Message-Id: <1270031934-15940-4-git-send-email-jengelh@medozas.de>
Date:	Wed, 31 Mar 2010 12:38:51 +0200
From:	Jan Engelhardt <jengelh@...ozas.de>
To:	kaber@...sh.net
Cc:	netfilter-devel@...r.kernel.org, netdev@...r.kernel.org
Subject: [PATCH 3/5] netfilter: xtables: inclusion of xt_TEE

xt_TEE can be used to clone and reroute a packet. This can for
example be used to copy traffic at a router for logging purposes
to another dedicated machine.

References: http://www.gossamer-threads.com/lists/iptables/devel/68781
Signed-off-by: Jan Engelhardt <jengelh@...ozas.de>
---
 include/linux/netfilter/Kbuild   |    1 +
 include/linux/netfilter/xt_TEE.h |    8 +
 net/ipv4/ip_output.c             |    1 +
 net/ipv6/ip6_output.c            |    1 +
 net/netfilter/Kconfig            |    7 +
 net/netfilter/Makefile           |    1 +
 net/netfilter/xt_TEE.c           |  272 ++++++++++++++++++++++++++++++++++++++
 7 files changed, 291 insertions(+), 0 deletions(-)
 create mode 100644 include/linux/netfilter/xt_TEE.h
 create mode 100644 net/netfilter/xt_TEE.c

diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index a5a63e4..48767cd 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -16,6 +16,7 @@ header-y += xt_RATEEST.h
 header-y += xt_SECMARK.h
 header-y += xt_TCPMSS.h
 header-y += xt_TCPOPTSTRIP.h
+header-y += xt_TEE.h
 header-y += xt_TPROXY.h
 header-y += xt_comment.h
 header-y += xt_connbytes.h
diff --git a/include/linux/netfilter/xt_TEE.h b/include/linux/netfilter/xt_TEE.h
new file mode 100644
index 0000000..83fa768
--- /dev/null
+++ b/include/linux/netfilter/xt_TEE.h
@@ -0,0 +1,8 @@
+#ifndef _XT_TEE_TARGET_H
+#define _XT_TEE_TARGET_H
+
+struct xt_tee_tginfo {
+	union nf_inet_addr gw;
+};
+
+#endif /* _XT_TEE_TARGET_H */
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index f09135e..0abfdde 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -309,6 +309,7 @@ int ip_output(struct sk_buff *skb)
 			    ip_finish_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
+EXPORT_SYMBOL_GPL(ip_output);
 
 int ip_queue_xmit(struct sk_buff *skb, int ipfragok)
 {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7e10f62..307d8bf 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -176,6 +176,7 @@ int ip6_output(struct sk_buff *skb)
 			    ip6_finish_output,
 			    !(IP6CB(skb)->flags & IPSKB_REROUTED));
 }
+EXPORT_SYMBOL_GPL(ip6_output);
 
 /*
  *	xmit an sk_buff (used by TCP)
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 8055786..673a6c8 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -502,6 +502,13 @@ config NETFILTER_XT_TARGET_RATEEST
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NETFILTER_XT_TARGET_TEE
+	tristate '"TEE" - packet cloning to alternate destiantion'
+	depends on NETFILTER_ADVANCED
+	---help---
+	This option adds a "TEE" target with which a packet can be cloned and
+	this clone be rerouted to another nexthop.
+
 config NETFILTER_XT_TARGET_TPROXY
 	tristate '"TPROXY" target support (EXPERIMENTAL)'
 	depends on EXPERIMENTAL
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index cd31afe..14e3a8f 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -59,6 +59,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_SECMARK) += xt_SECMARK.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_TPROXY) += xt_TPROXY.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_TCPMSS) += xt_TCPMSS.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP) += xt_TCPOPTSTRIP.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_TEE) += xt_TEE.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_TRACE) += xt_TRACE.o
 
 # matches
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
new file mode 100644
index 0000000..96dd746
--- /dev/null
+++ b/net/netfilter/xt_TEE.c
@@ -0,0 +1,272 @@
+/*
+ *	"TEE" target extension for Xtables
+ *	Copyright © Sebastian Claßen <sebastian.classen [at] freenet de>, 2007
+ *	Jan Engelhardt <jengelh [at] medozas de>, 2007 - 2010
+ *
+ *	based on ipt_ROUTE.c from Cédric de Launois
+ *	<delaunois@...o.ucl.be>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	version 2 or later, as published by the Free Software Foundation.
+ */
+#include <linux/ip.h>
+#include <linux/module.h>
+#include <linux/route.h>
+#include <linux/skbuff.h>
+#include <net/checksum.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/route.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_TEE.h>
+
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#	define WITH_CONNTRACK 1
+#	include <net/netfilter/nf_conntrack.h>
+static struct nf_conn tee_track;
+#endif
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#	define WITH_IPV6 1
+#endif
+
+static const union nf_inet_addr tee_zero_address;
+
+/*
+ * Try to route the packet according to the routing keys specified in
+ * route_info. Keys are :
+ *  - ifindex :
+ *      0 if no oif preferred,
+ *      otherwise set to the index of the desired oif
+ *  - route_info->gateway :
+ *      0 if no gateway specified,
+ *      otherwise set to the next host to which the pkt must be routed
+ * If success, skb->dev is the output device to which the packet must
+ * be sent and skb->dst is not NULL
+ *
+ * RETURN: false - if an error occured
+ *         true  - if the packet was succesfully routed to the
+ *                 destination desired
+ */
+static bool
+tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	struct rtable *rt;
+	struct flowi fl;
+	int err;
+
+	memset(&fl, 0, sizeof(fl));
+	fl.iif  = skb->skb_iif;
+	fl.mark = skb->mark;
+	fl.nl_u.ip4_u.daddr = info->gw.ip;
+	fl.nl_u.ip4_u.tos   = RT_TOS(iph->tos);
+	fl.nl_u.ip4_u.scope = RT_SCOPE_UNIVERSE;
+
+	/* Trying to route the packet using the standard routing table. */
+	err = ip_route_output_key(dev_net(skb->dev), &rt, &fl);
+	if (err != 0)
+		return false;
+
+	dst_release(skb_dst(skb));
+	skb_dst_set(skb, &rt->u.dst);
+	skb->dev      = rt->u.dst.dev;
+	skb->protocol = htons(ETH_P_IP);
+	IPCB(skb)->flags |= IPSKB_REROUTED;
+	return true;
+}
+
+/*
+ * To detect and deter routed packet loopback when using the --tee option, we
+ * take a page out of the raw.patch book: on the copied skb, we set up a fake
+ * ->nfct entry, pointing to the local &route_tee_track. We skip routing
+ * packets when we see they already have that ->nfct.
+ */
+static unsigned int
+tee_tg4(struct sk_buff *skb, const struct xt_target_param *par)
+{
+	const struct xt_tee_tginfo *info = par->targinfo;
+	struct iphdr *iph;
+
+#ifdef WITH_CONNTRACK
+	if (skb->nfct == &tee_track.ct_general)
+		/*
+		 * Loopback - a packet we already routed, is to be
+		 * routed another time. Avoid that, now.
+		 */
+		return NF_DROP;
+#endif
+	/*
+	 * Copy the skb, and route the copy. Will later return %XT_CONTINUE for
+	 * the original skb, which should continue on its way as if nothing has
+	 * happened. The copy should be independently delivered to the TEE
+	 * --gateway.
+	 */
+	skb = skb_copy(skb, GFP_ATOMIC);
+	if (skb == NULL)
+		return XT_CONTINUE;
+	/*
+	 * If we are in PREROUTING/INPUT, the checksum must be recalculated
+	 * since the length could have changed as a result of defragmentation.
+	 *
+	 * We also decrease the TTL to mitigate potential TEE loops
+	 * between two hosts.
+	 *
+	 * Set %IP_DF so that the original source is notified of a potentially
+	 * decreased MTU on the clone route. IPv6 does this too.
+	 */
+	iph = ip_hdr(skb);
+	iph->frag_off |= htons(IP_DF);
+	if (par->hooknum == NF_INET_PRE_ROUTING ||
+	    par->hooknum == NF_INET_LOCAL_IN)
+		--iph->ttl;
+	ip_send_check(iph);
+
+#ifdef WITH_CONNTRACK
+	nf_conntrack_put(skb->nfct);
+	skb->nfct     = &tee_track.ct_general;
+	skb->nfctinfo = IP_CT_NEW;
