diff --git a/include/net/act_api.h b/include/net/act_api.h
index 3ee4c92afd1bd2baf2b90201a9b4af896d020b5f..db2063ffd1812d797bbadd5e3df09b443e863e92 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -21,6 +21,8 @@ struct tcf_common {
 	struct gnet_stats_rate_est64	tcfc_rate_est;
 	spinlock_t			tcfc_lock;
 	struct rcu_head			tcfc_rcu;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_queue __percpu *cpu_qstats;
 };
 #define tcf_head	common.tcfc_head
 #define tcf_index	common.tcfc_index
@@ -103,7 +105,7 @@ int tcf_hash_release(struct tc_action *a, int bind);
 u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo);
 int tcf_hash_check(u32 index, struct tc_action *a, int bind);
 int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
-		    int size, int bind);
+		    int size, int bind, bool cpustats);
 void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
 void tcf_hash_insert(struct tc_action *a);
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index af427a3dbcba238103169ab2a58005feda5fa2f1..074a32f466f8f9168186828cdad6c6484fae1265 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -27,6 +27,15 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 
+static void free_tcf(struct rcu_head *head)
+{
+	struct tcf_common *p = container_of(head, struct tcf_common, tcfc_rcu);
+
+	free_percpu(p->cpu_bstats);
+	free_percpu(p->cpu_qstats);
+	kfree(p);
+}
+
 void tcf_hash_destroy(struct tc_action *a)
 {
 	struct tcf_common *p = a->priv;
@@ -41,7 +50,7 @@ void tcf_hash_destroy(struct tc_action *a)
 	 * gen_estimator est_timer() might access p->tcfc_lock
 	 * or bstats, wait a RCU grace period before freeing p
 	 */
-	kfree_rcu(p, tcfc_rcu);
+	call_rcu(&p->tcfc_rcu, free_tcf);
 }
 EXPORT_SYMBOL(tcf_hash_destroy);
 
@@ -230,15 +239,16 @@ void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est)
 	if (est)
 		gen_kill_estimator(&pc->tcfc_bstats,
 				   &pc->tcfc_rate_est);
-	kfree_rcu(pc, tcfc_rcu);
+	call_rcu(&pc->tcfc_rcu, free_tcf);
 }
 EXPORT_SYMBOL(tcf_hash_cleanup);
 
 int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
-		    int size, int bind)
+		    int size, int bind, bool cpustats)
 {
 	struct tcf_hashinfo *hinfo = a->ops->hinfo;
 	struct tcf_common *p = kzalloc(size, GFP_KERNEL);
+	int err = -ENOMEM;
 
 	if (unlikely(!p))
 		return -ENOMEM;
@@ -246,18 +256,32 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
 	if (bind)
 		p->tcfc_bindcnt = 1;
 
+	if (cpustats) {
+		p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
+		if (!p->cpu_bstats) {
+err1:
+			kfree(p);
+			return err;
+		}
+		p->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
+		if (!p->cpu_qstats) {
+err2:
+			free_percpu(p->cpu_bstats);
+			goto err1;
+		}
+	}
 	spin_lock_init(&p->tcfc_lock);
 	INIT_HLIST_NODE(&p->tcfc_head);
 	p->tcfc_index = index ? index : tcf_hash_new_index(hinfo);
 	p->tcfc_tm.install = jiffies;
 	p->tcfc_tm.lastuse = jiffies;
 	if (est) {
-		int err = gen_new_estimator(&p->tcfc_bstats, NULL,
-					    &p->tcfc_rate_est,
-					    &p->tcfc_lock, est);
+		err = gen_new_estimator(&p->tcfc_bstats, p->cpu_bstats,
+					&p->tcfc_rate_est,
+					&p->tcfc_lock, est);
 		if (err) {
-			kfree(p);
-			return err;
+			free_percpu(p->cpu_qstats);
+			goto err2;
 		}
 	}
 
@@ -615,10 +639,10 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 	if (err < 0)
 		goto errout;
 
-	if (gnet_stats_copy_basic(&d, NULL, &p->tcfc_bstats) < 0 ||
+	if (gnet_stats_copy_basic(&d, p->cpu_bstats, &p->tcfc_bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
 				     &p->tcfc_rate_est) < 0 ||
-	    gnet_stats_copy_queue(&d, NULL,
+	    gnet_stats_copy_queue(&d, p->cpu_qstats,
 				  &p->tcfc_qstats,
 				  p->tcfc_qstats.qlen) < 0)
 		goto errout;
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 1d56903fd4c79aa008c4c540aabd8b4c099e81a1..99aa271633e9011e7fb10042a97a07eea5b6375e 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -281,7 +281,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 
 	if (!tcf_hash_check(parm->index, act, bind)) {
 		ret = tcf_hash_create(parm->index, est, act,
-				      sizeof(*prog), bind);
+				      sizeof(*prog), bind, false);
 		if (ret < 0)
 			goto destroy_fp;
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 295d14bd6c678c31b56219371df83d4ebe3b0a2c..f2b540220ad02f1f8e3b2add9c7477a334081c3d 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -108,7 +108,8 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
 
 	if (!tcf_hash_check(parm->index, a, bind)) {
-		ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), bind);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*ci),
+				      bind, false);
 		if (ret)
 			return ret;
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 4cd5cf1aedf8b14bc8a8fb0529db868ee74433fd..b07c535ba8e7c6f8dcbc52f4eb69cf4a1ab3d0c2 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -62,7 +62,8 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est,
 	parm = nla_data(tb[TCA_CSUM_PARMS]);
 
 	if (!tcf_hash_check(parm->index, a, bind)) {
-		ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*p),
+				      bind, false);
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 7fffc2272701adb42d109318a80e8fef6fc3289f..a4f8af29ee300ea5145250206a2016893d6edde8 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -85,7 +85,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 #endif
 
 	if (!tcf_hash_check(parm->index, a, bind)) {
-		ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*gact),
+				      bind, false);
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index cbc8dd7dd48a50e77fdafa7b8cf4041659995cbb..99c9cc1c7af9240f9df444ae158df4fa7f7f8c73 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -114,7 +114,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 		index = nla_get_u32(tb[TCA_IPT_INDEX]);
 
 	if (!tcf_hash_check(index, a, bind) ) {
-		ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind);
+		ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind, false);
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index a42a3b257226178eb5af04054a17813c04368613..002cd6c83dc61e842102cd35ca3e43a351f21b8c 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -93,7 +93,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	if (!tcf_hash_check(parm->index, a, bind)) {
 		if (dev == NULL)
 			return -EINVAL;
-		ret = tcf_hash_create(parm->index, est, a, sizeof(*m), bind);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*m),
+				      bind, false);
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 270a030d5fd099ee7b6f6d74d51b6015aa690647..5be0b3c1c5b0c9f17e3fbd4e1dc1c92c7a8e5aed 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -55,7 +55,8 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	parm = nla_data(tb[TCA_NAT_PARMS]);
 
 	if (!tcf_hash_check(parm->index, a, bind)) {
-		ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*p),
+				      bind, false);
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 17e6d6669c7fdf138915ac9549d3f06d9535d745..ce8676ad892f20b2ea921073b655ef41dcf2ccec 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -57,7 +57,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (!tcf_hash_check(parm->index, a, bind)) {
 		if (!parm->nkeys)
 			return -EINVAL;
-		ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*p),
+				      bind, false);
 		if (ret)
 			return ret;
 		p = to_pedit(a);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 6a8d9488613a76d9cb2bd03e932ef95487ca0745..d6b708d6afdf37e7c1af4e47873755fc84b1167f 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -103,7 +103,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	defdata = nla_data(tb[TCA_DEF_DATA]);
 
 	if (!tcf_hash_check(parm->index, a, bind)) {
-		ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*d),
+				      bind, false);
 		if (ret)
 			return ret;
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index fcfeeaf838beb9e75f07f7cbda7fb2b73237a17f..6751b5f8c046a59912b78762855e51af8e6f29e7 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -99,7 +99,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
 
 	if (!tcf_hash_check(parm->index, a, bind)) {
-		ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*d),
+				      bind, false);
 		if (ret)
 			return ret;
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index d735ecf0b1a78d3fac6ac80b95931cc6cf6caba0..796785e0bf96b0e65f598d3b2dad8256485d034a 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -116,7 +116,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	action = parm->v_action;
 
 	if (!tcf_hash_check(parm->index, a, bind)) {
-		ret = tcf_hash_create(parm->index, est, a, sizeof(*v), bind);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*v),
+				      bind, false);
 		if (ret)
 			return ret;