From aaea4ed74d71dda1cf2cc19c206552d537201452 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Sat, 7 Jul 2012 20:32:12 +0300
Subject: [PATCH 01/10] ipvs: ip_vs_ftp depends on nf_conntrack_ftp helper

	The FTP application indirectly depends on the
nf_conntrack_ftp helper for proper NAT support. If the
module is not loaded, IPVS can resize the packets for the
command connection, eg. PASV response but the SEQ adjustment
logic in ipv4_confirm is not called without helper.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index f9871385a65e..8b2cffdfdd99 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -250,7 +250,8 @@ comment 'IPVS application helper'
 
 config	IP_VS_FTP
   	tristate "FTP protocol helper"
-        depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT
+	depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT && \
+		NF_CONNTRACK_FTP
 	select IP_VS_NFCT
 	---help---
 	  FTP is a protocol that transfers IP address and/or port number in

From be97fdb5fbcc828240c51769cd28cba609158703 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Thu, 12 Jul 2012 23:06:20 +0300
Subject: [PATCH 02/10] ipvs: generalize app registration in netns

	Get rid of the ftp_app pointer and allow applications
to be registered without adding fields in the netns_ipvs structure.

v2: fix coding style as suggested by Pablo Neira Ayuso <pablo@netfilter.org>

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  5 ++-
 net/netfilter/ipvs/ip_vs_app.c | 58 ++++++++++++++++++++++++----------
 net/netfilter/ipvs/ip_vs_ftp.c | 21 +++---------
 3 files changed, 49 insertions(+), 35 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 95374d1696a1..4b8f18ff4789 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -808,8 +808,6 @@ struct netns_ipvs {
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
 	/* ip_vs_app */
 	struct list_head	app_list;
-	/* ip_vs_ftp */
-	struct ip_vs_app	*ftp_app;
 	/* ip_vs_proto */
 	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
 	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
@@ -1179,7 +1177,8 @@ extern void ip_vs_service_net_cleanup(struct net *net);
  *      (from ip_vs_app.c)
  */
 #define IP_VS_APP_MAX_PORTS  8
-extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app);
+extern struct ip_vs_app *register_ip_vs_app(struct net *net,
+					    struct ip_vs_app *app);
 extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app);
 extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
 extern void ip_vs_unbind_app(struct ip_vs_conn *cp);
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 64f9e8f13207..9713e6e86d47 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -180,22 +180,38 @@ register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
 }
 
 
-/*
- *	ip_vs_app registration routine
- */
-int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
+/* Register application for netns */
+struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
-	/* increase the module use count */
-	ip_vs_use_count_inc();
+	struct ip_vs_app *a;
+	int err = 0;
+
+	if (!ipvs)
+		return ERR_PTR(-ENOENT);
 
 	mutex_lock(&__ip_vs_app_mutex);
 
-	list_add(&app->a_list, &ipvs->app_list);
+	list_for_each_entry(a, &ipvs->app_list, a_list) {
+		if (!strcmp(app->name, a->name)) {
+			err = -EEXIST;
+			goto out_unlock;
+		}
+	}
+	a = kmemdup(app, sizeof(*app), GFP_KERNEL);
+	if (!a) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+	INIT_LIST_HEAD(&a->incs_list);
+	list_add(&a->a_list, &ipvs->app_list);
+	/* increase the module use count */
+	ip_vs_use_count_inc();
 
+out_unlock:
 	mutex_unlock(&__ip_vs_app_mutex);
 
-	return 0;
+	return err ? ERR_PTR(err) : a;
 }
 
 
@@ -205,20 +221,29 @@ int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
  */
 void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
-	struct ip_vs_app *inc, *nxt;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_app *a, *anxt, *inc, *nxt;
+
+	if (!ipvs)
+		return;
 
 	mutex_lock(&__ip_vs_app_mutex);
 
-	list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) {
-		ip_vs_app_inc_release(net, inc);
+	list_for_each_entry_safe(a, anxt, &ipvs->app_list, a_list) {
+		if (app && strcmp(app->name, a->name))
+			continue;
+		list_for_each_entry_safe(inc, nxt, &a->incs_list, a_list) {
+			ip_vs_app_inc_release(net, inc);
+		}
+
+		list_del(&a->a_list);
+		kfree(a);
+
+		/* decrease the module use count */
+		ip_vs_use_count_dec();
 	}
 
-	list_del(&app->a_list);
-
 	mutex_unlock(&__ip_vs_app_mutex);
-
-	/* decrease the module use count */
-	ip_vs_use_count_dec();
 }
 
 
@@ -586,5 +611,6 @@ int __net_init ip_vs_app_net_init(struct net *net)
 
 void __net_exit ip_vs_app_net_cleanup(struct net *net)
 {
+	unregister_ip_vs_app(net, NULL /* all */);
 	proc_net_remove(net, "ip_vs_app");
 }
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index b20b29c903ef..ad70b7e4ac4a 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -441,16 +441,10 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 
 	if (!ipvs)
 		return -ENOENT;
-	app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL);
-	if (!app)
-		return -ENOMEM;
-	INIT_LIST_HEAD(&app->a_list);
-	INIT_LIST_HEAD(&app->incs_list);
-	ipvs->ftp_app = app;
 
-	ret = register_ip_vs_app(net, app);
-	if (ret)
-		goto err_exit;
+	app = register_ip_vs_app(net, &ip_vs_ftp);
+	if (IS_ERR(app))
+		return PTR_ERR(app);
 
 	for (i = 0; i < ports_count; i++) {
 		if (!ports[i])
@@ -464,9 +458,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 	return 0;
 
 err_unreg:
-	unregister_ip_vs_app(net, app);
-err_exit:
-	kfree(ipvs->ftp_app);
+	unregister_ip_vs_app(net, &ip_vs_ftp);
 	return ret;
 }
 /*
@@ -474,10 +466,7 @@ err_exit:
  */
 static void __ip_vs_ftp_exit(struct net *net)
 {
-	struct netns_ipvs *ipvs = net_ipvs(net);
-
-	unregister_ip_vs_app(net, ipvs->ftp_app);
-	kfree(ipvs->ftp_app);
+	unregister_ip_vs_app(net, &ip_vs_ftp);
 }
 
 static struct pernet_operations ip_vs_ftp_ops = {

From 2b2d280817bd576e97ccd243b9b3a344d11ddd11 Mon Sep 17 00:00:00 2001
From: Claudiu Ghioc <claudiughioc@gmail.com>
Date: Wed, 18 Jul 2012 12:10:22 +0300
Subject: [PATCH 03/10] ipvs: fixed sparse warning

Removed the following sparse warnings, wether CONFIG_SYSCTL
is defined or not:
*       warning: symbol 'ip_vs_control_net_init_sysctl' was not
	declared. Should it be static?
*       warning: symbol 'ip_vs_control_net_cleanup_sysctl' was
	not declared. Should it be static?

Signed-off-by: Claudiu Ghioc <claudiu.ghioc@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 84444dda194b..d6d5ccabe067 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3675,7 +3675,7 @@ static void ip_vs_genl_unregister(void)
  * per netns intit/exit func.
  */
 #ifdef CONFIG_SYSCTL
-int __net_init ip_vs_control_net_init_sysctl(struct net *net)
+static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 {
 	int idx;
 	struct netns_ipvs *ipvs = net_ipvs(net);
@@ -3743,7 +3743,7 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 	return 0;
 }
 
-void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
+static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -3754,8 +3754,8 @@ void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
 
 #else
 
-int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; }
-void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { }
+static int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; }
+static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { }
 
 #endif
 

From f2edb9f7706dcb2c0d9a362b2ba849efe3a97f5e Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 20 Jul 2012 11:59:52 +0300
Subject: [PATCH 04/10] ipvs: implement passive PMTUD for IPIP packets

	IPVS is missing the logic to update PMTU in routing
for its IPIP packets. We monitor the dst_mtu and can return
FRAG_NEEDED messages but if the tunneled packets get ICMP
error we can not rely on other traffic to save the lowest
MTU.

	The following patch adds ICMP handling for IPIP
packets in incoming direction, from some remote host to
our local IP used as saddr in the outer header. By this
way we can forward any related ICMP traffic if it is for IPVS
TUN connection. For the special case of PMTUD we update the
routing and if client requested DF we can forward the
error.

	To properly update the routing we have to bind
the cached route (dest->dst_cache) to the selected saddr
because ipv4_update_pmtu uses saddr for dst lookup.
Add IP_VS_RT_MODE_CONNECT flag to force such binding with
second route.

	Update ip_vs_tunnel_xmit to provide IP_VS_RT_MODE_CONNECT
and change the code to copy DF. For now we prefer not to
force PMTU discovery (outer DF=1) because we don't have
configuration option to enable or disable PMTUD. As we
do not keep any packets to resend, we prefer not to
play games with packets without DF bit because the sender
is not informed when they are rejected.

