From e91ded8db57472c20b59b2242b100764cc152a10 Mon Sep 17 00:00:00 2001
From: Mike Frysinger <vapier@gentoo.org>
Date: Mon, 4 Aug 2014 04:50:41 -0400
Subject: uapi: netfilter_arp: use __u8 instead of u_int8_t

Similarly, the u_int8_t type is non-standard and not defined.  Change
it to use __u8 like the rest of the netfilter headers.

Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter_arp/arpt_mangle.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

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;
 };
 
-- 
cgit v1.2.3-59-g8ed1b


From e2a093ff0dbfa4c5d99f25241cf33325e9691d91 Mon Sep 17 00:00:00 2001
From: Ana Rey <anarey@gmail.com>
Date: Wed, 6 Aug 2014 13:52:49 +0200
Subject: netfilter: nft_meta: add pkttype support

Add pkttype support for ip, ipv6 and inet families of tables.

This allows you to fetch the meta packet type based on the link layer
information. The loopback traffic is a special case, the packet type
is guessed from the network layer header.

No special handling for bridge and arp since we're not going to see
such traffic in the loopback interface.

Joint work with Alvaro Neira Ayuso <alvaroneay@gmail.com>

Signed-off-by: Alvaro Neira Ayuso <alvaroneay@gmail.com>
Signed-off-by: Ana Rey <anarey@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nft_meta.c                 | 28 ++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 801bdd1e56e3..98144cdd8986 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -571,6 +571,7 @@ 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
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -592,6 +593,7 @@ enum nft_meta_keys {
 	NFT_META_L4PROTO,
 	NFT_META_BRI_IIFNAME,
 	NFT_META_BRI_OIFNAME,
+	NFT_META_PKTTYPE,
 };
 
 /**
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 852b178c6ae7..4f2862fc12c2 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -14,6 +14,9 @@
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/tcp_states.h> /* for TCP_TIME_WAIT */
@@ -124,6 +127,30 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 		dest->data[0] = skb->secmark;
 		break;
 #endif
+	case NFT_META_PKTTYPE:
+		if (skb->pkt_type != PACKET_LOOPBACK) {
+			dest->data[0] = skb->pkt_type;
+			break;
+		}
+
+		switch (pkt->ops->pf) {
+		case NFPROTO_IPV4:
+			if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+				dest->data[0] = PACKET_MULTICAST;
+			else
+				dest->data[0] = PACKET_BROADCAST;
+			break;
+		case NFPROTO_IPV6:
+			if (ipv6_hdr(skb)->daddr.s6_addr[0] == 0xFF)
+				dest->data[0] = PACKET_MULTICAST;
+			else
+				dest->data[0] = PACKET_BROADCAST;
+			break;
+		default:
+			WARN_ON(1);
+			goto err;
+		}
+		break;
 	default:
 		WARN_ON(1);
 		goto err;
@@ -195,6 +222,7 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 #ifdef CONFIG_NETWORK_SECMARK
 	case NFT_META_SECMARK:
 #endif
+	case NFT_META_PKTTYPE:
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3-59-g8ed1b


From afc5be3079796b024823bad42dc5ebf716453575 Mon Sep 17 00:00:00 2001
From: Ana Rey <anarey@gmail.com>
Date: Sun, 24 Aug 2014 14:08:36 +0200
Subject: netfilter: nft_meta: Add cpu attribute support

Add cpu support to meta expresion.

This allows you to match packets with cpu number.

Signed-off-by: Ana Rey <anarey@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 2 ++
 net/netfilter/nft_meta.c                 | 5 +++++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 98144cdd8986..c9b6f00a3fb7 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -572,6 +572,7 @@ enum nft_exthdr_attributes {
  * @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()
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -594,6 +595,7 @@ enum nft_meta_keys {
 	NFT_META_BRI_IIFNAME,
 	NFT_META_BRI_OIFNAME,
 	NFT_META_PKTTYPE,
+	NFT_META_CPU,
 };
 
 /**
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 4f2862fc12c2..843e099a962d 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -17,6 +17,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/smp.h>
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/tcp_states.h> /* for TCP_TIME_WAIT */
@@ -151,6 +152,9 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 			goto err;
 		}
 		break;
+	case NFT_META_CPU:
+		dest->data[0] = smp_processor_id();
+		break;
 	default:
 		WARN_ON(1);
 		goto err;
@@ -223,6 +227,7 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 	case NFT_META_SECMARK:
 #endif
 	case NFT_META_PKTTYPE:
+	case NFT_META_CPU:
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3-59-g8ed1b


From 1b05756c48ea07ced9604ef01d11194d936da163 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 5 Aug 2014 22:02:34 +0200
Subject: netfilter: ipset: Fix warn: integer overflows 'sizeof(*map) + size *
 set->dsize'

Dan Carpenter reported that the static checker emits the warning

        net/netfilter/ipset/ip_set_list_set.c:600 init_list_set()
        warn: integer overflows 'sizeof(*map) + size * set->dsize'

Limit the maximal number of elements in list type of sets.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set_list.h | 1 +
 net/netfilter/ipset/ip_set_list_set.c       | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

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/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 3e2317f3cf68..f87adbad6076 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -597,7 +597,9 @@ init_list_set(struct net *net, struct ip_set *set, u32 size)
 	struct set_elem *e;
 	u32 i;
 
