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
5f6c253ebe ("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>

include/linux/netfilter.h

@@ -141,22 +141,6 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg);
 
 #ifdef HAVE_JUMP_LABEL
 extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
-
-static inline bool nf_hook_list_active(struct list_head *hook_list,
-				       u_int8_t pf, unsigned int hook)
-{
-	if (__builtin_constant_p(pf) &&
-	    __builtin_constant_p(hook))
-		return static_key_false(&nf_hooks_needed[pf][hook]);
-
-	return !list_empty(hook_list);
-}
-#else
-static inline bool nf_hook_list_active(struct list_head *hook_list,
-				       u_int8_t pf, unsigned int hook)
-{
-	return !list_empty(hook_list);
-}
 #endif
 
 int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state);
@@ -177,9 +161,18 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
 				 int (*okfn)(struct net *, struct sock *, struct sk_buff *),
 				 int thresh)
 {
-	struct list_head *hook_list = &net->nf.hooks[pf][hook];
+	struct list_head *hook_list;
 
-	if (nf_hook_list_active(hook_list, pf, hook)) {
+#ifdef HAVE_JUMP_LABEL
+	if (__builtin_constant_p(pf) &&
+	    __builtin_constant_p(hook) &&
+	    !static_key_false(&nf_hooks_needed[pf][hook]))
+		return 1;
+#endif
+
+	hook_list = &net->nf.hooks[pf][hook];
+
+	if (!list_empty(hook_list)) {
 		struct nf_hook_state state;
 
 		nf_hook_state_init(&state, hook_list, hook, thresh,

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>

include/linux/netfilter_arp/arp_tables.h

@@ -48,10 +48,11 @@ struct arpt_error {
 }
 
 extern void *arpt_alloc_initial_table(const struct xt_table *);
-extern struct xt_table *arpt_register_table(struct net *net,
-					    const struct xt_table *table,
-					    const struct arpt_replace *repl);
-extern void arpt_unregister_table(struct xt_table *table);
+int arpt_register_table(struct net *net, const struct xt_table *table,
+			const struct arpt_replace *repl,
+			const struct nf_hook_ops *ops, struct xt_table **res);
+void arpt_unregister_table(struct net *net, struct xt_table *table,
+			   const struct nf_hook_ops *ops);
 extern unsigned int arpt_do_table(struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  struct xt_table *table);

include/linux/netfilter_ipv4/ip_tables.h

@@ -24,10 +24,11 @@
 
 extern void ipt_init(void) __init;
 
-extern struct xt_table *ipt_register_table(struct net *net,
-					   const struct xt_table *table,
-					   const struct ipt_replace *repl);
-extern void ipt_unregister_table(struct net *net, struct xt_table *table);
+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);
+void ipt_unregister_table(struct net *net, struct xt_table *table,
+			  const struct nf_hook_ops *ops);
 
 /* Standard entry. */
 struct ipt_standard {

include/linux/netfilter_ipv6/ip6_tables.h

@@ -25,10 +25,11 @@
 extern void ip6t_init(void) __init;
 
 extern void *ip6t_alloc_initial_table(const struct xt_table *);
-extern struct xt_table *ip6t_register_table(struct net *net,
-					    const struct xt_table *table,
-					    const struct ip6t_replace *repl);
-extern void ip6t_unregister_table(struct net *net, struct xt_table *table);
+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);
+void ip6t_unregister_table(struct net *net, struct xt_table *table,
+			   const struct nf_hook_ops *ops);
 extern unsigned int ip6t_do_table(struct sk_buff *skb,
 				  const struct nf_hook_state *state,
 				  struct xt_table *table);

include/net/netfilter/nft_masq.h

@@ -2,7 +2,9 @@
 #define _NFT_MASQ_H_
 
 struct nft_masq {
-	u32	flags;
+	u32			flags;
+	enum nft_registers      sreg_proto_min:8;
+	enum nft_registers      sreg_proto_max:8;
 };
 
 extern const struct nla_policy nft_masq_policy[];

include/uapi/linux/netfilter/nf_tables.h

@@ -681,6 +681,7 @@ enum nft_exthdr_attributes {
  * @NFT_META_IIFGROUP: packet input interface group
  * @NFT_META_OIFGROUP: packet output interface group
  * @NFT_META_CGROUP: socket control group (skb->sk->sk_classid)
+ * @NFT_META_PRANDOM: a 32bit pseudo-random number
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -707,6 +708,7 @@ enum nft_meta_keys {
 	NFT_META_IIFGROUP,
 	NFT_META_OIFGROUP,
 	NFT_META_CGROUP,
+	NFT_META_PRANDOM,
 };
 
