15 files changed, 283 insertions, 447 deletions

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 280048e1e395..bbfc356cb1b5 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -29,7 +29,10 @@ config NF_SOCKET_IPV4
 	tristate "IPv4 socket lookup support"
 	help
 	  This option enables the IPv4 socket lookup infrastructure. This is
-	  is required by the iptables socket match.
+	  is required by the {ip,nf}tables socket match.
+
+config NF_TPROXY_IPV4
+	tristate "IPv4 tproxy support"
 
 if NF_TABLES
 
@@ -129,10 +132,7 @@ config NFT_CHAIN_NAT_IPV4
 	  source and destination ports.
 
 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).
+	bool
 
 config NFT_MASQ_IPV4
 	tristate "IPv4 masquerading support for nf_tables"
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 0e5edd0c7926..8394c17c269f 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -10,12 +10,14 @@ nf_conntrack_ipv4-y	:=  nf_conntrack_l3proto_ipv4.o nf_conntrack_proto_icmp.o
 obj-$(CONFIG_NF_CONNTRACK_IPV4) += nf_conntrack_ipv4.o
 
 nf_nat_ipv4-y		:= nf_nat_l3proto_ipv4.o nf_nat_proto_icmp.o
+nf_nat_ipv4-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
 obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o
 
 # defrag
 obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o
 
 obj-$(CONFIG_NF_SOCKET_IPV4) += nf_socket_ipv4.o
+obj-$(CONFIG_NF_TPROXY_IPV4) += nf_tproxy_ipv4.o
 
 # logging
 obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o
@@ -32,9 +34,6 @@ nf_nat_snmp_basic-y := nf_nat_snmp_basic.asn1.o nf_nat_snmp_basic_main.o
 $(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h
 obj-$(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
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index e85f35b89c49..38ab97b0a2ec 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -301,7 +301,7 @@ ipt_do_table(struct sk_buff *skb,
 		counter = xt_get_this_cpu_counter(&e->counters);
 		ADD_COUNTER(*counter, skb->len, 1);
 
-		t = ipt_get_target(e);
+		t = ipt_get_target_c(e);
 		WARN_ON(!t->u.kernel.target);
 
 #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
@@ -1783,6 +1783,8 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
 
 	/* set res now, will see skbs right after nf_register_net_hooks */
 	WRITE_ONCE(*res, new_table);
+	if (!ops)
+		return 0;
 
 	ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
 	if (ret != 0) {
@@ -1800,7 +1802,8 @@ out_free:
 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));
+	if (ops)
+		nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
 	__ipt_unregister_table(net, table);
 }
 
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index a03e4e7ef5f9..ce1512b02cb2 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -47,7 +47,7 @@ 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_nat_range range;
+	struct nf_nat_range2 range;
 	const struct nf_nat_ipv4_multi_range_compat *mr;
 
 	mr = par->targinfo;
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 0f7255cc65ee..a317445448bf 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -33,75 +33,63 @@ static const struct xt_table nf_nat_ipv4_table = {
 
 static unsigned int iptable_nat_do_chain(void *priv,
 					 struct sk_buff *skb,
-					 const struct nf_hook_state *state,
-					 struct nf_conn *ct)
-{
-	return ipt_do_table(skb, state, state->net->ipv4.nat_table);
-}
-
-static unsigned int iptable_nat_ipv4_fn(void *priv,
-					struct sk_buff *skb,
-					const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_fn(priv, skb, state, iptable_nat_do_chain);
-}
-
-static unsigned int iptable_nat_ipv4_in(void *priv,
-					struct sk_buff *skb,
-					const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_in(priv, skb, state, iptable_nat_do_chain);
-}
-
-static unsigned int iptable_nat_ipv4_out(void *priv,
-					 struct sk_buff *skb,
 					 const struct nf_hook_state *state)
 {
-	return nf_nat_ipv4_out(priv, skb, state, iptable_nat_do_chain);
-}
-
-static unsigned int iptable_nat_ipv4_local_fn(void *priv,
-					      struct sk_buff *skb,
-					      const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_local_fn(priv, skb, state, iptable_nat_do_chain);
+	return ipt_do_table(skb, state, state->net->ipv4.nat_table);
 }
 