+	nf_conntrack_get(skb->nfct);
+#endif
+	/*
+	 * Xtables is not reentrant currently, so a choice has to be made:
+	 * 1. return absolute verdict for the original and let the cloned
+	 *    packet travel through the chains
+	 * 2. let the original continue travelling and not pass the clone
+	 *    to Xtables.
+	 * #2 is chosen. Normally, we would use ip_local_out for the clone.
+	 * Because iph->check is already correct and we don't pass it to
+	 * Xtables anyway, a shortcut to dst_output [forwards to ip_output] can
+	 * be taken. %IPSKB_REROUTED needs to be set so that ip_output does not
+	 * invoke POSTROUTING on the cloned packet.
+	 */
+	IPCB(skb)->flags |= IPSKB_REROUTED;
+	if (tee_tg_route4(skb, info))
+		ip_output(skb);
+
+	return XT_CONTINUE;
+}
+
+#ifdef WITH_IPV6
+static bool
+tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info)
+{
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct dst_entry *dst;
+	struct flowi fl;
+
+	memset(&fl, 0, sizeof(fl));
+	fl.iif  = skb->skb_iif;
+	fl.mark = skb->mark;
+	fl.nl_u.ip6_u.daddr = info->gw.in6;
+	fl.nl_u.ip6_u.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) |
+				  (iph->flow_lbl[1] << 8) | iph->flow_lbl[2];
+
+	dst = ip6_route_output(dev_net(skb->dev), NULL, &fl);
+	if (dst == NULL)
+		return false;
+
+	dst_release(skb_dst(skb));
+	skb_dst_set(skb, dst);
+	skb->dev      = dst->dev;
+	skb->protocol = htons(ETH_P_IPV6);
+	IP6CB(skb)->flags |= IPSKB_REROUTED;
+	return true;
+}
+
+static unsigned int
+tee_tg6(struct sk_buff *skb, const struct xt_target_param *par)
+{
+	const struct xt_tee_tginfo *info = par->targinfo;
+
+#ifdef WITH_CONNTRACK
+	if (skb->nfct == &tee_track.ct_general)
+		return NF_DROP;
+#endif
+	if ((skb = skb_copy(skb, GFP_ATOMIC)) == NULL)
+		return XT_CONTINUE;
+
+#ifdef WITH_CONNTRACK
+	nf_conntrack_put(skb->nfct);
+	skb->nfct     = &tee_track.ct_general;
+	skb->nfctinfo = IP_CT_NEW;
+	nf_conntrack_get(skb->nfct);
+#endif
+	if (par->hooknum == NF_INET_PRE_ROUTING ||
+	    par->hooknum == NF_INET_LOCAL_IN) {
+		struct ipv6hdr *iph = ipv6_hdr(skb);
+		--iph->hop_limit;
+	}
+	IP6CB(skb)->flags |= IPSKB_REROUTED;
+	if (tee_tg_route6(skb, info))
+		ip6_output(skb);
+
+	return XT_CONTINUE;
+}
+#endif /* WITH_IPV6 */
+
+static int tee_tg_check(const struct xt_tgchk_param *par)
+{
+	const struct xt_tee_tginfo *info = par->targinfo;
+
+	/* 0.0.0.0 and :: not allowed */
+	return (memcmp(&info->gw, &tee_zero_address,
+	       sizeof(tee_zero_address)) == 0) ? -EINVAL : 0;
+}
+
+static struct xt_target tee_tg_reg[] __read_mostly = {
+	{
+		.name       = "TEE",
+		.revision   = 0,
+		.family     = NFPROTO_IPV4,
+		.target     = tee_tg4,
+		.targetsize = sizeof(struct xt_tee_tginfo),
+		.checkentry = tee_tg_check,
+		.me         = THIS_MODULE,
+	},
+#ifdef WITH_IPV6
+	{
+		.name       = "TEE",
+		.revision   = 0,
+		.family     = NFPROTO_IPV6,
+		.target     = tee_tg6,
+		.targetsize = sizeof(struct xt_tee_tginfo),
+		.checkentry = tee_tg_check,
+		.me         = THIS_MODULE,
+	},
+#endif
+};
+
+static int __init tee_tg_init(void)
+{
+#ifdef WITH_CONNTRACK
+	/*
+	 * Set up fake conntrack (stolen from raw.patch):
+	 * - to never be deleted, not in any hashes
+	 */
+	atomic_set(&tee_track.ct_general.use, 1);
+
+	/* - and look it like as a confirmed connection */
+	set_bit(IPS_CONFIRMED_BIT, &tee_track.status);
+
+	/* Initialize fake conntrack so that NAT will skip it */
+	tee_track.status |= IPS_NAT_DONE_MASK;
+#endif
+	return xt_register_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg));
+}
+
+static void __exit tee_tg_exit(void)
+{
+	xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg));
+}
+
+module_init(tee_tg_init);
+module_exit(tee_tg_exit);
+MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@...enet.ag>");
+MODULE_AUTHOR("Jan Engelhardt <jengelh@...ozas.de>");
+MODULE_DESCRIPTION("Xtables: Reroute packet copy");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_TEE");
+MODULE_ALIAS("ip6t_TEE");
-- 
1.7.0.2

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists