nf-next: TEE and nesting

nf-next: TEE and nesting

[Jan Engelhardt]

Hi,


next on the calendar is the xt_TEE submission.


The following changes since commit b44672889c11e13e4f4dc0a8ee23f0e64f1e57c6:
  Jan Engelhardt (1):
        netfilter: xtables: merge registration structure to NFPROTO_UNSPEC

are available in the git repository at:

  git://dev.medozas.de/linux master

Jan Engelhardt (5):
      netfilter: ipv6: move POSTROUTING invocation before fragmentation
      net: ipv6: add IPSKB_REROUTED exclusion to NF_HOOK/POSTROUTING invocation
      netfilter: xtables: inclusion of xt_TEE
      netfilter: xtables2: make ip_tables reentrant
      netfilter: xt_TEE: have cloned packet travel through Xtables too

 include/linux/netfilter/Kbuild     |    1 +
 include/linux/netfilter/x_tables.h |    7 +
 include/linux/netfilter/xt_TEE.h   |    8 +
 net/ipv4/netfilter/arp_tables.c    |    6 +-
 net/ipv4/netfilter/ip_tables.c     |   65 +++++----
 net/ipv6/ip6_output.c              |   50 ++++----
 net/ipv6/netfilter/ip6_tables.c    |   56 +++-----
 net/netfilter/Kconfig              |    7 +
 net/netfilter/Makefile             |    1 +
 net/netfilter/x_tables.c           |   79 +++++++++++
 net/netfilter/xt_TEE.c             |  258 ++++++++++++++++++++++++++++++++++++
 11 files changed, 446 insertions(+), 92 deletions(-)
 create mode 100644 include/linux/netfilter/xt_TEE.h
 create mode 100644 net/netfilter/xt_TEE.c

[PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Jan Engelhardt]

Patrick McHardy notes: "We used to invoke IPv4 POST_ROUTING after
fragmentation as well just to defragment the packets in conntrack
immediately afterwards, but that got changed during the
netfilter-ipsec integration. Ideally IPv6 would behave like IPv4."

This patch makes it so. Sending an oversized frame (e.g. `ping6
-s64000 -c1 ::1`) will now show up in POSTROUTING as a single skb
rather than multiple ones.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 net/ipv6/ip6_output.c |   49 +++++++++++++++++++++++--------------------------
 1 files changed, 23 insertions(+), 26 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4535b7a..f314ba4 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -82,22 +82,6 @@ int ip6_local_out(struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(ip6_local_out);
 
-static int ip6_output_finish(struct sk_buff *skb)
-{
-	struct dst_entry *dst = skb_dst(skb);
-
-	if (dst->hh)
-		return neigh_hh_output(dst->hh, skb);
-	else if (dst->neighbour)
-		return dst->neighbour->output(skb);
-
-	IP6_INC_STATS_BH(dev_net(dst->dev),
-			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
-	kfree_skb(skb);
-	return -EINVAL;
-
-}
-
 /* dev_loopback_xmit for use with netfilter. */
 static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
 {
@@ -111,8 +95,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
 	return 0;
 }
 
-
-static int ip6_output2(struct sk_buff *skb)
+static int ip6_finish_output2(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
@@ -150,8 +133,15 @@ static int ip6_output2(struct sk_buff *skb)
 				skb->len);
 	}
 
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, skb->dev,
-		       ip6_output_finish);
+	if (dst->hh)
+		return neigh_hh_output(dst->hh, skb);
+	else if (dst->neighbour)
+		return dst->neighbour->output(skb);
+
+	IP6_INC_STATS_BH(dev_net(dst->dev),
+			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	kfree_skb(skb);
+	return -EINVAL;
 }
 
 static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
@@ -162,21 +152,28 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
 }
 
+static int ip6_finish_output(struct sk_buff *skb)
+{
+	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+				dst_allfrag(skb_dst(skb)))
+		return ip6_fragment(skb, ip6_finish_output2);
+	else
+		return ip6_finish_output2(skb);
+}
+
 int ip6_output(struct sk_buff *skb)
 {
+	struct net_device *dev = skb_dst(skb)->dev;
 	struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 	if (unlikely(idev->cnf.disable_ipv6)) {
-		IP6_INC_STATS(dev_net(skb_dst(skb)->dev), idev,
+		IP6_INC_STATS(dev_net(dev), idev,
 			      IPSTATS_MIB_OUTDISCARDS);
 		kfree_skb(skb);
 		return 0;
 	}
 
-	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
-				dst_allfrag(skb_dst(skb)))
-		return ip6_fragment(skb, ip6_output2);
-	else
-		return ip6_output2(skb);
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev,
+		       ip6_finish_output);
 }
 
 /*
-- 
1.7.0.2

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[YOSHIFUJI Hideaki]

Hello.

(2010/03/31 19:31), Jan Engelhardt wrote:
> Patrick McHardy notes: "We used to invoke IPv4 POST_ROUTING after
> fragmentation as well just to defragment the packets in conntrack
> immediately afterwards, but that got changed during the
> netfilter-ipsec integration. Ideally IPv6 would behave like IPv4."
> 
> This patch makes it so. Sending an oversized frame (e.g. `ping6
> -s64000 -c1 ::1`) will now show up in POSTROUTING as a single skb
> rather than multiple ones.

I am not in favor doing this
because we theoretically make fragments __before__ routing
in output path (as we reassemble __after__ routing in input path).

IMHO, FORWARDING and POSTROUTING share similar semantics
from routing POV.
As we see "fragments" in FORWARDING, we should see
fragments in POST_ROUTING, at least in IPv6.

--yoshfuji

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Jan Engelhardt]

On Thursday 2010-04-01 12:50, YOSHIFUJI Hideaki wrote:
>(2010/03/31 19:31), Jan Engelhardt wrote:
>> Patrick McHardy notes: "We used to invoke IPv4 POST_ROUTING after
>> fragmentation as well just to defragment the packets in conntrack
>> immediately afterwards, but that got changed during the
>> netfilter-ipsec integration. Ideally IPv6 would behave like IPv4."
>> 
>> This patch makes it so. Sending an oversized frame (e.g. `ping6
>> -s64000 -c1 ::1`) will now show up in POSTROUTING as a single skb
>> rather than multiple ones.
>
>I am not in favor doing this
>because we theoretically make fragments __before__ routing
>in output path (as we reassemble __after__ routing in input path).
>
>IMHO, FORWARDING and POSTROUTING share similar semantics
>from routing POV.
>As we see "fragments" in FORWARDING, we should see
>fragments in POST_ROUTING, at least in IPv6.

I don't have much of a problem with it, in fact, I also have a patch ready that
would turn things around in the IPv4 section instead to match the IPv6
behavior. Or it could be ignored altogether since it is not crucial for
IPSKB_REROUTED.
Patrick?

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Patrick McHardy]

YOSHIFUJI Hideaki wrote:
> Hello.
> 
> (2010/03/31 19:31), Jan Engelhardt wrote:
>> Patrick McHardy notes: "We used to invoke IPv4 POST_ROUTING after
>> fragmentation as well just to defragment the packets in conntrack
>> immediately afterwards, but that got changed during the
>> netfilter-ipsec integration. Ideally IPv6 would behave like IPv4."
>>
>> This patch makes it so. Sending an oversized frame (e.g. `ping6
>> -s64000 -c1 ::1`) will now show up in POSTROUTING as a single skb
>> rather than multiple ones.
> 
> I am not in favor doing this
> because we theoretically make fragments __before__ routing
> in output path (as we reassemble __after__ routing in input path).

That's true, but is symetry for fragment handling really something
worth keeping? Besides avoiding one refragmentation pass in conntrack,
its a lot easier to construct your ruleset when you don't have to
take care of fragments.

Granted, in IPv4 the main motivation for this change was to reduce
stack usage by not using the "okfn" anymore, which isn't too important
on the output path, and we don't fragment forwarded packets in IPv6.

> IMHO, FORWARDING and POSTROUTING share similar semantics
> from routing POV.
> As we see "fragments" in FORWARDING, we should see
> fragments in POST_ROUTING, at least in IPv6.

We'd still see them for forwarded packets.

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Jan Engelhardt]

On Thursday 2010-04-01 13:17, Patrick McHardy wrote:
>> (2010/03/31 19:31), Jan Engelhardt wrote:
>>> Patrick McHardy notes: "We used to invoke IPv4 POST_ROUTING after
>>> fragmentation as well just to defragment the packets in conntrack
>>> immediately afterwards, but that got changed during the
>>> netfilter-ipsec integration. Ideally IPv6 would behave like IPv4."
>>>
>>> This patch makes it so. Sending an oversized frame (e.g. `ping6
>>> -s64000 -c1 ::1`) will now show up in POSTROUTING as a single skb
>>> rather than multiple ones.
>> 
>> I am not in favor doing this
>> because we theoretically make fragments __before__ routing
>> in output path (as we reassemble __after__ routing in input path).
>
>That's true, but is symetry for fragment handling really something
>worth keeping? Besides avoiding one refragmentation pass in conntrack,

I am not quite following where this extra refragmentation is
happening. Assuming [nf-packet-flow.png] as a base, there are two
spots in which conntrack/defrag happens: PREROUTING and OUTPUT.

This translates to:

>its a lot easier to construct your ruleset when you don't have to
>take care of fragments.

We never see fragments in the ruleset

 a) for netif_rx received packets, defrag will be run early
    (yes, there's raw, but that's special anyway)

 b) locally-generated packets are fragmented only after all of
    Netfilter is done.

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Patrick McHardy]

Jan Engelhardt wrote:
> On Thursday 2010-04-01 13:17, Patrick McHardy wrote:
>>> (2010/03/31 19:31), Jan Engelhardt wrote:
>>>> Patrick McHardy notes: "We used to invoke IPv4 POST_ROUTING after
>>>> fragmentation as well just to defragment the packets in conntrack
>>>> immediately afterwards, but that got changed during the
>>>> netfilter-ipsec integration. Ideally IPv6 would behave like IPv4."
>>>>
>>>> This patch makes it so. Sending an oversized frame (e.g. `ping6
>>>> -s64000 -c1 ::1`) will now show up in POSTROUTING as a single skb
>>>> rather than multiple ones.
>>> I am not in favor doing this
>>> because we theoretically make fragments __before__ routing
>>> in output path (as we reassemble __after__ routing in input path).
>> That's true, but is symetry for fragment handling really something
>> worth keeping? Besides avoiding one refragmentation pass in conntrack,
> 
> I am not quite following where this extra refragmentation is
> happening.

This was supposed to read "one more *de*fragmentation pass. In
IPv6 we don't have to refragment, but simply output the original
fragments.

> Assuming [nf-packet-flow.png] as a base, there are two
> spots in which conntrack/defrag happens: PREROUTING and OUTPUT.
> 
> This translates to:
> 
>> its a lot easier to construct your ruleset when you don't have to
>> take care of fragments.
> 
> We never see fragments in the ruleset
> 
>  a) for netif_rx received packets, defrag will be run early
>     (yes, there's raw, but that's special anyway)
> 
>  b) locally-generated packets are fragmented only after all of
>     Netfilter is done.

You're assuming conntrack is used.

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Jan Engelhardt]

On Thursday 2010-04-01 13:56, Patrick McHardy wrote:
>
>>>>> just to defragment the packets in conntrack
>>>>> immediately afterwards
>
>This was supposed to read "one more *de*fragmentation pass. In
>IPv6 we don't have to refragment, but simply output the original
>fragments.
>
>> Assuming [nf-packet-flow.png] as a base, there are two
>> spots in which conntrack/defrag happens: PREROUTING and OUTPUT.
>> [...]
>> We never see fragments in the ruleset
>> 
>>  a) for netif_rx received packets, defrag will be run early
>>     (yes, there's raw, but that's special anyway)
>> 
>>  b) locally-generated packets are fragmented only after all of
>>     Netfilter is done.
>
>You're assuming conntrack is used.

That was what your original message was about, was it not?

If there is no nf_defrag loaded, there is not much left besides
the standard IPv4 stack defrag on input, the fragmentation
on output, and the double-fragmentation on forward.

What did I miss?

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Patrick McHardy]

Jan Engelhardt wrote:
> On Thursday 2010-04-01 13:56, Patrick McHardy wrote:
>>>>>> just to defragment the packets in conntrack
>>>>>> immediately afterwards
>> This was supposed to read "one more *de*fragmentation pass. In
>> IPv6 we don't have to refragment, but simply output the original
>> fragments.
>>
>>> Assuming [nf-packet-flow.png] as a base, there are two
>>> spots in which conntrack/defrag happens: PREROUTING and OUTPUT.
>>> [...]
>>> We never see fragments in the ruleset
>>>
>>>  a) for netif_rx received packets, defrag will be run early
>>>     (yes, there's raw, but that's special anyway)
>>>
>>>  b) locally-generated packets are fragmented only after all of
>>>     Netfilter is done.
>> You're assuming conntrack is used.
> 
> That was what your original message was about, was it not?

Partially, but the ruleset construction point you replied to of
course only applies when conntrack is not used.

> If there is no nf_defrag loaded, there is not much left besides
> the standard IPv4 stack defrag on input, the fragmentation
> on output, and the double-fragmentation on forward.
> 
> What did I miss?

Now I seem to be missing something. Why are we suddenly talking
about IPv4 and nf_defrag?

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Jan Engelhardt]

On Thursday 2010-04-01 14:28, Patrick McHardy wrote:
>>>
>>>> Assuming [nf-packet-flow.png] as a base, there are two
>>>> spots in which conntrack/defrag happens: PREROUTING and OUTPUT.
>>>> [...]
>>>> We never see fragments in the ruleset
>>>>
>>>>  a) for netif_rx received packets, defrag will be run early
>>>>     (yes, there's raw, but that's special anyway)
>>>>
>>>>  b) locally-generated packets are fragmented only after all of
>>>>     Netfilter is done.
>>> You're assuming conntrack is used.
>> 
>> That was what your original message was about, was it not?
>
>Partially, but the ruleset construction point you replied to of
>course only applies when conntrack is not used.
>
>> If there is no nf_defrag loaded, there is not much left besides
>> the standard IPv4 stack defrag on input, the fragmentation
>> on output, and the double-fragmentation on forward.
>> 
>> What did I miss?
>
>Now I seem to be missing something. Why are we suddenly talking
>about IPv4 and nf_defrag?

So when exactly is the problem showing?

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Jan Engelhardt]

On Thursday 2010-04-01 13:17, Patrick McHardy wrote:

>YOSHIFUJI Hideaki wrote:
>> Hello.
>> 
>> (2010/03/31 19:31), Jan Engelhardt wrote:
>>> Patrick McHardy notes: "We used to invoke IPv4 POST_ROUTING after
>>> fragmentation as well just to defragment the packets in conntrack
>>> immediately afterwards, but that got changed during the
>>> netfilter-ipsec integration. Ideally IPv6 would behave like IPv4."
>>>
>>> This patch makes it so. Sending an oversized frame (e.g. `ping6
>>> -s64000 -c1 ::1`) will now show up in POSTROUTING as a single skb
>>> rather than multiple ones.
>> 
>> I am not in favor doing this
>> because we theoretically make fragments __before__ routing
>> in output path (as we reassemble __after__ routing in input path).
>
>That's true, but is symetry for fragment handling really something
>worth keeping? Besides avoiding one refragmentation pass in conntrack,
>its a lot easier to construct your ruleset when you don't have to
>take care of fragments.
[...]

So, drop the patch or not?

[PATCH 2/5] net: ipv6: add IPSKB_REROUTED exclusion to NF_HOOK/POSTROUTING invocation

[Jan Engelhardt]

Similar to how IPv4's ip_output.c works, have ip6_output also check
the IPSKB_REROUTED flag. It will be set from xt_TEE for cloned packets
since Xtables can currently only deal with a single packet in flight
at a time.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 net/ipv6/ip6_output.c |    5 +++--
 1 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f314ba4..7e10f62 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -172,8 +172,9 @@ int ip6_output(struct sk_buff *skb)
 		return 0;
 	}
 
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev,
-		       ip6_finish_output);
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev,
+			    ip6_finish_output,
+			    !(IP6CB(skb)->flags & IPSKB_REROUTED));
 }
 
 /*
-- 
1.7.0.2

[PATCH 3/5] netfilter: xtables: inclusion of xt_TEE

[Jan Engelhardt]

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@medozas.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@info.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@freenet.ag>");
+MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.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 netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 4/5] netfilter: xtables2: make ip_tables reentrant

[Jan Engelhardt]

Currently, the table traverser stores return addresses in the ruleset
itself (struct ip6t_entry->comefrom). This has a well-known drawback:
the jumpstack is overwritten on reentry, making it necessary for
targets to return absolute verdicts. Also, the ruleset (which might
be heavy memory-wise) needs to be replicated for each CPU that can
possibly invoke ip6t_do_table.

This patch decouples the jumpstack from struct ip6t_entry and instead
puts it into xt_table_info. Not being restricted by 'comefrom'
anymore, we can set up a stack as needed. By default, there is room
allocated for two entries into the traverser. The setting is
configurable at runtime through sysfs and will take effect when a
table is replaced by a new one.

arp_tables is not touched though, because there is just one/two
modules and further patches seek to collapse the table traverser
anyhow.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 include/linux/netfilter/x_tables.h |    7 +++
 net/ipv4/netfilter/arp_tables.c    |    6 ++-
 net/ipv4/netfilter/ip_tables.c     |   65 ++++++++++++++++--------------
 net/ipv6/netfilter/ip6_tables.c    |   56 ++++++++++---------------
 net/netfilter/x_tables.c           |   79 ++++++++++++++++++++++++++++++++++++
 5 files changed, 147 insertions(+), 66 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 1a65d45..62cc5ca 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -401,6 +401,13 @@ struct xt_table_info {
 	unsigned int hook_entry[NF_INET_NUMHOOKS];
 	unsigned int underflow[NF_INET_NUMHOOKS];
 
+	/*
+	 * Number of user chains. Since tables cannot have loops, at most
+	 * @stacksize jumps (number of user chains) can possibly be made.
+	 */
+	unsigned int stacksize;
+	unsigned int *stackptr;
+	void ***jumpstack;
 	/* ipt_entry tables: one per CPU */
 	/* Note : this field MUST be the last one, see XT_TABLE_INFO_SZ */
 	void *entries[1];
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index e8e363d..07a6990 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -649,6 +649,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		if (ret != 0)
 			break;
 		++i;
+		if (strcmp(arpt_get_target(iter)->u.user.name,
+		    XT_ERROR_TARGET) == 0)
+			++newinfo->stacksize;
 	}
 	duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret);
 	if (ret != 0)
@@ -1774,8 +1777,7 @@ struct xt_table *arpt_register_table(struct net *net,
 {
 	int ret;
 	struct xt_table_info *newinfo;
-	struct xt_table_info bootstrap
-		= { 0, 0, 0, { 0 }, { 0 }, { } };
+	struct xt_table_info bootstrap = {0};
 	void *loc_cpu_entry;
 	struct xt_table *new_table;
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 18c5b15..70900ec 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -321,8 +321,6 @@ ipt_do_table(struct sk_buff *skb,
 	     const struct net_device *out,
 	     struct xt_table *table)
 {
-#define tb_comefrom ((struct ipt_entry *)table_base)->comefrom
-
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	const struct iphdr *ip;
 	bool hotdrop = false;
@@ -330,7 +328,8 @@ ipt_do_table(struct sk_buff *skb,
 	unsigned int verdict = NF_DROP;
 	const char *indev, *outdev;
 	const void *table_base;
-	struct ipt_entry *e, *back;
+	struct ipt_entry *e, **jumpstack;
+	unsigned int *stackptr, origptr, cpu;
 	const struct xt_table_info *private;
 	struct xt_match_param mtpar;
 	struct xt_target_param tgpar;
@@ -356,19 +355,23 @@ ipt_do_table(struct sk_buff *skb,
 	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
 	xt_info_rdlock_bh();
 	private = table->private;
-	table_base = private->entries[smp_processor_id()];
+	cpu        = smp_processor_id();
+	table_base = private->entries[cpu];
+	jumpstack  = (struct ipt_entry **)private->jumpstack[cpu];
+	stackptr   = &private->stackptr[cpu];
+	origptr    = *stackptr;
 
 	e = get_entry(table_base, private->hook_entry[hook]);
 
