netfilter: nf_conntrack: make event callback registration per-netns

This patch fixes an oops that can be triggered following this recipe:

0) make sure nf_conntrack_netlink and nf_conntrack_ipv4 are loaded.
1) container is started.
2) connect to it via lxc-console.
3) generate some traffic with the container to create some conntrack
   entries in its table.
4) stop the container: you hit one oops because the conntrack table
   cleanup tries to report the destroy event to user-space but the
   per-netns nfnetlink socket has already gone (as the nfnetlink
   socket is per-netns but event callback registration is global).

To fix this situation, we make the ctnl_notifier per-netns so the
callback is registered/unregistered if the container is
created/destroyed.

Alex Bligh and Alexey Dobriyan originally proposed one small patch to
check if the nfnetlink socket is gone in nfnetlink_has_listeners,
but this is a very visited path for events, thus, it may reduce
performance and it looks a bit hackish to check for the nfnetlink
socket only to workaround this situation. As a result, I decided
to follow the bigger path choice, which seems to look nicer to me.

Cc: Alexey Dobriyan <adobriyan@gmail.com>
Reported-by: Alex Bligh <alex@alex.org.uk>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

include/net/netfilter/nf_conntrack_ecache.h

@@ -67,18 +67,18 @@ struct nf_ct_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_ct_event *item);
 };
 
-extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
-extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb);
-extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb);
+extern int nf_conntrack_register_notifier(struct net *net, struct nf_ct_event_notifier *nb);
+extern void nf_conntrack_unregister_notifier(struct net *net, struct nf_ct_event_notifier *nb);
 
 extern void nf_ct_deliver_cached_events(struct nf_conn *ct);
 
 static inline void
 nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct)
 {
+	struct net *net = nf_ct_net(ct);
 	struct nf_conntrack_ecache *e;
 
-	if (nf_conntrack_event_cb == NULL)
+	if (net->ct.nf_conntrack_event_cb == NULL)
 		return;
 
 	e = nf_ct_ecache_find(ct);
@@ -95,11 +95,12 @@ nf_conntrack_eventmask_report(unsigned int eventmask,
 			      int report)
 {
 	int ret = 0;
+	struct net *net = nf_ct_net(ct);
 	struct nf_ct_event_notifier *notify;
 	struct nf_conntrack_ecache *e;
 
 	rcu_read_lock();
-	notify = rcu_dereference(nf_conntrack_event_cb);
+	notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
 	if (notify == NULL)
 		goto out_unlock;
 
@@ -164,9 +165,8 @@ struct nf_exp_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_exp_event *item);
 };
 
-extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
-extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb);
-extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb);
+extern int nf_ct_expect_register_notifier(struct net *net, struct nf_exp_event_notifier *nb);
+extern void nf_ct_expect_unregister_notifier(struct net *net, struct nf_exp_event_notifier *nb);
 
 static inline void
 nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
@@ -174,11 +174,12 @@ nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
 			  u32 pid,
 			  int report)
 {
+	struct net *net = nf_ct_exp_net(exp);
 	struct nf_exp_event_notifier *notify;
 	struct nf_conntrack_ecache *e;
 
 	rcu_read_lock();
-	notify = rcu_dereference(nf_expect_event_cb);
+	notify = rcu_dereference(net->ct.nf_expect_event_cb);
 	if (notify == NULL)
 		goto out_unlock;
 

include/net/netns/conntrack.h

@@ -18,6 +18,8 @@ struct netns_ct {
 	struct hlist_nulls_head	unconfirmed;
 	struct hlist_nulls_head	dying;
 	struct ip_conntrack_stat __percpu *stat;
+	struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
+	struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
 	int			sysctl_events;
 	unsigned int		sysctl_events_retry_timeout;
 	int			sysctl_acct;

net/netfilter/nf_conntrack_ecache.c

@@ -27,22 +27,17 @@
 
 static DEFINE_MUTEX(nf_ct_ecache_mutex);
 
-struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb __read_mostly;
-EXPORT_SYMBOL_GPL(nf_conntrack_event_cb);
-
-struct nf_exp_event_notifier __rcu *nf_expect_event_cb __read_mostly;
-EXPORT_SYMBOL_GPL(nf_expect_event_cb);
-
 /* deliver cached events and clear cache entry - must be called with locally
  * disabled softirqs */
 void nf_ct_deliver_cached_events(struct nf_conn *ct)
 {
+	struct net *net = nf_ct_net(ct);
 	unsigned long events;
 	struct nf_ct_event_notifier *notify;
 	struct nf_conntrack_ecache *e;
 
 	rcu_read_lock();
-	notify = rcu_dereference(nf_conntrack_event_cb);
+	notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
 	if (notify == NULL)
 		goto out_unlock;
 
@@ -83,19 +78,20 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct)
 }
 EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events);
 
-int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new)
+int nf_conntrack_register_notifier(struct net *net,
+				   struct nf_ct_event_notifier *new)
 {
 	int ret = 0;
 	struct nf_ct_event_notifier *notify;
 
 	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(nf_conntrack_event_cb,
+	notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb,
 					   lockdep_is_held(&nf_ct_ecache_mutex));
 	if (notify != NULL) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
-	RCU_INIT_POINTER(nf_conntrack_event_cb, new);
+	RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, new);
 	mutex_unlock(&nf_ct_ecache_mutex);
 	return ret;
 
@@ -105,32 +101,34 @@ int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new)
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier);
 
-void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *new)
+void nf_conntrack_unregister_notifier(struct net *net,
+				      struct nf_ct_event_notifier *new)
 {
 	struct nf_ct_event_notifier *notify;
 
 	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(nf_conntrack_event_cb,
+	notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb,
 					   lockdep_is_held(&nf_ct_ecache_mutex));
 	BUG_ON(notify != new);
-	RCU_INIT_POINTER(nf_conntrack_event_cb, NULL);
+	RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL);
 	mutex_unlock(&nf_ct_ecache_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier);
 
-int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new)
+int nf_ct_expect_register_notifier(struct net *net,
+				   struct nf_exp_event_notifier *new)
 {
 	int ret = 0;
 	struct nf_exp_event_notifier *notify;
 
 	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(nf_expect_event_cb,
+	notify = rcu_dereference_protected(net->ct.nf_expect_event_cb,
 					   lockdep_is_held(&nf_ct_ecache_mutex));
 	if (notify != NULL) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
-	RCU_INIT_POINTER(nf_expect_event_cb, new);
+	RCU_INIT_POINTER(net->ct.nf_expect_event_cb, new);
 	mutex_unlock(&nf_ct_ecache_mutex);
 	return ret;
 
@@ -140,15 +138,16 @@ int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new)
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier);
 
-void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *new)
+void nf_ct_expect_unregister_notifier(struct net *net,
+				      struct nf_exp_event_notifier *new)
 {
 	struct nf_exp_event_notifier *notify;
 
 	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(nf_expect_event_cb,
+	notify = rcu_dereference_protected(net->ct.nf_expect_event_cb,
 					   lockdep_is_held(&nf_ct_ecache_mutex));
 	BUG_ON(notify != new);
-	RCU_INIT_POINTER(nf_expect_event_cb, NULL);
+	RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL);
 	mutex_unlock(&nf_ct_ecache_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);

net/netfilter/nf_conntrack_netlink.c

@@ -4,7 +4,7 @@
  * (C) 2001 by Jay Schulist <jschlst@samba.org>
  * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org>
  * (C) 2003 by Patrick Mchardy <kaber@trash.net>
- * (C) 2005-2008 by Pablo Neira Ayuso <pablo@netfilter.org>
+ * (C) 2005-2011 by Pablo Neira Ayuso <pablo@netfilter.org>
  *
  * Initial connection tracking via netlink development funded and
  * generally made possible by Network Robots, Inc. (www.networkrobots.com)
@@ -2163,6 +2163,54 @@ MODULE_ALIAS("ip_conntrack_netlink");
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK);
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP);
 
+static int __net_init ctnetlink_net_init(struct net *net)
+{
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	int ret;
+
+	ret = nf_conntrack_register_notifier(net, &ctnl_notifier);
+	if (ret < 0) {
+		pr_err("ctnetlink_init: cannot register notifier.\n");
+		goto err_out;
+	}
+
+	ret = nf_ct_expect_register_notifier(net, &ctnl_notifier_exp);
+	if (ret < 0) {
+		pr_err("ctnetlink_init: cannot expect register notifier.\n");
+		goto err_unreg_notifier;
+	}
+#endif
+	return 0;
+
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+err_unreg_notifier:
+	nf_conntrack_unregister_notifier(net, &ctnl_notifier);
+err_out:
+	return ret;
+#endif
+}
+
+static void ctnetlink_net_exit(struct net *net)
+{
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp);
+	nf_conntrack_unregister_notifier(net, &ctnl_notifier);
+#endif
+}
+
+static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list)
+{
+	struct net *net;
+
+	list_for_each_entry(net, net_exit_list, exit_list)
+		ctnetlink_net_exit(net);
+}
+
+static struct pernet_operations ctnetlink_net_ops = {
+	.init		= ctnetlink_net_init,
+	.exit_batch	= ctnetlink_net_exit_batch,
+};
+
 static int __init ctnetlink_init(void)
 {
 	int ret;
@@ -2180,28 +2228,15 @@ static int __init ctnetlink_init(void)
 		goto err_unreg_subsys;
 	}
 
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-	ret = nf_conntrack_register_notifier(&ctnl_notifier);
-	if (ret < 0) {
-		pr_err("ctnetlink_init: cannot register notifier.\n");
+	if (register_pernet_subsys(&ctnetlink_net_ops)) {
+		pr_err("ctnetlink_init: cannot register pernet operations\n");
 		goto err_unreg_exp_subsys;
 	}
 
-	ret = nf_ct_expect_register_notifier(&ctnl_notifier_exp);
-	if (ret < 0) {
-		pr_err("ctnetlink_init: cannot expect register notifier.\n");
-		goto err_unreg_notifier;
-	}
-#endif
-
 	return 0;
 
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-err_unreg_notifier:
-	nf_conntrack_unregister_notifier(&ctnl_notifier);
 err_unreg_exp_subsys:
 	nfnetlink_subsys_unregister(&ctnl_exp_subsys);
-#endif
 err_unreg_subsys:
 	nfnetlink_subsys_unregister(&ctnl_subsys);
 err_out:
@@ -2213,11 +2248,7 @@ static void __exit ctnetlink_exit(void)
 	pr_info("ctnetlink: unregistering from nfnetlink.\n");
 
 	nf_ct_remove_userspace_expectations();
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-	nf_ct_expect_unregister_notifier(&ctnl_notifier_exp);
-	nf_conntrack_unregister_notifier(&ctnl_notifier);
-#endif
-
+	unregister_pernet_subsys(&ctnetlink_net_ops);
 	nfnetlink_subsys_unregister(&ctnl_exp_subsys);
 	nfnetlink_subsys_unregister(&ctnl_subsys);
 }