[PATCH 1/1] netfilter: Add possibility to turn off netfilters defrag per netns

[Hans Schillstrom <hans.schillstrom@ericsson.com>]

In some cases it not desirable to have auto defrag.
Ex. in a cluster where packets can arrive on different blades.
In that case it is possible to use containers (LXC) and send
all fragments to one place where defrag is enabled.

This patch makes it possible to turn off the defrag per network name space,
by setting net.netfilter.nf_conntrack_nodefrag to 1.
Both IPv4 and IPv6 is effected by this sysctl.
Default is 0 which is defrag.

Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
---
 include/net/netns/conntrack.h             |    1 +
 net/ipv4/netfilter/nf_defrag_ipv4.c       |    8 ++++++++
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c |    6 ++++++
 net/netfilter/nf_conntrack_standalone.c   |    8 ++++++++
 4 files changed, 23 insertions(+), 0 deletions(-)

diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 7a911ec..059f7b5 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -26,6 +26,7 @@ struct netns_ct {
 	int			sysctl_tstamp;
 	int			sysctl_checksum;
 	unsigned int		sysctl_log_invalid; /* Log invalid packets */
+	int			sysctl_nodefrag;
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*sysctl_header;
 	struct ctl_table_header	*acct_sysctl_header;
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 9bb1b8a..f4908b3 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -74,6 +74,14 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
 		return NF_ACCEPT;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	/* Check for no defrag options */
+	{
+		const struct net_device *dev = (hooknum == NF_INET_LOCAL_OUT ?
+						out : in);
+
+		if (dev_net(dev)->ct.sysctl_nodefrag)
+			return NF_ACCEPT;
+	}
 #if !defined(CONFIG_NF_NAT) && !defined(CONFIG_NF_NAT_MODULE)
 	/* Previously seen (loopback)?  Ignore.  Do this before
 	   fragment check. */
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index cdd6d04..4b0a05b 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -61,6 +61,12 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
 	struct sk_buff *reasm;
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	/* Check for no defrag options */
+	const struct net_device *dev = (hooknum == NF_INET_LOCAL_OUT ?
+					out : in);
+
+	if (dev_net(dev)->ct.sysctl_nodefrag)
+		return NF_ACCEPT;
 	/* Previously seen (loopback)?	*/
 	if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
 		return NF_ACCEPT;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 885f5ab..95c489f 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -446,6 +446,13 @@ static ctl_table nf_ct_sysctl_table[] = {
 		.extra2		= &log_invalid_proto_max,
 	},
 	{
+		.procname	= "nf_conntrack_nodefrag",
+		.data		= &init_net.ct.sysctl_nodefrag,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
 		.procname	= "nf_conntrack_expect_max",
 		.data		= &nf_ct_expect_max,
 		.maxlen		= sizeof(int),
@@ -493,6 +500,7 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	table[2].data = &net->ct.htable_size;
 	table[3].data = &net->ct.sysctl_checksum;
 	table[4].data = &net->ct.sysctl_log_invalid;
+	table[5].data = &net->ct.sysctl_nodefrag;
 
 	net->ct.sysctl_header = register_net_sysctl_table(net,
 					nf_net_netfilter_sysctl_path, table);
-- 
1.7.2.3