 /**
@@ -949,10 +951,14 @@ enum nft_nat_attributes {
  * enum nft_masq_attributes - nf_tables masquerade expression attributes
  *
  * @NFTA_MASQ_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32)
+ * @NFTA_MASQ_REG_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
+ * @NFTA_MASQ_REG_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
  */
 enum nft_masq_attributes {
 	NFTA_MASQ_UNSPEC,
 	NFTA_MASQ_FLAGS,
+	NFTA_MASQ_REG_PROTO_MIN,
+	NFTA_MASQ_REG_PROTO_MAX,
 	__NFTA_MASQ_MAX
 };
 #define NFTA_MASQ_MAX		(__NFTA_MASQ_MAX - 1)

lib/random32.c

@@ -255,6 +255,7 @@ void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state)
 		prandom_warmup(state);
 	}
 }
+EXPORT_SYMBOL(prandom_seed_full_state);
 
 /*
  *	Generate better values after random number generator

net/bridge/br_netfilter_hooks.c

@@ -37,6 +37,7 @@
 #include <net/addrconf.h>
 #include <net/route.h>
 #include <net/netfilter/br_netfilter.h>
+#include <net/netns/generic.h>
 
 #include <asm/uaccess.h>
 #include "br_private.h"
@@ -44,6 +45,12 @@
 #include <linux/sysctl.h>
 #endif
 
+static int brnf_net_id __read_mostly;
+
+struct brnf_net {
+	bool enabled;
+};
+
 #ifdef CONFIG_SYSCTL
 static struct ctl_table_header *brnf_sysctl_header;
 static int brnf_call_iptables __read_mostly = 1;
@@ -938,6 +945,53 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
 	},
 };
 
+static int brnf_device_event(struct notifier_block *unused, unsigned long event,
+			     void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct brnf_net *brnet;
+	struct net *net;
+	int ret;
+
+	if (event != NETDEV_REGISTER || !(dev->priv_flags & IFF_EBRIDGE))
+		return NOTIFY_DONE;
+
+	ASSERT_RTNL();
+
+	net = dev_net(dev);
+	brnet = net_generic(net, brnf_net_id);
+	if (brnet->enabled)
+		return NOTIFY_OK;
+
+	ret = nf_register_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
+	if (ret)
+		return NOTIFY_BAD;
+
+	brnet->enabled = true;
+	return NOTIFY_OK;
+}
+
+static void __net_exit brnf_exit_net(struct net *net)
+{
+	struct brnf_net *brnet = net_generic(net, brnf_net_id);
+
+	if (!brnet->enabled)
+		return;
+
+	nf_unregister_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops));
+	brnet->enabled = false;
+}
+
+static struct pernet_operations brnf_net_ops __read_mostly = {
+	.exit = brnf_exit_net,
+	.id   = &brnf_net_id,
+	.size = sizeof(struct brnf_net),
+};
+
+static struct notifier_block brnf_notifier __read_mostly = {
+	.notifier_call = brnf_device_event,
+};
+
 #ifdef CONFIG_SYSCTL
 static
 int brnf_sysctl_call_tables(struct ctl_table *ctl, int write,
@@ -1003,16 +1057,23 @@ static int __init br_netfilter_init(void)
 {
 	int ret;
 
-	ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+	ret = register_pernet_subsys(&brnf_net_ops);
 	if (ret < 0)
 		return ret;
 