	Also, change ops->update_pmtu to be called only
for local clients because there is no point to update
MTU for input routes, in our case skb->dst->dev is lo.
It seems the code is copied from ipip.c where the skb
dst points to tunnel device.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_core.c | 76 +++++++++++++++++++++++++++++--
 net/netfilter/ipvs/ip_vs_xmit.c | 79 +++++++++++++++++++++++----------
 2 files changed, 128 insertions(+), 27 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b54eccef40b5..58918e20f9d5 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1303,7 +1303,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
 	struct ip_vs_proto_data *pd;
-	unsigned int offset, ihl, verdict;
+	unsigned int offset, offset2, ihl, verdict;
+	bool ipip;
 
 	*related = 1;
 
@@ -1345,6 +1346,21 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	net = skb_net(skb);
 
+	/* Special case for errors for IPIP packets */
+	ipip = false;
+	if (cih->protocol == IPPROTO_IPIP) {
+		if (unlikely(cih->frag_off & htons(IP_OFFSET)))
+			return NF_ACCEPT;
+		/* Error for our IPIP must arrive at LOCAL_IN */
+		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
+			return NF_ACCEPT;
+		offset += cih->ihl * 4;
+		cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
+		if (cih == NULL)
+			return NF_ACCEPT; /* The packet looks wrong, ignore */
+		ipip = true;
+	}
+
 	pd = ip_vs_proto_data_get(net, cih->protocol);
 	if (!pd)
 		return NF_ACCEPT;
@@ -1358,11 +1374,14 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
 		      "Checking incoming ICMP for");
 
+	offset2 = offset;
 	offset += cih->ihl * 4;
 
 	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
-	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1);
+	/* The embedded headers contain source and dest in reverse order.
+	 * For IPIP this is error for request, not for reply.
+	 */
+	cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, ipip ? 0 : 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -1376,6 +1395,57 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 		goto out;
 	}
 
+	if (ipip) {
+		__be32 info = ic->un.gateway;
+
+		/* Update the MTU */
+		if (ic->type == ICMP_DEST_UNREACH &&
+		    ic->code == ICMP_FRAG_NEEDED) {
+			struct ip_vs_dest *dest = cp->dest;
+			u32 mtu = ntohs(ic->un.frag.mtu);
+
+			/* Strip outer IP and ICMP, go to IPIP header */
+			__skb_pull(skb, ihl + sizeof(_icmph));
+			offset2 -= ihl + sizeof(_icmph);
+			skb_reset_network_header(skb);
+			IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
+				&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
+			rcu_read_lock();
+			ipv4_update_pmtu(skb, dev_net(skb->dev),
+					 mtu, 0, 0, 0, 0);
+			rcu_read_unlock();
+			/* Client uses PMTUD? */
+			if (!(cih->frag_off & htons(IP_DF)))
+				goto ignore_ipip;
+			/* Prefer the resulting PMTU */
+			if (dest) {
+				spin_lock(&dest->dst_lock);
+				if (dest->dst_cache)
+					mtu = dst_mtu(dest->dst_cache);
+				spin_unlock(&dest->dst_lock);
+			}
+			if (mtu > 68 + sizeof(struct iphdr))
+				mtu -= sizeof(struct iphdr);
+			info = htonl(mtu);
+		}
+		/* Strip outer IP, ICMP and IPIP, go to IP header of
+		 * original request.
+		 */
+		__skb_pull(skb, offset2);
+		skb_reset_network_header(skb);
+		IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
+			&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
+			ic->type, ic->code, ntohl(info));
+		icmp_send(skb, ic->type, ic->code, info);
+		/* ICMP can be shorter but anyways, account it */
+		ip_vs_out_stats(cp, skb);
+
+ignore_ipip:
+		consume_skb(skb);
+		verdict = NF_STOLEN;
+		goto out;
+	}
+
 	/* do the statistics and put it back */
 	ip_vs_in_stats(cp, skb);
 	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 65b616ae1716..c2275ba048e9 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -49,6 +49,7 @@ enum {
 	IP_VS_RT_MODE_RDR	= 4, /* Allow redirect from remote daddr to
 				      * local
 				      */
+	IP_VS_RT_MODE_CONNECT	= 8, /* Always bind route to saddr */
 };
 
 /*
@@ -84,6 +85,42 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
 	return dst;
 }
 