-	map = kzalloc(sizeof(*map) + size * set->dsize, GFP_KERNEL);
+	map = kzalloc(sizeof(*map) +
+		      min_t(u32, size, IP_SET_LIST_MAX_SIZE) * set->dsize,
+		      GFP_KERNEL);
 	if (!map)
 		return false;
 
-- 
cgit v1.2.3-59-g8ed1b


From f111f780ae1abf4cdc464f24293be90c010a04f6 Mon Sep 17 00:00:00 2001
From: Alexey Perevalov <a.perevalov@samsung.com>
Date: Wed, 20 Aug 2014 22:03:18 +0400
Subject: netfilter: nfnetlink_acct: add filter support to nfacct counter
 list/reset

You can use this to skip accounting objects when listing/resetting
via NFNL_MSG_ACCT_GET/NFNL_MSG_ACCT_GET_CTRZERO messages with the
NLM_F_DUMP netlink flag. The filtering covers the following cases:

1. No filter specified. In this case, the client will get old behaviour,
2. List/reset counter object only: In this case, you have to use
   NFACCT_F_QUOTA as mask and value 0.
3. List/reset quota objects only: You have to use NFACCT_F_QUOTA_PKTS
   as mask and value - the same, for byte based quota mask should be
   NFACCT_F_QUOTA_BYTES and value - the same.

If you want to obtain the object with any quota type
(ie. NFACCT_F_QUOTA_PKTS|NFACCT_F_QUOTA_BYTES), you need to perform
two dump requests, one to obtain NFACCT_F_QUOTA_PKTS objects and
another for NFACCT_F_QUOTA_BYTES.

Signed-off-by: Alexey Perevalov <a.perevalov@samsung.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nfnetlink_acct.h |  8 ++++
 net/netfilter/nfnetlink_acct.c                | 54 +++++++++++++++++++++++++++
 2 files changed, 62 insertions(+)

(limited to 'include')

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/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 3ea0eacbd970..c18af2f63eef 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -40,6 +40,11 @@ struct nf_acct {
 	char			data[0];
 };
 
+struct nfacct_filter {
+	u32 value;
+	u32 mask;
+};
+
 #define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES)
 #define NFACCT_OVERQUOTA_BIT	2	/* NFACCT_F_OVERQUOTA */
 
@@ -181,6 +186,7 @@ static int
 nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct nf_acct *cur, *last;
+	const struct nfacct_filter *filter = cb->data;
 
 	if (cb->args[2])
 		return 0;
@@ -197,6 +203,10 @@ nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 			last = NULL;
 		}
+
+		if (filter && (cur->flags & filter->mask) != filter->value)
+			continue;
+
 		if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).portid,
 				       cb->nlh->nlmsg_seq,
 				       NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
@@ -211,6 +221,38 @@ nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static int nfnl_acct_done(struct netlink_callback *cb)
+{
+	kfree(cb->data);
+	return 0;
+}
+
+static const struct nla_policy filter_policy[NFACCT_FILTER_MAX + 1] = {
+	[NFACCT_FILTER_MASK]	= { .type = NLA_U32 },
+	[NFACCT_FILTER_VALUE]	= { .type = NLA_U32 },
+};
+
+static struct nfacct_filter *
+nfacct_filter_alloc(const struct nlattr * const attr)
+{
+	struct nfacct_filter *filter;
+	struct nlattr *tb[NFACCT_FILTER_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, NFACCT_FILTER_MAX, attr, filter_policy);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	filter = kzalloc(sizeof(struct nfacct_filter), GFP_KERNEL);
+	if (!filter)
+		return ERR_PTR(-ENOMEM);
+
+	filter->mask = ntohl(nla_get_be32(tb[NFACCT_FILTER_MASK]));
+	filter->value = ntohl(nla_get_be32(tb[NFACCT_FILTER_VALUE]));
+
+	return filter;
+}
+
 static int
 nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb,
 	     const struct nlmsghdr *nlh, const struct nlattr * const tb[])
@@ -222,7 +264,18 @@ nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb,
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
 			.dump = nfnl_acct_dump,
+			.done = nfnl_acct_done,
 		};
+
+		if (tb[NFACCT_FILTER]) {
+			struct nfacct_filter *filter;
+
+			filter = nfacct_filter_alloc(tb[NFACCT_FILTER]);
+			if (IS_ERR(filter))
+				return PTR_ERR(filter);
+
+			c.data = filter;
+		}
 		return netlink_dump_start(nfnl, skb, nlh, &c);
 	}
 
@@ -314,6 +367,7 @@ static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = {
 	[NFACCT_PKTS] = { .type = NLA_U64 },
 	[NFACCT_FLAGS] = { .type = NLA_U32 },
 	[NFACCT_QUOTA] = { .type = NLA_U64 },
+	[NFACCT_FILTER] = {.type = NLA_NESTED },
 };
 
 static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = {
-- 
cgit v1.2.3-59-g8ed1b


From 30766f4c2d60dd2a3fc67b7114174c417f43f4c6 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 5 Aug 2014 20:02:42 +0200
Subject: netfilter: nat: move specific NAT IPv4 to core