 static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
-	/* Before packet filtering, change destination */
 	{
-		.hook		= iptable_nat_ipv4_in,
+		.hook		= iptable_nat_do_chain,
 		.pf		= NFPROTO_IPV4,
-		.nat_hook	= true,
 		.hooknum	= NF_INET_PRE_ROUTING,
 		.priority	= NF_IP_PRI_NAT_DST,
 	},
-	/* After packet filtering, change source */
 	{
-		.hook		= iptable_nat_ipv4_out,
+		.hook		= iptable_nat_do_chain,
 		.pf		= NFPROTO_IPV4,
-		.nat_hook	= true,
 		.hooknum	= NF_INET_POST_ROUTING,
 		.priority	= NF_IP_PRI_NAT_SRC,
 	},
-	/* Before packet filtering, change destination */
 	{
-		.hook		= iptable_nat_ipv4_local_fn,
+		.hook		= iptable_nat_do_chain,
 		.pf		= NFPROTO_IPV4,
-		.nat_hook	= true,
 		.hooknum	= NF_INET_LOCAL_OUT,
 		.priority	= NF_IP_PRI_NAT_DST,
 	},
-	/* After packet filtering, change source */
 	{
-		.hook		= iptable_nat_ipv4_fn,
+		.hook		= iptable_nat_do_chain,
 		.pf		= NFPROTO_IPV4,
-		.nat_hook	= true,
 		.hooknum	= NF_INET_LOCAL_IN,
 		.priority	= NF_IP_PRI_NAT_SRC,
 	},
 };
 
+static int ipt_nat_register_lookups(struct net *net)
+{
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) {
+		ret = nf_nat_l3proto_ipv4_register_fn(net, &nf_nat_ipv4_ops[i]);
+		if (ret) {
+			while (i)
+				nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[--i]);
+
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void ipt_nat_unregister_lookups(struct net *net)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++)
+		nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[i]);
+}
+
 static int __net_init iptable_nat_table_init(struct net *net)
 {
 	struct ipt_replace *repl;
@@ -114,7 +102,18 @@ static int __net_init iptable_nat_table_init(struct net *net)
 	if (repl == NULL)
 		return -ENOMEM;
 	ret = ipt_register_table(net, &nf_nat_ipv4_table, repl,
-				 nf_nat_ipv4_ops, &net->ipv4.nat_table);
+				 NULL, &net->ipv4.nat_table);
+	if (ret < 0) {
+		kfree(repl);
+		return ret;
+	}
+
+	ret = ipt_nat_register_lookups(net);
+	if (ret < 0) {
+		ipt_unregister_table(net, net->ipv4.nat_table, NULL);
+		net->ipv4.nat_table = NULL;
+	}
+
 	kfree(repl);
 	return ret;
 }
@@ -123,7 +122,8 @@ static void __net_exit iptable_nat_net_exit(struct net *net)
 {
 	if (!net->ipv4.nat_table)
 		return;
-	ipt_unregister_table(net, net->ipv4.nat_table, nf_nat_ipv4_ops);
+	ipt_nat_unregister_lookups(net);
+	ipt_unregister_table(net, net->ipv4.nat_table, NULL);
 	net->ipv4.nat_table = NULL;
 }
 
