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

Pablo Neira Ayuso says:

====================
nf-next pull request

The following patchset contains Netfilter/IPVS updates for your
net-next tree. Regarding nf_tables, most updates focus on consolidating
the NAT infrastructure and adding support for masquerading. More
specifically, they are:

1) use __u8 instead of u_int8_t in arptables header, from
   Mike Frysinger.

2) Add support to match by skb->pkttype to the meta expression, from
   Ana Rey.

3) Add support to match by cpu to the meta expression, also from
   Ana Rey.

4) A smatch warning about IPSET_ATTR_MARKMASK validation, patch from
   Vytas Dauksa.

5) Fix netnet and netportnet hash types the range support for IPv4,
   from Sergey Popovich.

6) Fix missing-field-initializer warnings resolved, from Mark Rustad.

7) Dan Carperter reported possible integer overflows in ipset, from
   Jozsef Kadlecsick.

8) Filter out accounting objects in nfacct by type, so you can
   selectively reset quotas, from Alexey Perevalov.

9) Move specific NAT IPv4 functions to the core so x_tables and
   nf_tables can share the same NAT IPv4 engine.

10) Use the new NAT IPv4 functions from nft_chain_nat_ipv4.

11) Move specific NAT IPv6 functions to the core so x_tables and
    nf_tables can share the same NAT IPv4 engine.

12) Use the new NAT IPv6 functions from nft_chain_nat_ipv6.

13) Refactor code to add nft_delrule(), which can be reused in the
    enhancement of the NFT_MSG_DELTABLE to remove a table and its
    content, from Arturo Borrero.

14) Add a helper function to unregister chain hooks, from
    Arturo Borrero.

15) A cleanup to rename to nft_delrule_by_chain for consistency with
    the new nft_*() functions, also from Arturo.

16) Add support to match devgroup to the meta expression, from Ana Rey.

17) Reduce stack usage for IPVS socket option, from Julian Anastasov.

18) Remove unnecessary textsearch state initialization in xt_string,
    from Bojan Prtvar.

19) Add several helper functions to nf_tables, more work to prepare
    the enhancement of NFT_MSG_DELTABLE, again from Arturo Borrero.

20) Enhance NFT_MSG_DELTABLE to delete a table and its content, from
    Arturo Borrero.

21) Support NAT flags in the nat expression to indicate the flavour,
    eg. random fully, from Arturo.

22) Add missing audit code to ebtables when replacing tables, from
    Nicolas Dichtel.

23) Generalize the IPv4 masquerading code to allow its re-use from
    nf_tables, from Arturo.

24) Generalize the IPv6 masquerading code, also from Arturo.

25) Add the new masq expression to support IPv4/IPv6 masquerading
    from nf_tables, also from Arturo.
====================

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

45 files changed, 1759 insertions, 1070 deletions

diff --git a/include/linux/netfilter/ipset/ip_set_list.h b/include/linux/netfilter/ipset/ip_set_list.h
index 68c2aea897f5..fe2622a00151 100644
--- a/include/linux/netfilter/ipset/ip_set_list.h
+++ b/include/linux/netfilter/ipset/ip_set_list.h
@@ -6,5 +6,6 @@
 
 #define IP_SET_LIST_DEFAULT_SIZE	8
 #define IP_SET_LIST_MIN_SIZE		4
+#define IP_SET_LIST_MAX_SIZE		65536
 
