netfilter: add protocol independent NAT core

Convert the IPv4 NAT implementation to a protocol independent core and
address family specific modules.

Signed-off-by: Patrick McHardy <kaber@trash.net>

36 files changed, 1352 insertions, 1039 deletions

diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index ed1b36783192..f1643c0c3587 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -72,43 +72,6 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type)
 }
 EXPORT_SYMBOL(ip_route_me_harder);
 
-#ifdef CONFIG_XFRM
-int ip_xfrm_me_harder(struct sk_buff *skb)
-{
-	struct flowi fl;
-	unsigned int hh_len;
-	struct dst_entry *dst;
-
-	if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
-		return 0;
-	if (xfrm_decode_session(skb, &fl, AF_INET) < 0)
-		return -1;
-
-	dst = skb_dst(skb);
-	if (dst->xfrm)
-		dst = ((struct xfrm_dst *)dst)->route;
-	dst_hold(dst);
-
-	dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0);
-	if (IS_ERR(dst))
-		return -1;
-
-	skb_dst_drop(skb);
-	skb_dst_set(skb, dst);
-
-	/* Change in oif may mean change in hh_len. */
-	hh_len = skb_dst(skb)->dev->hard_header_len;
-	if (skb_headroom(skb) < hh_len &&
-	    pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
-		return -1;
-	return 0;
-}
-EXPORT_SYMBOL(ip_xfrm_me_harder);
-#endif
-
-void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *);
-EXPORT_SYMBOL(ip_nat_decode_session);
-
 /*
  * Extra routing may needed on local out, as the QUEUE target never
  * returns control to the table.
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index fcc543cd987a..b26629681bdb 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -143,25 +143,22 @@ config IP_NF_TARGET_ULOG
 	  To compile it as a module, choose M here.  If unsure, say N.
 
 # NAT + specific targets: nf_conntrack
-config NF_NAT
-	tristate "Full NAT"
+config NF_NAT_IPV4
+	tristate "IPv4 NAT"
 	depends on NF_CONNTRACK_IPV4
 	default m if NETFILTER_ADVANCED=n
+	select NF_NAT
 	help
-	  The Full NAT option allows masquerading, port forwarding and other
+	  The IPv4 NAT option allows masquerading, port forwarding and other
 	  forms of full Network Address Port Translation.  It is controlled by
 	  the `nat' table in iptables: see the man page for iptables(8).
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
-config NF_NAT_NEEDED
-	bool
-	depends on NF_NAT
-	default y
+if NF_NAT_IPV4
 
 config IP_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
-	depends on NF_NAT
 	default m if NETFILTER_ADVANCED=n
 	help
 	  Masquerading is a special case of NAT: all outgoing connections are
@@ -174,7 +171,6 @@ config IP_NF_TARGET_MASQUERADE
 
 config IP_NF_TARGET_NETMAP
 	tristate "NETMAP target support"
-	depends on NF_NAT
 	depends on NETFILTER_ADVANCED
 	help
 	  NETMAP is an implementation of static 1:1 NAT mapping of network
@@ -185,7 +181,6 @@ config IP_NF_TARGET_NETMAP
 
 config IP_NF_TARGET_REDIRECT
 	tristate "REDIRECT target support"
-	depends on NF_NAT
 	depends on NETFILTER_ADVANCED
 	help
 	  REDIRECT is a special case of NAT: all incoming connections are
@@ -195,9 +190,11 @@ config IP_NF_TARGET_REDIRECT
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+endif
+
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
-	depends on NF_CONNTRACK_SNMP && NF_NAT
+	depends on NF_CONNTRACK_SNMP && NF_NAT_IPV4
 	depends on NETFILTER_ADVANCED
 	default NF_NAT && NF_CONNTRACK_SNMP
 	---help---
@@ -219,61 +216,46 @@ config NF_NAT_SNMP_BASIC
 #           <expr> '&&' <expr>                   (6)
 #
 # (6) Returns the result of min(/expr/, /expr/).
-config NF_NAT_PROTO_DCCP
-	tristate
-	depends on NF_NAT && NF_CT_PROTO_DCCP
-	default NF_NAT && NF_CT_PROTO_DCCP
 