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index 0cd46bffa469..e1e56d7123d2 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -2,265 +2,12 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/netfilter.h>
-#include <linux/rhashtable.h>
-#include <linux/ip.h>
-#include <linux/netdevice.h>
-#include <net/ip.h>
-#include <net/neighbour.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_tables.h>
-/* For layer 4 checksum field offset. */
-#include <linux/tcp.h>
-#include <linux/udp.h>
-
-static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
-			      __be32 addr, __be32 new_addr)
-{
-	struct tcphdr *tcph;
-
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
-		return -1;
-
-	tcph = (void *)(skb_network_header(skb) + thoff);
-	inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true);
-
-	return 0;
-}
-
-static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
-			      __be32 addr, __be32 new_addr)
-{
-	struct udphdr *udph;
-
-	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
-		return -1;
-
-	udph = (void *)(skb_network_header(skb) + thoff);
-	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
-		inet_proto_csum_replace4(&udph->check, skb, addr,
-					 new_addr, true);
-		if (!udph->check)
-			udph->check = CSUM_MANGLED_0;
-	}
-
-	return 0;
-}
-
-static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
-				  unsigned int thoff, __be32 addr,
-				  __be32 new_addr)
-{
-	switch (iph->protocol) {
-	case IPPROTO_TCP:
-		if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
-		break;
-	case IPPROTO_UDP:
-		if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
-		break;
-	}
-
-	return 0;
-}
-
-static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			   struct iphdr *iph, unsigned int thoff,
-			   enum flow_offload_tuple_dir dir)
-{
-	__be32 addr, new_addr;
-
-	switch (dir) {
-	case FLOW_OFFLOAD_DIR_ORIGINAL:
-		addr = iph->saddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
-		iph->saddr = new_addr;
-		break;
-	case FLOW_OFFLOAD_DIR_REPLY:
-		addr = iph->daddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
-		iph->daddr = new_addr;
-		break;
-	default:
-		return -1;
-	}
-	csum_replace4(&iph->check, addr, new_addr);
-
-	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
-}
-
-static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			   struct iphdr *iph, unsigned int thoff,
-			   enum flow_offload_tuple_dir dir)
-{
-	__be32 addr, new_addr;
-
-	switch (dir) {
-	case FLOW_OFFLOAD_DIR_ORIGINAL:
-		addr = iph->daddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
-		iph->daddr = new_addr;
-		break;
-	case FLOW_OFFLOAD_DIR_REPLY:
-		addr = iph->saddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
-		iph->saddr = new_addr;
-		break;
-	default:
-		return -1;
-	}
-	csum_replace4(&iph->check, addr, new_addr);
-
-	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
-}
-
-static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			  enum flow_offload_tuple_dir dir)
-{
-	struct iphdr *iph = ip_hdr(skb);
-	unsigned int thoff = iph->ihl * 4;
-
-	if (flow->flags & FLOW_OFFLOAD_SNAT &&
-	    (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
-	     nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
-		return -1;
-	if (flow->flags & FLOW_OFFLOAD_DNAT &&
-	    (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
-	     nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
-		return -1;
-
-	return 0;
-}
-
-static bool ip_has_options(unsigned int thoff)
-{
-	return thoff != sizeof(struct iphdr);
-}
-
-static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
-			    struct flow_offload_tuple *tuple)
-{
-	struct flow_ports *ports;
-	unsigned int thoff;
-	struct iphdr *iph;
-
-	if (!pskb_may_pull(skb, sizeof(*iph)))
-		return -1;
-
-	iph = ip_hdr(skb);
-	thoff = iph->ihl * 4;
-
-	if (ip_is_fragment(iph) ||
-	    unlikely(ip_has_options(thoff)))
-		return -1;
-
-	if (iph->protocol != IPPROTO_TCP &&
-	    iph->protocol != IPPROTO_UDP)
-		return -1;
-
-	thoff = iph->ihl * 4;
-	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
-		return -1;
-
-	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
-
-	tuple->src_v4.s_addr	= iph->saddr;
-	tuple->dst_v4.s_addr	= iph->daddr;
-	tuple->src_port		= ports->source;
-	tuple->dst_port		= ports->dest;
-	tuple->l3proto		= AF_INET;
-	tuple->l4proto		= iph->protocol;
-	tuple->iifidx		= dev->ifindex;
-
-	return 0;
-}
-
-/* Based on ip_exceeds_mtu(). */
-static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
-{
-	if (skb->len <= mtu)
-		return false;
-
-	if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
-		return false;
-
-	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
-		return false;
-
-	return true;
-}
-
-static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rtable *rt)
-{
-	u32 mtu;
-
-	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
-	if (__nf_flow_exceeds_mtu(skb, mtu))
-		return true;
-
-	return false;
-}
-
-unsigned int
-nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
-			const struct nf_hook_state *state)
-{
-	struct flow_offload_tuple_rhash *tuplehash;
-	struct nf_flowtable *flow_table = priv;
-	struct flow_offload_tuple tuple = {};
-	enum flow_offload_tuple_dir dir;
-	struct flow_offload *flow;
-	struct net_device *outdev;
-	const struct rtable *rt;
-	struct iphdr *iph;
-	__be32 nexthop;
-
-	if (skb->protocol != htons(ETH_P_IP))
-		return NF_ACCEPT;
-
-	if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
-		return NF_ACCEPT;
-
-	tuplehash = flow_offload_lookup(flow_table, &tuple);
-	if (tuplehash == NULL)
-		return NF_ACCEPT;
-
-	outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
-	if (!outdev)
-		return NF_ACCEPT;
-
-	dir = tuplehash->tuple.dir;
-	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-
-	rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
-	if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
-		return NF_ACCEPT;
-
-	if (skb_try_make_writable(skb, sizeof(*iph)))
-		return NF_DROP;
-
-	if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
-	    nf_flow_nat_ip(flow, skb, dir) < 0)
-		return NF_DROP;
-
-	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
-	iph = ip_hdr(skb);
-	ip_decrease_ttl(iph);
-
-	skb->dev = outdev;
-	nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
-	neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
-
-	return NF_STOLEN;
-}
-EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook);
 