-	/* For return from builtin chain */
-	back = get_entry(table_base, private->underflow[hook]);
+	pr_devel("Entering %s(hook %u); sp at %u (UF %p)\n",
+		 table->name, hook, origptr,
+		 get_entry(table_base, private->underflow[hook]));
 
 	do {
 		const struct ipt_entry_target *t;
 		const struct xt_entry_match *ematch;
 
 		IP_NF_ASSERT(e);
-		IP_NF_ASSERT(back);
 		if (!ip_packet_match(ip, indev, outdev,
 		    &e->ip, mtpar.fragoff)) {
  no_match:
@@ -403,17 +406,28 @@ ipt_do_table(struct sk_buff *skb,
 					verdict = (unsigned)(-v) - 1;
 					break;
 				}
-				e = back;
-				back = get_entry(table_base, back->comefrom);
+				if (*stackptr == 0) {
+					e = get_entry(table_base,
+					    private->underflow[hook]);
+					pr_devel("Underflow (this is normal) "
+						 "to %p\n", e);
+				} else {
+					e = jumpstack[--*stackptr];
+					pr_devel("Pulled %p out from pos %u\n",
+						 e, *stackptr);
+					e = ipt_next_entry(e);
+				}
 				continue;
 			}
 			if (table_base + v != ipt_next_entry(e) &&
 			    !(e->ip.flags & IPT_F_GOTO)) {
-				/* Save old back ptr in next entry */
-				struct ipt_entry *next = ipt_next_entry(e);
-				next->comefrom = (void *)back - table_base;
-				/* set back pointer to next entry */
-				back = next;
+				if (*stackptr >= private->stacksize) {
+					verdict = NF_DROP;
+					break;
+				}
+				jumpstack[(*stackptr)++] = e;
+				pr_devel("Pushed %p into pos %u\n",
+					 e, *stackptr - 1);
 			}
 
 			e = get_entry(table_base, v);
@@ -426,18 +440,7 @@ ipt_do_table(struct sk_buff *skb,
 		tgpar.targinfo = t->data;
 
 
-#ifdef CONFIG_NETFILTER_DEBUG
-		tb_comefrom = 0xeeeeeeec;
-#endif
 		verdict = t->u.kernel.target->target(skb, &tgpar);
-#ifdef CONFIG_NETFILTER_DEBUG
-		if (tb_comefrom != 0xeeeeeeec && verdict == IPT_CONTINUE) {
-			printk("Target %s reentered!\n",
-			       t->u.kernel.target->name);
-			verdict = NF_DROP;
-		}
-		tb_comefrom = 0x57acc001;
-#endif
 		/* Target might have changed stuff. */
 		ip = ip_hdr(skb);
 		if (verdict == IPT_CONTINUE)
@@ -447,7 +450,9 @@ ipt_do_table(struct sk_buff *skb,
 			break;
 	} while (!hotdrop);
 	xt_info_rdunlock_bh();
-
+	pr_devel("Exiting %s; resetting sp from %u to %u\n",
+		 __func__, *stackptr, origptr);
+	*stackptr = origptr;
 #ifdef DEBUG_ALLOW_ALL
 	return NF_ACCEPT;
 #else
@@ -455,8 +460,6 @@ ipt_do_table(struct sk_buff *skb,
 		return NF_DROP;
 	else return verdict;
 #endif
-
-#undef tb_comefrom
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -838,6 +841,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		if (ret != 0)
 			return ret;
 		++i;
+		if (strcmp(ipt_get_target(iter)->u.user.name,
+		    XT_ERROR_TARGET) == 0)
+			++newinfo->stacksize;
 	}
 
 	if (i != repl->num_entries) {
@@ -2086,8 +2092,7 @@ struct xt_table *ipt_register_table(struct net *net,
 {
 	int ret;
 	struct xt_table_info *newinfo;
-	struct xt_table_info bootstrap
-		= { 0, 0, 0, { 0 }, { 0 }, { } };
+	struct xt_table_info bootstrap = {0};
 	void *loc_cpu_entry;
 	struct xt_table *new_table;
 
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index f2b815e..2a2770b 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -351,15 +351,14 @@ ip6t_do_table(struct sk_buff *skb,
 	      const struct net_device *out,
 	      struct xt_table *table)
 {
-#define tb_comefrom ((struct ip6t_entry *)table_base)->comefrom
-
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	bool hotdrop = false;
 	/* Initializing verdict to NF_DROP keeps gcc happy. */
 	unsigned int verdict = NF_DROP;
 	const char *indev, *outdev;
 	const void *table_base;
-	struct ip6t_entry *e, *back;
+	struct ip6t_entry *e, **jumpstack;
+	unsigned int *stackptr, origptr, cpu;
 	const struct xt_table_info *private;
 	struct xt_match_param mtpar;
 	struct xt_target_param tgpar;
@@ -383,19 +382,19 @@ ip6t_do_table(struct sk_buff *skb,
 
 	xt_info_rdlock_bh();
 	private = table->private;
-	table_base = private->entries[smp_processor_id()];
+	cpu        = smp_processor_id();
+	table_base = private->entries[cpu];
+	jumpstack  = (struct ip6t_entry **)private->jumpstack[cpu];
+	stackptr   = &private->stackptr[cpu];
+	origptr    = *stackptr;
 
 	e = get_entry(table_base, private->hook_entry[hook]);
 
-	/* For return from builtin chain */
-	back = get_entry(table_base, private->underflow[hook]);
-
 	do {
 		const struct ip6t_entry_target *t;
 		const struct xt_entry_match *ematch;
 
 		IP_NF_ASSERT(e);
-		IP_NF_ASSERT(back);
 		if (!ip6_packet_match(skb, indev, outdev, &e->ipv6,
 		    &mtpar.thoff, &mtpar.fragoff, &hotdrop)) {
  no_match:
@@ -432,17 +431,20 @@ ip6t_do_table(struct sk_buff *skb,
 					verdict = (unsigned)(-v) - 1;
 					break;
 				}
-				e = back;
-				back = get_entry(table_base, back->comefrom);
+				if (*stackptr == 0)
+					e = get_entry(table_base,
+					    private->underflow[hook]);
+				else
+					e = ip6t_next_entry(jumpstack[--*stackptr]);
 				continue;
 			}
 			if (table_base + v != ip6t_next_entry(e) &&
 			    !(e->ipv6.flags & IP6T_F_GOTO)) {
-				/* Save old back ptr in next entry */
-				struct ip6t_entry *next = ip6t_next_entry(e);
-				next->comefrom = (void *)back - table_base;
-				/* set back pointer to next entry */
-				back = next;
+				if (*stackptr >= private->stacksize) {
+					verdict = NF_DROP;
+					break;
+				}
+				jumpstack[(*stackptr)++] = e;
 			}
 
 			e = get_entry(table_base, v);
@@ -454,19 +456,7 @@ ip6t_do_table(struct sk_buff *skb,
 		tgpar.target   = t->u.kernel.target;
 		tgpar.targinfo = t->data;
 
-#ifdef CONFIG_NETFILTER_DEBUG
-		tb_comefrom = 0xeeeeeeec;
-#endif
 		verdict = t->u.kernel.target->target(skb, &tgpar);
-
-#ifdef CONFIG_NETFILTER_DEBUG
-		if (tb_comefrom != 0xeeeeeeec && verdict == IP6T_CONTINUE) {
-			printk("Target %s reentered!\n",
-			       t->u.kernel.target->name);
-			verdict = NF_DROP;
-		}
-		tb_comefrom = 0x57acc001;
-#endif
 		if (verdict == IP6T_CONTINUE)
 			e = ip6t_next_entry(e);
 		else
@@ -474,10 +464,8 @@ ip6t_do_table(struct sk_buff *skb,
 			break;
 	} while (!hotdrop);
 
-#ifdef CONFIG_NETFILTER_DEBUG
-	tb_comefrom = NETFILTER_LINK_POISON;
-#endif
 	xt_info_rdunlock_bh();
+	*stackptr = origptr;
 
 #ifdef DEBUG_ALLOW_ALL
 	return NF_ACCEPT;
@@ -486,8 +474,6 @@ ip6t_do_table(struct sk_buff *skb,
 		return NF_DROP;
 	else return verdict;
 #endif
-
-#undef tb_comefrom
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -869,6 +855,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		if (ret != 0)
 			return ret;
 		++i;
+		if (strcmp(ip6t_get_target(iter)->u.user.name,
+		    XT_ERROR_TARGET) == 0)
+			++newinfo->stacksize;
 	}
 
 	if (i != repl->num_entries) {
@@ -2120,8 +2109,7 @@ struct xt_table *ip6t_register_table(struct net *net,
 {
 	int ret;
 	struct xt_table_info *newinfo;
-	struct xt_table_info bootstrap
-		= { 0, 0, 0, { 0 }, { 0 }, { } };
+	struct xt_table_info bootstrap = {0};
 	void *loc_cpu_entry;
 	struct xt_table *new_table;
 
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 8e23d8f..2010b56 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -62,6 +62,11 @@ static const char *const xt_prefix[NFPROTO_NUMPROTO] = {
 	[NFPROTO_IPV6]   = "ip6",
 };
 