+	ret = register_netdevice_notifier(&brnf_notifier);
+	if (ret < 0) {
+		unregister_pernet_subsys(&brnf_net_ops);
+		return ret;
+	}
+
 #ifdef CONFIG_SYSCTL
 	brnf_sysctl_header = register_net_sysctl(&init_net, "net/bridge", brnf_table);
 	if (brnf_sysctl_header == NULL) {
 		printk(KERN_WARNING
 		       "br_netfilter: can't register to sysctl.\n");
-		nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+		unregister_netdevice_notifier(&brnf_notifier);
+		unregister_pernet_subsys(&brnf_net_ops);
 		return -ENOMEM;
 	}
 #endif
@@ -1024,7 +1085,8 @@ static int __init br_netfilter_init(void)
 static void __exit br_netfilter_fini(void)
 {
 	RCU_INIT_POINTER(nf_br_ops, NULL);
-	nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+	unregister_netdevice_notifier(&brnf_notifier);
+	unregister_pernet_subsys(&brnf_net_ops);
 #ifdef CONFIG_SYSCTL
 	unregister_net_sysctl_table(brnf_sysctl_header);
 #endif

net/ipv4/netfilter/arp_tables.c

@@ -1780,44 +1780,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
 	return ret;
 }
 
-struct xt_table *arpt_register_table(struct net *net,
-				     const struct xt_table *table,
-				     const struct arpt_replace *repl)
-{
-	int ret;
-	struct xt_table_info *newinfo;
-	struct xt_table_info bootstrap = {0};
-	void *loc_cpu_entry;
-	struct xt_table *new_table;
-
-	newinfo = xt_alloc_table_info(repl->size);
-	if (!newinfo) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	loc_cpu_entry = newinfo->entries;
-	memcpy(loc_cpu_entry, repl->entries, repl->size);
-
-	ret = translate_table(newinfo, loc_cpu_entry, repl);
-	duprintf("arpt_register_table: translate table gives %d\n", ret);
-	if (ret != 0)
-		goto out_free;
-
-	new_table = xt_register_table(net, table, &bootstrap, newinfo);
-	if (IS_ERR(new_table)) {
-		ret = PTR_ERR(new_table);
-		goto out_free;
-	}
-	return new_table;
-
-out_free:
-	xt_free_table_info(newinfo);
-out:
-	return ERR_PTR(ret);
-}
-
-void arpt_unregister_table(struct xt_table *table)
+static void __arpt_unregister_table(struct xt_table *table)
 {
 	struct xt_table_info *private;
 	void *loc_cpu_entry;
@@ -1835,6 +1798,59 @@ void arpt_unregister_table(struct xt_table *table)
 	xt_free_table_info(private);
 }
 
+int arpt_register_table(struct net *net,
+			const struct xt_table *table,
+			const struct arpt_replace *repl,
+			const struct nf_hook_ops *ops,
+			struct xt_table **res)
+{
+	int ret;
+	struct xt_table_info *newinfo;
+	struct xt_table_info bootstrap = {0};
+	void *loc_cpu_entry;
+	struct xt_table *new_table;
+
+	newinfo = xt_alloc_table_info(repl->size);
+	if (!newinfo)
+		return -ENOMEM;
+
+	loc_cpu_entry = newinfo->entries;
+	memcpy(loc_cpu_entry, repl->entries, repl->size);
+
+	ret = translate_table(newinfo, loc_cpu_entry, repl);
+	duprintf("arpt_register_table: translate table gives %d\n", ret);
+	if (ret != 0)
+		goto out_free;
+
+	new_table = xt_register_table(net, table, &bootstrap, newinfo);
+	if (IS_ERR(new_table)) {
+		ret = PTR_ERR(new_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) {
+		__arpt_unregister_table(new_table);
+		*res = NULL;
+	}
+
+	return ret;
+
+out_free:
+	xt_free_table_info(newinfo);
+	return ret;
+}
+
+void arpt_unregister_table(struct net *net, struct xt_table *table,
+			   const struct nf_hook_ops *ops)
+{
+	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+	__arpt_unregister_table(table);
+}
+
 /* The built-in targets: standard (NULL) and error. */
 static struct xt_target arpt_builtin_tg[] __read_mostly = {
 	{