 static struct nf_flowtable_type flowtable_ipv4 = {
 	.family		= NFPROTO_IPV4,
-	.params		= &nf_flow_offload_rhash_params,
-	.gc		= nf_flow_offload_work_gc,
+	.init		= nf_flow_table_init,
 	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_ip_hook,
 	.owner		= THIS_MODULE,
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index ac8342dcb55e..4e6b53ab6c33 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -395,7 +395,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct,
 static void ip_nat_q931_expect(struct nf_conn *new,
 			       struct nf_conntrack_expect *this)
 {
-	struct nf_nat_range range;
+	struct nf_nat_range2 range;
 
 	if (this->tuple.src.u3.ip != 0) {	/* Only accept calls from GK */
 		nf_nat_follow_master(new, this);
@@ -497,7 +497,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct,
 static void ip_nat_callforwarding_expect(struct nf_conn *new,
 					 struct nf_conntrack_expect *this)
 {
-	struct nf_nat_range range;
+	struct nf_nat_range2 range;
 
 	/* This must be a fresh one. */
 	BUG_ON(new->status & IPS_NAT_DONE_MASK);
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index f7ff6a364d7b..6115bf1ff6f0 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -63,7 +63,7 @@ static void nf_nat_ipv4_decode_session(struct sk_buff *skb,
 #endif /* CONFIG_XFRM */
 
 static bool nf_nat_ipv4_in_range(const struct nf_conntrack_tuple *t,
-				 const struct nf_nat_range *range)
+				 const struct nf_nat_range2 *range)
 {
 	return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) &&
 	       ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip);
@@ -143,7 +143,7 @@ static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb,
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[],
-				       struct nf_nat_range *range)
+				       struct nf_nat_range2 *range)
 {
 	if (tb[CTA_NAT_V4_MINIP]) {
 		range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]);
@@ -241,34 +241,18 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);
 
-unsigned int
+static unsigned int
 nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
-	       const struct nf_hook_state *state,
-	       unsigned int (*do_chain)(void *priv,
-					struct sk_buff *skb,
-					const struct nf_hook_state *state,
-					struct nf_conn *ct))
+	       const struct nf_hook_state *state)
 {
 	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(state->hook);
 
 	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;
 
-	nat = nfct_nat(ct);
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
+	if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) {
 		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
 			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
 							   state->hook))
@@ -276,78 +260,30 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 			else
 				return NF_ACCEPT;
 		}
-		/* Only ICMPs can be IP_CT_IS_REPLY: */
-		/* fall through */
-	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 = do_chain(priv, skb, state, ct);
-			if (ret != NF_ACCEPT)
-				return ret;
-
-			if (nf_nat_initialized(ct, HOOK2MANIP(state->hook)))
-				break;
-
-			ret = nf_nat_alloc_null_binding(ct, state->hook);
-			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(state->hook, ctinfo, nat,
-					       state->out))
-				goto oif_changed;
-		}
-		break;
-
-	default:
-		/* ESTABLISHED */
-		WARN_ON(ctinfo != IP_CT_ESTABLISHED &&
-			ctinfo != IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out))
-			goto oif_changed;
 	}
 
-	return nf_nat_packet(ct, ctinfo, state->hook, skb);
-
-oif_changed:
-	nf_ct_kill_acct(ct, ctinfo, skb);
-	return NF_DROP;
+	return nf_nat_inet_fn(priv, skb, state);
 }
 EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn);
 
