netfilter: nf_conntrack: improve nf_conn object traceability

This patch modifies the conntrack subsystem so that all existing
allocated conntrack objects can be found in any of the following
places:

* the hash table, this is the typical place for alive conntrack objects.
* the unconfirmed list, this is the place for newly created conntrack objects
  that are still traversing the stack.
* the dying list, this is where you can find conntrack objects that are dying
  or that should die anytime soon (eg. once the destroy event is delivered to
  the conntrackd daemon).

Thus, we make sure that we follow the track for all existing conntrack
objects. This patch, together with some extension of the ctnetlink interface
to dump the content of the dying and unconfirmed lists, will help in case
to debug suspected nf_conn object leaks.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

2 files changed, 10 insertions, 17 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0f241be28f9e..af175166fffa 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -221,11 +221,9 @@ destroy_conntrack(struct nf_conntrack *nfct)
 	 * too. */
 	nf_ct_remove_expectations(ct);
 
-	/* We overload first tuple to link into unconfirmed list. */
-	if (!nf_ct_is_confirmed(ct)) {
-		BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
-		hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
-	}
+	/* We overload first tuple to link into unconfirmed or dying list.*/
+	BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
+	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
 
 	NF_CT_STAT_INC(net, delete);
 	spin_unlock_bh(&nf_conntrack_lock);
@@ -247,6 +245,9 @@ void nf_ct_delete_from_lists(struct nf_conn *ct)
 	 * Otherwise we can get spurious warnings. */
 	NF_CT_STAT_INC(net, delete_list);
 	clean_from_lists(ct);
+	/* add this conntrack to the dying list */
+	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+			     &net->ct.dying);
 	spin_unlock_bh(&nf_conntrack_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists);
@@ -268,31 +269,23 @@ static void death_by_event(unsigned long ul_conntrack)
 	}
 	/* we've got the event delivered, now it's dying */
 	set_bit(IPS_DYING_BIT, &ct->status);
-	spin_lock(&nf_conntrack_lock);
-	hlist_nulls_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
-	spin_unlock(&nf_conntrack_lock);
 	nf_ct_put(ct);
 }
 
-void nf_ct_insert_dying_list(struct nf_conn *ct)
+void nf_ct_dying_timeout(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 	struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
 
 	BUG_ON(ecache == NULL);
 
-	/* add this conntrack to the dying list */
-	spin_lock_bh(&nf_conntrack_lock);
-	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-			     &net->ct.dying);
-	spin_unlock_bh(&nf_conntrack_lock);
 	/* set a new timer to retry event delivery */
 	setup_timer(&ecache->timeout, death_by_event, (unsigned long)ct);
 	ecache->timeout.expires = jiffies +
 		(random32() % net->ct.sysctl_events_retry_timeout);
 	add_timer(&ecache->timeout);
 }
-EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list);
+EXPORT_SYMBOL_GPL(nf_ct_dying_timeout);
 
 static void death_by_timeout(unsigned long ul_conntrack)
 {
@@ -307,7 +300,7 @@ static void death_by_timeout(unsigned long ul_conntrack)
 	    unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) {
 		/* destroy event was not delivered */
 		nf_ct_delete_from_lists(ct);
-		nf_ct_insert_dying_list(ct);
+		nf_ct_dying_timeout(ct);
 		return;
 	}
 	set_bit(IPS_DYING_BIT, &ct->status);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 7bbfb3deea30..34370a928360 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -989,7 +989,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 					      nlmsg_report(nlh)) < 0) {
 			nf_ct_delete_from_lists(ct);
 			/* we failed to report the event, try later */
-			nf_ct_insert_dying_list(ct);
+			nf_ct_dying_timeout(ct);
 			nf_ct_put(ct);
 			return 0;
 		}