+/* Get route to daddr, update *saddr, optionally bind route to saddr */
+static struct rtable *do_output_route4(struct net *net, __be32 daddr,
+				       u32 rtos, int rt_mode, __be32 *saddr)
+{
+	struct flowi4 fl4;
+	struct rtable *rt;
+	int loop = 0;
+
+	memset(&fl4, 0, sizeof(fl4));
+	fl4.daddr = daddr;
+	fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
+	fl4.flowi4_tos = rtos;
+
+retry:
+	rt = ip_route_output_key(net, &fl4);
+	if (IS_ERR(rt)) {
+		/* Invalid saddr ? */
+		if (PTR_ERR(rt) == -EINVAL && *saddr &&
+		    rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
+			*saddr = 0;
+			flowi4_update_output(&fl4, 0, rtos, daddr, 0);
+			goto retry;
+		}
+		IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
+		return NULL;
+	} else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
+		ip_rt_put(rt);
+		*saddr = fl4.saddr;
+		flowi4_update_output(&fl4, 0, rtos, daddr, fl4.saddr);
+		loop++;
+		goto retry;
+	}
+	*saddr = fl4.saddr;
+	return rt;
+}
+
 /* Get route to destination or remote server */
 static struct rtable *
 __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
@@ -98,20 +135,13 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 		spin_lock(&dest->dst_lock);
 		if (!(rt = (struct rtable *)
 		      __ip_vs_dst_check(dest, rtos))) {
-			struct flowi4 fl4;
-
-			memset(&fl4, 0, sizeof(fl4));
-			fl4.daddr = dest->addr.ip;
-			fl4.flowi4_tos = rtos;
-			rt = ip_route_output_key(net, &fl4);
-			if (IS_ERR(rt)) {
+			rt = do_output_route4(net, dest->addr.ip, rtos,
+					      rt_mode, &dest->dst_saddr.ip);
+			if (!rt) {
 				spin_unlock(&dest->dst_lock);
-				IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
-					     &dest->addr.ip);
 				return NULL;
 			}
 			__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
-			dest->dst_saddr.ip = fl4.saddr;
 			IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, "
 				  "rtos=%X\n",
 				  &dest->addr.ip, &dest->dst_saddr.ip,
@@ -122,19 +152,17 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 			*ret_saddr = dest->dst_saddr.ip;
 		spin_unlock(&dest->dst_lock);
 	} else {
-		struct flowi4 fl4;
+		__be32 saddr = htonl(INADDR_ANY);
 
-		memset(&fl4, 0, sizeof(fl4));
-		fl4.daddr = daddr;
-		fl4.flowi4_tos = rtos;
-		rt = ip_route_output_key(net, &fl4);
-		if (IS_ERR(rt)) {
-			IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
-				     &daddr);
+		/* For such unconfigured boxes avoid many route lookups
+		 * for performance reasons because we do not remember saddr
+		 */
+		rt_mode &= ~IP_VS_RT_MODE_CONNECT;
+		rt = do_output_route4(net, daddr, rtos, rt_mode, &saddr);
+		if (!rt)
 			return NULL;
-		}
 		if (ret_saddr)
-			*ret_saddr = fl4.saddr;
+			*ret_saddr = saddr;
 	}
 
 	local = rt->rt_flags & RTCF_LOCAL;
@@ -331,6 +359,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
 	old_dst = dest->dst_cache;
 	dest->dst_cache = NULL;
 	dst_release(old_dst);
+	dest->dst_saddr.ip = 0;
 }
 
 #define IP_VS_XMIT_TUNNEL(skb, cp)				\
@@ -771,7 +800,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	struct net_device *tdev;		/* Device to other host */
 	struct iphdr  *old_iph = ip_hdr(skb);
 	u8     tos = old_iph->tos;
-	__be16 df = old_iph->frag_off;
+	__be16 df;
 	struct iphdr  *iph;			/* Our new IP header */
 	unsigned int max_headroom;		/* The extra header space needed */
 	int    mtu;
@@ -781,7 +810,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
 				      RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
-						   IP_VS_RT_MODE_NON_LOCAL,
+						   IP_VS_RT_MODE_NON_LOCAL |
+						   IP_VS_RT_MODE_CONNECT,
 						   &saddr)))
 		goto tx_error_icmp;
 	if (rt->rt_flags & RTCF_LOCAL) {
@@ -796,10 +826,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
 		goto tx_error_put;
 	}
-	if (skb_dst(skb))
+	if (rt_is_output_route(skb_rtable(skb)))
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
-	df |= (old_iph->frag_off & htons(IP_DF));
+	/* Copy DF, reset fragment offset and MF */
+	df = old_iph->frag_off & htons(IP_DF);
 
 	if ((old_iph->frag_off & htons(IP_DF) &&
 	    mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {

From 3654e61137db891f5312e6dd813b961484b5fdf3 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 20 Jul 2012 11:59:53 +0300
Subject: [PATCH 05/10] ipvs: add pmtu_disc option to disable IP DF for TUN
 packets

	Disabling PMTU discovery can increase the output packet
rate but some users have enough resources and prefer to fragment
than to drop traffic. By default, we copy the DF bit but if
pmtu_disc is disabled we do not send FRAG_NEEDED messages anymore.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             | 11 +++++++++++
 net/netfilter/ipvs/ip_vs_ctl.c  |  8 ++++++++
 net/netfilter/ipvs/ip_vs_xmit.c |  6 +++---
 3 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4b8f18ff4789..ee75ccdf5188 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -888,6 +888,7 @@ struct netns_ipvs {
 	unsigned int		sysctl_sync_refresh_period;
 	int			sysctl_sync_retries;
 	int			sysctl_nat_icmp_send;
+	int			sysctl_pmtu_disc;
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
@@ -974,6 +975,11 @@ static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
 	return ipvs->sysctl_sync_sock_size;
 }
 