 #endif /* __IP_SET_LIST_H */
diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h
new file mode 100644
index 000000000000..a9c001c646da
--- /dev/null
+++ b/include/net/netfilter/ipv4/nf_nat_masquerade.h
@@ -0,0 +1,14 @@
+#ifndef _NF_NAT_MASQUERADE_IPV4_H_
+#define _NF_NAT_MASQUERADE_IPV4_H_
+
+#include <net/netfilter/nf_nat.h>
+
+unsigned int
+nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
+		       const struct nf_nat_range *range,
+		       const struct net_device *out);
+
+void nf_nat_masquerade_ipv4_register_notifier(void);
+void nf_nat_masquerade_ipv4_unregister_notifier(void);
+
+#endif /*_NF_NAT_MASQUERADE_IPV4_H_ */
diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h
new file mode 100644
index 000000000000..0a13396cd390
--- /dev/null
+++ b/include/net/netfilter/ipv6/nf_nat_masquerade.h
@@ -0,0 +1,10 @@
+#ifndef _NF_NAT_MASQUERADE_IPV6_H_
+#define _NF_NAT_MASQUERADE_IPV6_H_
+
+unsigned int
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		       const struct net_device *out);
+void nf_nat_masquerade_ipv6_register_notifier(void);
+void nf_nat_masquerade_ipv6_unregister_notifier(void);
+
+#endif /* _NF_NAT_MASQUERADE_IPV6_H_ */
diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index 5a2919b2e09a..340c013795a4 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -42,8 +42,83 @@ const struct nf_nat_l3proto *__nf_nat_l3proto_find(u8 l3proto);
 int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
 				  enum ip_conntrack_info ctinfo,
 				  unsigned int hooknum);
+
+unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
+unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			     const struct net_device *in,
+			     const struct net_device *out,
+			     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						      struct sk_buff *skb,
+						      const struct net_device *in,
+						      const struct net_device *out,
+						      struct nf_conn *ct));
+
+unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
+				  struct sk_buff *skb,
+				  const struct net_device *in,
+				  const struct net_device *out,
+				  unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+							   struct sk_buff *skb,
+							   const struct net_device *in,
+							   const struct net_device *out,
+							   struct nf_conn *ct));
+
+unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
 int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
 				    enum ip_conntrack_info ctinfo,
 				    unsigned int hooknum, unsigned int hdrlen);
 
+unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
+unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			     const struct net_device *in,
+			     const struct net_device *out,
+			     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						      struct sk_buff *skb,
+						      const struct net_device *in,
+						      const struct net_device *out,
+						      struct nf_conn *ct));
+
+unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops,
+				  struct sk_buff *skb,
+				  const struct net_device *in,
+				  const struct net_device *out,
+				  unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+							   struct sk_buff *skb,
+							   const struct net_device *in,
+							   const struct net_device *out,
+							   struct nf_conn *ct));
+
+unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
 #endif /* _NF_NAT_L3PROTO_H */
diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h
new file mode 100644
index 000000000000..c72729f954f4
--- /dev/null
+++ b/include/net/netfilter/nft_masq.h
@@ -0,0 +1,16 @@
+#ifndef _NFT_MASQ_H_
+#define _NFT_MASQ_H_
+
+struct nft_masq {
+	u32	flags;
+};
+
+extern const struct nla_policy nft_masq_policy[];
+
+int nft_masq_init(const struct nft_ctx *ctx,
+		  const struct nft_expr *expr,
+		  const struct nlattr * const tb[]);
+
+int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr);
+
+#endif /* _NFT_MASQ_H_ */
diff --git a/include/uapi/linux/netfilter/nf_nat.h b/include/uapi/linux/netfilter/nf_nat.h
index 1ad3659102b6..0880781ad7b6 100644
--- a/include/uapi/linux/netfilter/nf_nat.h
+++ b/include/uapi/linux/netfilter/nf_nat.h
@@ -13,6 +13,11 @@
 #define NF_NAT_RANGE_PROTO_RANDOM_ALL		\
 	(NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PROTO_RANDOM_FULLY)
 
+#define NF_NAT_RANGE_MASK					\
+	(NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED |	\
+	 NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PERSISTENT |	\
+	 NF_NAT_RANGE_PROTO_RANDOM_FULLY)
+
 struct nf_nat_ipv4_range {
 	unsigned int			flags;
 	__be32				min_ip;
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 801bdd1e56e3..eeec0ae845ef 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -571,6 +571,10 @@ enum nft_exthdr_attributes {
  * @NFT_META_L4PROTO: layer 4 protocol number
  * @NFT_META_BRI_IIFNAME: packet input bridge interface name
  * @NFT_META_BRI_OIFNAME: packet output bridge interface name
+ * @NFT_META_PKTTYPE: packet type (skb->pkt_type), special handling for loopback
+ * @NFT_META_CPU: cpu id through smp_processor_id()
+ * @NFT_META_IIFGROUP: packet input interface group
+ * @NFT_META_OIFGROUP: packet output interface group
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -592,6 +596,10 @@ enum nft_meta_keys {
 	NFT_META_L4PROTO,
 	NFT_META_BRI_IIFNAME,
 	NFT_META_BRI_OIFNAME,
+	NFT_META_PKTTYPE,
+	NFT_META_CPU,
+	NFT_META_IIFGROUP,
+	NFT_META_OIFGROUP,
 };
 
