diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 6601d4e3fb0a8..c4b2072e4ecef 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -767,15 +767,12 @@ static u32 qdisc_alloc_handle(struct net_device *dev)
 
 void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len)
 {
-	bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED;
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
 	bool notify;
 	int drops;
 
-	if (n == 0 && len == 0)
-		return;
 	drops = max_t(int, n, 0);
 	rcu_read_lock();
 	while ((parentid = sch->parent)) {
@@ -784,17 +781,8 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len)
 
 		if (sch->flags & TCQ_F_NOPARENT)
 			break;
-		/* Notify parent qdisc only if child qdisc becomes empty.
-		 *
-		 * If child was empty even before update then backlog
-		 * counter is screwed and we skip notification because
-		 * parent class is already passive.
-		 *
-		 * If the original child was offloaded then it is allowed
-		 * to be seem as empty, so the parent is notified anyway.
-		 */
-		notify = !sch->q.qlen && !WARN_ON_ONCE(!n &&
-						       !qdisc_is_offloaded);
+		/* Notify parent qdisc only if child qdisc becomes empty. */
+		notify = !sch->q.qlen;
 		/* TODO: perform the search on a per txq basis */
 		sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
 		if (sch == NULL) {
@@ -803,6 +791,9 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len)
 		}
 		cops = sch->ops->cl_ops;
 		if (notify && cops->qlen_notify) {
+			/* Note that qlen_notify must be idempotent as it may get called
+			 * multiple times.
+			 */
 			cl = cops->find(sch, parentid);
 			cops->qlen_notify(sch, cl);
 		}
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 269572bbd9019..554662e809930 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -296,7 +296,7 @@ static void ets_class_qlen_notify(struct Qdisc *sch, unsigned long arg)
 	 * to remove them.
 	 */
 	if (!ets_class_is_strict(q, cl) && sch->q.qlen)
-		list_del(&cl->alist);
+		list_del_init(&cl->alist);
 }
 
 static int ets_class_dump(struct Qdisc *sch, unsigned long arg,
@@ -497,7 +497,7 @@ static struct sk_buff *ets_qdisc_dequeue(struct Qdisc *sch)
 			if (unlikely(!skb))
 				goto out;
 			if (cl->qdisc->q.qlen == 0)
-				list_del(&cl->alist);
+				list_del_init(&cl->alist);
 			return ets_qdisc_dequeue_skb(sch, skb);
 		}
 
@@ -662,23 +662,24 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
 
 	sch_tree_lock(sch);
 
-	q->nbands = nbands;
+	for (i = nbands; i < oldbands; i++) {
+		if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
+			list_del_init(&q->classes[i].alist);
+		qdisc_purge_queue(q->classes[i].qdisc);
+	}
+
+	WRITE_ONCE(q->nbands, nbands);
 	for (i = nstrict; i < q->nstrict; i++) {
 		if (q->classes[i].qdisc->q.qlen) {
 			list_add_tail(&q->classes[i].alist, &q->active);
 			q->classes[i].deficit = quanta[i];
 		}
 	}
-	for (i = q->nbands; i < oldbands; i++) {
-		if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
-			list_del(&q->classes[i].alist);
-		qdisc_tree_flush_backlog(q->classes[i].qdisc);
-	}
-	q->nstrict = nstrict;
+	WRITE_ONCE(q->nstrict, nstrict);
 	memcpy(q->prio2band, priomap, sizeof(priomap));
 
 	for (i = 0; i < q->nbands; i++)
-		q->classes[i].quantum = quanta[i];
+		WRITE_ONCE(q->classes[i].quantum, quanta[i]);
 
 	for (i = oldbands; i < q->nbands; i++) {
 		q->classes[i].qdisc = queues[i];
@@ -692,7 +693,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
 	for (i = q->nbands; i < oldbands; i++) {
 		qdisc_put(q->classes[i].qdisc);
 		q->classes[i].qdisc = NULL;
-		q->classes[i].quantum = 0;
+		WRITE_ONCE(q->classes[i].quantum, 0);
 		q->classes[i].deficit = 0;
 		memset(&q->classes[i].bstats, 0, sizeof(q->classes[i].bstats));
 		memset(&q->classes[i].qstats, 0, sizeof(q->classes[i].qstats));
@@ -727,7 +728,7 @@ static void ets_qdisc_reset(struct Qdisc *sch)
 
 	for (band = q->nstrict; band < q->nbands; band++) {
 		if (q->classes[band].qdisc->q.qlen)
-			list_del(&q->classes[band].alist);
+			list_del_init(&q->classes[band].alist);
 	}
 	for (band = 0; band < q->nbands; band++)
 		qdisc_reset(q->classes[band].qdisc);
@@ -749,6 +750,7 @@ static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct ets_sched *q = qdisc_priv(sch);
 	struct nlattr *opts;
 	struct nlattr *nest;
+	u8 nbands, nstrict;
 	int band;
 	int prio;
 	int err;
@@ -761,21 +763,22 @@ static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (!opts)
 		goto nla_err;
 
-	if (nla_put_u8(skb, TCA_ETS_NBANDS, q->nbands))
+	nbands = READ_ONCE(q->nbands);
+	if (nla_put_u8(skb, TCA_ETS_NBANDS, nbands))
 		goto nla_err;
 
-	if (q->nstrict &&
-	    nla_put_u8(skb, TCA_ETS_NSTRICT, q->nstrict))
+	nstrict = READ_ONCE(q->nstrict);
+	if (nstrict && nla_put_u8(skb, TCA_ETS_NSTRICT, nstrict))
 		goto nla_err;
 
-	if (q->nbands > q->nstrict) {
+	if (nbands > nstrict) {
 		nest = nla_nest_start(skb, TCA_ETS_QUANTA);
 		if (!nest)
 			goto nla_err;
 
-		for (band = q->nstrict; band < q->nbands; band++) {
+		for (band = nstrict; band < nbands; band++) {
 			if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND,
-					q->classes[band].quantum))
+					READ_ONCE(q->classes[band].quantum)))
 				goto nla_err;
 		}
 
@@ -787,7 +790,8 @@ static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb)
 		goto nla_err;
 
 	for (prio = 0; prio <= TC_PRIO_MAX; prio++) {
-		if (nla_put_u8(skb, TCA_ETS_PRIOMAP_BAND, q->prio2band[prio]))
+		if (nla_put_u8(skb, TCA_ETS_PRIOMAP_BAND,
+			       READ_ONCE(q->prio2band[prio])))
 			goto nla_err;
 	}
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 730a2fd2ad11b..53b80c79cc607 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1579,6 +1579,9 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 		return err;
 	}
 
+	sch->qstats.backlog += len;
+	sch->q.qlen++;
+
 	if (first && !cl_in_el_or_vttree(cl)) {
 		if (cl->cl_flags & HFSC_RSC)
 			init_ed(cl, len);
@@ -1594,9 +1597,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 
 	}
 
-	sch->qstats.backlog += len;
-	sch->q.qlen++;
-
 	return NET_XMIT_SUCCESS;
 }
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 4054d5a87df84..74503f22b0f38 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -345,6 +345,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	struct nlattr *tb[TCA_TBF_MAX + 1];
 	struct tc_tbf_qopt *qopt;
 	struct Qdisc *child = NULL;
+	struct Qdisc *old = NULL;
 	struct psched_ratecfg rate;
 	struct psched_ratecfg peak;
 	u64 max_size;
@@ -435,8 +436,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 
 	sch_tree_lock(sch);
 	if (child) {
-		qdisc_tree_flush_backlog(q->qdisc);
-		qdisc_put(q->qdisc);
+		qdisc_purge_queue(q->qdisc);
+		old = q->qdisc;
 		q->qdisc = child;
 	}
 	q->limit = qopt->limit;
@@ -456,6 +457,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
 
 	sch_tree_unlock(sch);
+	qdisc_put(old);
 	err = 0;
 
 	tbf_offload_change(sch);