Move the specific NAT IPv4 core functions that are called from the
hooks from iptable_nat.c to nf_nat_l3proto_ipv4.c. This prepares the
ground to allow iptables and nft to use the same NAT engine code that
comes in a follow up patch.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l3proto.h   |  38 +++++
 net/ipv4/netfilter/iptable_nat.c         | 233 +++++--------------------------
 net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 199 ++++++++++++++++++++++++++
 3 files changed, 271 insertions(+), 199 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index 5a2919b2e09a..bc2d51574489 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -42,6 +42,44 @@ 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);
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,
-		const struct net_device *in,
-		const struct net_device *out,
-		int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_out(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 *))
 {
-#ifdef CONFIG_XFRM
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	int err;
-#endif
-	unsigned int ret;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct iphdr) ||
-	    ip_hdrlen(skb) < sizeof(struct iphdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv4_fn(ops, 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.dst.protonum != IPPROTO_ICMP &&
-		     ct->tuplehash[dir].tuple.src.u.all !=
-		     ct->tuplehash[!dir].tuple.dst.u.all)) {
-			err = nf_xfrm_me_harder(skb, AF_INET);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-	}
-#endif
-	return ret;
+	return nf_nat_ipv4_out(ops, skb, in, out, iptable_nat_do_chain);
 }
 
-static 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,
-		     int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_local_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 *))
 {
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	unsigned int ret;
-	int err;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct iphdr) ||
-	    ip_hdrlen(skb) < sizeof(struct iphdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv4_fn(ops, 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);
-
-		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
-		    ct->tuplehash[!dir].tuple.src.u3.ip) {
-			err = ip_route_me_harder(skb, RTN_UNSPEC);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#ifdef CONFIG_XFRM
-		else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
-			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
-			 ct->tuplehash[dir].tuple.dst.u.all !=
-			 ct->tuplehash[!dir].tuple.src.u.all) {
-			err = nf_xfrm_me_harder(skb, AF_INET);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#endif
-	}
-	return ret;
+	return nf_nat_ipv4_local_fn(ops, skb, in, out, iptable_nat_do_chain);
 }
 
 static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv4_in,
+		.hook		= iptable_nat_ipv4_in,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_PRE_ROUTING,
@@ -251,7 +86,7 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv4_out,
+		.hook		= iptable_nat_ipv4_out,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_POST_ROUTING,
@@ -259,7 +94,7 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv4_local_fn,
+		.hook		= iptable_nat_ipv4_local_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_LOCAL_OUT,
@@ -267,7 +102,7 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv4_fn,
+		.hook		= iptable_nat_ipv4_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_LOCAL_IN,
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 14f5ccd06337..fc37711e11f3 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -254,6 +254,205 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);
 
+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))
+{
+	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 = do_chain(ops, skb, in, out, ct);
+			if (ret != NF_ACCEPT)
+				return ret;
+
+			if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum)))
+				break;
+
+			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+			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;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn);
+
+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 ret;
+	__be32 daddr = ip_hdr(skb)->daddr;
+
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+	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
+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))
+{
+#ifdef CONFIG_XFRM
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	int err;
+#endif
+	unsigned int ret;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct iphdr) ||
+	    ip_hdrlen(skb) < sizeof(struct iphdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+#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.dst.protonum != IPPROTO_ICMP &&
+		     ct->tuplehash[dir].tuple.src.u.all !=
+		     ct->tuplehash[!dir].tuple.dst.u.all)) {
+			err = nf_xfrm_me_harder(skb, AF_INET);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+	}
+#endif
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_out);
+
+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))
+{
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned int ret;
+	int err;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct iphdr) ||
+	    ip_hdrlen(skb) < sizeof(struct iphdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
+		    ct->tuplehash[!dir].tuple.src.u3.ip) {
+			err = ip_route_me_harder(skb, RTN_UNSPEC);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#ifdef CONFIG_XFRM
+		else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
+			 ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all) {
+			err = nf_xfrm_me_harder(skb, AF_INET);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#endif
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_local_fn);
+
 static int __init nf_nat_l3proto_ipv4_init(void)
 {
 	int err;
-- 
cgit v1.2.3-59-g8ed1b


From 2a5538e9aa4929329813bee69922c9ae4990fcad Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 25 Aug 2014 12:05:27 +0200
Subject: netfilter: nat: move specific NAT IPv6 to core

Move the specific NAT IPv6 core functions that are called from the
hooks from ip6table_nat.c to nf_nat_l3proto_ipv6.c. This prepares the
ground to allow iptables and nft to use the same NAT engine code that
comes in a follow up patch.

This also renames nf_nat_ipv6_fn to nft_nat_ipv6_fn in
net/ipv6/netfilter/nft_chain_nat_ipv6.c to avoid a compilation breakage.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l3proto.h   |  37 +++++
 net/ipv6/netfilter/ip6table_nat.c        | 233 +++++--------------------------
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 199 ++++++++++++++++++++++++++
 net/ipv6/netfilter/nft_chain_nat_ipv6.c  |  10 +-
 4 files changed, 275 insertions(+), 204 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index bc2d51574489..340c013795a4 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -84,4 +84,41 @@ 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/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 387d8b8fc18d..b0634ac996b7 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -30,222 +30,57 @@ static const struct xt_table nf_nat_ipv6_table = {
 	.af		= NFPROTO_IPV6,
 };
 
-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 (%pI6)\n", ct,
-		 HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip6 :
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip6);
-
-	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 ip6table_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 = ip6t_do_table(skb, hooknum, in, out, net->ipv6.ip6table_nat);
-	if (ret == NF_ACCEPT) {
-		if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
-			ret = alloc_null_binding(ct, hooknum);
-	}
-	return ret;
+	return ip6t_do_table(skb, ops->hooknum, in, out, net->ipv6.ip6table_nat);
 }
 