+static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs)
+{
+	return ipvs->sysctl_pmtu_disc;
+}
+
 #else
 
 static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -1016,6 +1022,11 @@ static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
 	return 0;
 }
 
+static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs)
+{
+	return 1;
+}
+
 #endif
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index d6d5ccabe067..03d3fc6d9d64 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1801,6 +1801,12 @@ static struct ctl_table vs_vars[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "pmtu_disc",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #ifdef CONFIG_IP_VS_DEBUG
 	{
 		.procname	= "debug_level",
@@ -3726,6 +3732,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 	ipvs->sysctl_sync_retries = clamp_t(int, DEFAULT_SYNC_RETRIES, 0, 3);
 	tbl[idx++].data = &ipvs->sysctl_sync_retries;
 	tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
+	ipvs->sysctl_pmtu_disc = 1;
+	tbl[idx++].data = &ipvs->sysctl_pmtu_disc;
 
 
 	ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index c2275ba048e9..543a554008af 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -795,6 +795,7 @@ int
 ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  struct ip_vs_protocol *pp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
 	struct rtable *rt;			/* Route to the other host */
 	__be32 saddr;				/* Source for tunnel */
 	struct net_device *tdev;		/* Device to other host */
@@ -830,10 +831,9 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
 	/* Copy DF, reset fragment offset and MF */
-	df = old_iph->frag_off & htons(IP_DF);
+	df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
 
-	if ((old_iph->frag_off & htons(IP_DF) &&
-	    mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
+	if (df && mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb)) {
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;

From 19e303d67dc2e68a7f14b0baf7949195d7327145 Mon Sep 17 00:00:00 2001
From: Wu Fengguang <fengguang.wu@intel.com>
Date: Sat, 28 Jul 2012 14:45:50 +0000
Subject: [PATCH 06/10] netfilter: PTR_RET can be used

This quiets the coccinelle warnings:

net/bridge/netfilter/ebtable_filter.c:107:1-3: WARNING: PTR_RET can be used
net/bridge/netfilter/ebtable_nat.c:107:1-3: WARNING: PTR_RET can be used
net/ipv6/netfilter/ip6table_filter.c:65:1-3: WARNING: PTR_RET can be used
net/ipv6/netfilter/ip6table_mangle.c:100:1-3: WARNING: PTR_RET can be used
net/ipv6/netfilter/ip6table_raw.c:44:1-3: WARNING: PTR_RET can be used
net/ipv6/netfilter/ip6table_security.c:62:1-3: WARNING: PTR_RET can be used
net/ipv4/netfilter/iptable_filter.c:72:1-3: WARNING: PTR_RET can be used
net/ipv4/netfilter/iptable_mangle.c:107:1-3: WARNING: PTR_RET can be used
net/ipv4/netfilter/iptable_raw.c:51:1-3: WARNING: PTR_RET can be used
net/ipv4/netfilter/iptable_security.c:70:1-3: WARNING: PTR_RET can be used

Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/bridge/netfilter/ebtable_filter.c  | 4 +---
 net/bridge/netfilter/ebtable_nat.c     | 4 +---
 net/ipv4/netfilter/iptable_filter.c    | 4 +---
 net/ipv4/netfilter/iptable_mangle.c    | 4 +---
 net/ipv4/netfilter/iptable_raw.c       | 4 +---
 net/ipv4/netfilter/iptable_security.c  | 5 +----
 net/ipv6/netfilter/ip6table_filter.c   | 4 +---
 net/ipv6/netfilter/ip6table_mangle.c   | 4 +---
 net/ipv6/netfilter/ip6table_raw.c      | 4 +---
 net/ipv6/netfilter/ip6table_security.c | 5 +----
 10 files changed, 10 insertions(+), 32 deletions(-)

diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 42e6bd094574..3c2e9dced9e0 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -100,9 +100,7 @@ static struct nf_hook_ops ebt_ops_filter[] __read_mostly = {
 static int __net_init frame_filter_net_init(struct net *net)
 {
 	net->xt.frame_filter = ebt_register_table(net, &frame_filter);
-	if (IS_ERR(net->xt.frame_filter))
-		return PTR_ERR(net->xt.frame_filter);
-	return 0;
+	return PTR_RET(net->xt.frame_filter);
 }
 
 static void __net_exit frame_filter_net_exit(struct net *net)
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 6dc2f878ae05..10871bc77908 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -100,9 +100,7 @@ static struct nf_hook_ops ebt_ops_nat[] __read_mostly = {
 static int __net_init frame_nat_net_init(struct net *net)
 {
 	net->xt.frame_nat = ebt_register_table(net, &frame_nat);
-	if (IS_ERR(net->xt.frame_nat))
-		return PTR_ERR(net->xt.frame_nat);
-	return 0;
+	return PTR_RET(net->xt.frame_nat);
 }
 
 static void __net_exit frame_nat_net_exit(struct net *net)
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index 851acec852d2..d20cc374025c 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -69,9 +69,7 @@ static int __net_init iptable_filter_net_init(struct net *net)
 	net->ipv4.iptable_filter =
 		ipt_register_table(net, &packet_filter, repl);
 	kfree(repl);
-	if (IS_ERR(net->ipv4.iptable_filter))
-		return PTR_ERR(net->ipv4.iptable_filter);
-	return 0;
+	return PTR_RET(net->ipv4.iptable_filter);
 }
 
 static void __net_exit iptable_filter_net_exit(struct net *net)
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index aef5d1fbe77d..f38b94288cf5 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -104,9 +104,7 @@ static int __net_init iptable_mangle_net_init(struct net *net)
 	net->ipv4.iptable_mangle =
 		ipt_register_table(net, &packet_mangler, repl);
 	kfree(repl);
-	if (IS_ERR(net->ipv4.iptable_mangle))
-		return PTR_ERR(net->ipv4.iptable_mangle);
-	return 0;
+	return PTR_RET(net->ipv4.iptable_mangle);
 }
 
 static void __net_exit iptable_mangle_net_exit(struct net *net)
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 07fb710cd722..b21e2191e2f5 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -48,9 +48,7 @@ static int __net_init iptable_raw_net_init(struct net *net)
 	net->ipv4.iptable_raw =
 		ipt_register_table(net, &packet_raw, repl);
 	kfree(repl);
-	if (IS_ERR(net->ipv4.iptable_raw))
-		return PTR_ERR(net->ipv4.iptable_raw);
-	return 0;
+	return PTR_RET(net->ipv4.iptable_raw);
 }
 
 static void __net_exit iptable_raw_net_exit(struct net *net)
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index be45bdc4c602..b283d8e2601a 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -66,10 +66,7 @@ static int __net_init iptable_security_net_init(struct net *net)
 	net->ipv4.iptable_security =
 		ipt_register_table(net, &security_table, repl);
 	kfree(repl);
-	if (IS_ERR(net->ipv4.iptable_security))
-		return PTR_ERR(net->ipv4.iptable_security);
-
-	return 0;
+	return PTR_RET(net->ipv4.iptable_security);
 }
 
 static void __net_exit iptable_security_net_exit(struct net *net)
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index 325e59a0224f..beb5777d2043 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -61,9 +61,7 @@ static int __net_init ip6table_filter_net_init(struct net *net)
 	net->ipv6.ip6table_filter =
 		ip6t_register_table(net, &packet_filter, repl);
 	kfree(repl);
-	if (IS_ERR(net->ipv6.ip6table_filter))
-		return PTR_ERR(net->ipv6.ip6table_filter);
-	return 0;
+	return PTR_RET(net->ipv6.ip6table_filter);
 }
 
 static void __net_exit ip6table_filter_net_exit(struct net *net)
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 4d782405f125..7431121b87de 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -97,9 +97,7 @@ static int __net_init ip6table_mangle_net_init(struct net *net)
 	net->ipv6.ip6table_mangle =
 		ip6t_register_table(net, &packet_mangler, repl);
 	kfree(repl);
-	if (IS_ERR(net->ipv6.ip6table_mangle))
-		return PTR_ERR(net->ipv6.ip6table_mangle);
-	return 0;
+	return PTR_RET(net->ipv6.ip6table_mangle);
 }
 
 static void __net_exit ip6table_mangle_net_exit(struct net *net)
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 5b9926a011bd..60d1bddff7a0 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -40,9 +40,7 @@ static int __net_init ip6table_raw_net_init(struct net *net)
 	net->ipv6.ip6table_raw =
 		ip6t_register_table(net, &packet_raw, repl);
 	kfree(repl);
-	if (IS_ERR(net->ipv6.ip6table_raw))
-		return PTR_ERR(net->ipv6.ip6table_raw);
-	return 0;
+	return PTR_RET(net->ipv6.ip6table_raw);
 }
 
 static void __net_exit ip6table_raw_net_exit(struct net *net)
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index 91aa2b4d83c9..db155351339c 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -58,10 +58,7 @@ static int __net_init ip6table_security_net_init(struct net *net)
 	net->ipv6.ip6table_security =
 		ip6t_register_table(net, &security_table, repl);
 	kfree(repl);
-	if (IS_ERR(net->ipv6.ip6table_security))
-		return PTR_ERR(net->ipv6.ip6table_security);
-
-	return 0;
+	return PTR_RET(net->ipv6.ip6table_security);
 }
 
 static void __net_exit ip6table_security_net_exit(struct net *net)

From fe31d1a8605f020eee859375fdd877186e01b804 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Sun, 19 Aug 2012 10:16:09 +0000
Subject: [PATCH 07/10] netfilter: sparse endian fixes