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 */
@@ -35,26 +38,32 @@ 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;
-	net->ipv4.arptable_filter =
-		arpt_register_table(net, &packet_filter, repl);
+	err = arpt_register_table(net, &packet_filter, repl, arpfilter_ops,
+				  &net->ipv4.arptable_filter);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv4.arptable_filter);
+	return err;
 }
 
 static void __net_exit arptable_filter_net_exit(struct net *net)
 {
-	arpt_unregister_table(net->ipv4.arptable_filter);
+	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,
 };
 
@@ -62,26 +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

@@ -2062,44 +2062,7 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	return ret;
 }
 
-struct xt_table *ipt_register_table(struct net *net,
-				    const struct xt_table *table,
-				    const struct ipt_replace *repl)
-{
-	int ret;
-	struct xt_table_info *newinfo;
-	struct xt_table_info bootstrap = {0};
-	void *loc_cpu_entry;
-	struct xt_table *new_table;
-
-	newinfo = xt_alloc_table_info(repl->size);
-	if (!newinfo) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	loc_cpu_entry = newinfo->entries;
-	memcpy(loc_cpu_entry, repl->entries, repl->size);
-
-	ret = translate_table(net, newinfo, loc_cpu_entry, repl);
-	if (ret != 0)
-		goto out_free;
-
-	new_table = xt_register_table(net, table, &bootstrap, newinfo);
-	if (IS_ERR(new_table)) {
-		ret = PTR_ERR(new_table);
-		goto out_free;
-	}
-
-	return new_table;
-
-out_free:
-	xt_free_table_info(newinfo);
-out:
-	return ERR_PTR(ret);
-}
-
-void ipt_unregister_table(struct net *net, struct xt_table *table)
+static void __ipt_unregister_table(struct net *net, struct xt_table *table)
 {
 	struct xt_table_info *private;
 	void *loc_cpu_entry;
@@ -2117,6 +2080,56 @@ void ipt_unregister_table(struct net *net, struct xt_table *table)
 	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)
+{
+	int ret;
+	struct xt_table_info *newinfo;
+	struct xt_table_info bootstrap = {0};
+	void *loc_cpu_entry;
+	struct xt_table *new_table;
+
+	newinfo = xt_alloc_table_info(repl->size);
+	if (!newinfo)
+		return -ENOMEM;
+
+	loc_cpu_entry = newinfo->entries;
+	memcpy(loc_cpu_entry, repl->entries, repl->size);
+
+	ret = translate_table(net, newinfo, loc_cpu_entry, repl);
+	if (ret != 0)
+		goto out_free;
+
+	new_table = xt_register_table(net, table, &bootstrap, newinfo);
+	if (IS_ERR(new_table)) {
+		ret = PTR_ERR(new_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:
+	xt_free_table_info(newinfo);
+	return ret;
+}
+
+void ipt_unregister_table(struct net *net, struct xt_table *table,
+			  const struct nf_hook_ops *ops)
+{
+	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 */
 static inline bool
 icmp_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code,

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
@@ -48,12 +50,16 @@ 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)
@@ -62,15 +68,26 @@ static int __net_init iptable_filter_net_init(struct net *net)
 	((struct ipt_standard *)repl->entries)[1].target.verdict =
 		forward ? -NF_ACCEPT - 1 : -NF_DROP - 1;
 
-	net->ipv4.iptable_filter =
-		ipt_register_table(net, &packet_filter, repl);
+	err = ipt_register_table(net, &packet_filter, repl, filter_ops,
+				 &net->ipv4.iptable_filter);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv4.iptable_filter);
+	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)
 {
-	ipt_unregister_table(net, net->ipv4.iptable_filter);
+	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 = {
@@ -82,24 +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
@@ -92,27 +95,32 @@ 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;
-	net->ipv4.iptable_mangle =
-		ipt_register_table(net, &packet_mangler, repl);
+	ret = ipt_register_table(net, &packet_mangler, repl, mangle_ops,
+				 &net->ipv4.iptable_mangle);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv4.iptable_mangle);
+	return ret;
 }
 
 static void __net_exit iptable_mangle_net_exit(struct net *net)
 {
-	ipt_unregister_table(net, net->ipv4.iptable_mangle);
+	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,
 };
 
