[PKT_SCHED]: Add stateless NAT

Stateless NAT is useful in controlled environments where restrictions are
placed on through traffic such that we don't need connection tracking to
correctly NAT protocol-specific data.

In particular, this is of interest when the number of flows or the number
of addresses being NATed is large, or if connection tracking information
has to be replicated and where it is not practical to do so.

Previously we had stateless NAT functionality which was integrated into
the IPv4 routing subsystem.  This was a great solution as long as the NAT
worked on a subnet to subnet basis such that the number of NAT rules was
relatively small.  The reason is that for SNAT the routing based system
had to perform a linear scan through the rules.

If the number of rules is large then major renovations would have take
place in the routing subsystem to make this practical.

For the time being, the least intrusive way of achieving this is to use
the u32 classifier written by Alexey Kuznetsov along with the actions
infrastructure implemented by Jamal Hadi Salim.

The following patch is an attempt at this problem by creating a new nat
action that can be invoked from u32 hash tables which would allow large
number of stateless NAT rules that can be used/updated in constant time.

The actual NAT code is mostly based on the previous stateless NAT code
written by Alexey.  In future we might be able to utilise the protocol
NAT code from netfilter to improve support for other protocols.

Signed-off-by: Herbert Xu <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

include/linux/tc_act/tc_nat.h

@@ -0,0 +1,29 @@
+#ifndef __LINUX_TC_NAT_H
+#define __LINUX_TC_NAT_H
+
+#include <linux/pkt_cls.h>
+#include <linux/types.h>
+
+#define TCA_ACT_NAT 9
+
+enum
+{
+	TCA_NAT_UNSPEC,
+	TCA_NAT_PARMS,
+	TCA_NAT_TM,
+	__TCA_NAT_MAX
+};
+#define TCA_NAT_MAX (__TCA_NAT_MAX - 1)
+
+#define TCA_NAT_FLAG_EGRESS 1
+
+struct tc_nat
+{
+	tc_gen;
+	__be32 old_addr;
+	__be32 new_addr;
+	__be32 mask;
+	__u32 flags;
+};
+
+#endif

include/net/tc_act/tc_nat.h

@@ -0,0 +1,21 @@
+#ifndef __NET_TC_NAT_H
+#define __NET_TC_NAT_H
+
+#include <linux/types.h>
+#include <net/act_api.h>
+
+struct tcf_nat {
+	struct tcf_common common;
+
+	__be32 old_addr;
+	__be32 new_addr;
+	__be32 mask;
+	u32 flags;
+};
+
+static inline struct tcf_nat *to_tcf_nat(struct tcf_common *pc)
+{
+	return container_of(pc, struct tcf_nat, common);
+}
+
+#endif /* __NET_TC_NAT_H */

net/sched/Kconfig

@@ -447,6 +447,17 @@ config NET_ACT_IPT
 	  To compile this code as a module, choose M here: the
 	  module will be called ipt.
 
+config NET_ACT_NAT
+        tristate "Stateless NAT"
+        depends on NET_CLS_ACT
+        select NETFILTER
+        ---help---
+	  Say Y here to do stateless NAT on IPv4 packets.  You should use
+	  netfilter for NAT unless you know what you are doing.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called nat.
+
 config NET_ACT_PEDIT
         tristate "Packet Editing"
         depends on NET_CLS_ACT

net/sched/Makefile

@@ -11,6 +11,7 @@ obj-$(CONFIG_NET_ACT_POLICE)	+= act_police.o
 obj-$(CONFIG_NET_ACT_GACT)	+= act_gact.o
 obj-$(CONFIG_NET_ACT_MIRRED)	+= act_mirred.o
 obj-$(CONFIG_NET_ACT_IPT)	+= act_ipt.o
+obj-$(CONFIG_NET_ACT_NAT)	+= act_nat.o
 obj-$(CONFIG_NET_ACT_PEDIT)	+= act_pedit.o
 obj-$(CONFIG_NET_ACT_SIMP)	+= act_simple.o
 obj-$(CONFIG_NET_SCH_FIFO)	+= sch_fifo.o