diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e9eee99d8b1f4668aef09526341d0e032a6f120b..160a407c19632a2220fa6fc5efc120086fd076ee 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -445,7 +445,6 @@ static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch,
 {
 	__skb_queue_tail(list, skb);
 	sch->qstats.backlog += qdisc_pkt_len(skb);
-	qdisc_bstats_update(sch, skb);
 
 	return NET_XMIT_SUCCESS;
 }
@@ -460,8 +459,10 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct Qdisc *sch,
 {
 	struct sk_buff *skb = __skb_dequeue(list);
 
-	if (likely(skb != NULL))
+	if (likely(skb != NULL)) {
 		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_bstats_update(sch, skb);
+	}
 
 	return skb;
 }
@@ -474,10 +475,11 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
 static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch,
 					      struct sk_buff_head *list)
 {
-	struct sk_buff *skb = __qdisc_dequeue_head(sch, list);
+	struct sk_buff *skb = __skb_dequeue(list);
 
 	if (likely(skb != NULL)) {
 		unsigned int len = qdisc_pkt_len(skb);
+		sch->qstats.backlog -= len;
 		kfree_skb(skb);
 		return len;
 	}
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index c80d1c210c5d621454acf3388a63440c3fbfe740..5f63ec58942c10ac5088c6e6fca6e40463235a0b 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -390,7 +390,6 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	ret = qdisc_enqueue(skb, cl->q);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
-		qdisc_bstats_update(sch, skb);
 		cbq_mark_toplevel(q, cl);
 		if (!cl->next_alive)
 			cbq_activate_class(cl);
@@ -649,7 +648,6 @@ static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child)
 		ret = qdisc_enqueue(skb, cl->q);
 		if (ret == NET_XMIT_SUCCESS) {
 			sch->q.qlen++;
-			qdisc_bstats_update(sch, skb);
 			if (!cl->next_alive)
 				cbq_activate_class(cl);
 			return 0;
@@ -971,6 +969,7 @@ cbq_dequeue(struct Qdisc *sch)
 
 		skb = cbq_dequeue_1(sch);
 		if (skb) {
+			qdisc_bstats_update(sch, skb);
 			sch->q.qlen--;
 			sch->flags &= ~TCQ_F_THROTTLED;
 			return skb;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index de55e642eafc2924bd2b6220aaac1d38e879954e..6b7fe4a84f138b903928a8c5f5f90f8fe3b855dc 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -376,7 +376,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 
 	bstats_update(&cl->bstats, skb);
-	qdisc_bstats_update(sch, skb);
 
 	sch->q.qlen++;
 	return err;
@@ -403,6 +402,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
 			skb = qdisc_dequeue_peeked(cl->qdisc);
 			if (cl->qdisc->q.qlen == 0)
 				list_del(&cl->alist);
+			qdisc_bstats_update(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 60f4bdd4408e25888b4575bd9ab7b75441cab8c6..0f7bf3fdfea5a63683d86887e4d9fad99ff40a82 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -260,7 +260,6 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
-	qdisc_bstats_update(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -283,6 +282,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 	if (skb == NULL)
 		return NULL;
 
+	qdisc_bstats_update(sch, skb);
 	sch->q.qlen--;
 
 	index = skb->tc_index & (p->indices - 1);
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index aa4d6337e43cab4f3a094d6b2028be50afdcada5..d468b479aa937f410a665045eb4018bfc08de255 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -46,17 +46,14 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 
 static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 {
-	struct sk_buff *skb_head;
 	struct fifo_sched_data *q = qdisc_priv(sch);
 
 	if (likely(skb_queue_len(&sch->q) < q->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
 	/* queue full, remove one skb to fulfill the limit */
-	skb_head = qdisc_dequeue_head(sch);
+	__qdisc_queue_drop_head(sch, &sch->q);
 	sch->qstats.drops++;
-	kfree_skb(skb_head);
-
 	qdisc_enqueue_tail(skb, sch);
 
 	return NET_XMIT_CN;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 2e45791d4f6cf7970d590fde138981254b359403..14a799de1c3535ed99c9af448080265fa406fe88 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1600,7 +1600,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		set_active(cl, qdisc_pkt_len(skb));
 
 	bstats_update(&cl->bstats, skb);
-	qdisc_bstats_update(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -1666,6 +1665,7 @@ hfsc_dequeue(struct Qdisc *sch)
 	}
 
 	sch->flags &= ~TCQ_F_THROTTLED;
+	qdisc_bstats_update(sch, skb);
 	sch->q.qlen--;
 
 	return skb;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 984c1b0c68369dd24b4837fd681126abc229ce92..fc12fe6f559796d11aaa8b4e769b26a6a28643e9 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -574,7 +574,6 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 
 	sch->q.qlen++;
-	qdisc_bstats_update(sch, skb);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -842,7 +841,7 @@ static struct sk_buff *htb_dequeue_tree(struct htb_sched *q, int prio,
 
 static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 {
-	struct sk_buff *skb = NULL;
+	struct sk_buff *skb;
 	struct htb_sched *q = qdisc_priv(sch);
 	int level;
 	psched_time_t next_event;
@@ -851,6 +850,8 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 	/* try to dequeue direct packets as high prio (!) to minimize cpu work */
 	skb = __skb_dequeue(&q->direct_queue);
 	if (skb != NULL) {
+ok:
+		qdisc_bstats_update(sch, skb);
 		sch->flags &= ~TCQ_F_THROTTLED;
 		sch->q.qlen--;
 		return skb;
@@ -884,11 +885,8 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 			int prio = ffz(m);
 			m |= 1 << prio;
 			skb = htb_dequeue_tree(q, prio, level);
-			if (likely(skb != NULL)) {
-				sch->q.qlen--;
-				sch->flags &= ~TCQ_F_THROTTLED;
-				goto fin;
-			}
+			if (likely(skb != NULL))
+				goto ok;
 		}
 	}
 	sch->qstats.overlimits++;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 21f13da24763977eaea671c19a58357018f72899..436a2e75b322db524764a2483cd385e905aa4534 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -83,7 +83,6 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	ret = qdisc_enqueue(skb, qdisc);
 	if (ret == NET_XMIT_SUCCESS) {
-		qdisc_bstats_update(sch, skb);
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
 	}
@@ -112,6 +111,7 @@ static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
 			qdisc = q->queues[q->curband];
 			skb = qdisc->dequeue(qdisc);
 			if (skb) {
+				qdisc_bstats_update(sch, skb);
 				sch->q.qlen--;
 				return skb;
 			}
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 1c4bce86347977ec93b1fa5a0fdcceaf34cfe257..6a3006b38dc55e65c4629a967a326eed684d7fd1 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -240,7 +240,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		sch->q.qlen++;
-		qdisc_bstats_update(sch, skb);
 	} else if (net_xmit_drop_count(ret)) {
 		sch->qstats.drops++;
 	}
@@ -289,6 +288,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 				skb->tstamp.tv64 = 0;
 #endif
 			pr_debug("netem_dequeue: return skb=%p\n", skb);
+			qdisc_bstats_update(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
@@ -476,7 +476,6 @@ static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 		__skb_queue_after(list, skb, nskb);
 
 		sch->qstats.backlog += qdisc_pkt_len(nskb);
-		qdisc_bstats_update(sch, nskb);
 
 		return NET_XMIT_SUCCESS;
 	}
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 966158d49dd105ce882ece6a6ccd6f072f5676ca..fbd710d619bf372535d21ef38c750c7e6e6c9cf0 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -84,7 +84,6 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	ret = qdisc_enqueue(skb, qdisc);
 	if (ret == NET_XMIT_SUCCESS) {
-		qdisc_bstats_update(sch, skb);
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
 	}
@@ -116,6 +115,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc* sch)
 		struct Qdisc *qdisc = q->queues[prio];
 		struct sk_buff *skb = qdisc->dequeue(qdisc);
 		if (skb) {
+			qdisc_bstats_update(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index a6009c5a2c97dbe446b162923fb997db00f00ee6..9f98dbd32d4c8176d6c940dd098f71fa0c00cb4d 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -94,7 +94,6 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 
 	ret = qdisc_enqueue(skb, child);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
-		qdisc_bstats_update(sch, skb);
 		sch->q.qlen++;
 	} else if (net_xmit_drop_count(ret)) {
 		q->stats.pdrop++;
@@ -114,11 +113,13 @@ static struct sk_buff * red_dequeue(struct Qdisc* sch)
 	struct Qdisc *child = q->qdisc;
 
 	skb = child->dequeue(child);
-	if (skb)
+	if (skb) {
+		qdisc_bstats_update(sch, skb);
 		sch->q.qlen--;
-	else if (!red_is_idling(&q->parms))
-		red_start_of_idle_period(&q->parms);
-
+	} else {
+		if (!red_is_idling(&q->parms))
+			red_start_of_idle_period(&q->parms);
+	}
 	return skb;
 }
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 239ec53a634dace6d29a3294c2a98e4c401539b8..edea8cefec6c9502e0a841e4bb4bd3ef11003495 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -402,10 +402,8 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		q->tail = slot;
 		slot->allot = q->scaled_quantum;
 	}
-	if (++sch->q.qlen <= q->limit) {
-		qdisc_bstats_update(sch, skb);
+	if (++sch->q.qlen <= q->limit)
 		return NET_XMIT_SUCCESS;
-	}
 
 	sfq_drop(sch);
 	return NET_XMIT_CN;
@@ -445,6 +443,7 @@ sfq_dequeue(struct Qdisc *sch)
 	}
 	skb = slot_dequeue_head(slot);
 	sfq_dec(q, a);
+	qdisc_bstats_update(sch, skb);
 	sch->q.qlen--;
 	sch->qstats.backlog -= qdisc_pkt_len(skb);
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 77565e721811f5cc5789a24987be3b0c04a6b371..e93165820c3f02ec4edc072b26b04dcdd4645ce0 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -134,7 +134,6 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 	}
 
 	sch->q.qlen++;
-	qdisc_bstats_update(sch, skb);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -187,6 +186,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch)
 			q->ptokens = ptoks;
 			sch->q.qlen--;
 			sch->flags &= ~TCQ_F_THROTTLED;
+			qdisc_bstats_update(sch, skb);
 			return skb;
 		}
 
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 84ce48eadff4952e2552306fae3197858af86c59..d84e7329660fb5f21e5e87d11fae435e27907a8b 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -87,7 +87,6 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 
 	if (q->q.qlen < dev->tx_queue_len) {
 		__skb_queue_tail(&q->q, skb);
-		qdisc_bstats_update(sch, skb);
 		return NET_XMIT_SUCCESS;
 	}
 
@@ -111,6 +110,8 @@ teql_dequeue(struct Qdisc* sch)
 			dat->m->slaves = sch;
 			netif_wake_queue(m);
 		}
+	} else {
+		qdisc_bstats_update(sch, skb);
 	}
 	sch->q.qlen = dat->q.qlen + dat_queue->qdisc->q.qlen;
 	return skb;