-static 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,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_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;
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
-	__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;
-
-	/* 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:
-		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,
-							     ops->hooknum,
-							     hdrlen))
-				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_ipv6_fn(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
-static 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,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_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;
-	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
-
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
-		skb_dst_drop(skb);
-
-	return ret;
+	return nf_nat_ipv6_in(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
-static 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,
-		int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_out(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 *))
 {
-#ifdef CONFIG_XFRM
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	int err;
-#endif
-	unsigned int ret;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct ipv6hdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
-#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(skb, AF_INET6);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-	}
-#endif
-	return ret;
+	return nf_nat_ipv6_out(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
-static 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,
-		     int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_local_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 *))
 {
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	unsigned int ret;
-	int err;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct ipv6hdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv6_fn(ops, 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);
-
-		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
-				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			err = ip6_route_me_harder(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(skb, AF_INET6);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#endif
-	}
-	return ret;
+	return nf_nat_ipv6_local_fn(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
 static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv6_in,
+		.hook		= ip6table_nat_in,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_PRE_ROUTING,
@@ -253,7 +88,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv6_out,
+		.hook		= ip6table_nat_out,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_POST_ROUTING,
@@ -261,7 +96,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv6_local_fn,
+		.hook		= ip6table_nat_local_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_LOCAL_OUT,
@@ -269,7 +104,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv6_fn,
+		.hook		= ip6table_nat_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_LOCAL_IN,
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index fc8e49b2ff3e..c5812e1c1ffb 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -261,6 +261,205 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation);
 
+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))
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn_nat *nat;
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+	__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;
+
+	/* 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:
+		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,
+							     ops->hooknum,
+							     hdrlen))
+				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 = do_chain(ops, skb, in, out, ct);
+			if (ret != NF_ACCEPT)
+				return ret;
+
+			if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum)))
+				break;
+
+			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+			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;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_fn);
+
+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 ret;
+	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
+		skb_dst_drop(skb);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_in);
+
+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))
+{
+#ifdef CONFIG_XFRM
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	int err;
+#endif
+	unsigned int ret;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+#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(skb, AF_INET6);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+	}
+#endif
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_out);
+
+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))
+{
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned int ret;
+	int err;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+	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 = ip6_route_me_harder(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(skb, AF_INET6);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#endif
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_local_fn);
+
 static int __init nf_nat_l3proto_ipv6_init(void)
 {
 	int err;
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index d189fcb437fe..c1c74491a10b 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -28,7 +28,7 @@
  * IPv6 NAT chains
  */
 
-static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
+static unsigned int nft_nat_ipv6_fn(const struct nf_hook_ops *ops,
 			      struct sk_buff *skb,
 			      const struct net_device *in,
 			      const struct net_device *out,
@@ -97,7 +97,7 @@ static unsigned int nf_nat_ipv6_prerouting(const struct nf_hook_ops *ops,
 	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
 	unsigned int ret;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
 		skb_dst_drop(skb);
@@ -115,7 +115,7 @@ static unsigned int nf_nat_ipv6_postrouting(const struct nf_hook_ops *ops,
 	const struct nf_conn *ct __maybe_unused;
 	unsigned int ret;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
@@ -143,7 +143,7 @@ static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops,
 	const struct nf_conn *ct;
 	unsigned int ret;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	ret = nft_nat_ipv6_fn(ops, 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);
@@ -177,7 +177,7 @@ static const struct nf_chain_type nft_chain_nat_ipv6 = {
 		[NF_INET_PRE_ROUTING]	= nf_nat_ipv6_prerouting,
 		[NF_INET_POST_ROUTING]	= nf_nat_ipv6_postrouting,
 		[NF_INET_LOCAL_OUT]	= nf_nat_ipv6_output,
-		[NF_INET_LOCAL_IN]	= nf_nat_ipv6_fn,
+		[NF_INET_LOCAL_IN]	= nft_nat_ipv6_fn,
 	},
 };
 
-- 
cgit v1.2.3-59-g8ed1b


From 3045d76070abe725dbb7fd8ff39c27b820d5a7eb Mon Sep 17 00:00:00 2001
From: Ana Rey <anarey@gmail.com>
Date: Tue, 2 Sep 2014 20:36:14 +0200
Subject: netfilter: nf_tables: add devgroup support in meta expresion

Add devgroup support to let us match device group of a packets incoming
or outgoing interface.

Signed-off-by: Ana Rey <anarey@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  4 ++++
 net/netfilter/nft_meta.c                 | 12 ++++++++++++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index c9b6f00a3fb7..c000947d3f38 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -573,6 +573,8 @@ enum nft_exthdr_attributes {
  * @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,
@@ -596,6 +598,8 @@ enum nft_meta_keys {
 	NFT_META_BRI_OIFNAME,
 	NFT_META_PKTTYPE,
 	NFT_META_CPU,
+	NFT_META_IIFGROUP,
+	NFT_META_OIFGROUP,
 };
 
 /**
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 843e099a962d..1e7c076ca63a 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -155,6 +155,16 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 	case NFT_META_CPU:
 		dest->data[0] = smp_processor_id();
 		break;
+	case NFT_META_IIFGROUP:
+		if (in == NULL)
+			goto err;
+		dest->data[0] = in->group;
+		break;
+	case NFT_META_OIFGROUP:
+		if (out == NULL)
+			goto err;
+		dest->data[0] = out->group;
+		break;
 	default:
 		WARN_ON(1);
 		goto err;
@@ -228,6 +238,8 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 #endif
 	case NFT_META_PKTTYPE:
 	case NFT_META_CPU:
+	case NFT_META_IIFGROUP:
+	case NFT_META_OIFGROUP:
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3-59-g8ed1b


From e42eff8a32f8b7bde88ea3c5a56391407cbe84f3 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Thu, 4 Sep 2014 14:06:14 +0200
Subject: netfilter: nft_nat: include a flag attribute

Both SNAT and DNAT (and the upcoming masquerade) can have additional
configuration parameters, such as port randomization and NAT addressing
persistence. We can cover these scenarios by simply adding a flag
attribute for userspace to fill when needed.