@@ -120,15 +128,22 @@ static int __init iptable_mangle_init(void)
 {
 	int ret;
 
-	ret = register_pernet_subsys(&iptable_mangle_net_ops);
-	if (ret < 0)
-		return ret;
-
-	/* Register hooks */
-	mangle_ops = xt_hook_link(&packet_mangler, iptable_mangle_hook);
+	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) {
+		kfree(mangle_ops);
+		return ret;
+	}
+
+	ret = iptable_mangle_table_init(&init_net);
+	if (ret) {
 		unregister_pernet_subsys(&iptable_mangle_net_ops);
+		kfree(mangle_ops);
 	}
 
 	return ret;
@@ -136,8 +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,
@@ -95,50 +98,50 @@ 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;
-	net->ipv4.nat_table = ipt_register_table(net, &nf_nat_ipv4_table, repl);
+	ret = ipt_register_table(net, &nf_nat_ipv4_table, repl,
+				 nf_nat_ipv4_ops, &net->ipv4.nat_table);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv4.nat_table);
+	return ret;
 }
 
 static void __net_exit iptable_nat_net_exit(struct net *net)
 {
-	ipt_unregister_table(net, net->ipv4.nat_table);
+	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;
+	int ret = register_pernet_subsys(&iptable_nat_net_ops);
 
-	err = register_pernet_subsys(&iptable_nat_net_ops);
-	if (err < 0)
-		goto err1;
+	if (ret)
+		return ret;
 
-	err = nf_register_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
-	if (err < 0)
-		goto err2;
-	return 0;
-
-err2:
-	unregister_pernet_subsys(&iptable_nat_net_ops);
-err1:
-	return err;
+	ret = iptable_nat_table_init(&init_net);
+	if (ret)
+		unregister_pernet_subsys(&iptable_nat_net_ops);
+	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. */
@@ -34,26 +37,32 @@ 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;
-	net->ipv4.iptable_raw =
-		ipt_register_table(net, &packet_raw, repl);
+	ret = ipt_register_table(net, &packet_raw, repl, rawtable_ops,
+				 &net->ipv4.iptable_raw);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv4.iptable_raw);
+	return ret;
 }
 
 static void __net_exit iptable_raw_net_exit(struct net *net)
 {
-	ipt_unregister_table(net, net->ipv4.iptable_raw);
+	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,
 };
 
@@ -61,15 +70,20 @@ static int __init iptable_raw_init(void)
 {
 	int ret;
 
-	ret = register_pernet_subsys(&iptable_raw_net_ops);
-	if (ret < 0)
-		return ret;
+	rawtable_ops = xt_hook_ops_alloc(&packet_raw, iptable_raw_hook);
+	if (IS_ERR(rawtable_ops))
+		return PTR_ERR(rawtable_ops);
 
-	/* Register hooks */
-	rawtable_ops = xt_hook_link(&packet_raw, iptable_raw_hook);
-	if (IS_ERR(rawtable_ops)) {
-		ret = PTR_ERR(rawtable_ops);
+	ret = register_pernet_subsys(&iptable_raw_net_ops);
+	if (ret < 0) {
+		kfree(rawtable_ops);
+		return ret;
+	}
+
+	ret = iptable_raw_table_init(&init_net);
+	if (ret) {
 		unregister_pernet_subsys(&iptable_raw_net_ops);
+		kfree(rawtable_ops);
 	}
 
 	return ret;
@@ -77,8 +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
@@ -51,26 +54,33 @@ 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;
-	net->ipv4.iptable_security =
-		ipt_register_table(net, &security_table, repl);
+	ret = ipt_register_table(net, &security_table, repl, sectbl_ops,
+				 &net->ipv4.iptable_security);
 	kfree(repl);
-	return PTR_ERR_OR_ZERO(net->ipv4.iptable_security);
+	return ret;
 }
 
 static void __net_exit iptable_security_net_exit(struct net *net)
 {
-	ipt_unregister_table(net, net->ipv4.iptable_security);
+	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,
 };
 
