net/sched: Retire CBQ qdisc

commit 051d442098421c28c7951625652f61b1e15c4bd5 upstream.

While this amazing qdisc has served us well over the years it has not been
getting any tender love and care and has bitrotted over time.
It has become mostly a shooting target for syzkaller lately.
For this reason, we are retiring it. Goodbye CBQ - we loved you.

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 0 insertions, 1745 deletions

diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 24cf0bf7c80e..bbd84d8bc64a 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -45,23 +45,6 @@ if NET_SCHED
 
 comment "Queueing/Scheduling"
 
-config NET_SCH_CBQ
-	tristate "Class Based Queueing (CBQ)"
-	help
-	  Say Y here if you want to use the Class-Based Queueing (CBQ) packet
-	  scheduling algorithm. This algorithm classifies the waiting packets
-	  into a tree-like hierarchy of classes; the leaves of this tree are
-	  in turn scheduled by separate algorithms.
-
-	  See the top of <file:net/sched/sch_cbq.c> for more details.
-
-	  CBQ is a commonly used scheduler, so if you're unsure, you should
-	  say Y here. Then say Y to all the queueing algorithms below that you
-	  want to use as leaf disciplines.
-
-	  To compile this code as a module, choose M here: the
-	  module will be called sch_cbq.
-
 config NET_SCH_HTB
 	tristate "Hierarchical Token Bucket (HTB)"
 	help
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 8a33a35fc50d..0108d1bffa51 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -33,7 +33,6 @@ obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o
 obj-$(CONFIG_NET_ACT_CT)	+= act_ct.o
 obj-$(CONFIG_NET_ACT_GATE)	+= act_gate.o
 obj-$(CONFIG_NET_SCH_FIFO)	+= sch_fifo.o
-obj-$(CONFIG_NET_SCH_CBQ)	+= sch_cbq.o
 obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o
 obj-$(CONFIG_NET_SCH_HFSC)	+= sch_hfsc.o
 obj-$(CONFIG_NET_SCH_RED)	+= sch_red.o
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
deleted file mode 100644
index 36db5f6782f2..000000000000
--- a/net/sched/sch_cbq.c
+++ /dev/null
@@ -1,1727 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * net/sched/sch_cbq.c	Class-Based Queueing discipline.
- *
- * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
- */
-
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/skbuff.h>
-#include <net/netlink.h>
-#include <net/pkt_sched.h>
-#include <net/pkt_cls.h>
-
-
-/*	Class-Based Queueing (CBQ) algorithm.
-	=======================================
-
-	Sources: [1] Sally Floyd and Van Jacobson, "Link-sharing and Resource
-		 Management Models for Packet Networks",
-		 IEEE/ACM Transactions on Networking, Vol.3, No.4, 1995
-
-		 [2] Sally Floyd, "Notes on CBQ and Guaranteed Service", 1995
-
-		 [3] Sally Floyd, "Notes on Class-Based Queueing: Setting
-		 Parameters", 1996
-
-		 [4] Sally Floyd and Michael Speer, "Experimental Results
-		 for Class-Based Queueing", 1998, not published.
-
-	-----------------------------------------------------------------------
-
-	Algorithm skeleton was taken from NS simulator cbq.cc.
-	If someone wants to check this code against the LBL version,
-	he should take into account that ONLY the skeleton was borrowed,
-	the implementation is different. Particularly:
-
-	--- The WRR algorithm is different. Our version looks more
-	reasonable (I hope) and works when quanta are allowed to be
-	less than MTU, which is always the case when real time classes
-	have small rates. Note, that the statement of [3] is
-	incomplete, delay may actually be estimated even if class
-	per-round allotment is less than MTU. Namely, if per-round
-	allotment is W*r_i, and r_1+...+r_k = r < 1
-
-	delay_i <= ([MTU/(W*r_i)]*W*r + W*r + k*MTU)/B
-
-	In the worst case we have IntServ estimate with D = W*r+k*MTU
-	and C = MTU*r. The proof (if correct at all) is trivial.
-
-
-	--- It seems that cbq-2.0 is not very accurate. At least, I cannot
-	interpret some places, which look like wrong translations
-	from NS. Anyone is advised to find these differences
-	and explain to me, why I am wrong 8).
-
-	--- Linux has no EOI event, so that we cannot estimate true class
-	idle time. Workaround is to consider the next dequeue event
-	as sign that previous packet is finished. This is wrong because of
-	internal device queueing, but on a permanently loaded link it is true.