+/* Allow this many total (re)entries. */
+static unsigned int xt_jumpstack_multiplier = 2;
+module_param_named(jumpstack_multiplier, xt_jumpstack_multiplier,
+	uint, S_IRUGO | S_IWUSR);
+
 /* Registration hooks for targets. */
 int
 xt_register_target(struct xt_target *target)
@@ -680,6 +685,26 @@ void xt_free_table_info(struct xt_table_info *info)
 		else
 			vfree(info->entries[cpu]);
 	}
+
+	if (info->jumpstack != NULL) {
+		if (sizeof(void *) * info->stacksize > PAGE_SIZE) {
+			for_each_possible_cpu(cpu)
+				vfree(info->jumpstack[cpu]);
+		} else {
+			for_each_possible_cpu(cpu)
+				kfree(info->jumpstack[cpu]);
+		}
+	}
+
+	if (sizeof(void **) * nr_cpu_ids > PAGE_SIZE)
+		vfree(info->jumpstack);
+	else
+		kfree(info->jumpstack);
+	if (sizeof(unsigned int) * nr_cpu_ids > PAGE_SIZE)
+		vfree(info->stackptr);
+	else
+		kfree(info->stackptr);
+
 	kfree(info);
 }
 EXPORT_SYMBOL(xt_free_table_info);
@@ -724,6 +749,49 @@ EXPORT_SYMBOL_GPL(xt_compat_unlock);
 DEFINE_PER_CPU(struct xt_info_lock, xt_info_locks);
 EXPORT_PER_CPU_SYMBOL_GPL(xt_info_locks);
 
+static int xt_jumpstack_alloc(struct xt_table_info *i)
+{
+	unsigned int size;
+	int cpu;
+
+	size = sizeof(unsigned int) * nr_cpu_ids;
+	if (size > PAGE_SIZE)
+		i->stackptr = vmalloc(size);
+	else
+		i->stackptr = kmalloc(size, GFP_KERNEL);
+	if (i->stackptr == NULL)
+		return -ENOMEM;
+	memset(i->stackptr, 0, size);
+
+	size = sizeof(void **) * nr_cpu_ids;
+	if (size > PAGE_SIZE)
+		i->jumpstack = vmalloc(size);
+	else
+		i->jumpstack = kmalloc(size, GFP_KERNEL);
+	if (i->jumpstack == NULL)
+		return -ENOMEM;
+	memset(i->jumpstack, 0, size);
+
+	i->stacksize *= xt_jumpstack_multiplier;
+	size = sizeof(void *) * i->stacksize;
+	for_each_possible_cpu(cpu) {
+		if (size > PAGE_SIZE)
+			i->jumpstack[cpu] = vmalloc_node(size,
+				cpu_to_node(cpu));
+		else
+			i->jumpstack[cpu] = kmalloc_node(size,
+				GFP_KERNEL, cpu_to_node(cpu));
+		if (i->jumpstack[cpu] == NULL)
+			/*
+			 * Freeing will be done later on by the callers. The
+			 * chain is: xt_replace_table -> __do_replace ->
+			 * do_replace -> xt_free_table_info.
+			 */
+			return -ENOMEM;
+	}
+
+	return 0;
+}
 
 struct xt_table_info *
 xt_replace_table(struct xt_table *table,
@@ -732,6 +800,7 @@ xt_replace_table(struct xt_table *table,
 	      int *error)
 {
 	struct xt_table_info *private;
+	int ret;
 
 	/* Do the substitution. */
 	local_bh_disable();
@@ -746,6 +815,12 @@ xt_replace_table(struct xt_table *table,
 		return NULL;
 	}
 
+	ret = xt_jumpstack_alloc(newinfo);
+	if (ret < 0) {
+		*error = ret;
+		return NULL;
+	}
+
 	table->private = newinfo;
 	newinfo->initial_entries = private->initial_entries;
 
@@ -770,6 +845,10 @@ struct xt_table *xt_register_table(struct net *net,
 	struct xt_table_info *private;
 	struct xt_table *t, *table;
 
+	ret = xt_jumpstack_alloc(newinfo);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
 	/* Don't add one object to multiple lists. */
 	table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL);
 	if (!table) {
-- 
1.7.0.2

[PATCH 5/5] netfilter: xt_TEE: have cloned packet travel through Xtables too

[Jan Engelhardt]

Since Xtables is now reentrant/nestable, the cloned packet can also go
through Xtables and be subject to rules itself.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 net/ipv4/ip_output.c   |    1 -
 net/ipv6/ip6_output.c  |    1 -
 net/netfilter/xt_TEE.c |   18 ++----------------
 3 files changed, 2 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 0abfdde..f09135e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -309,7 +309,6 @@ 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 307d8bf..7e10f62 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -176,7 +176,6 @@ 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/xt_TEE.c b/net/netfilter/xt_TEE.c
index 96dd746..70078f1 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -130,21 +130,8 @@ tee_tg4(struct sk_buff *skb, const struct xt_target_param *par)
 	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);
+		ip_local_out(skb);
 
 	return XT_CONTINUE;
 }
@@ -199,9 +186,8 @@ tee_tg6(struct sk_buff *skb, const struct xt_target_param *par)
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 		--iph->hop_limit;
 	}
-	IP6CB(skb)->flags |= IPSKB_REROUTED;
 	if (tee_tg_route6(skb, info))
-		ip6_output(skb);
+		ip6_local_out(skb);
 
 	return XT_CONTINUE;
 }
-- 
1.7.0.2

Re: nf-next: TEE and nesting

[Patrick McHardy]