 config NF_NAT_PROTO_GRE
 	tristate
-	depends on NF_NAT && NF_CT_PROTO_GRE
-
-config NF_NAT_PROTO_UDPLITE
-	tristate
-	depends on NF_NAT && NF_CT_PROTO_UDPLITE
-	default NF_NAT && NF_CT_PROTO_UDPLITE
-
-config NF_NAT_PROTO_SCTP
-	tristate
-	default NF_NAT && NF_CT_PROTO_SCTP
-	depends on NF_NAT && NF_CT_PROTO_SCTP
-	select LIBCRC32C
+	depends on NF_NAT_IPV4 && NF_CT_PROTO_GRE
 
 config NF_NAT_FTP
 	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_FTP
+	depends on NF_CONNTRACK && NF_NAT_IPV4
+	default NF_NAT_IPV4 && NF_CONNTRACK_FTP
 
 config NF_NAT_IRC
 	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_IRC
+	depends on NF_CONNTRACK && NF_NAT_IPV4
+	default NF_NAT_IPV4 && NF_CONNTRACK_IRC
 
 config NF_NAT_TFTP
 	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_TFTP
+	depends on NF_CONNTRACK && NF_NAT_IPV4
+	default NF_NAT_IPV4 && NF_CONNTRACK_TFTP
 
 config NF_NAT_AMANDA
 	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_AMANDA
+	depends on NF_CONNTRACK && NF_NAT_IPV4
+	default NF_NAT_IPV4 && NF_CONNTRACK_AMANDA
 
 config NF_NAT_PPTP
 	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_PPTP
+	depends on NF_CONNTRACK && NF_NAT_IPV4
+	default NF_NAT_IPV4 && NF_CONNTRACK_PPTP
 	select NF_NAT_PROTO_GRE
 
 config NF_NAT_H323
 	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_H323
+	depends on NF_CONNTRACK && NF_NAT_IPV4
+	default NF_NAT_IPV4 && NF_CONNTRACK_H323
 
 config NF_NAT_SIP
 	tristate
-	depends on NF_CONNTRACK && NF_NAT
-	default NF_NAT && NF_CONNTRACK_SIP
+	depends on NF_CONNTRACK && NF_NAT_IPV4
+	default NF_NAT_IPV4 && NF_CONNTRACK_SIP
 
 # mangle + specific targets
 config IP_NF_MANGLE
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index c20674dc9452..0ea3acc510e2 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -10,13 +10,11 @@ nf_conntrack_ipv4-objs	+= nf_conntrack_l3proto_ipv4_compat.o
 endif
 endif
 
-nf_nat-y		:= nf_nat_core.o nf_nat_helper.o nf_nat_proto_unknown.o nf_nat_proto_common.o nf_nat_proto_tcp.o nf_nat_proto_udp.o nf_nat_proto_icmp.o
-iptable_nat-y	:= nf_nat_rule.o nf_nat_standalone.o
-
 # connection tracking
 obj-$(CONFIG_NF_CONNTRACK_IPV4) += nf_conntrack_ipv4.o
 
-obj-$(CONFIG_NF_NAT) += nf_nat.o
+nf_nat_ipv4-y		:= nf_nat_l3proto_ipv4.o nf_nat_proto_icmp.o
+obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o
 
 # defrag
 obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o
@@ -32,10 +30,7 @@ obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
 obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o
 
 # NAT protocols (nf_nat)
-obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
-obj-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o
-obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o
 
 # generic IP tables 
 obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
@@ -43,7 +38,7 @@ obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
 # the three instances of ip_tables
 obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o
 obj-$(CONFIG_IP_NF_MANGLE) += iptable_mangle.o
-obj-$(CONFIG_NF_NAT) += iptable_nat.o
+obj-$(CONFIG_NF_NAT_IPV4) += iptable_nat.o
 obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o
 obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o
 
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index cbb6a1a6f6f7..1c3aa28b51ae 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -19,9 +19,9 @@
 #include <net/ip.h>
 #include <net/checksum.h>
 #include <net/route.h>
-#include <net/netfilter/nf_nat_rule.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_nat.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -49,7 +49,7 @@ 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_ipv4_range newrange;
+	struct nf_nat_range newrange;
 	const struct nf_nat_ipv4_multi_range_compat *mr;
 	const struct rtable *rt;
 	__be32 newsrc, nh;
@@ -80,10 +80,13 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	nat->masq_index = par->out->ifindex;
 
 	/* Transfer from original range. */
-	newrange = ((struct nf_nat_ipv4_range)
-		{ mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
-		  newsrc, newsrc,
-		  mr->range[0].min, mr->range[0].max });
+	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;
 
 	/* Hand modified range to generic setup. */
 	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c
index b5bfbbabf70d..85028dc0425d 100644
--- a/net/ipv4/netfilter/ipt_NETMAP.c
+++ b/net/ipv4/netfilter/ipt_NETMAP.c
@@ -16,7 +16,7 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
-#include <net/netfilter/nf_nat_rule.h>
+#include <net/netfilter/nf_nat.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Svenning Soerensen <svenning@post5.tele.dk>");
@@ -44,7 +44,7 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	enum ip_conntrack_info ctinfo;
 	__be32 new_ip, netmask;
 	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-	struct nf_nat_ipv4_range newrange;
+	struct nf_nat_range newrange;
 
 	NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
 		     par->hooknum == NF_INET_POST_ROUTING ||
@@ -61,10 +61,13 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par)
 		new_ip = ip_hdr(skb)->saddr & ~netmask;
 	new_ip |= mr->range[0].min_ip & netmask;
 
-	newrange = ((struct nf_nat_ipv4_range)
-		{ mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
-		  new_ip, new_ip,
-		  mr->range[0].min, mr->range[0].max });
+	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 = new_ip;
+	newrange.max_addr.ip = new_ip;
+	newrange.min_proto   = mr->range[0].min;
+	newrange.max_proto   = mr->range[0].max;
 
 	/* Hand modified range to generic setup. */
 	return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum));
diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c
index 7c0103a5203e..11407d7d2472 100644
--- a/net/ipv4/netfilter/ipt_REDIRECT.c
+++ b/net/ipv4/netfilter/ipt_REDIRECT.c
@@ -19,7 +19,7 @@
 #include <net/checksum.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
-#include <net/netfilter/nf_nat_rule.h>
+#include <net/netfilter/nf_nat.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -48,7 +48,7 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	enum ip_conntrack_info ctinfo;
 	__be32 newdst;
 	const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
-	struct nf_nat_ipv4_range newrange;
+	struct nf_nat_range newrange;
 
 	NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
 		     par->hooknum == NF_INET_LOCAL_OUT);
@@ -76,10 +76,13 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	}
 
 	/* Transfer from original range. */
-	newrange = ((struct nf_nat_ipv4_range)
-		{ mr->range[0].flags | NF_NAT_RANGE_MAP_IPS,
-		  newdst, newdst,
-		  mr->range[0].min, mr->range[0].max });
+	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 = newdst;
+	newrange.max_addr.ip = newdst;
+	newrange.min_proto   = mr->range[0].min;
+	newrange.max_proto   = mr->range[0].max;
 
 	/* Hand modified range to generic setup. */
 	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST);
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/iptable_nat.c
index 3828a4229822..9e0ffaf1d942 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -1,84 +1,71 @@
 /* (C) 1999-2001 Paul `Rusty' Russell
  * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ * (C) 2011 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#include <linux/types.h>
-#include <linux/icmp.h>
-#include <linux/gfp.h>
-#include <linux/ip.h>
+
+#include <linux/module.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/proc_fs.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/ip.h>
 #include <net/ip.h>
-#include <net/checksum.h>
-#include <linux/spinlock.h>
 
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_extend.h>
 #include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_rule.h>
-#include <net/netfilter/nf_nat_protocol.h>
 #include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_helper.h>
-#include <linux/netfilter_ipv4/ip_tables.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+
+static const struct xt_table nf_nat_ipv4_table = {
+	.name		= "nat",
+	.valid_hooks	= (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_LOCAL_IN),
+	.me		= THIS_MODULE,
+	.af		= NFPROTO_IPV4,
+};
 
-#ifdef CONFIG_XFRM
-static void nat_decode_session(struct sk_buff *skb, struct flowi *fl)
+static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
 {
-	struct flowi4 *fl4 = &fl->u.ip4;
-	const struct nf_conn *ct;
-	const struct nf_conntrack_tuple *t;
-	enum ip_conntrack_info ctinfo;
-	enum ip_conntrack_dir dir;
-	unsigned long statusbit;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	if (ct == NULL)
-		return;
-	dir = CTINFO2DIR(ctinfo);
-	t = &ct->tuplehash[dir].tuple;
-
-	if (dir == IP_CT_DIR_ORIGINAL)
-		statusbit = IPS_DST_NAT;
-	else
-		statusbit = IPS_SRC_NAT;
-
-	if (ct->status & statusbit) {
-		fl4->daddr = t->dst.u3.ip;
-		if (t->dst.protonum == IPPROTO_TCP ||
-		    t->dst.protonum == IPPROTO_UDP ||
-		    t->dst.protonum == IPPROTO_UDPLITE ||
-		    t->dst.protonum == IPPROTO_DCCP ||
-		    t->dst.protonum == IPPROTO_SCTP)
-			fl4->fl4_dport = t->dst.u.tcp.port;
-	}
+	/* 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));
+}
 
