25 files changed, 254 insertions, 185 deletions

diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 67dc7ce9b63..83ddfc07e45 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -508,8 +508,7 @@ static int tcf_csum(struct sk_buff *skb,
 
 	spin_lock(&p->tcf_lock);
 	p->tcf_tm.lastuse = jiffies;
-	p->tcf_bstats.bytes += qdisc_pkt_len(skb);
-	p->tcf_bstats.packets++;
+	bstats_update(&p->tcf_bstats, skb);
 	action = p->tcf_action;
 	update_flags = p->update_flags;
 	spin_unlock(&p->tcf_lock);
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 8daef963225..c2a7c20e81c 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -209,8 +209,7 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a,
 	spin_lock(&ipt->tcf_lock);
 
 	ipt->tcf_tm.lastuse = jiffies;
-	ipt->tcf_bstats.bytes += qdisc_pkt_len(skb);
-	ipt->tcf_bstats.packets++;
+	bstats_update(&ipt->tcf_bstats, skb);
 
 	/* yes, we have to worry about both in and out dev
 	 worry later - danger - this API seems to have changed
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 0c311be9282..d765067e99d 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -165,8 +165,7 @@ static int tcf_mirred(struct sk_buff *skb, struct tc_action *a,
 
 	spin_lock(&m->tcf_lock);
 	m->tcf_tm.lastuse = jiffies;
-	m->tcf_bstats.bytes += qdisc_pkt_len(skb);
-	m->tcf_bstats.packets++;
+	bstats_update(&m->tcf_bstats, skb);
 
 	dev = m->tcfm_dev;
 	if (!dev) {
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 186eb837e60..178a4bd7b7c 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -125,8 +125,7 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a,
 	egress = p->flags & TCA_NAT_FLAG_EGRESS;
 	action = p->tcf_action;
 
-	p->tcf_bstats.bytes += qdisc_pkt_len(skb);
-	p->tcf_bstats.packets++;
+	bstats_update(&p->tcf_bstats, skb);
 
 	spin_unlock(&p->tcf_lock);
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index a0593c9640d..445bef716f7 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -187,8 +187,7 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a,
 bad:
 	p->tcf_qstats.overlimits++;
 done:
-	p->tcf_bstats.bytes += qdisc_pkt_len(skb);
-	p->tcf_bstats.packets++;
+	bstats_update(&p->tcf_bstats, skb);
 	spin_unlock(&p->tcf_lock);
 	return p->tcf_action;
 }
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 7ebf7439b47..e2f08b1e2e5 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -298,8 +298,7 @@ static int tcf_act_police(struct sk_buff *skb, struct tc_action *a,
 
 	spin_lock(&police->tcf_lock);
 
-	police->tcf_bstats.bytes += qdisc_pkt_len(skb);
-	police->tcf_bstats.packets++;
+	bstats_update(&police->tcf_bstats, skb);
 
 	if (police->tcfp_ewma_rate &&
 	    police->tcf_rate_est.bps >= police->tcfp_ewma_rate) {
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 97e84f3ee77..7287cff7af3 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -42,8 +42,7 @@ static int tcf_simp(struct sk_buff *skb, struct tc_action *a, struct tcf_result
 
 	spin_lock(&d->tcf_lock);
 	d->tcf_tm.lastuse = jiffies;
-	d->tcf_bstats.bytes += qdisc_pkt_len(skb);
-	d->tcf_bstats.packets++;
+	bstats_update(&d->tcf_bstats, skb);
 
 	/* print policy string followed by _ then packet count
 	 * Example if this was the 3rd packet and the string was "hello"
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 66cbf4eb885..836f5fee9e5 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -46,8 +46,7 @@ static int tcf_skbedit(struct sk_buff *skb, struct tc_action *a,
 
 	spin_lock(&d->tcf_lock);
 	d->tcf_tm.lastuse = jiffies;
-	d->tcf_bstats.bytes += qdisc_pkt_len(skb);
-	d->tcf_bstats.packets++;
+	bstats_update(&d->tcf_bstats, skb);
 
 	if (d->flags & SKBEDIT_F_PRIORITY)
 		skb->priority = d->priority;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index efd4f95fd05..f23d9155b1e 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -268,6 +268,10 @@ static int basic_dump(struct tcf_proto *tp, unsigned long fh,
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
+
+	if (tcf_exts_dump_stats(skb, &f->exts, &basic_ext_map) < 0)
+		goto nla_put_failure;
+
 	return skb->len;
 
 nla_put_failure:
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 282540778aa..943d733409d 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -422,10 +422,8 @@ drop: __maybe_unused
 		}
 		return ret;
 	}
-	sch->bstats.bytes += qdisc_pkt_len(skb);
-	sch->bstats.packets++;
-	flow->bstats.bytes += qdisc_pkt_len(skb);
-	flow->bstats.packets++;
+	qdisc_bstats_update(sch, skb);
+	bstats_update(&flow->bstats, skb);
 	/*
 	 * Okay, this may seem weird. We pretend we've dropped the packet if
 	 * it goes via ATM. The reason for this is that the outer qdisc
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index eb763159086..c80d1c210c5 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -390,8 +390,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	ret = qdisc_enqueue(skb, cl->q);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
-		sch->bstats.packets++;
-		sch->bstats.bytes += qdisc_pkt_len(skb);
+		qdisc_bstats_update(sch, skb);
 		cbq_mark_toplevel(q, cl);
 		if (!cl->next_alive)
 			cbq_activate_class(cl);
@@ -650,8 +649,7 @@ 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++;
-			sch->bstats.packets++;
-			sch->bstats.bytes += qdisc_pkt_len(skb);
+			qdisc_bstats_update(sch, skb);
 			if (!cl->next_alive)
 				cbq_activate_class(cl);
 			return 0;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index aa8b5313f8c..de55e642eaf 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -351,7 +351,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct drr_sched *q = qdisc_priv(sch);
 	struct drr_class *cl;
-	unsigned int len;
 	int err;
 
 	cl = drr_classify(skb, sch, &err);
@@ -362,7 +361,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
-	len = qdisc_pkt_len(skb);
 	err = qdisc_enqueue(skb, cl->qdisc);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
@@ -377,10 +375,8 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		cl->deficit = cl->quantum;
 	}
 
-	cl->bstats.packets++;
-	cl->bstats.bytes += len;
-	sch->bstats.packets++;
-	sch->bstats.bytes += len;
+	bstats_update(&cl->bstats, skb);
+	qdisc_bstats_update(sch, skb);
 
 	sch->q.qlen++;
 	return err;
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 1d295d62bb5..60f4bdd4408 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -260,8 +260,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
-	sch->bstats.bytes += qdisc_pkt_len(skb);
-	sch->bstats.packets++;
+	qdisc_bstats_update(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 4dfecb0cba3..aa4d6337e43 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -54,8 +54,6 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 
 	/* queue full, remove one skb to fulfill the limit */
 	skb_head = qdisc_dequeue_head(sch);
-	sch->bstats.bytes -= qdisc_pkt_len(skb_head);
-	sch->bstats.packets--;
 	sch->qstats.drops++;
 	kfree_skb(skb_head);
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 5dbb3cd96e5..34dc598440a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -60,8 +60,7 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 
 		/* check the reason of requeuing without tx lock first */
 		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
-		if (!netif_tx_queue_stopped(txq) &&
-		    !netif_tx_queue_frozen(txq)) {
+		if (!netif_tx_queue_frozen_or_stopped(txq)) {
 			q->gso_skb = NULL;
 			q->q.qlen--;
 		} else
@@ -122,7 +121,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 	spin_unlock(root_lock);
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
-	if (!netif_tx_queue_stopped(txq) && !netif_tx_queue_frozen(txq))
+	if (!netif_tx_queue_frozen_or_stopped(txq))
 		ret = dev_hard_start_xmit(skb, dev, txq);
 
 	HARD_TX_UNLOCK(dev, txq);
@@ -144,8 +143,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 		ret = dev_requeue_skb(skb, q);
 	}
 
