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>

5 files changed, 184 insertions, 99 deletions

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>");