diff --git a/include/net/act_api.h b/include/net/act_api.h
index c6f195b..1ddff33 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -31,10 +31,12 @@ struct tc_action {
 	int				tcfa_action;
 	struct tcf_t			tcfa_tm;
 	struct gnet_stats_basic_packed	tcfa_bstats;
+	struct gnet_stats_basic_packed	tcfa_bstats_hw;
 	struct gnet_stats_queue		tcfa_qstats;
 	struct net_rate_estimator __rcu *tcfa_rate_est;
 	spinlock_t			tcfa_lock;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw;
 	struct gnet_stats_queue __percpu *cpu_qstats;
 	struct tc_cookie	__rcu *act_cookie;
 	struct tcf_chain	*goto_chain;
@@ -94,7 +96,7 @@ struct tc_action_ops {
 			struct netlink_callback *, int,
 			const struct tc_action_ops *,
 			struct netlink_ext_ack *);
-	void	(*stats_update)(struct tc_action *, u64, u32, u64);
+	void	(*stats_update)(struct tc_action *, u64, u32, u64, bool);
 	size_t  (*get_fill_size)(const struct tc_action *act);
 	struct net_device *(*get_dev)(const struct tc_action *a);
 	void	(*put_dev)(struct net_device *dev);
@@ -182,13 +184,13 @@ int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
 #endif /* CONFIG_NET_CLS_ACT */
 
 static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
-					   u64 packets, u64 lastuse)
+					   u64 packets, u64 lastuse, bool hw)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	if (!a->ops->stats_update)
 		return;
 
-	a->ops->stats_update(a, bytes, packets, lastuse);
+	a->ops->stats_update(a, bytes, packets, lastuse, hw);
 #endif
 }
 
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 75a3f3f..bbfe27f 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -318,7 +318,7 @@ tcf_exts_stats_update(const struct tcf_exts *exts,
 	for (i = 0; i < exts->nr_actions; i++) {
 		struct tc_action *a = exts->actions[i];
 
-		tcf_action_stats_update(a, bytes, packets, lastuse);
+		tcf_action_stats_update(a, bytes, packets, lastuse, true);
 	}
 
 	preempt_enable();
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index fac8c76..3c7c234 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -81,6 +81,7 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
 static void free_tcf(struct tc_action *p)
 {
 	free_percpu(p->cpu_bstats);
+	free_percpu(p->cpu_bstats_hw);
 	free_percpu(p->cpu_qstats);
 
 	tcf_set_action_cookie(&p->act_cookie, NULL);
@@ -390,9 +391,12 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
 		if (!p->cpu_bstats)
 			goto err1;
+		p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
+		if (!p->cpu_bstats_hw)
+			goto err2;
 		p->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
 		if (!p->cpu_qstats)
-			goto err2;
+			goto err3;
 	}
 	spin_lock_init(&p->tcfa_lock);
 	p->tcfa_index = index;
@@ -404,15 +408,17 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 					&p->tcfa_rate_est,
 					&p->tcfa_lock, NULL, est);
 		if (err)
-			goto err3;
+			goto err4;
 	}
 
 	p->idrinfo = idrinfo;
 	p->ops = ops;
 	*a = p;
 	return 0;
-err3:
+err4:
 	free_percpu(p->cpu_qstats);
+err3:
+	free_percpu(p->cpu_bstats_hw);
 err2:
 	free_percpu(p->cpu_bstats);
 err1:
@@ -997,6 +1003,8 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
 		goto errout;
 
 	if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 ||
+	    gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw,
+				     &p->tcfa_bstats_hw) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, p->cpu_qstats,
 				  &p->tcfa_qstats,
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index aa44d14..c89a7fa 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -157,7 +157,7 @@ static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a,
 }
 
 static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-				  u64 lastuse)
+				  u64 lastuse, bool hw)
 {
 	struct tcf_gact *gact = to_gact(a);
 	int action = READ_ONCE(gact->tcf_action);
@@ -168,6 +168,10 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	if (action == TC_ACT_SHOT)
 		this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;
 
+	if (hw)
+		_bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats_hw),
+				   bytes, packets);
+
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index a9d64bf..1dae5f2 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -283,12 +283,15 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 }
 
 static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-			     u64 lastuse)
+			     u64 lastuse, bool hw)
 {
 	struct tcf_mirred *m = to_mirred(a);
 	struct tcf_t *tm = &m->tcf_tm;
 
 	_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
+	if (hw)
+		_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
+				   bytes, packets);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }