diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 65d0d25f2648..83a3e47d5845 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -71,6 +71,7 @@ struct Qdisc {
 				      * qdisc_tree_decrease_qlen() should stop.
 				      */
 #define TCQ_F_INVISIBLE		0x80 /* invisible by default in dump */
+#define TCQ_F_OFFLOADED		0x200 /* qdisc is offloaded to HW */
 	u32			limit;
 	const struct Qdisc_ops	*ops;
 	struct qdisc_size_table	__rcu *stab;
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index d8b5f80c2ea6..843e29aa3cac 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -557,6 +557,7 @@ enum {
 	TCA_PAD,
 	TCA_DUMP_INVISIBLE,
 	TCA_CHAIN,
+	TCA_HW_OFFLOAD,
 	__TCA_MAX
 };
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index b6c4f536876b..0f1eab99ff4e 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -795,6 +795,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 	tcm->tcm_info = refcount_read(&q->refcnt);
 	if (nla_put_string(skb, TCA_KIND, q->ops->id))
 		goto nla_put_failure;
+	if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED)))
+		goto nla_put_failure;
 	if (q->ops->dump && q->ops->dump(q, skb) < 0)
 		goto nla_put_failure;
 	qlen = q->q.qlen;