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>

2 files changed, 12 insertions, 9 deletions

diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 4283508b3e18..a88fb6939387 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/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;
 
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 0249399e51a7..7a911eca0f18 100644
--- a/include/net/netns/conntrack.h
+++ b/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;