-	if (ret && (netif_tx_queue_stopped(txq) ||
-		    netif_tx_queue_frozen(txq)))
+	if (ret && netif_tx_queue_frozen_or_stopped(txq))
 		ret = 0;
 
 	return ret;
@@ -555,7 +553,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	size = QDISC_ALIGN(sizeof(*sch));
 	size += ops->priv_size + (QDISC_ALIGNTO - 1);
 
-	p = kzalloc(size, GFP_KERNEL);
+	p = kzalloc_node(size, GFP_KERNEL,
+			 netdev_queue_numa_node_read(dev_queue));
+
 	if (!p)
 		goto errout;
 	sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
@@ -810,20 +810,35 @@ static bool some_qdisc_is_busy(struct net_device *dev)
 	return false;
 }
 
-void dev_deactivate(struct net_device *dev)
+void dev_deactivate_many(struct list_head *head)
 {
-	netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc);
-	if (dev_ingress_queue(dev))
-		dev_deactivate_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
+	struct net_device *dev;
+
+	list_for_each_entry(dev, head, unreg_list) {
+		netdev_for_each_tx_queue(dev, dev_deactivate_queue,
+					 &noop_qdisc);
+		if (dev_ingress_queue(dev))
+			dev_deactivate_queue(dev, dev_ingress_queue(dev),
+					     &noop_qdisc);
 
-	dev_watchdog_down(dev);
+		dev_watchdog_down(dev);
+	}
 
 	/* Wait for outstanding qdisc-less dev_queue_xmit calls. */
 	synchronize_rcu();
 
 	/* Wait for outstanding qdisc_run calls. */
-	while (some_qdisc_is_busy(dev))
-		yield();
+	list_for_each_entry(dev, head, unreg_list)
+		while (some_qdisc_is_busy(dev))
+			yield();
+}
+
+void dev_deactivate(struct net_device *dev)
+{
+	LIST_HEAD(single);
+
+	list_add(&dev->unreg_list, &single);
+	dev_deactivate_many(&single);
 }
 
 static void dev_init_scheduler_queue(struct net_device *dev,
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 069c62b7bb3..2e45791d4f6 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1599,10 +1599,8 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (cl->qdisc->q.qlen == 1)
 		set_active(cl, qdisc_pkt_len(skb));
 
-	cl->bstats.packets++;
-	cl->bstats.bytes += qdisc_pkt_len(skb);
-	sch->bstats.packets++;
-	sch->bstats.bytes += qdisc_pkt_len(skb);
+	bstats_update(&cl->bstats, skb);
+	qdisc_bstats_update(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 01b519d6c52..984c1b0c683 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -569,15 +569,12 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		}
 		return ret;
 	} else {
-		cl->bstats.packets +=
-			skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1;
-		cl->bstats.bytes += qdisc_pkt_len(skb);
+		bstats_update(&cl->bstats, skb);
 		htb_activate(q, cl);
 	}
 
 	sch->q.qlen++;
-	sch->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1;
-	sch->bstats.bytes += qdisc_pkt_len(skb);
+	qdisc_bstats_update(sch, skb);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -648,12 +645,10 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl,
 				htb_add_to_wait_tree(q, cl, diff);
 		}
 
-		/* update byte stats except for leaves which are already updated */
-		if (cl->level) {
-			cl->bstats.bytes += bytes;
-			cl->bstats.packets += skb_is_gso(skb)?
-					skb_shinfo(skb)->gso_segs:1;
-		}
+		/* update basic stats except for leaves which are already updated */
+		if (cl->level)
+			bstats_update(&cl->bstats, skb);
+
 		cl = cl->parent;
 	}
 }
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index f10e34a6844..bce1665239b 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -63,8 +63,7 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	result = tc_classify(skb, p->filter_list, &res);
 
-	sch->bstats.packets++;
-	sch->bstats.bytes += qdisc_pkt_len(skb);
+	qdisc_bstats_update(sch, skb);
 	switch (result) {
 	case TC_ACT_SHOT:
 		result = TC_ACT_SHOT;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 32690deab5d..21f13da2476 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -83,8 +83,7 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	ret = qdisc_enqueue(skb, qdisc);
 	if (ret == NET_XMIT_SUCCESS) {
-		sch->bstats.bytes += qdisc_pkt_len(skb);
-		sch->bstats.packets++;
+		qdisc_bstats_update(sch, skb);
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
 	}
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index e5593c083a7..1c4bce86347 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -240,8 +240,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		sch->q.qlen++;
-		sch->bstats.bytes += qdisc_pkt_len(skb);
-		sch->bstats.packets++;
+		qdisc_bstats_update(sch, skb);
 	} else if (net_xmit_drop_count(ret)) {
 		sch->qstats.drops++;
 	}
@@ -477,8 +476,7 @@ static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 		__skb_queue_after(list, skb, nskb);
 
 		sch->qstats.backlog += qdisc_pkt_len(nskb);
-		sch->bstats.bytes += qdisc_pkt_len(nskb);
-		sch->bstats.packets++;
+		qdisc_bstats_update(sch, nskb);
 
 		return NET_XMIT_SUCCESS;
 	}
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index b1c95bce33c..966158d49dd 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -84,8 +84,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	ret = qdisc_enqueue(skb, qdisc);
 	if (ret == NET_XMIT_SUCCESS) {
-		sch->bstats.bytes += qdisc_pkt_len(skb);
-		sch->bstats.packets++;
+		qdisc_bstats_update(sch, skb);
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
 	}
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 8d42bb3ba54..a6009c5a2c9 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -94,8 +94,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 
 	ret = qdisc_enqueue(skb, child);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
-		sch->bstats.bytes += qdisc_pkt_len(skb);
-		sch->bstats.packets++;
+		qdisc_bstats_update(sch, skb);
 		sch->q.qlen++;
 	} else if (net_xmit_drop_count(ret)) {
 		q->stats.pdrop++;
@@ -239,6 +238,7 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 		.Scell_log	= q->parms.Scell_log,
 	};
 
+	sch->qstats.backlog = q->qdisc->qstats.backlog;
 	opts = nla_nest_start(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 3cf478d012d..239ec53a634 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -67,27 +67,47 @@
 
 	IMPLEMENTATION:
 	This implementation limits maximal queue length to 128;
-	maximal mtu to 2^15-1; number of hash buckets to 1024.
+	max mtu to 2^18-1; max 128 flows, number of hash buckets to 1024.
 	The only goal of this restrictions was that all data
-	fit into one 4K page :-). Struct sfq_sched_data is
-	organized in anti-cache manner: all the data for a bucket
-	are scattered over different locations. This is not good,
-	but it allowed me to put it into 4K.
+	fit into one 4K page on 32bit arches.
 
 	It is easy to increase these values, but not in flight.  */
 
-#define SFQ_DEPTH		128
+#define SFQ_DEPTH		128 /* max number of packets per flow */
+#define SFQ_SLOTS		128 /* max number of flows */
+#define SFQ_EMPTY_SLOT		255
 #define SFQ_HASH_DIVISOR	1024
+/* We use 16 bits to store allot, and want to handle packets up to 64K
+ * Scale allot by 8 (1<<3) so that no overflow occurs.
+ */
+#define SFQ_ALLOT_SHIFT		3
+#define SFQ_ALLOT_SIZE(X)	DIV_ROUND_UP(X, 1 << SFQ_ALLOT_SHIFT)
 
-/* This type should contain at least SFQ_DEPTH*2 values */
+/* This type should contain at least SFQ_DEPTH + SFQ_SLOTS values */
 typedef unsigned char sfq_index;
 
+/*
+ * We dont use pointers to save space.
+ * Small indexes [0 ... SFQ_SLOTS - 1] are 'pointers' to slots[] array
+ * while following values [SFQ_SLOTS ... SFQ_SLOTS + SFQ_DEPTH - 1]
+ * are 'pointers' to dep[] array
+ */
 struct sfq_head
 {
 	sfq_index	next;
 	sfq_index	prev;
 };
 
+struct sfq_slot {
+	struct sk_buff	*skblist_next;
+	struct sk_buff	*skblist_prev;
+	sfq_index	qlen; /* number of skbs in skblist */
+	sfq_index	next; /* next slot in sfq chain */
+	struct sfq_head dep; /* anchor in dep[] chains */
+	unsigned short	hash; /* hash value (index in ht[]) */
+	short		allot; /* credit for this slot */
+};
+
 struct sfq_sched_data
 {
 /* Parameters */
@@ -99,17 +119,24 @@ struct sfq_sched_data
 	struct tcf_proto *filter_list;
 	struct timer_list perturb_timer;
 	u32		perturbation;
-	sfq_index	tail;		/* Index of current slot in round */
-	sfq_index	max_depth;	/* Maximal depth */
-
+	sfq_index	cur_depth;	/* depth of longest slot */
+	unsigned short  scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
+	struct sfq_slot *tail;		/* current slot in round */
 	sfq_index	ht[SFQ_HASH_DIVISOR];	/* Hash table */
-	sfq_index	next[SFQ_DEPTH];	/* Active slots link */
-	short		allot[SFQ_DEPTH];	/* Current allotment per slot */
-	unsigned short	hash[SFQ_DEPTH];	/* Hash value indexed by slots */
-	struct sk_buff_head	qs[SFQ_DEPTH];		/* Slot queue */
-	struct sfq_head	dep[SFQ_DEPTH*2];	/* Linked list of slots, indexed by depth */
+	struct sfq_slot	slots[SFQ_SLOTS];
+	struct sfq_head	dep[SFQ_DEPTH];	/* Linked list of slots, indexed by depth */
 };
 
+/*
+ * sfq_head are either in a sfq_slot or in dep[] array
+ */
+static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index val)
+{
+	if (val < SFQ_SLOTS)
+		return &q->slots[val].dep;
+	return &q->dep[val - SFQ_SLOTS];
+}
+
 static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1)
 {
 	return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1);
@@ -200,30 +227,41 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 	return 0;
 }
 
+/*
+ * x : slot number [0 .. SFQ_SLOTS - 1]
+ */
 static inline void sfq_link(struct sfq_sched_data *q, sfq_index x)
 {
 	sfq_index p, n;
-	int d = q->qs[x].qlen + SFQ_DEPTH;
+	int qlen = q->slots[x].qlen;
+
+	p = qlen + SFQ_SLOTS;
+	n = q->dep[qlen].next;
 
-	p = d;
-	n = q->dep[d].next;
-	q->dep[x].next = n;
-	q->dep[x].prev = p;
-	q->dep[p].next = q->dep[n].prev = x;
+	q->slots[x].dep.next = n;
+	q->slots[x].dep.prev = p;
+
+	q->dep[qlen].next = x;		/* sfq_dep_head(q, p)->next = x */
+	sfq_dep_head(q, n)->prev = x;
 }
 
+#define sfq_unlink(q, x, n, p)			\
+	n = q->slots[x].dep.next;		\
+	p = q->slots[x].dep.prev;		\
+	sfq_dep_head(q, p)->next = n;		\
+	sfq_dep_head(q, n)->prev = p
+
+
 static inline void sfq_dec(struct sfq_sched_data *q, sfq_index x)
 {
 	sfq_index p, n;
+	int d;
 
-	n = q->dep[x].next;
-	p = q->dep[x].prev;
-	q->dep[p].next = n;
-	q->dep[n].prev = p;
-
-	if (n == p && q->max_depth == q->qs[x].qlen + 1)
-		q->max_depth--;
+	sfq_unlink(q, x, n, p);
 
+	d = q->slots[x].qlen--;
+	if (n == p && q->cur_depth == d)
+		q->cur_depth--;
 	sfq_link(q, x);
 }
 
@@ -232,34 +270,74 @@ static inline void sfq_inc(struct sfq_sched_data *q, sfq_index x)
 	sfq_index p, n;
 	int d;
 
-	n = q->dep[x].next;
-	p = q->dep[x].prev;
-	q->dep[p].next = n;
-	q->dep[n].prev = p;
-	d = q->qs[x].qlen;
-	if (q->max_depth < d)
-		q->max_depth = d;
+	sfq_unlink(q, x, n, p);
 
+	d = ++q->slots[x].qlen;
+	if (q->cur_depth < d)
+		q->cur_depth = d;
 	sfq_link(q, x);
 }
 
+/* helper functions : might be changed when/if skb use a standard list_head */
+
+/* remove one skb from tail of slot queue */
+static inline struct sk_buff *slot_dequeue_tail(struct sfq_slot *slot)
+{
+	struct sk_buff *skb = slot->skblist_prev;
+
+	slot->skblist_prev = skb->prev;
+	skb->prev->next = (struct sk_buff *)slot;
+	skb->next = skb->prev = NULL;
+	return skb;
+}
+
+/* remove one skb from head of slot queue */
+static inline struct sk_buff *slot_dequeue_head(struct sfq_slot *slot)
+{
+	struct sk_buff *skb = slot->skblist_next;
+
+	slot->skblist_next = skb->next;
+	skb->next->prev = (struct sk_buff *)slot;
+	skb->next = skb->prev = NULL;
+	return skb;
+}
+
+static inline void slot_queue_init(struct sfq_slot *slot)
+{
+	slot->skblist_prev = slot->skblist_next = (struct sk_buff *)slot;
+}
+
+/* add skb to slot queue (tail add) */
+static inline void slot_queue_add(struct sfq_slot *slot, struct sk_buff *skb)
+{
+	skb->prev = slot->skblist_prev;
+	skb->next = (struct sk_buff *)slot;
+	slot->skblist_prev->next = skb;
+	slot->skblist_prev = skb;
+}
+
+#define	slot_queue_walk(slot, skb)		\
+	for (skb = slot->skblist_next;		\
+	     skb != (struct sk_buff *)slot;	\
+	     skb = skb->next)
+
 static unsigned int sfq_drop(struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
-	sfq_index d = q->max_depth;
+	sfq_index x, d = q->cur_depth;
 	struct sk_buff *skb;
 	unsigned int len;
+	struct sfq_slot *slot;
 
-	/* Queue is full! Find the longest slot and
-	   drop a packet from it */
-
+	/* Queue is full! Find the longest slot and drop tail packet from it */
 	if (d > 1) {
-		sfq_index x = q->dep[d + SFQ_DEPTH].next;
-		skb = q->qs[x].prev;
+		x = q->dep[d].next;
+		slot = &q->slots[x];
+drop:
+		skb = slot_dequeue_tail(slot);
 		len = qdisc_pkt_len(skb);
-		__skb_unlink(skb, &q->qs[x]);
-		kfree_skb(skb);
 		sfq_dec(q, x);
+		kfree_skb(skb);
 		sch->q.qlen--;
 		sch->qstats.drops++;
 		sch->qstats.backlog -= len;
@@ -268,19 +346,11 @@ static unsigned int sfq_drop(struct Qdisc *sch)
 
 	if (d == 1) {
 		/* It is difficult to believe, but ALL THE SLOTS HAVE LENGTH 1. */
-		d = q->next[q->tail];
-		q->next[q->tail] = q->next[d];
-		q->allot[q->next[d]] += q->quantum;
-		skb = q->qs[d].prev;
-		len = qdisc_pkt_len(skb);
-		__skb_unlink(skb, &q->qs[d]);
-		kfree_skb(skb);
-		sfq_dec(q, d);
-		sch->q.qlen--;
-		q->ht[q->hash[d]] = SFQ_DEPTH;
-		sch->qstats.drops++;
-		sch->qstats.backlog -= len;
-		return len;
+		x = q->tail->next;
+		slot = &q->slots[x];
+		q->tail->next = slot->next;
+		q->ht[slot->hash] = SFQ_EMPTY_SLOT;
+		goto drop;
 	}
 
 	return 0;
@@ -292,6 +362,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	unsigned int hash;
 	sfq_index x;
+	struct sfq_slot *slot;
 	int uninitialized_var(ret);
 
 	hash = sfq_classify(skb, sch, &ret);
@@ -304,35 +375,35 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	hash--;
 
 	x = q->ht[hash];
-	if (x == SFQ_DEPTH) {
-		q->ht[hash] = x = q->dep[SFQ_DEPTH].next;
-		q->hash[x] = hash;
+	slot = &q->slots[x];
+	if (x == SFQ_EMPTY_SLOT) {
+		x = q->dep[0].next; /* get a free slot */
+		q->ht[hash] = x;
+		slot = &q->slots[x];
+		slot->hash = hash;
 	}
 
-	/* If selected queue has length q->limit, this means that
-	 * all another queues are empty and that we do simple tail drop,
+	/* If selected queue has length q->limit, do simple tail drop,
 	 * i.e. drop _this_ packet.
 	 */
-	if (q->qs[x].qlen >= q->limit)
+	if (slot->qlen >= q->limit)
 		return qdisc_drop(skb, sch);
 
 	sch->qstats.backlog += qdisc_pkt_len(skb);
-	__skb_queue_tail(&q->qs[x], skb);
+	slot_queue_add(slot, skb);
 	sfq_inc(q, x);
-	if (q->qs[x].qlen == 1) {		/* The flow is new */
-		if (q->tail == SFQ_DEPTH) {	/* It is the first flow */
-			q->tail = x;
-			q->next[x] = x;
-			q->allot[x] = q->quantum;
+	if (slot->qlen == 1) {		/* The flow is new */
+		if (q->tail == NULL) {	/* It is the first flow */
+			slot->next = x;
 		} else {
-			q->next[x] = q->next[q->tail];
-			q->next[q->tail] = x;
-			q->tail = x;
+			slot->next = q->tail->next;
+			q->tail->next = x;
 		}
+		q->tail = slot;
+		slot->allot = q->scaled_quantum;
 	}
 	if (++sch->q.qlen <= q->limit) {
-		sch->bstats.bytes += qdisc_pkt_len(skb);
-		sch->bstats.packets++;
+		qdisc_bstats_update(sch, skb);
 		return NET_XMIT_SUCCESS;
 	}
 
@@ -344,14 +415,12 @@ static struct sk_buff *
 sfq_peek(struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
-	sfq_index a;
 
 	/* No active slots */
-	if (q->tail == SFQ_DEPTH)
+	if (q->tail == NULL)
 		return NULL;
 
-	a = q->next[q->tail];
-	return skb_peek(&q->qs[a]);
+	return q->slots[q->tail->next].skblist_next;
 }
 
 static struct sk_buff *
@@ -359,34 +428,37 @@ sfq_dequeue(struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
-	sfq_index a, old_a;
+	sfq_index a, next_a;
+	struct sfq_slot *slot;
 
 	/* No active slots */
-	if (q->tail == SFQ_DEPTH)
+	if (q->tail == NULL)
 		return NULL;
 
-	a = old_a = q->next[q->tail];
-
-	/* Grab packet */
-	skb = __skb_dequeue(&q->qs[a]);
+next_slot:
+	a = q->tail->next;
+	slot = &q->slots[a];
+	if (slot->allot <= 0) {
+		q->tail = slot;
+		slot->allot += q->scaled_quantum;
+		goto next_slot;
+	}
+	skb = slot_dequeue_head(slot);
 	sfq_dec(q, a);
 	sch->q.qlen--;
 	sch->qstats.backlog -= qdisc_pkt_len(skb);
 
 	/* Is the slot empty? */
-	if (q->qs[a].qlen == 0) {
-		q->ht[q->hash[a]] = SFQ_DEPTH;
-		a = q->next[a];
-		if (a == old_a) {
-			q->tail = SFQ_DEPTH;
+	if (slot->qlen == 0) {
+		q->ht[slot->hash] = SFQ_EMPTY_SLOT;
+		next_a = slot->next;
+		if (a == next_a) {
+			q->tail = NULL; /* no more active slots */
 			return skb;
 		}
-		q->next[q->tail] = a;
-		q->allot[a] += q->quantum;
-	} else if ((q->allot[a] -= qdisc_pkt_len(skb)) <= 0) {
-		q->tail = a;
-		a = q->next[a];
-		q->allot[a] += q->quantum;
+		q->tail->next = next_a;
+	} else {
+		slot->allot -= SFQ_ALLOT_SIZE(qdisc_pkt_len(skb));
 	}
 	return skb;
 }
@@ -422,6 +494,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 	q->quantum = ctl->quantum ? : psched_mtu(qdisc_dev(sch));
+	q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
 	q->perturb_period = ctl->perturb_period * HZ;
 	if (ctl->limit)
 		q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1);
@@ -450,19 +523,19 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 	init_timer_deferrable(&q->perturb_timer);
 