-	Moreover, combined with clock integrator, this scheme looks
-	very close to an ideal solution.  */
-
-struct cbq_sched_data;
-
-
-struct cbq_class {
-	struct Qdisc_class_common common;
-	struct cbq_class	*next_alive;	/* next class with backlog in this priority band */
-
-/* Parameters */
-	unsigned char		priority;	/* class priority */
-	unsigned char		priority2;	/* priority to be used after overlimit */
-	unsigned char		ewma_log;	/* time constant for idle time calculation */
-
-	u32			defmap;
-
-	/* Link-sharing scheduler parameters */
-	long			maxidle;	/* Class parameters: see below. */
-	long			offtime;
-	long			minidle;
-	u32			avpkt;
-	struct qdisc_rate_table	*R_tab;
-
-	/* General scheduler (WRR) parameters */
-	long			allot;
-	long			quantum;	/* Allotment per WRR round */
-	long			weight;		/* Relative allotment: see below */
-
-	struct Qdisc		*qdisc;		/* Ptr to CBQ discipline */
-	struct cbq_class	*split;		/* Ptr to split node */
-	struct cbq_class	*share;		/* Ptr to LS parent in the class tree */
-	struct cbq_class	*tparent;	/* Ptr to tree parent in the class tree */
-	struct cbq_class	*borrow;	/* NULL if class is bandwidth limited;
-						   parent otherwise */
-	struct cbq_class	*sibling;	/* Sibling chain */
-	struct cbq_class	*children;	/* Pointer to children chain */
-
-	struct Qdisc		*q;		/* Elementary queueing discipline */
-
-
-/* Variables */
-	unsigned char		cpriority;	/* Effective priority */
-	unsigned char		delayed;
-	unsigned char		level;		/* level of the class in hierarchy:
-						   0 for leaf classes, and maximal
-						   level of children + 1 for nodes.
-						 */
-
-	psched_time_t		last;		/* Last end of service */
-	psched_time_t		undertime;
-	long			avgidle;
-	long			deficit;	/* Saved deficit for WRR */
-	psched_time_t		penalized;
-	struct gnet_stats_basic_sync bstats;
-	struct gnet_stats_queue qstats;
-	struct net_rate_estimator __rcu *rate_est;
-	struct tc_cbq_xstats	xstats;
-
-	struct tcf_proto __rcu	*filter_list;
-	struct tcf_block	*block;
-
-	int			filters;
-
-	struct cbq_class	*defaults[TC_PRIO_MAX + 1];
-};
-
-struct cbq_sched_data {
-	struct Qdisc_class_hash	clhash;			/* Hash table of all classes */
-	int			nclasses[TC_CBQ_MAXPRIO + 1];
-	unsigned int		quanta[TC_CBQ_MAXPRIO + 1];
-
-	struct cbq_class	link;
-
-	unsigned int		activemask;
-	struct cbq_class	*active[TC_CBQ_MAXPRIO + 1];	/* List of all classes
-								   with backlog */
-
-#ifdef CONFIG_NET_CLS_ACT
-	struct cbq_class	*rx_class;
-#endif
-	struct cbq_class	*tx_class;
-	struct cbq_class	*tx_borrowed;
-	int			tx_len;
-	psched_time_t		now;		/* Cached timestamp */
-	unsigned int		pmask;
-
-	struct qdisc_watchdog	watchdog;	/* Watchdog timer,
-						   started when CBQ has
-						   backlog, but cannot
-						   transmit just now */
-	psched_tdiff_t		wd_expires;
-	int			toplevel;
-	u32			hgenerator;
-};
-
-
-#define L2T(cl, len)	qdisc_l2t((cl)->R_tab, len)
-
-static inline struct cbq_class *
-cbq_class_lookup(struct cbq_sched_data *q, u32 classid)
-{
-	struct Qdisc_class_common *clc;
-
-	clc = qdisc_class_find(&q->clhash, classid);
-	if (clc == NULL)
-		return NULL;
-	return container_of(clc, struct cbq_class, common);
-}
-
-#ifdef CONFIG_NET_CLS_ACT
-
-static struct cbq_class *
-cbq_reclassify(struct sk_buff *skb, struct cbq_class *this)
-{
-	struct cbq_class *cl;
-
-	for (cl = this->tparent; cl; cl = cl->tparent) {
-		struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT];
-
-		if (new != NULL && new != this)
-			return new;
-	}
-	return NULL;
-}
-
-#endif
-
-/* Classify packet. The procedure is pretty complicated, but
- * it allows us to combine link sharing and priority scheduling
- * transparently.