The flags to use are defined in include/uapi/linux/netfilter/nf_nat.h:

 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
 NF_NAT_RANGE_PROTO_RANDOM_ALL

The caller must take care of not messing up with the flags, as they are
added unconditionally to the final resulting nf_nat_range.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_nat.h    |  5 +++++
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nft_nat.c                  | 16 ++++++++++++++++
 3 files changed, 23 insertions(+)

(limited to 'include')

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 c000947d3f38..6022c6e6be18 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -785,6 +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,
@@ -794,6 +795,7 @@ 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)
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 79ff58cd36dc..799550b476fb 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -33,6 +33,7 @@ struct nft_nat {
 	enum nft_registers      sreg_proto_max:8;
 	enum nf_nat_manip_type  type:8;
 	u8			family;
+	u16			flags;
 };
 
 static void nft_nat_eval(const struct nft_expr *expr,
@@ -71,6 +72,8 @@ static void nft_nat_eval(const struct nft_expr *expr,
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
+	range.flags |= priv->flags;
+
 	data[NFT_REG_VERDICT].verdict =
 		nf_nat_setup_info(ct, &range, priv->type);
 }
@@ -82,6 +85,7 @@ static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
 	[NFTA_NAT_REG_ADDR_MAX]	 = { .type = NLA_U32 },
 	[NFTA_NAT_REG_PROTO_MIN] = { .type = NLA_U32 },
 	[NFTA_NAT_REG_PROTO_MAX] = { .type = NLA_U32 },
+	[NFTA_NAT_FLAGS]	 = { .type = NLA_U32 },
 };
 
 static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
@@ -149,6 +153,12 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	} else
 		priv->sreg_proto_max = priv->sreg_proto_min;
 
+	if (tb[NFTA_NAT_FLAGS]) {
+		priv->flags = ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS]));
+		if (priv->flags & ~NF_NAT_RANGE_MASK)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -183,6 +193,12 @@ static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
 				 htonl(priv->sreg_proto_max)))
 			goto nla_put_failure;
 	}
+
+	if (priv->flags != 0) {
+		if (nla_put_be32(skb, NFTA_NAT_FLAGS, htonl(priv->flags)))
+			goto nla_put_failure;
+	}
+
 	return 0;
 
 nla_put_failure:
-- 
cgit v1.2.3-59-g8ed1b


From 8dd33cc93ec92b8460ed2ad98c6db39276f6a72b Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Thu, 4 Sep 2014 14:06:33 +0200
Subject: netfilter: nf_nat: generalize IPv4 masquerading support for nf_tables

Let's refactor the code so we can reach the masquerade functionality
from outside the xt context (ie. nftables).

The patch includes the addition of an atomic counter to the masquerade
notifier: the stuff to be done by the notifier is the same for xt and
nftables. Therefore, only one notification handler is needed.

This factorization only involves IPv4; a similar patch follows to
handle IPv6.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv4/nf_nat_masquerade.h |  14 +++
 net/ipv4/netfilter/Kconfig                     |   7 ++
 net/ipv4/netfilter/Makefile                    |   1 +
 net/ipv4/netfilter/ipt_MASQUERADE.c            | 108 ++---------------
 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c    | 153 +++++++++++++++++++++++++
 5 files changed, 184 insertions(+), 99 deletions(-)
 create mode 100644 include/net/netfilter/ipv4/nf_nat_masquerade.h
 create mode 100644 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c

(limited to 'include')

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/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index fb173126f03d..4be3e541350e 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -184,8 +184,15 @@ config NF_NAT_IPV4
 
 if NF_NAT_IPV4
 
+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 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 33001621465b..42056b2fd0e3 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
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/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
new file mode 100644
index 000000000000..c6eb42100e9a
--- /dev/null
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -0,0 +1,153 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * 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/module.h>
+#include <linux/atomic.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/timer.h>
+#include <linux/netfilter.h>
+#include <net/protocol.h>
+#include <net/ip.h>
+#include <net/checksum.h>
+#include <net/route.h>
+#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>
+
+unsigned int
+nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
+		       const struct nf_nat_range *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;
+	const struct rtable *rt;
+	__be32 newsrc, nh;
+
+	NF_CT_ASSERT(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;
+
+	rt = skb_rtable(skb);
+	nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
+	newsrc = inet_select_addr(out, nh, RT_SCOPE_UNIVERSE);
+	if (!newsrc) {
+		pr_info("%s ate my IP address\n", out->name);
+		return NF_DROP;
+	}
+
+	nat->masq_index = 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       = range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.ip = newsrc;
+	newrange.max_addr.ip = newsrc;
+	newrange.min_proto   = range->min_proto;
+	newrange.max_proto   = range->max_proto;
+
+	/* Hand modified range to generic setup. */
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4);
+
+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 atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+
+void nf_nat_masquerade_ipv4_register_notifier(void)
+{
+	/* check if the notifier was already set */
+	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
+		return;
+
+	/* Register for device down reports */
+	register_netdevice_notifier(&masq_dev_notifier);
+	/* Register IP address change reports */
+	register_inetaddr_notifier(&masq_inet_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
+
+void nf_nat_masquerade_ipv4_unregister_notifier(void)
+{
+	/* check if the notifier still has clients */
+	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
+		return;
+
+	unregister_netdevice_notifier(&masq_dev_notifier);
+	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>");
-- 
cgit v1.2.3-59-g8ed1b


From be6b635cd674add9410efa9ac6f03e0040848b12 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Thu, 4 Sep 2014 14:06:49 +0200
Subject: netfilter: nf_nat: generalize IPv6 masquerading support for nf_tables

Let's refactor the code so we can reach the masquerade functionality
from outside the xt context (ie. nftables).

The patch includes the addition of an atomic counter to the masquerade
notifier: the stuff to be done by the notifier is the same for xt and
nftables. Therefore, only one notification handler is needed.

This factorization only involves IPv6; a similar patch exists to
handle IPv4.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv6/nf_nat_masquerade.h |  10 +++
 net/ipv6/netfilter/Kconfig                     |   7 ++
 net/ipv6/netfilter/Makefile                    |   1 +
 net/ipv6/netfilter/ip6t_MASQUERADE.c           |  76 ++--------------
 net/ipv6/netfilter/nf_nat_masquerade_ipv6.c    | 120 +++++++++++++++++++++++++
 5 files changed, 143 insertions(+), 71 deletions(-)
 create mode 100644 include/net/netfilter/ipv6/nf_nat_masquerade.h
 create mode 100644 net/ipv6/netfilter/nf_nat_masquerade_ipv6.c

(limited to 'include')

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/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ac93df16f5af..6c8cfec6836a 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -246,8 +246,15 @@ config NF_NAT_IPV6
 
 if NF_NAT_IPV6
 
+config NF_NAT_MASQUERADE_IPV6
+	tristate "IPv6 masquerade support"
+	help
+	 This is the kernel functionality to provide NAT in the masquerade
+	 flavour (automatic source address selection) for IPv6.
+
 config IP6_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
+	select NF_NAT_MASQUERADE_IPV6
 	help
 	  Masquerading is a special case of NAT: all outgoing connections are
 	  changed to seem to come from a particular interface's address, and
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index c0b263104ed2..89a0bd751f82 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o
 
 nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
 obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
+obj-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o
 
 # defrag
 nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 3e4e92d5e157..7f9f45d829d2 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -19,33 +19,12 @@
 #include <net/netfilter/nf_nat.h>
 #include <net/addrconf.h>
 #include <net/ipv6.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
 
 static unsigned int
 masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	const struct nf_nat_range *range = par->targinfo;
-	enum ip_conntrack_info ctinfo;
-	struct in6_addr src;
-	struct nf_conn *ct;
-	struct nf_nat_range newrange;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED_REPLY));
-
-	if (ipv6_dev_get_saddr(dev_net(par->out), par->out,
-			       &ipv6_hdr(skb)->daddr, 0, &src) < 0)
-		return NF_DROP;
-
-	nfct_nat(ct)->masq_index = par->out->ifindex;
-
-	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.in6	= src;
-	newrange.max_addr.in6	= src;
-	newrange.min_proto	= range->min_proto;
-	newrange.max_proto	= range->max_proto;
-
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+	return nf_nat_masquerade_ipv6(skb, par->targinfo, par->out);
 }
 
 static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
@@ -57,48 +36,6 @@ static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
 	return 0;
 }
 
-static int device_cmp(struct nf_conn *ct, void *ifindex)
-{
-	const struct nf_conn_nat *nat = nfct_nat(ct);
-
-	if (!nat)
-		return 0;
-	if (nf_ct_l3num(ct) != NFPROTO_IPV6)
-		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)
-		nf_ct_iterate_cleanup(net, device_cmp,
-				      (void *)(long)dev->ifindex, 0, 0);
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block masq_dev_notifier = {
-	.notifier_call	= masq_device_event,
-};
-
-static int masq_inet_event(struct notifier_block *this,
-			   unsigned long event, void *ptr)
-{
-	struct inet6_ifaddr *ifa = ptr;
-	struct netdev_notifier_info info;
-
-	netdev_notifier_info_init(&info, ifa->idev->dev);
-	return masq_device_event(this, event, &info);
-}
-
-static struct notifier_block masq_inet_notifier = {
-	.notifier_call	= masq_inet_event,
-};
-
 static struct xt_target masquerade_tg6_reg __read_mostly = {
 	.name		= "MASQUERADE",
 	.family		= NFPROTO_IPV6,
@@ -115,17 +52,14 @@ static int __init masquerade_tg6_init(void)
 	int err;
 
 	err = xt_register_target(&masquerade_tg6_reg);
-	if (err == 0) {
-		register_netdevice_notifier(&masq_dev_notifier);
-		register_inet6addr_notifier(&masq_inet_notifier);
-	}
+	if (err == 0)
+		nf_nat_masquerade_ipv6_register_notifier();
 
 	return err;
 }
 static void __exit masquerade_tg6_exit(void)
 {
-	unregister_inet6addr_notifier(&masq_inet_notifier);
-	unregister_netdevice_notifier(&masq_dev_notifier);
+	nf_nat_masquerade_ipv6_unregister_notifier();
 	xt_unregister_target(&masquerade_tg6_reg);
 }
 
