After this patch none of the netlink callback support anything
except the initial network namespace but the rtnetlink infrastructure
now handles multiple network namespaces.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 include/linux/rtnetlink.h   |    8 ++--
 include/net/net_namespace.h |    3 +
 net/bridge/br_netlink.c     |    4 +-
 net/core/fib_rules.c        |    4 +-
 net/core/neighbour.c        |    4 +-
 net/core/rtnetlink.c        |   96 +++++++++++++++++++++++++++++++++++++------
 net/decnet/dn_dev.c         |    4 +-
 net/decnet/dn_route.c       |    2 +-
 net/decnet/dn_table.c       |    4 +-
 net/ipv4/devinet.c          |    4 +-
 net/ipv4/fib_semantics.c    |    4 +-
 net/ipv4/ipmr.c             |    4 +-
 net/ipv4/route.c            |    2 +-
 net/ipv6/addrconf.c         |   14 +++---
 net/ipv6/route.c            |    6 +-
 net/sched/act_api.c         |    8 ++--
 net/sched/cls_api.c         |    2 +-
 net/sched/sch_api.c         |    4 +-
 net/wireless/wext.c         |    5 ++-
 19 files changed, 129 insertions(+), 53 deletions(-)

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 9c21e45..518247e 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -582,11 +582,11 @@ extern int __rtattr_parse_nested_compat(struct rtattr *tb[], int maxattr,
 ({	data = RTA_PAYLOAD(rta) >= len ? RTA_DATA(rta) : NULL; \
 	__rtattr_parse_nested_compat(tb, max, rta, len); })
 
-extern int rtnetlink_send(struct sk_buff *skb, u32 pid, u32 group, int echo);
-extern int rtnl_unicast(struct sk_buff *skb, u32 pid);
-extern int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group,
+extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
+extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid);
+extern int rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
 		       struct nlmsghdr *nlh, gfp_t flags);
-extern void rtnl_set_sk_err(u32 group, int error);
+extern void rtnl_set_sk_err(struct net *net, u32 group, int error);
 extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics);
 extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst,
 			      u32 id, u32 ts, u32 tsage, long expires,
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 934c840..f75607a 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -10,6 +10,7 @@
 
 struct proc_dir_entry;
 struct net_device;
+struct sock;
 struct net {
 	atomic_t		count;		/* To decided when the network
 						 *  namespace should be freed.
@@ -29,6 +30,8 @@ struct net {
 	struct list_head 	dev_base_head;
 	struct hlist_head 	*dev_name_head;
 	struct hlist_head	*dev_index_head;
+
+	struct sock 		*rtnl;			/* rtnetlink socket */
 };
 
 #ifdef CONFIG_NET
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index a4ffa2b..f5d6933 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -97,10 +97,10 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port)
 		kfree_skb(skb);
 		goto errout;
 	}
-	err = rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
+	err = rtnl_notify(skb, &init_net,0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
 errout:
 	if (err < 0)
-		rtnl_set_sk_err(RTNLGRP_LINK, err);
+		rtnl_set_sk_err(&init_net, RTNLGRP_LINK, err);
 }
 
 /*
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 357bfa0..03c803c 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -577,10 +577,10 @@ static void notify_rule_change(int event, struct fib_rule *rule,
 		kfree_skb(skb);
 		goto errout;
 	}
-	err = rtnl_notify(skb, pid, ops->nlgroup, nlh, GFP_KERNEL);
+	err = rtnl_notify(skb, &init_net, pid, ops->nlgroup, nlh, GFP_KERNEL);
 errout:
 	if (err < 0)
-		rtnl_set_sk_err(ops->nlgroup, err);
+		rtnl_set_sk_err(&init_net, ops->nlgroup, err);
 }
 
 static void attach_rules(struct list_head *rules, struct net_device *dev)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 27001db..c452584 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2466,10 +2466,10 @@ static void __neigh_notify(struct neighbour *n, int type, int flags)
 		kfree_skb(skb);
 		goto errout;
 	}
-	err = rtnl_notify(skb, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
+	err = rtnl_notify(skb, &init_net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
 errout:
 	if (err < 0)
-		rtnl_set_sk_err(RTNLGRP_NEIGH, err);
+		rtnl_set_sk_err(&init_net, RTNLGRP_NEIGH, err);
 }
 
 #ifdef CONFIG_ARPD
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 56fc4f9..fc49104 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -60,7 +60,6 @@ struct rtnl_link
 };
 
 static DEFINE_MUTEX(rtnl_mutex);
-static struct sock *rtnl;
 
 void rtnl_lock(void)
 {
@@ -74,9 +73,38 @@ void __rtnl_unlock(void)
 
 void rtnl_unlock(void)
 {
-	mutex_unlock(&rtnl_mutex);
-	if (rtnl && rtnl->sk_receive_queue.qlen)
+	struct net *net;
+
+	/*
+	 * Loop through all of the rtnl sockets until none of them (in
+	 * a live network namespace) have queue packets.
+	 *
+	 * We have to be careful with the locking here as
+	 * sk_data_ready aka rtnetlink_rcv takes the rtnl_mutex.
+	 *
+	 * To ensure the network namespace does not exit while
+	 * we are processing packets on it's rtnl socket we
+	 * grab a reference to the network namespace, ignoring
+	 * it if the network namespace has already exited.
+	 */
+retry:
+	for_each_net(net) {
+		struct sock *rtnl = net->rtnl;
+
+		if (!rtnl || !rtnl->sk_receive_queue.qlen)
+			continue;
+
+		if (!maybe_get_net(net))
+			continue;
+
+		mutex_unlock(&rtnl_mutex);
 		rtnl->sk_data_ready(rtnl, 0);
+		mutex_lock(&rtnl_mutex);
+		put_net(net);
+		goto retry;
+	}
+	mutex_unlock(&rtnl_mutex);
+
 	netdev_run_todo();
 }
 
@@ -462,8 +490,9 @@ size_t rtattr_strlcpy(char *dest, const struct rtattr *rta, size_t size)
 	return ret;
 }
 
-int rtnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo)
+int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo)
 {
+	struct sock *rtnl = net->rtnl;
 	int err = 0;
 
 	NETLINK_CB(skb).dst_group = group;
@@ -475,14 +504,17 @@ int rtnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo)
 	return err;
 }
 
-int rtnl_unicast(struct sk_buff *skb, u32 pid)
+int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid)
 {
+	struct sock *rtnl = net->rtnl;
+
 	return nlmsg_unicast(rtnl, skb, pid);
 }
 
-int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group,
+int rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
 		struct nlmsghdr *nlh, gfp_t flags)
 {
+	struct sock *rtnl = net->rtnl;
 	int report = 0;
 
 	if (nlh)
@@ -491,8 +523,10 @@ int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group,
 	return nlmsg_notify(rtnl, skb, pid, group, report, flags);
 }
 
-void rtnl_set_sk_err(u32 group, int error)
+void rtnl_set_sk_err(struct net *net, u32 group, int error)
 {
+	struct sock *rtnl = net->rtnl;
+
 	netlink_set_err(rtnl, 0, group, error);
 }
 
@@ -1205,7 +1239,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 		kfree_skb(nskb);
 		goto errout;
 	}
-	err = rtnl_unicast(nskb, NETLINK_CB(skb).pid);
+	err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid);
 errout:
 	dev_put(dev);
 
@@ -1256,10 +1290,10 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
 		kfree_skb(skb);
 		goto errout;
 	}
-	err = rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_KERNEL);
+	err = rtnl_notify(skb, &init_net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL);
 errout:
 	if (err < 0)
-		rtnl_set_sk_err(RTNLGRP_LINK, err);
+		rtnl_set_sk_err(&init_net, RTNLGRP_LINK, err);
 }
 
 /* Protected by RTNL sempahore.  */
@@ -1270,6 +1304,7 @@ static int rtattr_max;
 
 static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
+	struct net *net = skb->sk->sk_net;
 	rtnl_doit_func doit;
 	int sz_idx, kind;
 	int min_len;
@@ -1298,6 +1333,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return -EPERM;
 
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
+		struct sock *rtnl;
 		rtnl_dumpit_func dumpit;
 
 		dumpit = rtnl_get_dumpit(family, type);
@@ -1305,6 +1341,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			return -EOPNOTSUPP;
 
 		__rtnl_unlock();
+		rtnl = net->rtnl;
 		err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL);
 		rtnl_lock();
 		return err;
@@ -1383,6 +1420,40 @@ static struct notifier_block rtnetlink_dev_notifier = {
 	.notifier_call	= rtnetlink_event,
 };
 
+
+static int rtnetlink_net_init(struct net *net)
+{
+	struct sock *sk;
+	sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX,
+				   rtnetlink_rcv, &rtnl_mutex, THIS_MODULE);
+	if (!sk)
+		return -ENOMEM;
+
+	/* Don't hold an extra reference on the namespace */
+	put_net(sk->sk_net);
+	net->rtnl = sk;
+	return 0;
+}
+
+static void rtnetlink_net_exit(struct net *net)
+{
+	struct sock *sk = net->rtnl;
+	if (sk) {
+		/* At the last minute lie and say this is a socket for the
+		 * initial network namespace.  So the socket will be safe to
+		 * free.
+		 */
+		sk->sk_net = get_net(&init_net);
+		sock_put(sk);
+		net->rtnl = NULL;
+	}
+}
+
+static struct pernet_operations rtnetlink_net_ops = {
+	.init = rtnetlink_net_init,
+	.exit = rtnetlink_net_exit,
+};
+
 void __init rtnetlink_init(void)
 {
 	int i;
@@ -1395,10 +1466,9 @@ void __init rtnetlink_init(void)
 	if (!rta_buf)
 		panic("rtnetlink_init: cannot allocate rta_buf\n");
 
-	rtnl = netlink_kernel_create(&init_net, NETLINK_ROUTE, RTNLGRP_MAX,
-				     rtnetlink_rcv, &rtnl_mutex, THIS_MODULE);
-	if (rtnl == NULL)
+	if (register_pernet_subsys(&rtnetlink_net_ops))
 		panic("rtnetlink_init: cannot initialize rtnetlink\n");
+
 	netlink_set_nonroot(NETLINK_ROUTE, NL_NONROO