netfilter: add xt_cpu match

In some situations a CPU match permits a better spreading of
connections, or select targets only for a given cpu.

With Remote Packet Steering or multiqueue NIC and appropriate IRQ
affinities, we can distribute trafic on available cpus, per session.
(all RX packets for a given flow is handled by a given cpu)

Some legacy applications being not SMP friendly, one way to scale a
server is to run multiple copies of them.

Instead of randomly choosing an instance, we can use the cpu number as a
key so that softirq handler for a whole instance is running on a single
cpu, maximizing cache effects in TCP/UDP stacks.

Using NAT for example, a four ways machine might run four copies of
server application, using a separate listening port for each instance,
but still presenting an unique external port :

iptables -t nat -A PREROUTING -p tcp --dport 80 -m cpu --cpu 0 \
        -j REDIRECT --to-port 8080

iptables -t nat -A PREROUTING -p tcp --dport 80 -m cpu --cpu 1 \
        -j REDIRECT --to-port 8081

iptables -t nat -A PREROUTING -p tcp --dport 80 -m cpu --cpu 2 \
        -j REDIRECT --to-port 8082

iptables -t nat -A PREROUTING -p tcp --dport 80 -m cpu --cpu 3 \
        -j REDIRECT --to-port 8083

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 0cb62c8..edeeabd 100644 (file)
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -20,12 +20,13 @@ header-y += xt_TCPMSS.h
 header-y += xt_TCPOPTSTRIP.h
 header-y += xt_TEE.h
 header-y += xt_TPROXY.h
+header-y += xt_cluster.h
 header-y += xt_comment.h
 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_cpu.h
 header-y += xt_dccp.h
 header-y += xt_dscp.h
 header-y += xt_esp.h

diff --git a/include/linux/netfilter/xt_cpu.h b/include/linux/netfilter/xt_cpu.h
new file mode 100644 (file)
index 0000000..93c7f11
--- /dev/null
+++ b/include/linux/netfilter/xt_cpu.h
@@ -0,0 +1,11 @@
+#ifndef _XT_CPU_H
+#define _XT_CPU_H
+
+#include <linux/types.h>
+
+struct xt_cpu_info {
+       __u32   cpu;
+       __u32   invert;
+};
+
+#endif /*_XT_CPU_H*/

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 551b584..4328825 100644 (file)
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -663,6 +663,15 @@ config NETFILTER_XT_MATCH_CONNTRACK
 
          To compile it as a module, choose M here.  If unsure, say N.
 
+config NETFILTER_XT_MATCH_CPU
+       tristate '"cpu" match support'
+       depends on NETFILTER_ADVANCED
+       help
+         CPU matching allows you to match packets based on the CPU
+         currently handling the packet.
+
+         To compile it as a module, choose M here.  If unsure, say N.
+
 config NETFILTER_XT_MATCH_DCCP
        tristate '"dccp" protocol match support'
        depends on NETFILTER_ADVANCED

diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 4366c79..441050f 100644 (file)
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -70,6 +70,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_CPU) += xt_cpu.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o

diff --git a/net/netfilter/xt_cpu.c b/net/netfilter/xt_cpu.c
new file mode 100644 (file)
index 0000000..b39db8a
--- /dev/null
+++ b/net/netfilter/xt_cpu.c
@@ -0,0 +1,63 @@
+/* Kernel module to match running CPU */
+
+/*
+ * Might be used to distribute connections on several daemons, if
+ * RPS (Remote Packet Steering) is enabled or NIC is multiqueue capable,
+ * each RX queue IRQ affined to one CPU (1:1 mapping)
+ *
+ */
+
+/* (C) 2010 Eric Dumazet
+ *
+ * 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/module.h>
+#include <linux/skbuff.h>
+#include <linux/netfilter/xt_cpu.h>
+#include <linux/netfilter/x_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Dumazet <eric.dumazet@gmail.com>");
+MODULE_DESCRIPTION("Xtables: CPU match");
+
+static int cpu_mt_check(const struct xt_mtchk_param *par)
+{
+       const struct xt_cpu_info *info = par->matchinfo;
+
+       if (info->invert & ~1)
+               return -EINVAL;
+       return 0;
+}
+
+static bool cpu_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+       const struct xt_cpu_info *info = par->matchinfo;
+
+       return (info->cpu == smp_processor_id()) ^ info->invert;
+}
+
+static struct xt_match cpu_mt_reg __read_mostly = {
+       .name       = "cpu",
+       .revision   = 0,
+       .family     = NFPROTO_UNSPEC,
+       .checkentry = cpu_mt_check,
+       .match      = cpu_mt,
+       .matchsize  = sizeof(struct xt_cpu_info),
+       .me         = THIS_MODULE,
+};
+
+static int __init cpu_mt_init(void)
+{
+       return xt_register_match(&cpu_mt_reg);
+}
+
+static void __exit cpu_mt_exit(void)
+{
+       xt_unregister_match(&cpu_mt_reg);
+}
+
+module_init(cpu_mt_init);
+module_exit(cpu_mt_exit);