-unsigned int
+static unsigned int
 nf_nat_ipv4_in(void *priv, struct sk_buff *skb,
-	       const struct nf_hook_state *state,
-	       unsigned int (*do_chain)(void *priv,
-					 struct sk_buff *skb,
-					 const struct nf_hook_state *state,
-					 struct nf_conn *ct))
+	       const struct nf_hook_state *state)
 {
 	unsigned int ret;
 	__be32 daddr = ip_hdr(skb)->daddr;
 
-	ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
+	ret = nf_nat_ipv4_fn(priv, skb, state);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    daddr != ip_hdr(skb)->daddr)
 		skb_dst_drop(skb);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nf_nat_ipv4_in);
 
-unsigned int
+static unsigned int
 nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
-		const struct nf_hook_state *state,
-		unsigned int (*do_chain)(void *priv,
-					  struct sk_buff *skb,
-					  const struct nf_hook_state *state,
-					  struct nf_conn *ct))
+		const struct nf_hook_state *state)
 {
 #ifdef CONFIG_XFRM
 	const struct nf_conn *ct;
@@ -356,7 +292,7 @@ nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
 #endif
 	unsigned int ret;
 
-	ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
+	ret = nf_nat_ipv4_fn(priv, skb, state);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
@@ -376,22 +312,17 @@ nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
 #endif
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nf_nat_ipv4_out);
 
-unsigned int
+static unsigned int
 nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
-		     const struct nf_hook_state *state,
-		     unsigned int (*do_chain)(void *priv,
-					       struct sk_buff *skb,
-					       const struct nf_hook_state *state,
-					       struct nf_conn *ct))
+		     const struct nf_hook_state *state)
 {
 	const struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
 	unsigned int ret;
 	int err;
 
-	ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
+	ret = nf_nat_ipv4_fn(priv, skb, state);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
@@ -415,7 +346,49 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
 	}
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nf_nat_ipv4_local_fn);
+
+static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
+	/* Before packet filtering, change destination */
+	{
+		.hook		= nf_nat_ipv4_in,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP_PRI_NAT_DST,
+	},
+	/* After packet filtering, change source */
+	{
+		.hook		= nf_nat_ipv4_out,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP_PRI_NAT_SRC,
+	},
+	/* Before packet filtering, change destination */
+	{
+		.hook		= nf_nat_ipv4_local_fn,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP_PRI_NAT_DST,
+	},
+	/* After packet filtering, change source */
+	{
+		.hook		= nf_nat_ipv4_fn,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP_PRI_NAT_SRC,
+	},
+};
+
+int nf_nat_l3proto_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+	return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+}
+EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_register_fn);
+
+void nf_nat_l3proto_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+	nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+}
+EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_unregister_fn);
 
 static int __init nf_nat_l3proto_ipv4_init(void)
 {
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index 0c366aad89cb..ad3aeff152ed 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/types.h>
-#include <linux/module.h>
 #include <linux/atomic.h>
 #include <linux/inetdevice.h>
 #include <linux/ip.h>
@@ -24,13 +23,13 @@
 
 unsigned int
 nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
-		       const struct nf_nat_range *range,
+		       const struct nf_nat_range2 *range,
 		       const struct net_device *out)
 {
 	struct nf_conn *ct;
 	struct nf_conn_nat *nat;
 	enum ip_conntrack_info ctinfo;
-	struct nf_nat_range newrange;
+	struct nf_nat_range2 newrange;
 	const struct rtable *rt;
 	__be32 newsrc, nh;
 
@@ -157,6 +156,3 @@ void nf_nat_masquerade_ipv4_unregister_notifier(void)
 	unregister_inetaddr_notifier(&masq_inet_notifier);
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>");
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 8a69363b4884..5d259a12e25f 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -48,7 +48,7 @@ static void pptp_nat_expected(struct nf_conn *ct,
 	struct nf_conntrack_tuple t = {};
 	const struct nf_ct_pptp_master *ct_pptp_info;
 	const struct nf_nat_pptp *nat_pptp_info;
-	struct nf_nat_range range;
+	struct nf_nat_range2 range;
 	struct nf_conn_nat *nat;
 