- *
- * Namely, you can put link sharing rules (f.e. route based) at root of CBQ,
- * so that it resolves to split nodes. Then packets are classified
- * by logical priority, or a more specific classifier may be attached
- * to the split node.
- */
-
-static struct cbq_class *
-cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
-{
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct cbq_class *head = &q->link;
-	struct cbq_class **defmap;
-	struct cbq_class *cl = NULL;
-	u32 prio = skb->priority;
-	struct tcf_proto *fl;
-	struct tcf_result res;
-
-	/*
-	 *  Step 1. If skb->priority points to one of our classes, use it.
-	 */
-	if (TC_H_MAJ(prio ^ sch->handle) == 0 &&
-	    (cl = cbq_class_lookup(q, prio)) != NULL)
-		return cl;
-
-	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	for (;;) {
-		int result = 0;
-		defmap = head->defaults;
-
-		fl = rcu_dereference_bh(head->filter_list);
-		/*
-		 * Step 2+n. Apply classifier.
-		 */
-		result = tcf_classify(skb, NULL, fl, &res, true);
-		if (!fl || result < 0)
-			goto fallback;
-		if (result == TC_ACT_SHOT)
-			return NULL;
-
-		cl = (void *)res.class;
-		if (!cl) {
-			if (TC_H_MAJ(res.classid))
-				cl = cbq_class_lookup(q, res.classid);
-			else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL)
-				cl = defmap[TC_PRIO_BESTEFFORT];
-
-			if (cl == NULL)
-				goto fallback;
-		}
-		if (cl->level >= head->level)
-			goto fallback;
-#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_RECLASSIFY:
-			return cbq_reclassify(skb, cl);
-		}
-#endif
-		if (cl->level == 0)
-			return cl;
-
-		/*
-		 * Step 3+n. If classifier selected a link sharing class,
-		 *	   apply agency specific classifier.
-		 *	   Repeat this procedure until we hit a leaf node.
-		 */
-		head = cl;
-	}
-
-fallback:
-	cl = head;
-
-	/*
-	 * Step 4. No success...
-	 */
-	if (TC_H_MAJ(prio) == 0 &&
-	    !(cl = head->defaults[prio & TC_PRIO_MAX]) &&
-	    !(cl = head->defaults[TC_PRIO_BESTEFFORT]))
-		return head;
-
-	return cl;
-}
-
-/*
- * A packet has just been enqueued on the empty class.
- * cbq_activate_class adds it to the tail of active class list
- * of its priority band.
- */
-
-static inline void cbq_activate_class(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-	int prio = cl->cpriority;
-	struct cbq_class *cl_tail;
-
-	cl_tail = q->active[prio];
-	q->active[prio] = cl;
-
-	if (cl_tail != NULL) {
-		cl->next_alive = cl_tail->next_alive;
-		cl_tail->next_alive = cl;
-	} else {
-		cl->next_alive = cl;
-		q->activemask |= (1<<prio);
-	}
-}
-
-/*
- * Unlink class from active chain.
- * Note that this same procedure is done directly in cbq_dequeue*
- * during round-robin procedure.