 /**
@@ -777,6 +785,7 @@ enum nft_nat_types {
  * @NFTA_NAT_REG_ADDR_MAX: source register of address range end (NLA_U32: nft_registers)
  * @NFTA_NAT_REG_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
  * @NFTA_NAT_REG_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
+ * @NFTA_NAT_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32)
  */
 enum nft_nat_attributes {
 	NFTA_NAT_UNSPEC,
@@ -786,8 +795,20 @@ enum nft_nat_attributes {
 	NFTA_NAT_REG_ADDR_MAX,
 	NFTA_NAT_REG_PROTO_MIN,
 	NFTA_NAT_REG_PROTO_MAX,
+	NFTA_NAT_FLAGS,
 	__NFTA_NAT_MAX
 };
 #define NFTA_NAT_MAX		(__NFTA_NAT_MAX - 1)
 
+/**
+ * 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)
+ */
+enum nft_masq_attributes {
+	NFTA_MASQ_FLAGS,
+	__NFTA_MASQ_MAX
+};
+#define NFTA_MASQ_MAX		(__NFTA_MASQ_MAX - 1)
+
 #endif /* _LINUX_NF_TABLES_H */
diff --git a/include/uapi/linux/netfilter/nfnetlink_acct.h b/include/uapi/linux/netfilter/nfnetlink_acct.h
index 51404ec19022..f3e34dbbf966 100644
--- a/include/uapi/linux/netfilter/nfnetlink_acct.h
+++ b/include/uapi/linux/netfilter/nfnetlink_acct.h
@@ -28,9 +28,17 @@ enum nfnl_acct_type {
 	NFACCT_USE,
 	NFACCT_FLAGS,
 	NFACCT_QUOTA,
+	NFACCT_FILTER,
 	__NFACCT_MAX
 };
 #define NFACCT_MAX (__NFACCT_MAX - 1)
 
+enum nfnl_attr_filter_type {
+	NFACCT_FILTER_UNSPEC,
+	NFACCT_FILTER_MASK,
+	NFACCT_FILTER_VALUE,
+	__NFACCT_FILTER_MAX
+};
+#define NFACCT_FILTER_MAX (__NFACCT_FILTER_MAX - 1)
 
 #endif /* _UAPI_NFNL_ACCT_H_ */
diff --git a/include/uapi/linux/netfilter_arp/arpt_mangle.h b/include/uapi/linux/netfilter_arp/arpt_mangle.h
index 250f502902bb..8c2b16a1f5a0 100644
--- a/include/uapi/linux/netfilter_arp/arpt_mangle.h
+++ b/include/uapi/linux/netfilter_arp/arpt_mangle.h
@@ -13,7 +13,7 @@ struct arpt_mangle
 	union {
 		struct in_addr tgt_ip;
 	} u_t;
-	u_int8_t flags;
+	__u8 flags;
 	int target;
 };
 
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 6d69631b9f4d..d9a8c05d995d 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -26,6 +26,7 @@
 #include <asm/uaccess.h>
 #include <linux/smp.h>
 #include <linux/cpumask.h>
+#include <linux/audit.h>
 #include <net/sock.h>
 /* needed for logical [in,out]-dev filtering */
 #include "../br_private.h"
@@ -1058,6 +1059,20 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
 	vfree(table);
 
 	vfree(counterstmp);
+
+#ifdef CONFIG_AUDIT
+	if (audit_enabled) {
+		struct audit_buffer *ab;
+
+		ab = audit_log_start(current->audit_context, GFP_KERNEL,
+				     AUDIT_NETFILTER_CFG);
+		if (ab) {
+			audit_log_format(ab, "table=%s family=%u entries=%u",
+					 repl->name, AF_BRIDGE, repl->nentries);
+			audit_log_end(ab);
+		}
+	}
+#endif
 	return ret;
 
 free_unlock:
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 7cbcaf4f0194..d189c5262bdb 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -232,8 +232,21 @@ config IP_NF_NAT
 