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
new file mode 100644
index 000000000000..7745609665cd
--- /dev/null
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -0,0 +1,120 @@
+/*
+ * 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.
+ *
+ * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/atomic.h>
+#include <linux/netdevice.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+
+unsigned int
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		       const struct net_device *out)
+{
+	enum ip_conntrack_info ctinfo;
+	struct in6_addr src;
+	struct nf_conn *ct;
+	struct nf_nat_range newrange;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
+			    ctinfo == IP_CT_RELATED_REPLY));
+
+	if (ipv6_dev_get_saddr(dev_net(out), out,
+			       &ipv6_hdr(skb)->daddr, 0, &src) < 0)
+		return NF_DROP;
+
+	nfct_nat(ct)->masq_index = out->ifindex;
+
+	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.in6	= src;
+	newrange.max_addr.in6	= src;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6);
+
+static int device_cmp(struct nf_conn *ct, void *ifindex)
+{
+	const struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (!nat)
+		return 0;
+	if (nf_ct_l3num(ct) != NFPROTO_IPV6)
+		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)
+		nf_ct_iterate_cleanup(net, device_cmp,
+				      (void *)(long)dev->ifindex, 0, 0);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block masq_dev_notifier = {
+	.notifier_call	= masq_device_event,
+};
+
+static int masq_inet_event(struct notifier_block *this,
+			   unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = ptr;
+	struct netdev_notifier_info info;
+
+	netdev_notifier_info_init(&info, ifa->idev->dev);
+	return masq_device_event(this, event, &info);
+}
+
+static struct notifier_block masq_inet_notifier = {
+	.notifier_call	= masq_inet_event,
+};
+
+static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+
+void nf_nat_masquerade_ipv6_register_notifier(void)
+{
+	/* check if the notifier is already set */
+	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
+		return;
+
+	register_netdevice_notifier(&masq_dev_notifier);
+	register_inet6addr_notifier(&masq_inet_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
+
+void nf_nat_masquerade_ipv6_unregister_notifier(void)
+{
+	/* check if the notifier still has clients */
+	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
+		return;
+
+	unregister_inet6addr_notifier(&masq_inet_notifier);
+	unregister_netdevice_notifier(&masq_dev_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-- 
cgit v1.2.3-59-g8ed1b


From 9ba1f726bec090399eb9bb9157eb32dedc8e8c45 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Mon, 8 Sep 2014 13:45:00 +0200
Subject: netfilter: nf_tables: add new nft_masq expression

The nft_masq expression is intended to perform NAT in the masquerade flavour.

We decided to have the masquerade functionality in a separated expression other
than nft_nat.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nft_masq.h         | 16 ++++++
 include/uapi/linux/netfilter/nf_tables.h | 11 ++++
 net/ipv4/netfilter/Kconfig               |  6 +++
 net/ipv4/netfilter/Makefile              |  1 +
 net/ipv4/netfilter/nft_masq_ipv4.c       | 89 ++++++++++++++++++++++++++++++++
 net/ipv6/netfilter/Kconfig               |  6 +++
 net/ipv6/netfilter/Makefile              |  1 +
 net/ipv6/netfilter/nft_masq_ipv6.c       | 89 ++++++++++++++++++++++++++++++++
 net/netfilter/Kconfig                    |  9 ++++
 net/netfilter/Makefile                   |  1 +
 net/netfilter/nft_masq.c                 | 59 +++++++++++++++++++++
 11 files changed, 288 insertions(+)
 create mode 100644 include/net/netfilter/nft_masq.h
 create mode 100644 net/ipv4/netfilter/nft_masq_ipv4.c
 create mode 100644 net/ipv6/netfilter/nft_masq_ipv6.c
 create mode 100644 net/netfilter/nft_masq.c

(limited to 'include')

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_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 6022c6e6be18..eeec0ae845ef 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -800,4 +800,15 @@ enum nft_nat_attributes {
 };
 #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/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 4be3e541350e..8dd3d9f19d82 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -190,6 +190,12 @@ config NF_NAT_MASQUERADE_IPV4
 	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
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 42056b2fd0e3..7d019aefb0ed 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -36,6 +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/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
new file mode 100644
index 000000000000..6ea1d207b6a5
--- /dev/null
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * 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/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_masq.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+
+static void nft_masq_ipv4_eval(const struct nft_expr *expr,
+			       struct nft_data data[NFT_REG_MAX + 1],
+			       const struct nft_pktinfo *pkt)
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+	struct nf_nat_range range;
+	unsigned int verdict;
+
+	range.flags = priv->flags;
+
+	verdict = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum,
+					 &range, pkt->out);
+
+	data[NFT_REG_VERDICT].verdict = verdict;
+}
+
+static int nft_masq_ipv4_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr * const tb[])
+{
+	int err;
+
+	err = nft_masq_init(ctx, expr, tb);
+	if (err < 0)
+		return err;
+
+	nf_nat_masquerade_ipv4_register_notifier();
+	return 0;
+}
+
+static void nft_masq_ipv4_destroy(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr)
+{
+	nf_nat_masquerade_ipv4_unregister_notifier();
+}
+
+static struct nft_expr_type nft_masq_ipv4_type;
+static const struct nft_expr_ops nft_masq_ipv4_ops = {
+	.type		= &nft_masq_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+	.eval		= nft_masq_ipv4_eval,
+	.init		= nft_masq_ipv4_init,
+	.destroy	= nft_masq_ipv4_destroy,
+	.dump		= nft_masq_dump,
+};
+
+static struct nft_expr_type nft_masq_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "masq",
+	.ops		= &nft_masq_ipv4_ops,
+	.policy		= nft_masq_policy,
+	.maxattr	= NFTA_MASQ_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_masq_ipv4_module_init(void)
+{
+	return nft_register_expr(&nft_masq_ipv4_type);
+}
+
+static void __exit nft_masq_ipv4_module_exit(void)
+{
+	nft_unregister_expr(&nft_masq_ipv4_type);
+}
+
+module_init(nft_masq_ipv4_module_init);
+module_exit(nft_masq_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "masq");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 6c8cfec6836a..24c535f66df0 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -252,6 +252,12 @@ config NF_NAT_MASQUERADE_IPV6
 	 This is the kernel functionality to provide NAT in the masquerade
 	 flavour (automatic source address selection) for IPv6.
 