 	for (i = 0; i < SFQ_HASH_DIVISOR; i++)
-		q->ht[i] = SFQ_DEPTH;
+		q->ht[i] = SFQ_EMPTY_SLOT;
 
 	for (i = 0; i < SFQ_DEPTH; i++) {
-		skb_queue_head_init(&q->qs[i]);
-		q->dep[i + SFQ_DEPTH].next = i + SFQ_DEPTH;
-		q->dep[i + SFQ_DEPTH].prev = i + SFQ_DEPTH;
+		q->dep[i].next = i + SFQ_SLOTS;
+		q->dep[i].prev = i + SFQ_SLOTS;
 	}
 
 	q->limit = SFQ_DEPTH - 1;
-	q->max_depth = 0;
-	q->tail = SFQ_DEPTH;
+	q->cur_depth = 0;
+	q->tail = NULL;
 	if (opt == NULL) {
 		q->quantum = psched_mtu(qdisc_dev(sch));
+		q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
 		q->perturb_period = 0;
 		q->perturbation = net_random();
 	} else {
@@ -471,8 +544,10 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 			return err;
 	}
 
-	for (i = 0; i < SFQ_DEPTH; i++)
+	for (i = 0; i < SFQ_SLOTS; i++) {
+		slot_queue_init(&q->slots[i]);
 		sfq_link(q, i);
+	}
 	return 0;
 }
 
@@ -547,10 +622,19 @@ static int sfq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 				struct gnet_dump *d)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
-	sfq_index idx = q->ht[cl-1];
-	struct gnet_stats_queue qs = { .qlen = q->qs[idx].qlen };
-	struct tc_sfq_xstats xstats = { .allot = q->allot[idx] };
+	sfq_index idx = q->ht[cl - 1];
+	struct gnet_stats_queue qs = { 0 };
+	struct tc_sfq_xstats xstats = { 0 };
+	struct sk_buff *skb;
+
+	if (idx != SFQ_EMPTY_SLOT) {
+		const struct sfq_slot *slot = &q->slots[idx];
 
+		xstats.allot = slot->allot << SFQ_ALLOT_SHIFT;
+		qs.qlen = slot->qlen;
+		slot_queue_walk(slot, skb)
+			qs.backlog += qdisc_pkt_len(skb);
+	}
 	if (gnet_stats_copy_queue(d, &qs) < 0)
 		return -1;
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
@@ -565,7 +649,7 @@ static void sfq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 		return;
 
 	for (i = 0; i < SFQ_HASH_DIVISOR; i++) {
-		if (q->ht[i] == SFQ_DEPTH ||
+		if (q->ht[i] == SFQ_EMPTY_SLOT ||
 		    arg->count < arg->skip) {
 			arg->count++;
 			continue;
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 641a30d6463..77565e72181 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -134,8 +134,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 	}
 
 	sch->q.qlen++;
-	sch->bstats.bytes += qdisc_pkt_len(skb);
-	sch->bstats.packets++;
+	qdisc_bstats_update(sch, skb);
 	return NET_XMIT_SUCCESS;
 }
 
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 401af959670..af9360d1f6e 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -83,8 +83,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 
 	if (q->q.qlen < dev->tx_queue_len) {
 		__skb_queue_tail(&q->q, skb);
-		sch->bstats.bytes += qdisc_pkt_len(skb);
-		sch->bstats.packets++;
+		qdisc_bstats_update(sch, skb);
 		return NET_XMIT_SUCCESS;
 	}
 
@@ -309,8 +308,7 @@ restart:
 			if (__netif_tx_trylock(slave_txq)) {
 				unsigned int length = qdisc_pkt_len(skb);
 
-				if (!netif_tx_queue_stopped(slave_txq) &&
-				    !netif_tx_queue_frozen(slave_txq) &&
+				if (!netif_tx_queue_frozen_or_stopped(slave_txq) &&
 				    slave_ops->ndo_start_xmit(skb, slave) == NETDEV_TX_OK) {
 					txq_trans_update(slave_txq);
 					__netif_tx_unlock(slave_txq);