_table, repl, sectbl_ops,
+				  &net->ipv6.ip6table_security);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv6.ip6table_security);
+	return ret;
 }
 
 static void __net_exit ip6table_security_net_exit(struct net *net)
 {
-	ip6t_unregister_table(net, net->ipv6.ip6table_security);
+	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,
 };
 
@@ -71,27 +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);
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index cd1ac1637a05..9597ffb74077 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -26,7 +26,12 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr,
 
 	memset(&range, 0, sizeof(range));
 	range.flags = priv->flags;
-
+	if (priv->sreg_proto_min) {
+		range.min_proto.all =
+			*(__be16 *)&regs->data[priv->sreg_proto_min];
+		range.max_proto.all =
+			*(__be16 *)&regs->data[priv->sreg_proto_max];
+	}
 	regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out);
 }