Fix a couple of endian annotation in net/netfilter:

net/netfilter/nfnetlink_acct.c:82:30: warning: cast to restricted __be64
net/netfilter/nfnetlink_acct.c:86:30: warning: cast to restricted __be64
net/netfilter/nfnetlink_cthelper.c:77:28: warning: cast to restricted __be16
net/netfilter/xt_NFQUEUE.c:46:16: warning: restricted __be32 degrades to integer
net/netfilter/xt_NFQUEUE.c:60:34: warning: restricted __be32 degrades to integer
net/netfilter/xt_NFQUEUE.c:68:34: warning: restricted __be32 degrades to integer
net/netfilter/xt_osf.c:272:55: warning: cast to restricted __be16

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nfnetlink_acct.c     | 4 ++--
 net/netfilter/nfnetlink_cthelper.c | 2 +-
 net/netfilter/xt_NFQUEUE.c         | 8 +++++---
 net/netfilter/xt_osf.c             | 2 +-
 4 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index b2e7310ca0b8..d7ec92879071 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -79,11 +79,11 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb,
 
 	if (tb[NFACCT_BYTES]) {
 		atomic64_set(&nfacct->bytes,
-			     be64_to_cpu(nla_get_u64(tb[NFACCT_BYTES])));
+			     be64_to_cpu(nla_get_be64(tb[NFACCT_BYTES])));
 	}
 	if (tb[NFACCT_PKTS]) {
 		atomic64_set(&nfacct->pkts,
-			     be64_to_cpu(nla_get_u64(tb[NFACCT_PKTS])));
+			     be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS])));
 	}
 	atomic_set(&nfacct->refcnt, 1);
 	list_add_tail_rcu(&nfacct->head, &nfnl_acct_list);
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index d6836193d479..32a1ba3f3e27 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -74,7 +74,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 	if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
 		return -EINVAL;
 
-	tuple->src.l3num = ntohs(nla_get_u16(tb[NFCTH_TUPLE_L3PROTONUM]));
+	tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM]));
 	tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
 
 	return 0;
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 7babe7d68716..817f9e9f2b16 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -43,7 +43,7 @@ static u32 hash_v4(const struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 
 	/* packets in either direction go into same queue */
-	if (iph->saddr < iph->daddr)
+	if ((__force u32)iph->saddr < (__force u32)iph->daddr)
 		return jhash_3words((__force u32)iph->saddr,
 			(__force u32)iph->daddr, iph->protocol, jhash_initval);
 
@@ -57,7 +57,8 @@ static u32 hash_v6(const struct sk_buff *skb)
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	u32 a, b, c;
 
-	if (ip6h->saddr.s6_addr32[3] < ip6h->daddr.s6_addr32[3]) {
+	if ((__force u32)ip6h->saddr.s6_addr32[3] <
+	    (__force u32)ip6h->daddr.s6_addr32[3]) {
 		a = (__force u32) ip6h->saddr.s6_addr32[3];
 		b = (__force u32) ip6h->daddr.s6_addr32[3];
 	} else {
@@ -65,7 +66,8 @@ static u32 hash_v6(const struct sk_buff *skb)
 		a = (__force u32) ip6h->daddr.s6_addr32[3];
 	}
 
-	if (ip6h->saddr.s6_addr32[1] < ip6h->daddr.s6_addr32[1])
+	if ((__force u32)ip6h->saddr.s6_addr32[1] <
+	    (__force u32)ip6h->daddr.s6_addr32[1])
 		c = (__force u32) ip6h->saddr.s6_addr32[1];
 	else
 		c = (__force u32) ip6h->daddr.s6_addr32[1];
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index 846f895cb656..a5e673d32bda 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -269,7 +269,7 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
 						mss <<= 8;
 						mss |= optp[2];
 
-						mss = ntohs(mss);
+						mss = ntohs((__force __be16)mss);
 						break;
 					case OSFOPT_TS:
 						loop_cont = 1;

From 2834a6386b86a5dd20380aadb01897c525448aa7 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Sun, 19 Aug 2012 10:16:10 +0000
Subject: [PATCH 08/10] netfilter: nf_conntrack: remove unnecessary RTNL
 locking

Locking the rtnl was added to nf_conntrack_l{3,4}_proto_unregister()
for walking the network namespace list. This is not done anymore since
we have proper namespace support in the protocols now, so we don't
need to take the RTNL anymore.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_proto.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 0dc63854390f..51e928db48c8 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -21,7 +21,6 @@
 #include <linux/notifier.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
-#include <linux/rtnetlink.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
@@ -294,9 +293,7 @@ void nf_conntrack_l3proto_unregister(struct net *net,
 	nf_ct_l3proto_unregister_sysctl(net, proto);
 
 	/* Remove all contrack entries for this protocol */
-	rtnl_lock();
 	nf_ct_iterate_cleanup(net, kill_l3proto, proto);
-	rtnl_unlock();
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_unregister);
 