 	nat = nf_ct_nat_ext_add(ct);
diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c
index edf05002d674..00fda6331ce5 100644
--- a/net/ipv4/netfilter/nf_nat_proto_gre.c
+++ b/net/ipv4/netfilter/nf_nat_proto_gre.c
@@ -41,7 +41,7 @@ MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE");
 static void
 gre_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		 struct nf_conntrack_tuple *tuple,
-		 const struct nf_nat_range *range,
+		 const struct nf_nat_range2 *range,
 		 enum nf_nat_manip_type maniptype,
 		 const struct nf_conn *ct)
 {
diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c
index 7b98baa13ede..6d7cf1d79baf 100644
--- a/net/ipv4/netfilter/nf_nat_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c
@@ -30,7 +30,7 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple,
 static void
 icmp_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		  struct nf_conntrack_tuple *tuple,
-		  const struct nf_nat_range *range,
+		  const struct nf_nat_range2 *range,
 		  enum nf_nat_manip_type maniptype,
 		  const struct nf_conn *ct)
 {
diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c
new file mode 100644
index 000000000000..805e83ec3ad9
--- /dev/null
+++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright (C) 2007-2008 BalaBit IT Ltd.
+ * Author: Krisztian Kovacs
+ *
+ * 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 <net/netfilter/nf_tproxy.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/inet_sock.h>
+#include <linux/ip.h>
+#include <net/checksum.h>
+#include <net/udp.h>
+#include <net/tcp.h>
+#include <linux/inetdevice.h>
+
+struct sock *
+nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
+			 __be32 laddr, __be16 lport, struct sock *sk)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	struct tcphdr _hdr, *hp;
+
+	hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
+	if (hp == NULL) {
+		inet_twsk_put(inet_twsk(sk));
+		return NULL;
+	}
+
+	if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
+		/* SYN to a TIME_WAIT socket, we'd rather redirect it
+		 * to a listener socket if there's one */
+		struct sock *sk2;
+
+		sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+					    iph->saddr, laddr ? laddr : iph->daddr,
+					    hp->source, lport ? lport : hp->dest,
+					    skb->dev, NF_TPROXY_LOOKUP_LISTENER);
+		if (sk2) {
+			inet_twsk_deschedule_put(inet_twsk(sk));
+			sk = sk2;
+		}
+	}
+
+	return sk;
+}
+EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait4);
+
+__be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
+{
+	struct in_device *indev;
+	__be32 laddr;
+
+	if (user_laddr)
+		return user_laddr;
+
+	laddr = 0;
+	indev = __in_dev_get_rcu(skb->dev);
+	for_primary_ifa(indev) {
+		laddr = ifa->ifa_local;
+		break;
+	} endfor_ifa(indev);
+
+	return laddr ? laddr : daddr;
+}
+EXPORT_SYMBOL_GPL(nf_tproxy_laddr4);
+
+struct sock *
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+		      const u8 protocol,
+		      const __be32 saddr, const __be32 daddr,
+		      const __be16 sport, const __be16 dport,
+		      const struct net_device *in,
+		      const enum nf_tproxy_lookup_t lookup_type)
+{
+	struct sock *sk;
+	struct tcphdr *tcph;
+
+	switch (protocol) {
+	case IPPROTO_TCP:
+		switch (lookup_type) {
+		case NF_TPROXY_LOOKUP_LISTENER:
+			tcph = hp;
+			sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
+						    ip_hdrlen(skb) +
+						      __tcp_hdrlen(tcph),
+						    saddr, sport,
+						    daddr, dport,
+						    in->ifindex, 0);
+
+			if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
+				sk = NULL;
+			/* NOTE: we return listeners even if bound to
+			 * 0.0.0.0, those are filtered out in
+			 * xt_socket, since xt_TPROXY needs 0 bound
+			 * listeners too
+			 */
+			break;
+		case NF_TPROXY_LOOKUP_ESTABLISHED:
+			sk = inet_lookup_established(net, &tcp_hashinfo,
+						    saddr, sport, daddr, dport,
+						    in->ifindex);
+			break;
+		default:
+			BUG();
+		}
+		break;
+	case IPPROTO_UDP:
+		sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
+				     in->ifindex);
+		if (sk) {
+			int connected = (sk->sk_state == TCP_ESTABLISHED);
+			int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0);
+
+			/* NOTE: we return listeners even if bound to
+			 * 0.0.0.0, those are filtered out in
+			 * xt_socket, since xt_TPROXY needs 0 bound
+			 * listeners too
+			 */
+			if ((lookup_type == NF_TPROXY_LOOKUP_ESTABLISHED &&
+			      (!connected