netfilter: xtables: add cluster match

This patch adds the iptables cluster match. This match can be used
to deploy gateway and back-end load-sharing clusters. The cluster
can be composed of 32 nodes maximum (although I have only tested
this with two nodes, so I cannot tell what is the real scalability
limit of this solution in terms of cluster nodes).

Assuming that all the nodes see all packets (see below for an
example on how to do that if your switch does not allow this), the
cluster match decides if this node has to handle a packet given:

	(jhash(source IP) % total_nodes) & node_mask

For related connections, the master conntrack is used. The following
is an example of its use to deploy a gateway cluster composed of two
nodes (where this is the node 1):

iptables -I PREROUTING -t mangle -i eth1 -m cluster \
	--cluster-total-nodes 2 --cluster-local-node 1 \
	--cluster-proc-name eth1 -j MARK --set-mark 0xffff
iptables -A PREROUTING -t mangle -i eth1 \
	-m mark ! --mark 0xffff -j DROP
iptables -A PREROUTING -t mangle -i eth2 -m cluster \
	--cluster-total-nodes 2 --cluster-local-node 1 \
	--cluster-proc-name eth2 -j MARK --set-mark 0xffff
iptables -A PREROUTING -t mangle -i eth2 \
	-m mark ! --mark 0xffff -j DROP

And the following commands to make all nodes see the same packets:

ip maddr add 01:00:5e:00:01:01 dev eth1
ip maddr add 01:00:5e:00:01:02 dev eth2
arptables -I OUTPUT -o eth1 --h-length 6 \
	-j mangle --mangle-mac-s 01:00:5e:00:01:01
arptables -I INPUT -i eth1 --h-length 6 \
	--destination-mac 01:00:5e:00:01:01 \
	-j mangle --mangle-mac-d 00:zz:yy:xx:5a:27
arptables -I OUTPUT -o eth2 --h-length 6 \
	-j mangle --mangle-mac-s 01:00:5e:00:01:02
arptables -I INPUT -i eth2 --h-length 6 \
	--destination-mac 01:00:5e:00:01:02 \
	-j mangle --mangle-mac-d 00:zz:yy:xx:5a:27

In the case of TCP connections, pickup facility has to be disabled
to avoid marking TCP ACK packets coming in the reply direction as
valid.

echo 0 > /proc/sys/net/netfilter/nf_conntrack_tcp_loose

BTW, some final notes:

 * This match mangles the skbuff pkt_type in case that it detects
PACKET_MULTICAST for a non-multicast address. This may be done in
a PKTTYPE target for this sole purpose.
 * This match supersedes the CLUSTERIP target.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>

2 files changed, 16 insertions, 0 deletions

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 947b47d7f6c0..af9d2fb97212 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -21,6 +21,7 @@ header-y += xt_connbytes.h
 header-y += xt_connlimit.h
 header-y += xt_connmark.h
 header-y += xt_conntrack.h
+header-y += xt_cluster.h
 header-y += xt_dccp.h
 header-y += xt_dscp.h
 header-y += xt_esp.h
diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h
new file mode 100644
index 000000000000..5e0a0d07b526
--- /dev/null
+++ b/include/linux/netfilter/xt_cluster.h
@@ -0,0 +1,15 @@
+#ifndef _XT_CLUSTER_MATCH_H
+#define _XT_CLUSTER_MATCH_H
+
+enum xt_cluster_flags {
+	XT_CLUSTER_F_INV	= (1 << 0)
+};
+
+struct xt_cluster_match_info {
+	u_int32_t		total_nodes;
+	u_int32_t		node_mask;
+	u_int32_t		hash_seed;
+	u_int32_t		flags;
+};
+
+#endif /* _XT_CLUSTER_MATCH_H */