From: Eric Dumazet <eric.dumazet@gmail.com>
To: Patrick McHardy <kaber@trash.net>
Cc: Jan Engelhardt <jengelh@medozas.de>,
Netfilter Development Mailinglist
<netfilter-devel@vger.kernel.org>,
netdev <netdev@vger.kernel.org>
Subject: [PATCH iptables] extension: add xt_cpu match
Date: Fri, 23 Jul 2010 15:43:41 +0200 [thread overview]
Message-ID: <1279892621.2481.53.camel@edumazet-laptop> (raw)
In-Reply-To: <4C497644.7050201@trash.net>
Patrick,
Here is iptables extension for xt_cpu match.
I put same changelog than kernel one, tell me if its ok or not ;)
Thanks
[PATCH iptables] extension: add xt_cpu match
Kernel 2.6.36 supports 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 are 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>
---
extensions/libxt_cpu.c | 98 +++++++++++++++++++++++++++++
extensions/libxt_cpu.man | 16 ++++
include/linux/netfilter/xt_cpu.h | 11 +++
3 files changed, 125 insertions(+)
diff --git a/extensions/libxt_cpu.c b/extensions/libxt_cpu.c
index e69de29..869998d 100644
--- a/extensions/libxt_cpu.c
+++ b/extensions/libxt_cpu.c
@@ -0,0 +1,98 @@
+/* Shared library add-on to iptables to add CPU match support. */
+#include <stdio.h>
+#include <netdb.h>
+#include <string.h>
+#include <stdlib.h>
+#include <getopt.h>
+#include <xtables.h>
+#include <linux/netfilter/xt_cpu.h>
+
+static void cpu_help(void)
+{
+ printf(
+"cpu match options:\n"
+"[!] --cpu number Match CPU number\n");
+}
+
+static const struct option cpu_opts[] = {
+ { "cpu", 1, NULL, '1' },
+ { .name = NULL }
+};
+
+static void
+parse_cpu(const char *s, struct xt_cpu_info *info)
+{
+ unsigned int cpu;
+ char *end;
+
+ if (!xtables_strtoui(s, &end, &cpu, 0, UINT32_MAX))
+ xtables_param_act(XTF_BAD_VALUE, "cpu", "--cpu", s);
+
+ if (*end != '\0')
+ xtables_param_act(XTF_BAD_VALUE, "cpu", "--cpu", s);
+
+ info->cpu = cpu;
+}
+
+static int
+cpu_parse(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry, struct xt_entry_match **match)
+{
+ struct xt_cpu_info *cpuinfo = (struct xt_cpu_info *)(*match)->data;
+
+ switch (c) {
+ case '1':
+ xtables_check_inverse(optarg, &invert, &optind, 0, argv);
+ parse_cpu(optarg, cpuinfo);
+ if (invert)
+ cpuinfo->invert = 1;
+ *flags = 1;
+ break;
+
+ default:
+ return 0;
+ }
+
+ return 1;
+}
+
+static void cpu_check(unsigned int flags)
+{
+ if (!flags)
+ xtables_error(PARAMETER_PROBLEM,
+ "You must specify `--cpu'");
+}
+
+static void
+cpu_print(const void *ip, const struct xt_entry_match *match, int numeric)
+{
+ const struct xt_cpu_info *info = (void *)match->data;
+
+ printf("cpu %s%u ", info->invert ? "! ":"", info->cpu);
+}
+
+static void cpu_save(const void *ip, const struct xt_entry_match *match)
+{
+ const struct xt_cpu_info *info = (void *)match->data;
+
+ printf("%s--cpu %u ", info->invert ? "! ":"", info->cpu);
+}
+
+static struct xtables_match cpu_match = {
+ .family = NFPROTO_UNSPEC,
+ .name = "cpu",
+ .version = XTABLES_VERSION,
+ .size = XT_ALIGN(sizeof(struct xt_cpu_info)),
+ .userspacesize = XT_ALIGN(sizeof(struct xt_cpu_info)),
+ .help = cpu_help,
+ .parse = cpu_parse,
+ .final_check = cpu_check,
+ .print = cpu_print,
+ .save = cpu_save,
+ .extra_opts = cpu_opts,
+};
+
+void _init(void)
+{
+ xtables_register_match(&cpu_match);
+}
diff --git a/extensions/libxt_cpu.man b/extensions/libxt_cpu.man
index e69de29..f42ac7a 100644
--- a/extensions/libxt_cpu.man
+++ b/extensions/libxt_cpu.man
@@ -0,0 +1,16 @@
+.TP
+[\fB!\fP] \fB\-\-cpu\fP \fInumber\fP
+
+Match cpu handling this packet. cpus are numbered from 0 to NR_CPUS-1
+Can be used in combination with RPS (Remote Packet Steering) or
+multiqueue NICS to spread network traffic on different queues.
+.PP
+Example:
+.PP
+iptables \-t nat \-A PREROUTING \-p tcp \-\-dport 80 \-m cpu \-\-cpu 0
+ \-j REDIRECT \-\-to\-port 8080
+.PP
+iptables \-t nat \-A PREROUTING \-p tcp \-\-dport 80 \-m cpu \-\-cpu 1
+ \-j REDIRECT \-\-to\-port 8081
+.PP
+Available since linux 2.6.36
diff --git a/include/linux/netfilter/xt_cpu.h b/include/linux/netfilter/xt_cpu.h
index e69de29..93c7f11 100644
--- a/include/linux/netfilter/xt_cpu.h
+++ 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*/
next prev parent reply other threads:[~2010-07-23 13:43 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-22 14:03 [PATCH nf-next-2.6] netfilter: add xt_cpu match Eric Dumazet
2010-07-22 14:19 ` Jan Engelhardt
2010-07-22 15:18 ` Eric Dumazet
2010-07-22 15:39 ` Jan Engelhardt
2010-07-22 16:24 ` Eric Dumazet
2010-07-23 11:00 ` Patrick McHardy
2010-07-23 13:43 ` Eric Dumazet [this message]
2010-07-23 14:13 ` [PATCH iptables] extension: " Patrick McHardy
2010-07-23 16:46 ` Jan Engelhardt
2010-07-23 17:30 ` Eric Dumazet
2010-07-23 17:53 ` Jan Engelhardt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1279892621.2481.53.camel@edumazet-laptop \
--to=eric.dumazet@gmail.com \
--cc=jengelh@medozas.de \
--cc=kaber@trash.net \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox