1 files changed, 228 insertions, 230 deletions

diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index a7ab323849b6..d920f57dc6d7 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * net/sched/sch_qfq.c         Quick Fair Queueing Plus Scheduler.
  *
  * Copyright (c) 2009 Fabio Checconi, Luigi Rizzo, and Paolo Valente.
  * Copyright (c) 2012 Paolo Valente.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -113,10 +110,10 @@
 
 #define FRAC_BITS		30	/* fixed point arithmetic */
 #define ONE_FP			(1UL << FRAC_BITS)
-#define IWSUM			(ONE_FP/QFQ_MAX_WSUM)
 
 #define QFQ_MTU_SHIFT		16	/* to support TSO/GSO */
 #define QFQ_MIN_LMAX		512	/* see qfq_slot_insert */
+#define QFQ_MAX_LMAX		(1UL << QFQ_MTU_SHIFT)
 
 #define QFQ_MAX_AGG_CLASSES	8 /* max num classes per aggregate allowed */
 
@@ -133,12 +130,9 @@ struct qfq_aggregate;
 struct qfq_class {
 	struct Qdisc_class_common common;
 
-	unsigned int refcnt;
-	unsigned int filter_cnt;
-
-	struct gnet_stats_basic_packed bstats;
+	struct gnet_stats_basic_sync bstats;
 	struct gnet_stats_queue qstats;
-	struct gnet_stats_rate_est64 rate_est;
+	struct net_rate_estimator __rcu *rate_est;
 	struct Qdisc *qdisc;
 	struct list_head alist;		/* Link for active-classes list. */
 	struct qfq_aggregate *agg;	/* Parent aggregate. */
@@ -182,13 +176,14 @@ struct qfq_group {
 };
 
 struct qfq_sched {
-	struct tcf_proto *filter_list;
+	struct tcf_proto __rcu *filter_list;
+	struct tcf_block	*block;
 	struct Qdisc_class_hash clhash;
 
 	u64			oldV, V;	/* Precise virtual times. */
 	struct qfq_aggregate	*in_serv_agg;   /* Aggregate being served. */
-	u32			num_active_agg; /* Num. of active aggregates */
 	u32			wsum;		/* weight sum */
+	u32			iwsum;		/* inverse weight sum */
 
 	unsigned long bitmaps[QFQ_MAX_STATE];	    /* Group bitmaps. */
 	struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */
@@ -207,6 +202,11 @@ struct qfq_sched {
  */
 enum update_reason {enqueue, requeue};
 
+static bool cl_is_active(struct qfq_class *cl)
+{
+	return !list_empty(&cl->alist);
+}
+
 static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
@@ -218,17 +218,14 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 	return container_of(clc, struct qfq_class, common);
 }
 
-static void qfq_purge_queue(struct qfq_class *cl)
-{
-	unsigned int len = cl->qdisc->q.qlen;
-
-	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
-}
+static const struct netlink_range_validation lmax_range = {
+	.min = QFQ_MIN_LMAX,
+	.max = QFQ_MAX_LMAX,
+};
 
 static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = {
-	[TCA_QFQ_WEIGHT] = { .type = NLA_U32 },
-	[TCA_QFQ_LMAX] = { .type = NLA_U32 },
+	[TCA_QFQ_WEIGHT] = NLA_POLICY_RANGE(NLA_U32, 1, QFQ_MAX_WEIGHT),
+	[TCA_QFQ_LMAX] = NLA_POLICY_FULL_RANGE(NLA_U32, &lmax_range),
 };
 
 /*
@@ -314,6 +311,7 @@ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg,
 
 	q->wsum +=
 		(int) agg->class_weight * (new_num_classes - agg->num_classes);
+	q->iwsum = ONE_FP / q->wsum;
 
 	agg->num_classes = new_num_classes;
 }
@@ -338,8 +336,11 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *);
 
 static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg)
 {
-	if (!hlist_unhashed(&agg->nonfull_next))
-		hlist_del_init(&agg->nonfull_next);
+	hlist_del_init(&agg->nonfull_next);
+	q->wsum -= agg->class_weight;
+	if (q->wsum != 0)
+		q->iwsum = ONE_FP / q->wsum;
+
 	if (q->in_serv_agg == agg)
 		q->in_serv_agg = qfq_choose_next_agg(q);
 	kfree(agg);
@@ -351,7 +352,7 @@ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl)
 	struct qfq_aggregate *agg = cl->agg;
 
 
-	list_del(&cl->alist); /* remove from RR queue of the aggregate */
+	list_del_init(&cl->alist); /* remove from RR queue of the aggregate */
 	if (list_empty(&agg->active)) /* agg is now inactive */
 		qfq_deactivate_agg(q, agg);
 }
@@ -383,8 +384,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight,
 			   u32 lmax)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
-	struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight);
+	struct qfq_aggregate *new_agg;
+
+	/* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */
+	if (lmax > QFQ_MAX_LMAX)
+		return -EINVAL;
 
+	new_agg = qfq_find_agg(q, lmax, weight);
 	if (new_agg == NULL) { /* create new aggregate */
 		new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC);
 		if (new_agg == NULL)
@@ -398,64 +404,69 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight,
 }
 
 static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
-			    struct nlattr **tca, unsigned long *arg)
+			    struct nlattr **tca, unsigned long *arg,
+			    struct netlink_ext_ack *extack)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl = (struct qfq_class *)*arg;
 	bool existing = false;
 	struct nlattr *tb[TCA_QFQ_MAX + 1];
 	struct qfq_aggregate *new_agg = NULL;
-	u32 weight, lmax, inv_w;
+	u32 weight, lmax, inv_w, old_weight, old_lmax;
 	int err;
 	int delta_w;
 
-	if (tca[TCA_OPTIONS] == NULL) {
-		pr_notice("qfq: no options\n");
+	if (NL_REQ_ATTR_CHECK(extack, NULL, tca, TCA_OPTIONS)) {
+		NL_SET_ERR_MSG_MOD(extack, "missing options");
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], qfq_policy);
+	err = nla_parse_nested_deprecated(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS],
+					  qfq_policy, extack);
 	if (err < 0)
 		return err;
 
-	if (tb[TCA_QFQ_WEIGHT]) {
-		weight = nla_get_u32(tb[TCA_QFQ_WEIGHT]);
-		if (!weight || weight > (1UL << QFQ_MAX_WSHIFT)) {
-			pr_notice("qfq: invalid weight %u\n", weight);
-			return -EINVAL;
-		}
-	} else
-		weight = 1;
+	weight = nla_get_u32_default(tb[TCA_QFQ_WEIGHT], 1);
 
 	if (tb[TCA_QFQ_LMAX]) {
 		lmax = nla_get_u32(tb[TCA_QFQ_LMAX]);
-		if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) {
-			pr_notice("qfq: invalid max length %u\n", lmax);
+	} else {
+		/* MTU size is user controlled */
+		lmax = psched_mtu(qdisc_dev(sch));
+		if (lmax < QFQ_MIN_LMAX || lmax > QFQ_MAX_LMAX) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "MTU size out of bounds for qfq");
 			return -EINVAL;
 		}
-	} else
-		lmax = psched_mtu(qdisc_dev(sch));
+	}
 
 	inv_w = ONE_FP / weight;
 	weight = ONE_FP / inv_w;
 
-	if (cl != NULL &&
-	    lmax == cl->agg->lmax &&
-	    weight == cl->agg->class_weight)
-		return 0; /* nothing to change */
+	if (cl != NULL) {
+		sch_tree_lock(sch);
+		old_weight = cl->agg->class_weight;
+		old_lmax   = cl->agg->lmax;
+		sch_tree_unlock(sch);
+		if (lmax == old_lmax && weight == old_weight)
+			return 0; /* nothing to change */
+	}
 
-	delta_w = weight - (cl ? cl->agg->class_weight : 0);
+	delta_w = weight - (cl ? old_weight : 0);
 
 	if (q->wsum + delta_w > QFQ_MAX_WSUM) {
-		pr_notice("qfq: total weight out of range (%d + %u)\n",
-			  delta_w, q->wsum);
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "total weight out of range (%d + %u)",
+				       delta_w, q->wsum);
 		return -EINVAL;
 	}
 
 	if (cl != NULL) { /* modify existing class */
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
-						    qdisc_root_sleeping_lock(sch),
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
+						    NULL,
+						    true,
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
@@ -469,28 +480,28 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	if (cl == NULL)
 		return -ENOBUFS;
 
-	cl->refcnt = 1;
+	gnet_stats_basic_sync_init(&cl->bstats);
 	cl->common.classid = classid;
 	cl->deficit = lmax;
+	INIT_LIST_HEAD(&cl->alist);
 
-	cl->qdisc = qdisc_create_dflt(sch->dev_queue,
-				      &pfifo_qdisc_ops, classid);
+	cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+				      classid, NULL);
 	if (cl->qdisc == NULL)
 		cl->qdisc = &noop_qdisc;
 
 	if (tca[TCA_RATE]) {
-		err = gen_new_estimator(&cl->bstats, &cl->rate_est,
-					qdisc_root_sleeping_lock(sch),
+		err = gen_new_estimator(&cl->bstats, NULL,
+					&cl->rate_est,
+					NULL,
+					true,
 					tca[TCA_RATE]);
 		if (err)
 			goto destroy_class;
 	}
 
-	sch_tree_lock(sch);
-	qdisc_class_hash_insert(&q->clhash, &cl->common);
-	sch_tree_unlock(sch);
-
-	qdisc_class_hash_grow(sch, &q->clhash);
+	if (cl->qdisc != &noop_qdisc)
+		qdisc_hash_add(cl->qdisc, true);
 
 set_change_agg:
 	sch_tree_lock(sch);
@@ -500,7 +511,7 @@ set_change_agg:
 		new_agg = kzalloc(sizeof(*new_agg), GFP_KERNEL);
 		if (new_agg == NULL) {
 			err = -ENOBUFS;
-			gen_kill_estimator(&cl->bstats, &cl->rate_est);
+			gen_kill_estimator(&cl->rate_est);
 			goto destroy_class;
 		}
 		sch_tree_lock(sch);
@@ -508,77 +519,65 @@ set_change_agg:
 	}
 	if (existing)
 		qfq_deact_rm_from_agg(q, cl);
+	else
+		qdisc_class_hash_insert(&q->clhash, &cl->common);
 	qfq_add_to_agg(q, new_agg, cl);
 	sch_tree_unlock(sch);
+	qdisc_class_hash_grow(sch, &q->clhash);
 
 	*arg = (unsigned long)cl;
 	return 0;
 
 destroy_class:
-	qdisc_destroy(cl->qdisc);
+	qdisc_put(cl->qdisc);
 	kfree(cl);
 	return err;
 }
 
 static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl)
 {
-	struct qfq_sched *q = qdisc_priv(sch);
-
-	qfq_rm_from_agg(q, cl);
-	gen_kill_estimator(&cl->bstats, &cl->rate_est);
-	qdisc_destroy(cl->qdisc);
+	gen_kill_estimator(&cl->rate_est);
+	qdisc_put(cl->qdisc);
 	kfree(cl);
 }
 
-static int qfq_delete_class(struct Qdisc *sch, unsigned long arg)
+static int qfq_delete_class(struct Qdisc *sch, unsigned long arg,
+			    struct netlink_ext_ack *extack)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl = (struct qfq_class *)arg;
 
-	if (cl->filter_cnt > 0)
+	if (qdisc_class_in_use(&cl->common)) {
+		NL_SET_ERR_MSG_MOD(extack, "QFQ class in use");
 		return -EBUSY;
+	}
 
 	sch_tree_lock(sch);
 
-	qfq_purge_queue(cl);
+	qdisc_purge_queue(cl->qdisc);
 	qdisc_class_hash_remove(&q->clhash, &cl->common);
-
-	BUG_ON(--cl->refcnt == 0);
-	/*
-	 * This shouldn't happen: we "hold" one cops->get() when called
-	 * from tc_ctl_tclass; the destroy method is done from cops->put().
-	 */
+	qfq_rm_from_agg(q, cl);
 
 	sch_tree_unlock(sch);
-	return 0;
-}
-
-static unsigned long qfq_get_class(struct Qdisc *sch, u32 classid)
-{
-	struct qfq_class *cl = qfq_find_class(sch, classid);
 
-	if (cl != NULL)
-		cl->refcnt++;
-
-	return (unsigned long)cl;
+	qfq_destroy_class(sch, cl);
+	return 0;
 }
 
-static void qfq_put_class(struct Qdisc *sch, unsigned long arg)
+static unsigned long qfq_search_class(struct Qdisc *sch, u32 classid)
 {
-	struct qfq_class *cl = (struct qfq_class *)arg;
-
-	if (--cl->refcnt == 0)
-		qfq_destroy_class(sch, cl);
+	return (unsigned long)qfq_find_class(sch, classid);
 }
 
-static struct tcf_proto **qfq_tcf_chain(struct Qdisc *sch, unsigned long cl)
+static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl,
+				       struct netlink_ext_ack *extack)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
 
 	if (cl)
 		return NULL;
 
-	return &q->filter_list;
+	return q->block;
 }
 
 static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent,
@@ -586,8 +585,8 @@ static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent,
 {
 	struct qfq_class *cl = qfq_find_class(sch, classid);
 
-	if (cl != NULL)
-		cl->filter_cnt++;
+	if (cl)
+		qdisc_class_get(&cl->common);
 
 	return (unsigned long)cl;
 }
@@ -596,26 +595,23 @@ static void qfq_unbind_tcf(struct Qdisc *sch, unsigned long arg)
 {
 	struct qfq_class *cl = (struct qfq_class *)arg;
 
-	cl->filter_cnt--;
+	qdisc_class_put(&cl->common);
 }
 
 static int qfq_graft_class(struct Qdisc *sch, unsigned long arg,
-			   struct Qdisc *new, struct Qdisc **old)
+			   struct Qdisc *new, struct Qdisc **old,
+			   struct netlink_ext_ack *extack)
 {
 	struct qfq_class *cl = (struct qfq_class *)arg;
 
 	if (new == NULL) {
-		new = qdisc_create_dflt(sch->dev_queue,
-					&pfifo_qdisc_ops, cl->common.classid);
+		new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					cl->common.classid, NULL);
 		if (new == NULL)
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	qfq_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
@@ -631,16 +627,22 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg,
 {
 	struct qfq_class *cl = (struct qfq_class *)arg;
 	struct nlattr *nest;
+	u32 class_weight, lmax;
 
 	tcm->tcm_parent	= TC_H_ROOT;
 	tcm->tcm_handle	= cl->common.classid;
 	tcm->tcm_info	= cl->qdisc->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
-	if (nla_put_u32(skb, TCA_QFQ_WEIGHT, cl->agg->class_weight) ||
-	    nla_put_u32(skb, TCA_QFQ_LMAX, cl->agg->lmax))
+
+	sch_tree_lock(sch);
+	class_weight	= cl->agg->class_weight;
+	lmax		= cl->agg->lmax;
+	sch_tree_unlock(sch);
+	if (nla_put_u32(skb, TCA_QFQ_WEIGHT, class_weight) ||
+	    nla_put_u32(skb, TCA_QFQ_LMAX, lmax))
 		goto nla_put_failure;
 	return nla_nest_end(skb, nest);
 
@@ -656,14 +658,15 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	struct tc_qfq_stats xstats;
 
 	memset(&xstats, 0, sizeof(xstats));
-	cl->qdisc->qstats.qlen = cl->qdisc->q.qlen;
 
+	sch_tree_lock(sch);
 	xstats.weight = cl->agg->class_weight;
 	xstats.lmax = cl->agg->lmax;
+	sch_tree_unlock(sch);
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
-	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 ||
+	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
+	    qdisc_qstats_copy(d, cl->qdisc) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
@@ -680,15 +683,8 @@ static void qfq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
-			if (arg->count < arg->skip) {
-				arg->count++;
-				continue;
-			}
-			if (arg->fn(sch, (unsigned long)cl, arg) < 0) {
-				arg->stop = 1;
+			if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg))
 				return;
-			}
-			arg->count++;
 		}
 	}
 }
@@ -699,6 +695,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl;
 	struct tcf_result res;
+	struct tcf_proto *fl;
 	int result;
 
 	if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) {
@@ -709,13 +706,16 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	result = tc_classify(skb, q->filter_list, &res);
+	fl = rcu_dereference_bh(q->filter_list);
+	result = tcf_classify(skb, NULL, fl, &res, false);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
 		case TC_ACT_QUEUED:
 		case TC_ACT_STOLEN:
+		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			fallthrough;
 		case TC_ACT_SHOT:
 			return NULL;
 		}
@@ -834,38 +834,60 @@ static void qfq_make_eligible(struct qfq_sched *q)
 	}
 }
 
-
 /*
- * The index of the slot in which the aggregate is to be inserted must
- * not be higher than QFQ_MAX_SLOTS-2. There is a '-2' and not a '-1'
- * because the start time of the group may be moved backward by one
- * slot after the aggregate has been inserted, and this would cause
- * non-empty slots to be right-shifted by one position.
+ * The index of the slot in which the input aggregate agg is to be
+ * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2'
+ * and not a '-1' because the start time of the group may be moved
+ * backward by one slot after the aggregate has been inserted, and
+ * this would cause non-empty slots to be right-shifted by one
+ * position.
+ *
+ * QFQ+ fully satisfies this bound to the slot index if the parameters
+ * of the classes are not changed dynamically, and if QFQ+ never
+ * happens to postpone the service of agg unjustly, i.e., it never
+ * happens that the aggregate becomes backlogged and eligible, or just
+ * eligible, while an aggregate with a higher approximated finish time
+ * is being served. In particular, in this case QFQ+ guarantees that
+ * the timestamps of agg are low enough that the slot index is never
+ * higher than 2. Unfortunately, QFQ+ cannot provide the same
+ * guarantee if it happens to unjustly postpone the service of agg, or
+ * if the parameters of some class are changed.
+ *
+ * As for the first event, i.e., an out-of-order service, the
+ * upper bound to the slot index guaranteed by QFQ+ grows to
+ * 2 +
+ * QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) *
+ * (current_max_weight/current_wsum) <= 2 + 8 * 128 * 1.
  *
- * If the weight and lmax (max_pkt_size) of the classes do not change,
- * then QFQ+ does meet the above contraint according to the current
- * values of its parameters. In fact, if the weight and lmax of the
- * classes do not change, then, from the theory, QFQ+ guarantees that
- * the slot index is never higher than
- * 2 + QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) *
- * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM) = 2 + 8 * 128 * (1 / 64) = 18
+ * The following function deals with this problem by backward-shifting
+ * the timestamps of agg, if needed, so as to guarantee that the slot
+ * index is never higher than QFQ_MAX_SLOTS-2. This backward-shift may
+ * cause the service of other aggregates to be postponed, yet the
+ * worst-case guarantees of these aggregates are not violated.  In
+ * fact, in case of no out-of-order service, the timestamps of agg
+ * would have been even lower than they are after the backward shift,
+ * because QFQ+ would have guaranteed a maximum value equal to 2 for
+ * the slot index, and 2 < QFQ_MAX_SLOTS-2. Hence the aggregates whose
+ * service is postponed because of the backward-shift would have
+ * however waited for the service of agg before being served.
  *
- * When the weight of a class is increased or the lmax of the class is
- * decreased, a new aggregate with smaller slot size than the original
- * parent aggregate of the class may happen to be activated. The
- * activation of this aggregate should be properly delayed to when the
- * service of the class has finished in the ideal system tracked by
- * QFQ+. If the activation of the aggregate is not delayed to this
- * reference time instant, then this aggregate may be unjustly served
- * before other aggregates waiting for service. This may cause the
- * above bound to the slot index to be violated for some of these
- * unlucky aggregates.
+ * The other event that may cause the slot index to be higher than 2
+ * for agg is a recent change of the parameters of some class. If the
+ * weight of a class is increased or the lmax (max_pkt_size) of the
+ * class is decreased, then a new aggregate with smaller slot size
+ * than the original parent aggregate of the class may happen to be
+ * activated. The activation of this aggregate should be properly
+ * delayed to when the service of the class has finished in the ideal
+ * system tracked by QFQ+. If the activation of the aggregate is not
+ * delayed to this reference time instant, then this aggregate may be
+ * unjustly served before other aggregates waiting for service. This
+ * may cause the above bound to the slot index to be violated for some
+ * of these unlucky aggregates.
  *
  * Instead of delaying the activation of the new aggregate, which is
- * quite complex, the following inaccurate but simple solution is used:
- * if the slot index is higher than QFQ_MAX_SLOTS-2, then the
- * timestamps of the aggregate are shifted backward so as to let the
- * slot index become equal to QFQ_MAX_SLOTS-2.
+ * quite complex, the above-discussed capping of the slot index is
+ * used to handle also the consequences of a change of the parameters
+ * of a class.
  */
 static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg,
 			    u64 roundedS)
@@ -965,19 +987,24 @@ static void qfq_update_eligible(struct qfq_sched *q)
 }
 
 /* Dequeue head packet of the head class in the DRR queue of the aggregate. */
-static void agg_dequeue(struct qfq_aggregate *agg,
-			struct qfq_class *cl, unsigned int len)
+static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
+				   struct qfq_class *cl, unsigned int len)
 {
-	qdisc_dequeue_peeked(cl->qdisc);
+	struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc);
+
+	if (!skb)
+		return NULL;
 
 	cl->deficit -= (int) len;
 
 	if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */
-		list_del(&cl->alist);
-	else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) {
+		list_del_init(&cl->alist);
+	else if (cl->deficit < qdisc_peek_len(cl->qdisc)) {
 		cl->deficit += agg->lmax;
 		list_move_tail(&cl->alist, &agg->active);
 	}
+
+	return skb;
 }
 
 static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg,
@@ -989,7 +1016,7 @@ static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg,
 	*cl = list_first_entry(&agg->active, struct qfq_class, alist);
 	skb = (*cl)->qdisc->ops->peek((*cl)->qdisc);
 	if (skb == NULL)
-		WARN_ONCE(1, "qfq_dequeue: non-workconserving leaf\n");
+		qdisc_warn_nonwc("qfq_dequeue", (*cl)->qdisc);
 	else
 		*len = qdisc_pkt_len(skb);
 
@@ -1124,9 +1151,17 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 		return NULL;
 
 	sch->q.qlen--;
+
+	skb = agg_dequeue(in_serv_agg, cl, len);
+
+	if (!skb) {
+		sch->q.qlen++;
+		return NULL;
+	}
+
+	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_bstats_update(sch, skb);
 
-	agg_dequeue(in_serv_agg, cl, len);
 	/* If lmax is lowered, through qfq_change_class, for a class
 	 * owning pending packets with larger size than the new value
 	 * of lmax, then the following condition may hold.
@@ -1136,7 +1171,7 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
 	else
 		in_serv_agg->budget -= len;
 
-	q->V += (u64)len * IWSUM;
+	q->V += (u64)len * q->iwsum;
 	pr_debug("qfq dequeue: len %u F %lld now %lld\n",
 		 len, (unsigned long long) in_serv_agg->F,
 		 (unsigned long long) q->V);
@@ -1187,8 +1222,10 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q)
 	return agg;
 }
 
-static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free)
 {
+	unsigned int len = qdisc_pkt_len(skb), gso_segs;
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl;
 	struct qfq_aggregate *agg;
@@ -1197,40 +1234,43 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	cl = qfq_classify(skb, sch, &err);
 	if (cl == NULL) {
 		if (err & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
-		kfree_skb(skb);
+			qdisc_qstats_drop(sch);
+		__qdisc_drop(skb, to_free);
 		return err;
 	}
 	pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid);
 
-	if (unlikely(cl->agg->lmax < qdisc_pkt_len(skb))) {
+	if (unlikely(cl->agg->lmax < len)) {
 		pr_debug("qfq: increasing maxpkt from %u to %u for class %u",
-			 cl->agg->lmax, qdisc_pkt_len(skb), cl->common.classid);
-		err = qfq_change_agg(sch, cl, cl->agg->class_weight,
-				     qdisc_pkt_len(skb));
-		if (err)
-			return err;
+			 cl->agg->lmax, len, cl->common.classid);
+		err = qfq_change_agg(sch, cl, cl->agg->class_weight, len);
+		if (err) {
+			cl->qstats.drops++;
+			return qdisc_drop(skb, sch, to_free);
+		}
 	}
 
-	err = qdisc_enqueue(skb, cl->qdisc);
+	gso_segs = qdisc_pkt_segs(skb);
+	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		pr_debug("qfq_enqueue: enqueue failed %d\n", err);
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		}
 		return err;
 	}
 
-	bstats_update(&cl->bstats, skb);
+	_bstats_update(&cl->bstats, len, gso_segs);
+	sch->qstats.backlog += len;
 	++sch->q.qlen;
 
 	agg = cl->agg;
-	/* if the queue was not empty, then done here */
-	if (cl->qdisc->q.qlen != 1) {
+	/* if the class is active, then done here */
+	if (cl_is_active(cl)) {
 		if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) &&
 		    list_first_entry(&agg->active, struct qfq_class, alist)
-		    == cl && cl->deficit < qdisc_pkt_len(skb))
+		    == cl && cl->deficit < len)
 			list_move_tail(&cl->alist, &agg->active);
 
 		return err;
@@ -1389,71 +1429,29 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg)
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl = (struct qfq_class *)arg;
 