-	statusbit ^= IPS_NAT_MASK;
+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)
+{
+	struct net *net = nf_ct_net(ct);
+	unsigned int ret;
 
-	if (ct->status & statusbit) {
-		fl4->saddr = t->src.u3.ip;
-		if (t->dst.protonum == IPPROTO_TCP ||
-		    t->dst.protonum == IPPROTO_UDP ||
-		    t->dst.protonum == IPPROTO_UDPLITE ||
-		    t->dst.protonum == IPPROTO_DCCP ||
-		    t->dst.protonum == IPPROTO_SCTP)
-			fl4->fl4_sport = t->src.u.tcp.port;
+	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;
 }
-#endif
 
 static unsigned int
-nf_nat_fn(unsigned int hooknum,
-	  struct sk_buff *skb,
-	  const struct net_device *in,
-	  const struct net_device *out,
-	  int (*okfn)(struct sk_buff *))
+nf_nat_ipv4_fn(unsigned int hooknum,
+	       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;
@@ -87,14 +74,16 @@ nf_nat_fn(unsigned int hooknum,
 	enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
 
 	/* We never see fragments: conntrack defrags on pre-routing
-	   and local-out, and nf_nat_out protects post-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 */
+	 * 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;
 
@@ -118,17 +107,17 @@ nf_nat_fn(unsigned int hooknum,
 	case IP_CT_RELATED:
 	case IP_CT_RELATED_REPLY:
 		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-			if (!nf_nat_icmp_reply_translation(ct, ctinfo,
-							   hooknum, skb))
+			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
+							   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.. */
+		 * or local packets.
+		 */
 		if (!nf_nat_initialized(ct, maniptype)) {
 			unsigned int ret;
 
@@ -151,16 +140,16 @@ nf_nat_fn(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_in(unsigned int hooknum,
-	  struct sk_buff *skb,
-	  const struct net_device *in,
-	  const struct net_device *out,
-	  int (*okfn)(struct sk_buff *))
+nf_nat_ipv4_in(unsigned int hooknum,
+	       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_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    daddr != ip_hdr(skb)->daddr)
 		skb_dst_drop(skb);
@@ -169,11 +158,11 @@ nf_nat_in(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_out(unsigned int hooknum,
-	   struct sk_buff *skb,
-	   const struct net_device *in,
-	   const struct net_device *out,
-	   int (*okfn)(struct sk_buff *))
+nf_nat_ipv4_out(unsigned int hooknum,
+		struct sk_buff *skb,
+		const struct net_device *in,
+		const struct net_device *out,
+		int (*okfn)(struct sk_buff *))
 {
 #ifdef CONFIG_XFRM
 	const struct nf_conn *ct;
@@ -186,29 +175,30 @@ nf_nat_out(unsigned int hooknum,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
 
 		if ((ct->tuplehash[dir].tuple.src.u3.ip !=
 		     ct->tuplehash[!dir].tuple.dst.u3.ip) ||
 		    (ct->tuplehash[dir].tuple.src.u.all !=
-		     ct->tuplehash[!dir].tuple.dst.u.all)
-		   )
-			return ip_xfrm_me_harder(skb) == 0 ? ret : NF_DROP;
+		     ct->tuplehash[!dir].tuple.dst.u.all))
+			if (nf_xfrm_me_harder(skb, AF_INET) < 0)
+				ret = NF_DROP;
 	}
 #endif
 	return ret;
 }
 