Jan Engelhardt wrote:
> next on the calendar is the xt_TEE submission.
> 
> 
> The following changes since commit b44672889c11e13e4f4dc0a8ee23f0e64f1e57c6:
>   Jan Engelhardt (1):
>         netfilter: xtables: merge registration structure to NFPROTO_UNSPEC
> 
> are available in the git repository at:
> 
>   git://dev.medozas.de/linux master
> 
> Jan Engelhardt (5):
>       netfilter: ipv6: move POSTROUTING invocation before fragmentation
>       net: ipv6: add IPSKB_REROUTED exclusion to NF_HOOK/POSTROUTING invocation
>       netfilter: xtables: inclusion of xt_TEE
>       netfilter: xtables2: make ip_tables reentrant
>       netfilter: xt_TEE: have cloned packet travel through Xtables too

Please CC netdev since this includes larger changes to the IPv6 code.

nf-next: TEE and nesting

[Jan Engelhardt]

> Hi,
>
> next on the calendar is the xt_TEE submission.
>
>
> The following changes since commit b44672889c11e13e4f4dc0a8ee23f0e64f1e57c6:
>   Jan Engelhardt (1):
>         netfilter: xtables: merge registration structure to NFPROTO_UNSPEC
>
> are available in the git repository at:
>
>   git://dev.medozas.de/linux master
>
> Jan Engelhardt (5):
>       netfilter: ipv6: move POSTROUTING invocation before fragmentation
>       net: ipv6: add IPSKB_REROUTED exclusion to NF_HOOK/POSTROUTING invocation
>       netfilter: xtables: inclusion of xt_TEE
>       netfilter: xtables2: make ip_tables reentrant
>       netfilter: xt_TEE: have cloned packet travel through Xtables too

cc'd netdev due to larger changes to the IPv6 code.

[PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Jan Engelhardt]

Patrick McHardy notes: "We used to invoke IPv4 POST_ROUTING after
fragmentation as well just to defragment the packets in conntrack
immediately afterwards, but that got changed during the
netfilter-ipsec integration. Ideally IPv6 would behave like IPv4."

This patch makes it so. Sending an oversized frame (e.g. `ping6
-s64000 -c1 ::1`) will now show up in POSTROUTING as a single skb
rather than multiple ones.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
---
 net/ipv6/ip6_output.c |   49 +++++++++++++++++++++++--------------------------
 1 files changed, 23 insertions(+), 26 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4535b7a..f314ba4 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -82,22 +82,6 @@ int ip6_local_out(struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(ip6_local_out);
 
-static int ip6_output_finish(struct sk_buff *skb)
-{
-	struct dst_entry *dst = skb_dst(skb);
-
-	if (dst->hh)
-		return neigh_hh_output(dst->hh, skb);
-	else if (dst->neighbour)
-		return dst->neighbour->output(skb);
-
-	IP6_INC_STATS_BH(dev_net(dst->dev),
-			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
-	kfree_skb(skb);
-	return -EINVAL;
-
-}
-
 /* dev_loopback_xmit for use with netfilter. */
 static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
 {
@@ -111,8 +95,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
 	return 0;
 }
 
-
-static int ip6_output2(struct sk_buff *skb)
+static int ip6_finish_output2(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
@@ -150,8 +133,15 @@ static int ip6_output2(struct sk_buff *skb)
 				skb->len);
 	}
 
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, skb->dev,
-		       ip6_output_finish);
+	if (dst->hh)
+		return neigh_hh_output(dst->hh, skb);
+	else if (dst->neighbour)
+		return dst->neighbour->output(skb);
+
+	IP6_INC_STATS_BH(dev_net(dst->dev),
+			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	kfree_skb(skb);
+	return -EINVAL;
 }
 
 static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
@@ -162,21 +152,28 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
 }
 
+static int ip6_finish_output(struct sk_buff *skb)
+{
+	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+				dst_allfrag(skb_dst(skb)))
+		return ip6_fragment(skb, ip6_finish_output2);
+	else
+		return ip6_finish_output2(skb);
+}
+
 int ip6_output(struct sk_buff *skb)
 {
+	struct net_device *dev = skb_dst(skb)->dev;
 	struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 	if (unlikely(idev->cnf.disable_ipv6)) {
-		IP6_INC_STATS(dev_net(skb_dst(skb)->dev), idev,
+		IP6_INC_STATS(dev_net(dev), idev,
 			      IPSTATS_MIB_OUTDISCARDS);
 		kfree_skb(skb);
 		return 0;
 	}
 
-	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
-				dst_allfrag(skb_dst(skb)))
-		return ip6_fragment(skb, ip6_output2);
-	else
-		return ip6_output2(skb);
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev,
+		       ip6_finish_output);
 }
 
 /*
-- 
1.7.0.2

Re: [PATCH 1/5] netfilter: ipv6: move POSTROUTING invocation before fragmentation

[Patrick McHardy]

Jan Engelhardt wrote:
> Patrick McHardy notes: "We used to invoke IPv4 POST_ROUTING after
> fragmentation as well just to defragment the packets in conntrack
> immediately afterwards, but that got changed during the
> netfilter-ipsec integration. Ideally IPv6 would behave like IPv4."
> 
> This patch makes it so. Sending an oversized frame (e.g. `ping6
> -s64000 -c1 ::1`) will now show up in POSTROUTING as a single skb
> rather than multiple ones.

Looks good to me. I'll wait until next week in case anyone
else has comments on this patch.