 if IP_NF_NAT
 
+config NF_NAT_MASQUERADE_IPV4
+	tristate "IPv4 masquerade support"
+	help
+	This is the kernel functionality to provide NAT in the masquerade
+	flavour (automatic source address selection).
+
+config NFT_MASQ_IPV4
+	tristate "IPv4 masquerading support for nf_tables"
+	depends on NF_TABLES_IPV4
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV4
+
 config IP_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
+	select NF_NAT_MASQUERADE_IPV4
 	default m if NETFILTER_ADVANCED=n
 	help
 	  Masquerading is a special case of NAT: all outgoing connections are
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index edf4af32e9f2..14488cc5fd2c 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o
 obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
 obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
+obj-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
 
 # NAT protocols (nf_nat)
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
@@ -35,6 +36,7 @@ obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
+obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index 00352ce0f0de..da7f02a0b868 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -22,6 +22,7 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
 #include <net/netfilter/nf_nat.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -46,103 +47,17 @@ static int masquerade_tg_check(const struct xt_tgchk_param *par)
 static unsigned int
 masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	struct nf_conn *ct;
-	struct nf_conn_nat *nat;
-	enum ip_conntrack_info ctinfo;
-	struct nf_nat_range newrange;
+	struct nf_nat_range range;
 	const struct nf_nat_ipv4_multi_range_compat *mr;
-	const struct rtable *rt;
-	__be32 newsrc, nh;
-
-	NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING);
-
-	ct = nf_ct_get(skb, &ctinfo);
-	nat = nfct_nat(ct);
-
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED_REPLY));
-
-	/* Source address is 0.0.0.0 - locally generated packet that is
-	 * probably not supposed to be masqueraded.
-	 */
-	if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0)
-		return NF_ACCEPT;
 
 	mr = par->targinfo;
-	rt = skb_rtable(skb);
-	nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
-	newsrc = inet_select_addr(par->out, nh, RT_SCOPE_UNIVERSE);
-	if (!newsrc) {
-		pr_info("%s ate my IP address\n", par->out->name);
-		return NF_DROP;
-	}
-
-	nat->masq_index = par->out->ifindex;
-
-	/* Transfer from original range. */
-	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
-	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
-	newrange.flags       = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.ip = newsrc;
-	newrange.max_addr.ip = newsrc;
-	newrange.min_proto   = mr->range[0].min;
-	newrange.max_proto   = mr->range[0].max;
+	range.flags = mr->range[0].flags;
+	range.min_proto = mr->range[0].min;
+	range.max_proto = mr->range[0].max;
 
-	/* Hand modified range to generic setup. */
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+	return nf_nat_masquerade_ipv4(skb, par->hooknum, &range, par->out);
 }
 
-static int
-device_cmp(struct nf_conn *i, void *ifindex)
-{
-	const struct nf_conn_nat *nat = nfct_nat(i);
-
-	if (!nat)
-		return 0;
-	if (nf_ct_l3num(i) != NFPROTO_IPV4)
-		return 0;
-	return nat->masq_index == (int)(long)ifindex;
-}
-
-static int masq_device_event(struct notifier_block *this,
-			     unsigned long event,
-			     void *ptr)
-{
-	const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct net *net = dev_net(dev);
-
-	if (event == NETDEV_DOWN) {
-		/* Device was downed.  Search entire table for
-		   conntracks which were associated with that device,
-		   and forget them. */
-		NF_CT_ASSERT(dev->ifindex != 0);
-
-		nf_ct_iterate_cleanup(net, device_cmp,
-				      (void *)(long)dev->ifindex, 0, 0);
-	}
-
-	return NOTIFY_DONE;
-}
-
-static int masq_inet_event(struct notifier_block *this,
-			   unsigned long event,
-			   void *ptr)
-{
-	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
-	struct netdev_notifier_info info;
-
-	netdev_notifier_info_init(&info, dev);
-	return masq_device_event(this, event, &info);
-}
-
-static struct notifier_block masq_dev_notifier = {
-	.notifier_call	= masq_device_event,
-};
-
-static struct notifier_block masq_inet_notifier = {
-	.notifier_call	= masq_inet_event,
-};
-
 static struct xt_target masquerade_tg_reg __read_mostly = {
 	.name		= "MASQUERADE",
 	.family		= NFPROTO_IPV4,
@@ -160,12 +75,8 @@ static int __init masquerade_tg_init(void)
 
 	ret = xt_register_target(&masquerade_tg_reg);
 