@@ -78,27 +88,29 @@ static int __init iptable_security_init(void)
 {
 	int ret;
 
-	ret = register_pernet_subsys(&iptable_security_net_ops);
-	if (ret < 0)
-		return ret;
+	sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook);
+	if (IS_ERR(sectbl_ops))
+		return PTR_ERR(sectbl_ops);
 
-	sectbl_ops = xt_hook_link(&security_table, iptable_security_hook);
-	if (IS_ERR(sectbl_ops)) {
-		ret = PTR_ERR(sectbl_ops);
-		goto cleanup_table;
+	ret = register_pernet_subsys(&iptable_security_net_ops);
+	if (ret < 0) {
+		kfree(sectbl_ops);
+		return ret;
 	}
 
-	return ret;
+	ret = iptable_security_table_init(&init_net);
+	if (ret) {
+		unregister_pernet_subsys(&iptable_security_net_ops);
+		kfree(sectbl_ops);
+	}
 
-cleanup_table:
-	unregister_pernet_subsys(&iptable_security_net_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/ipv4/netfilter/nf_defrag_ipv4.c

@@ -31,10 +31,8 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
 	err = ip_defrag(net, skb, user);
 	local_bh_enable();
 
-	if (!err) {
-		ip_send_check(ip_hdr(skb));
+	if (!err)
 		skb->ignore_df = 1;
-	}
 
 	return err;
 }

net/ipv4/netfilter/nft_masq_ipv4.c

@@ -25,7 +25,12 @@ static void nft_masq_ipv4_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_ipv4(pkt->skb, pkt->hook,
 						    &range, pkt->out);
 }

net/ipv6/netfilter/ip6_tables.c

@@ -2071,43 +2071,7 @@ 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)
-{
-	int ret;
-	struct xt_table_info *newinfo;
-	struct xt_table_info bootstrap = {0};
-	void *loc_cpu_entry;
-	struct xt_table *new_table;
-
-	newinfo = xt_alloc_table_info(repl->size);
-	if (!newinfo) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	loc_cpu_entry = newinfo->entries;
-	memcpy(loc_cpu_entry, repl->entries, repl->size);
-
-	ret = translate_table(net, newinfo, loc_cpu_entry, repl);
-	if (ret != 0)
-		goto out_free;
-
-	new_table = xt_register_table(net, table, &bootstrap, newinfo);
-	if (IS_ERR(new_table)) {
-		ret = PTR_ERR(new_table);
-		goto out_free;
-	}
-	return new_table;
-
-out_free:
-	xt_free_table_info(newinfo);
-out:
-	return ERR_PTR(ret);
-}
-
-void ip6t_unregister_table(struct net *net, struct xt_table *table)
+static void __ip6t_unregister_table(struct net *net, struct xt_table *table)
 {
 	struct xt_table_info *private;
 	void *loc_cpu_entry;
@@ -2125,6 +2089,57 @@ void ip6t_unregister_table(struct net *net, struct xt_table *table)
 	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;
+	struct xt_table_info bootstrap = {0};
+	void *loc_cpu_entry;
+	struct xt_table *new_table;
+
+	newinfo = xt_alloc_table_info(repl->size);
+	if (!newinfo)
+		return -ENOMEM;
+
+	loc_cpu_entry = newinfo->entries;
+	memcpy(loc_cpu_entry, repl->entries, repl->size);
+
+	ret = translate_table(net, newinfo, loc_cpu_entry, repl);
+	if (ret != 0)
+		goto out_free;
+
+	new_table = xt_register_table(net, table, &bootstrap, newinfo);
+	if (IS_ERR(new_table)) {
+		ret = PTR_ERR(new_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:
+	xt_free_table_info(newinfo);
+	return ret;
+}
+
+void ip6t_unregister_table(struct net *net, struct xt_table *table,
+			   const struct nf_hook_ops *ops)
+{
+	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 */
 static inline bool
 icmp6_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code,