+config NFT_MASQ_IPV6
+	tristate "IPv6 masquerade support for nf_tables"
+	depends on NF_TABLES_IPV6
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV6
+
 config IP6_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
 	select NF_NAT_MASQUERADE_IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 89a0bd751f82..482c4dff273f 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
 obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
+obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
new file mode 100644
index 000000000000..4e51334ef6b7
--- /dev/null
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * 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/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nft_masq.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+
+static void nft_masq_ipv6_eval(const struct nft_expr *expr,
+			       struct nft_data data[NFT_REG_MAX + 1],
+			       const struct nft_pktinfo *pkt)
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+	struct nf_nat_range range;
+	unsigned int verdict;
+
+	range.flags = priv->flags;
+
+	verdict = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out);
+
+	data[NFT_REG_VERDICT].verdict = verdict;
+}
+
+static int nft_masq_ipv6_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr * const tb[])
+{
+	int err;
+
+	err = nft_masq_init(ctx, expr, tb);
+	if (err < 0)
+		return err;
+
+	nf_nat_masquerade_ipv6_register_notifier();
+	return 0;
+}
+
+static void nft_masq_ipv6_destroy(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr)
+{
+	nf_nat_masquerade_ipv6_unregister_notifier();
+}
+
+static struct nft_expr_type nft_masq_ipv6_type;
+static const struct nft_expr_ops nft_masq_ipv6_ops = {
+	.type		= &nft_masq_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+	.eval		= nft_masq_ipv6_eval,
+	.init		= nft_masq_ipv6_init,
+	.destroy	= nft_masq_ipv6_destroy,
+	.dump		= nft_masq_dump,
+};
+
+static struct nft_expr_type nft_masq_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "masq",
+	.ops		= &nft_masq_ipv6_ops,
+	.policy		= nft_masq_policy,
+	.maxattr	= NFTA_MASQ_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_masq_ipv6_module_init(void)
+{
+	return nft_register_expr(&nft_masq_ipv6_type);
+}
+
+static void __exit nft_masq_ipv6_module_exit(void)
+{
+	nft_unregister_expr(&nft_masq_ipv6_type);
+}
+
+module_init(nft_masq_ipv6_module_init);
+module_exit(nft_masq_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "masq");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index ad751fe2e82b..37428723394f 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -496,6 +496,15 @@ config NFT_LIMIT
 	  This option adds the "limit" expression that you can use to
 	  ratelimit rule matchings.
 
+config NFT_MASQ
+	depends on NF_TABLES
+	depends on NF_CONNTRACK
+	depends on NF_NAT
+	tristate "Netfilter nf_tables masquerade support"
+	help
+	  This option adds the "masquerade" expression that you can use
+	  to perform NAT in the masquerade flavour.
+
 config NFT_NAT
 	depends on NF_TABLES
 	depends on NF_CONNTRACK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 8308624a406a..0637792f6faf 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -87,6 +87,7 @@ obj-$(CONFIG_NFT_RBTREE)	+= nft_rbtree.o
 obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
+obj-$(CONFIG_NFT_MASQ)		+= nft_masq.o
 
 # generic X tables 
 obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
new file mode 100644
index 000000000000..6637bab00567
--- /dev/null
+++ b/net/netfilter/nft_masq.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * 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/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nft_masq.h>
+
+const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = {
+	[NFTA_MASQ_FLAGS]	= { .type = NLA_U32 },
+};
+EXPORT_SYMBOL_GPL(nft_masq_policy);
+
+int nft_masq_init(const struct nft_ctx *ctx,
+		  const struct nft_expr *expr,
+		  const struct nlattr * const tb[])
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_MASQ_FLAGS] == NULL)
+		return 0;
+
+	priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS]));
+	if (priv->flags & ~NF_NAT_RANGE_MASK)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_masq_init);
+
+int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_masq *priv = nft_expr_priv(expr);
+
+	if (priv->flags == 0)
+		return 0;
+
+	if (nla_put_be32(skb, NFTA_MASQ_FLAGS, htonl(priv->flags)))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nft_masq_dump);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
-- 
cgit v1.2.3-59-g8ed1b