 static unsigned int
-nf_nat_local_fn(unsigned int hooknum,
-		struct sk_buff *skb,
-		const struct net_device *in,
-		const struct net_device *out,
-		int (*okfn)(struct sk_buff *))
+nf_nat_ipv4_local_fn(unsigned int hooknum,
+		     struct sk_buff *skb,
+		     const struct net_device *in,
+		     const struct net_device *out,
+		     int (*okfn)(struct sk_buff *))
 {
 	const struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
@@ -219,7 +209,7 @@ nf_nat_local_fn(unsigned int hooknum,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
@@ -230,21 +220,20 @@ nf_nat_local_fn(unsigned int hooknum,
 				ret = NF_DROP;
 		}
 #ifdef CONFIG_XFRM
-		else if (ct->tuplehash[dir].tuple.dst.u.all !=
+		else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+			 ct->tuplehash[dir].tuple.dst.u.all !=
 			 ct->tuplehash[!dir].tuple.src.u.all)
-			if (ip_xfrm_me_harder(skb))
+			if (nf_xfrm_me_harder(skb, AF_INET) < 0)
 				ret = NF_DROP;
 #endif
 	}
 	return ret;
 }
 
-/* We must be after connection tracking and before packet filtering. */
-
-static struct nf_hook_ops nf_nat_ops[] __read_mostly = {
+static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_in,
+		.hook		= nf_nat_ipv4_in,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_PRE_ROUTING,
@@ -252,7 +241,7 @@ static struct nf_hook_ops nf_nat_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_out,
+		.hook		= nf_nat_ipv4_out,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_POST_ROUTING,
@@ -260,7 +249,7 @@ static struct nf_hook_ops nf_nat_ops[] __read_mostly = {
 	},
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_local_fn,
+		.hook		= nf_nat_ipv4_local_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_LOCAL_OUT,
@@ -268,7 +257,7 @@ static struct nf_hook_ops nf_nat_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_fn,
+		.hook		= nf_nat_ipv4_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_LOCAL_IN,
@@ -276,51 +265,56 @@ static struct nf_hook_ops nf_nat_ops[] __read_mostly = {
 	},
 };
 
-static int __init nf_nat_standalone_init(void)
+static int __net_init iptable_nat_net_init(struct net *net)
 {
-	int ret = 0;
+	struct ipt_replace *repl;
+
+	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);
+	kfree(repl);
+	if (IS_ERR(net->ipv4.nat_table))
+		return PTR_ERR(net->ipv4.nat_table);
+	return 0;
+}
 
-	need_ipv4_conntrack();
+static void __net_exit iptable_nat_net_exit(struct net *net)
+{
+	ipt_unregister_table(net, net->ipv4.nat_table);
+}
 
-#ifdef CONFIG_XFRM
-	BUG_ON(ip_nat_decode_session != NULL);
-	RCU_INIT_POINTER(ip_nat_decode_session, nat_decode_session);
-#endif
-	ret = nf_nat_rule_init();
-	if (ret < 0) {
-		pr_err("nf_nat_init: can't setup rules.\n");
-		goto cleanup_decode_session;
-	}
-	ret = nf_register_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops));
-	if (ret < 0) {
-		pr_err("nf_nat_init: can't register hooks.\n");
-		goto cleanup_rule_init;
-	}
-	return ret;
+static struct pernet_operations iptable_nat_net_ops = {
+	.init	= iptable_nat_net_init,
+	.exit	= iptable_nat_net_exit,
+};
 
- cleanup_rule_init:
-	nf_nat_rule_cleanup();
- cleanup_decode_session:
-#ifdef CONFIG_XFRM
-	RCU_INIT_POINTER(ip_nat_decode_session, NULL);
-	synchronize_net();
-#endif
-	return ret;
+static int __init iptable_nat_init(void)
+{
+	int err;
+
+	err = register_pernet_subsys(&iptable_nat_net_ops);
+	if (err < 0)
+		goto err1;
+
+	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;
 }
 
-static void __exit nf_nat_standalone_fini(void)
+static void __exit iptable_nat_exit(void)
 {
-	nf_unregister_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops));
-	nf_nat_rule_cleanup();
-#ifdef CONFIG_XFRM
-	RCU_INIT_POINTER(ip_nat_decode_session, NULL);
-	synchronize_net();
-#endif
-	/* Conntrack caches are unregistered in nf_conntrack_cleanup */
+	nf_unregister_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+	unregister_pernet_subsys(&iptable_nat_net_ops);
 }
 
-module_init(nf_nat_standalone_init);
-module_exit(nf_nat_standalone_fini);
+module_init(iptable_nat_init);
+module_exit(iptable_nat_exit);
 
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("ip_nat");
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 4ada3295d9a7..fcdd0c2406e6 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -29,12 +29,6 @@
 #include <net/netfilter/ipv4/