1 files changed, 20 insertions, 5 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5f72b94b4918..7508f11c5b39 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -335,7 +335,8 @@ begin:
 	h = __nf_conntrack_find(net, tuple);
 	if (h) {
 		ct = nf_ct_tuplehash_to_ctrack(h);
-		if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
+		if (unlikely(nf_ct_is_dying(ct) ||
+			     !atomic_inc_not_zero(&ct->ct_general.use)))
 			h = NULL;
 		else {
 			if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) {
@@ -425,7 +426,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	/* Remove from unconfirmed list */
 	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
 
-	__nf_conntrack_hash_insert(ct, hash, repl_hash);
 	/* Timer relative to confirmation time, not original
 	   setting time, otherwise we'd get timer wrap in
 	   weird delay cases. */
@@ -433,8 +433,16 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	add_timer(&ct->timeout);
 	atomic_inc(&ct->ct_general.use);
 	set_bit(IPS_CONFIRMED_BIT, &ct->status);
+
+	/* Since the lookup is lockless, hash insertion must be done after
+	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
+	 * guarantee that no other CPU can find the conntrack before the above
+	 * stores are visible.
+	 */
+	__nf_conntrack_hash_insert(ct, hash, repl_hash);
 	NF_CT_STAT_INC(net, insert);
 	spin_unlock_bh(&nf_conntrack_lock);
+
 	help = nfct_help(ct);
 	if (help && help->helper)
 		nf_conntrack_event_cache(IPCT_HELPER, ct);
@@ -503,7 +511,8 @@ static noinline int early_drop(struct net *net, unsigned int hash)
 			cnt++;
 		}
 
-		if (ct && unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
+		if (ct && unlikely(nf_ct_is_dying(ct) ||
+				   !atomic_inc_not_zero(&ct->ct_general.use)))
 			ct = NULL;
 		if (ct || cnt >= NF_CT_EVICTION_RANGE)
 			break;
@@ -1267,13 +1276,19 @@ err_cache:
 	return ret;
 }
 
+/*
+ * We need to use special "null" values, not used in hash table
+ */
+#define UNCONFIRMED_NULLS_VAL	((1<<30)+0)
+#define DYING_NULLS_VAL		((1<<30)+1)
+
 static int nf_conntrack_init_net(struct net *net)
 {
 	int ret;
 
 	atomic_set(&net->ct.count, 0);
-	INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, 0);
-	INIT_HLIST_NULLS_HEAD(&net->ct.dying, 0);
+	INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL);
+	INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL);
 	net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
 	if (!net->ct.stat) {
 		ret = -ENOMEM;