netfilter: nat: merge nf_nat_ipv4,6 into nat core

before:
   text    data     bss     dec     hex filename
  16566    1576    4136   22278    5706 nf_nat.ko
   3598	    844	      0	   4442	   115a	nf_nat_ipv6.ko
   3187	    844	      0	   4031	    fbf	nf_nat_ipv4.ko

after:
   text    data     bss     dec     hex filename
  22948    1612    4136   28696    7018 nf_nat.ko

... with ipv4/v6 nat now provided directly via nf_nat.ko.

Also changes:
       ret = nf_nat_ipv4_fn(priv, skb, state);
       if (ret != NF_DROP && ret != NF_STOLEN &&
into
	if (ret != NF_ACCEPT)
		return ret;

everywhere.

The nat hooks never should return anything other than
ACCEPT or DROP (and the latter only in rare error cases).

The original code uses multi-line ANDing including assignment-in-if:
        if (ret != NF_DROP && ret != NF_STOLEN &&
           !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
            (ct = nf_ct_get(skb, &ctinfo)) != NULL) {

I removed this while moving, breaking those in separate conditionals
and moving the assignments into extra lines.

checkpatch still generates some warnings:
 1. Overly long lines (of moved code).
    Breaking them is even more ugly. so I kept this as-is.
 2. use of extern function declarations in a .c file.
    This is necessary evil, we must call
    nf_nat_l3proto_register() from the nat core now.
    All l3proto related functions are removed later in this series,
    those prototypes are then removed as well.

v2: keep empty nf_nat_ipv6_csum_update stub for CONFIG_IPV6=n case.
v3: remove IS_ENABLED(NF_NAT_IPV4/6) tests, NF_NAT_IPVx toggles
    are removed here.
v4: also get rid of the assignments in conditionals.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

3 files changed, 2 insertions, 383 deletions

diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index f57fc99e9a04..a04a38166d8c 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -31,7 +31,7 @@ config NFT_CHAIN_ROUTE_IPV6
 	  fields such as the source, destination, flowlabel, hop-limit and
 	  the packet mark.
 
-if NF_NAT_IPV6
+if NF_NAT
 
 config NFT_CHAIN_NAT_IPV6
 	tristate "IPv6 nf_tables nat chain support"
@@ -57,7 +57,7 @@ config NFT_REDIR_IPV6
 	  This is the expression that provides IPv4 redirect support for
 	  nf_tables.
 
-endif # NF_NAT_IPV6
+endif # NF_NAT
 
 config NFT_REJECT_IPV6
 	select NF_REJECT_IPV6
@@ -106,16 +106,6 @@ config NF_LOG_IPV6
 	default m if NETFILTER_ADVANCED=n
 	select NF_LOG_COMMON
 
-config NF_NAT_IPV6
-	tristate "IPv6 NAT"
-	depends on NF_CONNTRACK
-	depends on NETFILTER_ADVANCED
-	select NF_NAT
-	help
-	  The IPv6 NAT option allows masquerading, port forwarding and other
-	  forms of full Network Address Port Translation. This can be
-	  controlled by iptables or nft.
-
 config IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
 	depends on INET && IPV6
@@ -304,7 +294,6 @@ config IP6_NF_NAT
 	depends on NF_CONNTRACK
 	depends on NETFILTER_ADVANCED
 	select NF_NAT
-	select NF_NAT_IPV6
 	select NETFILTER_XT_NAT
 	help
 	  This enables the `nat' table in ip6tables. This allows masquerading,
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index a7b18d13e056..afb880427133 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -11,9 +11,6 @@ obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
 obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o
 obj-$(CONFIG_IP6_NF_NAT) += ip6table_nat.o
 
-nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o
-obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
-
 # defrag
 nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
 obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
deleted file mode 100644
index 5d667cf9bab8..000000000000
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ /dev/null
@@ -1,367 +0,0 @@
-/*
- * Copyright (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.
- *
- * Development of IPv6 NAT funded by Astaro.
- */
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/ipv6.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv6.h>
-#include <net/secure_seq.h>
-#include <net/checksum.h>
-#include <net/ip6_checksum.h>
-#include <net/ip6_route.h>
-#include <net/xfrm.h>
-#include <net/ipv6.h>
-
-#include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_nat_l3proto.h>
-#include <net/netfilter/nf_nat_l4proto.h>
-
-static const struct nf_nat_l3proto nf_nat_l3proto_ipv6;
-
-static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
-				  unsigned int iphdroff,
-				  const struct nf_conntrack_tuple *target,
-				  enum nf_nat_manip_type maniptype)
-{
-	struct ipv6hdr *ipv6h;
-	__be16 frag_off;
-	int hdroff;
-	u8 nexthdr;
-
-	if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h)))
-		return false;
-
-	ipv6h = (void *)skb->data + iphdroff;
-	nexthdr = ipv6h->nexthdr;
-	hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h),
-				  &nexthdr, &frag_off);
-	if (hdroff < 0)
-		goto manip_addr;
-
-	if ((frag_off & htons(~0x7)) == 0 &&
-	    !nf_nat_l4proto_manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff,
-				      target, maniptype))
-		return false;
-
-	/* must reload, offset might have changed */
-	ipv6h = (void *)skb->data + iphdroff;
-
-manip_addr:
-	if (maniptype == NF_NAT_MANIP_SRC)
-		ipv6h->saddr = target->src.u3.in6;
-	else
-		ipv6h->daddr = target->dst.u3.in6;
-
-	return true;
-}
-
-static void nf_nat_ipv6_csum_update(struct sk_buff *skb,
-				    unsigned int iphdroff, __sum16 *check,
-				    const struct nf_conntrack_tuple *t,
-				    enum nf_nat_manip_type maniptype)
-{
-	const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff);
-	const struct in6_addr *oldip, *newip;
-
-	if (maniptype == NF_NAT_MANIP_SRC) {
-		oldip = &ipv6h->saddr;
-		newip = &t->src.u3.in6;
-	} else {
-		oldip = &ipv6h->daddr;
-		newip = &t->dst.u3.in6;
-	}
-	inet_proto_csum_replace16(check, skb, oldip->s6_addr32,
-				  newip->s6_addr32, true);
-}
-
-static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb,
-				    u8 proto, void *data, __sum16 *check,
-				    int datalen, int oldlen)
-{
-	if (skb->ip_summed != CHECKSUM_PARTIAL) {
-		const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-
-		skb->ip_summed = CHECKSUM_PARTIAL;
-		skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) +
-			(data - (void *)skb->data);
-		skb->csum_offset = (void *)check - data;
-		*check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
-					  datalen, proto, 0);
-	} else
-		inet_proto_csum_replace2(check, skb,
-					 htons(oldlen), htons(datalen), true);
-}
-
-static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = {
-	.l3proto		= NFPROTO_IPV6,
-	.manip_pkt		= nf_nat_ipv6_manip_pkt,
-	.csum_update		= nf_nat_ipv6_csum_update,
-	.csum_recalc		= nf_nat_ipv6_csum_recalc,
-};
-
-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)
-{
-	struct {
-		struct icmp6hdr	icmp6;
-		struct ipv6hdr	ip6;
-	} *inside;
-	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-	enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
-	struct nf_conntrack_tuple target;
-	unsigned long statusbit;
-
-	WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY);
-
-	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
-		return 0;
-	if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6))
-		return 0;
-
-	inside = (void *)skb->data + hdrlen;
-	if (inside->icmp6.icmp6_type == NDISC_REDIRECT) {
-		if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
-			return 0;
-		if (ct->status & IPS_NAT_MASK)
-			return 0;
-	}
-
-	if (manip == NF_NAT_MANIP_SRC)
-		statusbit = IPS_SRC_NAT;
-	else
-		statusbit = IPS_DST_NAT;
-
-	/* Invert if this is reply direction */
-	if (dir == IP_CT_DIR_REPLY)
-		statusbit ^= IPS_NAT_MASK;
-
-	if (!(ct->status & statusbit))
-		return 1;
-
-	if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6),
-				   &ct->tuplehash[!dir].tuple, !manip))
-		return 0;
-
-	if (skb->ip_summed != CHECKSUM_PARTIAL) {
-		struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-		inside = (void *)skb->data + hdrlen;
-		inside->icmp6.icmp6_cksum = 0;
-		inside->icmp6.icmp6_cksum =
-			csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
-					skb->len - hdrlen, IPPROTO_ICMPV6,
-					skb_checksum(skb, hdrlen,
-						     skb->len - hdrlen, 0));
-	}
-
-	nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);
-	target.dst.protonum = IPPROTO_ICMPV6;
-	if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip))
-		return 0;
-
-	return 1;
-}
-EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation);
-
-static unsigned int
-nf_nat_ipv6_fn(void *priv, struct sk_buff *skb,
-	       const struct nf_hook_state *state)
-{
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	__be16 frag_off;
-	int hdrlen;
-	u8 nexthdr;
-
-	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;
-
-	if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) {
-		nexthdr = ipv6_hdr(skb)->nexthdr;
-		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
-					  &nexthdr, &frag_off);
-
-		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
-			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
-							     state->hook,
-							     hdrlen))
-				return NF_DROP;
-			else
-				return NF_ACCEPT;
-		}
-	}
-
-	return nf_nat_inet_fn(priv, skb, state);
-}
-
-static unsigned int
-nf_nat_ipv6_in(void *priv, struct sk_buff *skb,
-	       const struct nf_hook_state *state)
-{
-	unsigned int ret;
-	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
-
-	ret = nf_nat_ipv6_fn(priv, skb, state);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
-		skb_dst_drop(skb);
-
-	return ret;
-}
-
-static unsigned int
-nf_nat_ipv6_out(void *priv, struct sk_buff *skb,
-		const struct nf_hook_state *state)
-{
-#ifdef CONFIG_XFRM
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	int err;
-#endif
-	unsigned int ret;
-
-	ret = nf_nat_ipv6_fn(priv, skb, state);
-#ifdef CONFIG_XFRM
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
-				      &ct->tuplehash[!dir].tuple.dst.u3) ||
-		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
-		     ct->tuplehash[dir].tuple.src.u.all !=
-		     ct->tuplehash[!dir].tuple.dst.u.all)) {
-			err = nf_xfrm_me_harder(state->net, skb, AF_INET6);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-	}
-#endif
-	return ret;
-}
-
-static int nat_route_me_harder(struct net *net, struct sk_buff *skb)
-{
-#ifdef CONFIG_IPV6_MODULE
-	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
-
-	if (!v6_ops)
-		return -EHOSTUNREACH;
-
-	return v6_ops->route_me_harder(net, skb);
-#else
-	return ip6_route_me_harder(net, skb);
-#endif
-}
-
-static unsigned int
-nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
-		     const struct nf_hook_state *state)
-{
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	unsigned int ret;
-	int err;
-
-	ret = nf_nat_ipv6_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);
-
-		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
-				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			err = nat_route_me_harder(state->net, skb);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#ifdef CONFIG_XFRM
-		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
-			 ct->tuplehash[dir].tuple.dst.u.all !=
-			 ct->tuplehash[!dir].tuple.src.u.all) {
-			err = nf_xfrm_me_harder(state->net, skb, AF_INET6);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#endif
-	}
-	return ret;
-}
-
-static const struct nf_hook_ops nf_nat_ipv6_ops[] = {
-	/* Before packet filtering, change destination */
-	{
-		.hook		= nf_nat_ipv6_in,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_PRE_ROUTING,
-		.priority	= NF_IP6_PRI_NAT_DST,
-	},
-	/* After packet filtering, change source */
-	{
-		.hook		= nf_nat_ipv6_out,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_POST_ROUTING,
-		.priority	= NF_IP6_PRI_NAT_SRC,
-	},
-	/* Before packet filtering, change destination */
-	{
-		.hook		= nf_nat_ipv6_local_fn,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= NF_IP6_PRI_NAT_DST,
-	},
-	/* After packet filtering, change source */
-	{
-		.hook		= nf_nat_ipv6_fn,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= NF_IP6_PRI_NAT_SRC,
-	},
-};
-
-int nf_nat_l3proto_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops)
-{
-	return nf_nat_register_fn(net, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
-}
-EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv6_register_fn);
-
-void nf_nat_l3proto_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
-{
-	nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
-}
-EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv6_unregister_fn);
-
-static int __init nf_nat_l3proto_ipv6_init(void)
-{
-	return nf_nat_l3proto_register(&nf_nat_l3proto_ipv6);
-}
-
-static void __exit nf_nat_l3proto_ipv6_exit(void)
-{
-	nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv6);
-}
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("nf-nat-" __stringify(AF_INET6));
-
-module_init(nf_nat_l3proto_ipv6_init);
-module_exit(nf_nat_l3proto_ipv6_exit);