diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 095433b8a8b0..37cd3911d5c5 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -291,7 +291,7 @@ extern unsigned int nf_conntrack_max;
 extern unsigned int nf_conntrack_hash_rnd;
 void init_nf_conntrack_hash_rnd(void);
 
-void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl);
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags);
 
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 29d6a94db54d..723b61c82b3f 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -68,7 +68,6 @@ struct ct_pcpu {
 	spinlock_t		lock;
 	struct hlist_nulls_head unconfirmed;
 	struct hlist_nulls_head dying;
-	struct hlist_nulls_head tmpl;
 };
 
 struct netns_ct {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 13fad8668f83..651039ad1681 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -287,6 +287,46 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
 	spin_unlock(&pcpu->lock);
 }
 
+/* Released via destroy_conntrack() */
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags)
+{
+	struct nf_conn *tmpl;
+
+	tmpl = kzalloc(sizeof(struct nf_conn), GFP_KERNEL);
+	if (tmpl == NULL)
+		return NULL;
+
+	tmpl->status = IPS_TEMPLATE;
+	write_pnet(&tmpl->ct_net, net);
+
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	if (zone) {
+		struct nf_conntrack_zone *nf_ct_zone;
+
+		nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, GFP_ATOMIC);
+		if (!nf_ct_zone)
+			goto out_free;
+		nf_ct_zone->id = zone;
+	}
+#endif
+	atomic_set(&tmpl->ct_general.use, 0);
+
+	return tmpl;
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+out_free:
+	kfree(tmpl);
+	return NULL;
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);
+
+static void nf_ct_tmpl_free(struct nf_conn *tmpl)
+{
+	nf_ct_ext_destroy(tmpl);
+	nf_ct_ext_free(tmpl);
+	kfree(tmpl);
+}
+
 static void
 destroy_conntrack(struct nf_conntrack *nfct)
 {
@@ -298,6 +338,10 @@ destroy_conntrack(struct nf_conntrack *nfct)
 	NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
 	NF_CT_ASSERT(!timer_pending(&ct->timeout));
 
+	if (unlikely(nf_ct_is_template(ct))) {
+		nf_ct_tmpl_free(ct);
+		return;
+	}
 	rcu_read_lock();
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	if (l4proto && l4proto->destroy)
@@ -540,28 +584,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
 
-/* deletion from this larval template list happens via nf_ct_put() */
-void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
-{
-	struct ct_pcpu *pcpu;
-
-	__set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
-	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
-	nf_conntrack_get(&tmpl->ct_general);
-
-	/* add this conntrack to the (per cpu) tmpl list */
-	local_bh_disable();
-	tmpl->cpu = smp_processor_id();
-	pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu);
-
-	spin_lock(&pcpu->lock);
-	/* Overload tuple linked list to put us in template list. */
-	hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-				 &pcpu->tmpl);
-	spin_unlock_bh(&pcpu->lock);
-}
-EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
-
 /* Confirm a connection given skb; places it in hash table */
 int
 __nf_conntrack_confirm(struct sk_buff *skb)
@@ -1751,7 +1773,6 @@ int nf_conntrack_init_net(struct net *net)
 		spin_lock_init(&pcpu->lock);
 		INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
 		INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
-		INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL);
 	}
 
 	net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 789feeae6c44..71f1e9fdfa18 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -349,12 +349,10 @@ static void __net_exit synproxy_proc_exit(struct net *net)
 static int __net_init synproxy_net_init(struct net *net)
 {
 	struct synproxy_net *snet = synproxy_pernet(net);
-	struct nf_conntrack_tuple t;
 	struct nf_conn *ct;
 	int err = -ENOMEM;
 
-	memset(&t, 0, sizeof(t));
-	ct = nf_conntrack_alloc(net, 0, &t, &t, GFP_KERNEL);
+	ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL);
 	if (IS_ERR(ct)) {
 		err = PTR_ERR(ct);
 		goto err1;
@@ -365,7 +363,8 @@ static int __net_init synproxy_net_init(struct net *net)
 	if (!nfct_synproxy_ext_add(ct))
 		goto err2;
 
-	nf_conntrack_tmpl_insert(net, ct);
+	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
+	nf_conntrack_get(&ct->ct_general);
 	snet->tmpl = ct;
 
 	snet->stats = alloc_percpu(struct synproxy_stats);
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 75747aecdebe..c6630030c912 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -184,7 +184,6 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par,
 static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 			  struct xt_ct_target_info_v1 *info)
 {
-	struct nf_conntrack_tuple t;
 	struct nf_conn *ct;
 	int ret = -EOPNOTSUPP;
 
@@ -202,8 +201,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 	if (ret < 0)
 		goto err1;
 
-	memset(&t, 0, sizeof(t));
-	ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL);
+	ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL);
 	ret = PTR_ERR(ct);
 	if (IS_ERR(ct))
 		goto err2;
@@ -227,8 +225,8 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 		if (ret < 0)
 			goto err3;
 	}
-
-	nf_conntrack_tmpl_insert(par->net, ct);
+	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
+	nf_conntrack_get(&ct->ct_general);
 out:
 	info->ct = ct;
 	return 0;