@@ -502,9 +499,7 @@ void nf_conntrack_l4proto_unregister(struct net *net,
 	nf_ct_l4proto_unregister_sysctl(net, pn, l4proto);
 
 	/* Remove all contrack entries for this protocol */
-	rtnl_lock();
 	nf_ct_iterate_cleanup(net, kill_l4proto, l4proto);
-	rtnl_unlock();
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_unregister);
 

From 6705e86724f1ac83394592be7dbfc0c07ac25aa2 Mon Sep 17 00:00:00 2001
From: Michael Wang <wangyun@linux.vnet.ibm.com>
Date: Thu, 16 Aug 2012 18:33:39 +0000
Subject: [PATCH 09/10] netfilter: replace list_for_each_continue_rcu with new
 interface

This patch replaces list_for_each_continue_rcu() with
list_for_each_entry_continue_rcu() to allow removing
list_for_each_continue_rcu().

Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/core.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 0bc6b60db4df..8f4b0b2b6f80 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -131,14 +131,13 @@ unsigned int nf_iterate(struct list_head *head,
 			int hook_thresh)
 {
 	unsigned int verdict;
+	struct nf_hook_ops *elem = list_entry_rcu(*i, struct nf_hook_ops, list);
 
 	/*
 	 * The caller must not block between calls to this
 	 * function because of risk of continuing from deleted element.
 	 */
-	list_for_each_continue_rcu(*i, head) {
-		struct nf_hook_ops *elem = (struct nf_hook_ops *)*i;
-
+	list_for_each_entry_continue_rcu(elem, head, list) {
 		if (hook_thresh > elem->priority)
 			continue;
 
@@ -155,11 +154,14 @@ repeat:
 				continue;
 			}
 #endif
-			if (verdict != NF_REPEAT)
+			if (verdict != NF_REPEAT) {
+				*i = &elem->list;
 				return verdict;
+			}
 			goto repeat;
 		}
 	}
+	*i = &elem->list;
 	return NF_ACCEPT;
 }
 

From 90efbed18a30d78145419cdbd44f9ec152efeb16 Mon Sep 17 00:00:00 2001
From: Jean Sacren <sakiwit@gmail.com>
Date: Sun, 19 Aug 2012 15:11:32 +0000
Subject: [PATCH 10/10] netfilter: remove unnecessary goto statement for error
 recovery

Usually it's a good practice to use goto statement for error recovery
when initializing the module. This approach could be an overkill if:

 1) there is only one fail case;
 2) success and failure use the same return statement.

For a cleaner approach, remove the unnecessary goto statement and
directly implement error recovery.

Signed-off-by: Jean Sacren <sakiwit@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/iptable_filter.c | 6 +-----
 net/ipv4/netfilter/iptable_mangle.c | 6 +-----
 net/ipv4/netfilter/iptable_raw.c    | 6 +-----
 3 files changed, 3 insertions(+), 15 deletions(-)

diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index d20cc374025c..6b3da5cf54e9 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -94,14 +94,10 @@ static int __init iptable_filter_init(void)
 	filter_ops = xt_hook_link(&packet_filter, iptable_filter_hook);
 	if (IS_ERR(filter_ops)) {
 		ret = PTR_ERR(filter_ops);
-		goto cleanup_table;
+		unregister_pernet_subsys(&iptable_filter_net_ops);
 	}
 
 	return ret;
-
- cleanup_table:
-	unregister_pernet_subsys(&iptable_filter_net_ops);
-	return ret;
 }
 
 static void __exit iptable_filter_fini(void)
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index f38b94288cf5..85d88f206447 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -129,14 +129,10 @@ static int __init iptable_mangle_init(void)
 	mangle_ops = xt_hook_link(&packet_mangler, iptable_mangle_hook);
 	if (IS_ERR(mangle_ops)) {
 		ret = PTR_ERR(mangle_ops);
-		goto cleanup_table;
+		unregister_pernet_subsys(&iptable_mangle_net_ops);
 	}
 
 	return ret;
-
- cleanup_table:
-	unregister_pernet_subsys(&iptable_mangle_net_ops);
-	return ret;
 }
 
 static void __exit iptable_mangle_fini(void)
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index b21e2191e2f5..03d9696d3c6e 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -73,14 +73,10 @@ static int __init iptable_raw_init(void)
 	rawtable_ops = xt_hook_link(&packet_raw, iptable_raw_hook);
 	if (IS_ERR(rawtable_ops)) {
 		ret = PTR_ERR(rawtable_ops);
-		goto cleanup_table;
+		unregister_pernet_subsys(&iptable_raw_net_ops);
 	}
 
 	return ret;
-
- cleanup_table:
-	unregister_pernet_subsys(&iptable_raw_net_ops);
-	return ret;
 }
 
 static void __exit iptable_raw_fini(void)