-	if (ret == 0) {
-		/* Register for device down reports */
-		register_netdevice_notifier(&masq_dev_notifier);
-		/* Register IP address change reports */
-		register_inetaddr_notifier(&masq_inet_notifier);
-	}
+	if (ret == 0)
+		nf_nat_masquerade_ipv4_register_notifier();
 
 	return ret;
 }
@@ -173,8 +84,7 @@ static int __init masquerade_tg_init(void)
 static void __exit masquerade_tg_exit(void)
 {
 	xt_unregister_target(&masquerade_tg_reg);
-	unregister_netdevice_notifier(&masq_dev_notifier);
-	unregister_inetaddr_notifier(&masq_inet_notifier);
+	nf_nat_masquerade_ipv4_unregister_notifier();
 }
 
 module_init(masquerade_tg_init);
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index f1787c04a4dd..6b67d7e9a75d 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -28,222 +28,57 @@ static const struct xt_table nf_nat_ipv4_table = {
 	.af		= NFPROTO_IPV4,
 };
 
-static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
-{
-	/* Force range to this IP; let proto decide mapping for
-	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
-	 */
-	struct nf_nat_range range;
-
-	range.flags = 0;
-	pr_debug("Allocating NULL binding for %p (%pI4)\n", ct,
-		 HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip :
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
-
-	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
-}
-
-static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
-				     const struct net_device *in,
-				     const struct net_device *out,
-				     struct nf_conn *ct)
+static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
-	unsigned int ret;
 
-	ret = ipt_do_table(skb, hooknum, in, out, net->ipv4.nat_table);
-	if (ret == NF_ACCEPT) {
-		if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
-			ret = alloc_null_binding(ct, hooknum);
-	}
-	return ret;
+	return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.nat_table);
 }
 
-static unsigned int
-nf_nat_ipv4_fn(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_fn(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
 {
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn_nat *nat;
-	/* maniptype == SRC for postrouting. */
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
-
-	/* We never see fragments: conntrack defrags on pre-routing
-	 * and local-out, and nf_nat_out protects post-routing.
-	 */
-	NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
-
-	ct = nf_ct_get(skb, &ctinfo);
-	/* Can't track?  It's not due to stress, or conntrack would
-	 * have dropped it.  Hence it's the user's responsibilty to
-	 * packet filter it out, or implement conntrack/NAT for that
-	 * protocol. 8) --RR
-	 */
-	if (!ct)
-		return NF_ACCEPT;
-
-	/* Don't try to NAT if this packet is not conntracked */
-	if (nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
-		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   ops->hooknum))
-				return NF_DROP;
-			else
-				return NF_ACCEPT;
-		}
-		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
-	case IP_CT_NEW:
-		/* Seen it before?  This can happen for loopback, retrans,
-		 * or local packets.
-		 */
-		if (!nf_nat_initialized(ct, maniptype)) {
-			unsigned int ret;
-
-			ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
-			if (ret != NF_ACCEPT)
-				return ret;
-		} else {
-			pr_debug("Already setup manip %s for ct %p\n",
-				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
-				 ct);
-			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-				goto oif_changed;
-		}
-		break;
-
-	default:
-		/* ESTABLISHED */
-		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
-			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-			goto oif_changed;
-	}
-
-	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
-
-oif_changed:
-	nf_ct_kill_acct(ct, ctinfo, skb);
-	return NF_DROP;
+	return nf_nat_ipv4_fn(ops, skb, in, out, iptable_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv4_in(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_in(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
 {
-	unsigned int ret;
-	__be32 daddr = ip_hdr(skb)->daddr;
-
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    daddr != ip_hdr(skb)->daddr)
-		skb_dst_drop(skb);
-
-	return ret;
+	return nf_nat_ipv4_in(ops, skb, in, out, iptable_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv4_out(const struct nf_hook_ops *ops,
-		struct sk_buff *skb,
-		cons