-	if (cl->qdisc->q.qlen == 0)
-		qfq_deactivate_class(q, cl);
-}
-
-static unsigned int qfq_drop_from_slot(struct qfq_sched *q,
-				       struct hlist_head *slot)
-{
-	struct qfq_aggregate *agg;
-	struct qfq_class *cl;
-	unsigned int len;
-
-	hlist_for_each_entry(agg, slot, next) {
-		list_for_each_entry(cl, &agg->active, alist) {
-
-			if (!cl->qdisc->ops->drop)
-				continue;
-
-			len = cl->qdisc->ops->drop(cl->qdisc);
-			if (len > 0) {
-				if (cl->qdisc->q.qlen == 0)
-					qfq_deactivate_class(q, cl);
-
-				return len;
-			}
-		}
-	}
-	return 0;
-}
-
-static unsigned int qfq_drop(struct Qdisc *sch)
-{
-	struct qfq_sched *q = qdisc_priv(sch);
-	struct qfq_group *grp;
-	unsigned int i, j, len;
-
-	for (i = 0; i <= QFQ_MAX_INDEX; i++) {
-		grp = &q->groups[i];
-		for (j = 0; j < QFQ_MAX_SLOTS; j++) {
-			len = qfq_drop_from_slot(q, &grp->slots[j]);
-			if (len > 0) {
-				sch->q.qlen--;
-				return len;
-			}
-		}
-
-	}
-
-	return 0;
+	if (list_empty(&cl->alist))
+		return;
+	qfq_deactivate_class(q, cl);
 }
 
-static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
+static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt,
+			  struct netlink_ext_ack *extack)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_group *grp;
 	int i, j, err;
 	u32 max_cl_shift, maxbudg_shift, max_classes;
 
+	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
+	if (err)
+		return err;
+
 	err = qdisc_class_hash_init(&q->clhash);
 	if (err < 0)
 		return err;
 
-	if (qdisc_dev(sch)->tx_queue_len + 1 > QFQ_MAX_AGG_CLASSES)
-		max_classes = QFQ_MAX_AGG_CLASSES;
-	else
-		max_classes = qdisc_dev(sch)->tx_queue_len + 1;
+	max_classes = min_t(u64, (u64)qdisc_dev(sch)->tx_queue_len + 1,
+			    QFQ_MAX_AGG_CLASSES);
 	/* max_cl_shift = floor(log_2(max_classes)) */
 	max_cl_shift = __fls(max_classes);
 	q->max_agg_classes = 1<<max_cl_shift;
@@ -1489,7 +1487,6 @@ static void qfq_reset_qdisc(struct Qdisc *sch)
 			qdisc_reset(cl->qdisc);
 		}
 	}
-	sch->q.qlen = 0;
 }
 
 static void qfq_destroy_qdisc(struct Qdisc *sch)
@@ -1499,11 +1496,12 @@ static void qfq_destroy_qdisc(struct Qdisc *sch)
 	struct hlist_node *next;
 	unsigned int i;
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
 					  common.hnode) {
+			qfq_rm_from_agg(q, cl);
 			qfq_destroy_class(sch, cl);
 		}
 	}
@@ -1513,9 +1511,8 @@ static void qfq_destroy_qdisc(struct Qdisc *sch)
 static const struct Qdisc_class_ops qfq_class_ops = {
 	.change		= qfq_change_class,
 	.delete		= qfq_delete_class,
-	.get		= qfq_get_class,
-	.put		= qfq_put_class,
-	.tcf_chain	= qfq_tcf_chain,
+	.find		= qfq_search_class,
+	.tcf_block	= qfq_tcf_block,
 	.bind_tcf	= qfq_bind_tcf,
 	.unbind_tcf	= qfq_unbind_tcf,
 	.graft		= qfq_graft_class,
@@ -1533,12 +1530,12 @@ static struct Qdisc_ops qfq_qdisc_ops __read_mostly = {
 	.enqueue	= qfq_enqueue,
 	.dequeue	= qfq_dequeue,
 	.peek		= qdisc_peek_dequeued,
-	.drop		= qfq_drop,
 	.init		= qfq_init_qdisc,
 	.reset		= qfq_reset_qdisc,
 	.destroy	= qfq_destroy_qdisc,
 	.owner		= THIS_MODULE,
 };
+MODULE_ALIAS_NET_SCH("qfq");
 
 static int __init qfq_init(void)
 {
@@ -1553,3 +1550,4 @@ static void __exit qfq_exit(void)
 module_init(qfq_init);
 module_exit(qfq_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Quick Fair Queueing Plus qdisc");