- */
-
-static void cbq_deactivate_class(struct cbq_class *this)
-{
-	struct cbq_sched_data *q = qdisc_priv(this->qdisc);
-	int prio = this->cpriority;
-	struct cbq_class *cl;
-	struct cbq_class *cl_prev = q->active[prio];
-
-	do {
-		cl = cl_prev->next_alive;
-		if (cl == this) {
-			cl_prev->next_alive = cl->next_alive;
-			cl->next_alive = NULL;
-
-			if (cl == q->active[prio]) {
-				q->active[prio] = cl_prev;
-				if (cl == q->active[prio]) {
-					q->active[prio] = NULL;
-					q->activemask &= ~(1<<prio);
-					return;
-				}
-			}
-			return;
-		}
-	} while ((cl_prev = cl) != q->active[prio]);
-}
-
-static void
-cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl)
-{
-	int toplevel = q->toplevel;
-
-	if (toplevel > cl->level) {
-		psched_time_t now = psched_get_time();
-
-		do {
-			if (cl->undertime < now) {
-				q->toplevel = cl->level;
-				return;
-			}
-		} while ((cl = cl->borrow) != NULL && toplevel > cl->level);
-	}
-}
-
-static int
-cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
-	    struct sk_buff **to_free)
-{
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	int ret;
-	struct cbq_class *cl = cbq_classify(skb, sch, &ret);
-
-#ifdef CONFIG_NET_CLS_ACT
-	q->rx_class = cl;
-#endif
-	if (cl == NULL) {
-		if (ret & __NET_XMIT_BYPASS)
-			qdisc_qstats_drop(sch);
-		__qdisc_drop(skb, to_free);
-		return ret;
-	}
-
-	ret = qdisc_enqueue(skb, cl->q, to_free);
-	if (ret == NET_XMIT_SUCCESS) {
-		sch->q.qlen++;
-		cbq_mark_toplevel(q, cl);
-		if (!cl->next_alive)
-			cbq_activate_class(cl);
-		return ret;
-	}
-
-	if (net_xmit_drop_count(ret)) {
-		qdisc_qstats_drop(sch);
-		cbq_mark_toplevel(q, cl);
-		cl->qstats.drops++;
-	}
-	return ret;
-}
-
-/* Overlimit action: penalize leaf class by adding offtime */
-static void cbq_overlimit(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-	psched_tdiff_t delay = cl->undertime - q->now;
-
-	if (!cl->delayed) {
-		delay += cl->offtime;
-
-		/*
-		 * Class goes to sleep, so that it will have no
-		 * chance to work avgidle. Let's forgive it 8)
-		 *
-		 * BTW cbq-2.0 has a crap in this
-		 * place, apparently they forgot to shift it by cl->ewma_log.
-		 */
-		if (cl->avgidle < 0)
-			delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log);
-		if (cl->avgidle < cl->minidle)
-			cl->avgidle = cl->minidle;
-		if (delay <= 0)
-			delay = 1;
-		cl->undertime = q->now + delay;
-
-		cl->xstats.overactions++;
-		cl->delayed = 1;
-	}
-	if (q->wd_expires == 0 || q->wd_expires > delay)
-		q->wd_expires = delay;
-
-	/* Dirty work! We must schedule wakeups based on
-	 * real available rate, rather than leaf rate,
-	 * which may be tiny (even zero).
-	 */
-	if (q->toplevel == TC_CBQ_MAXLEVEL) {
-		struct cbq_class *b;
-		psched_tdiff_t base_delay = q->wd_expires;
-
-		for (b = cl->borrow; b; b = b->borrow) {
-			delay = b->undertime - q->now;
-			if (delay < base_delay) {
-				if (delay <= 0)
-					delay = 1;
-				base_delay = delay;
-			}
-		}
-
-		q->wd_expires = base_delay;
-	}
-}
-
-/*
- * It is mission critical procedure.
- *
- * We "regenerate" toplevel cutoff, if transmitting class
- * has backlog and it is not regulated. It is not part of
- * original CBQ description, but looks more reasonable.
- * Probably, it is wrong. This question needs further investigation.
- */
-
-static inline void
-cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl,
-		    struct cbq_class *borrowed)
-{
-	if (cl && q->toplevel >= borrowed->level) {
-		if (cl->q->q.qlen > 1) {
-			do {
-				if (borrowed->undertime == PSCHED_PASTPERFECT) {
-					q->toplevel = borrowed->level;
-					return;
-				}
-			} while ((borrowed = borrowed->borrow) != NULL);
-		}
-#if 0
-	/* It is not necessary now. Uncommenting it
-	   will save CPU cycles, but decrease fairness.
-	 */
-		q->toplevel = TC_CBQ_MAXLEVEL;
-#endif
-	}
-}
-
-static void
-cbq_update(struct cbq_sched_data *q)
-{
-	struct cbq_class *this = q->tx_class;
-	struct cbq_class *cl = this;
-	int len = q->tx_len;
-	psched_time_t now;
-
-	q->tx_class = NULL;
-	/* Time integrator. We calculate EOS time
-	 * by adding expected packet transmission time.
-	 */
-	now = q->now + L2T(&q->link, len);
-
-	for ( ; cl; cl = cl->share) {
-		long avgidle = cl->avgidle;
-		long idle;
-
-		_bstats_update(&cl->bstats, len, 1);
-
-		/*
-		 * (now - last) is total time between packet right edges.
-		 * (last_pktlen/rate) is "virtual" busy time, so that
-		 *
-		 *	idle = (now - last) - last_pktlen/rate
-		 */
-
-		idle = now - cl->last;
-		if ((unsigned long)idle > 128*1024*1024) {
-			avgidle = cl->maxidle;
-		} else {
-			idle -= L2T(cl, len);
-
-		/* true_avgidle := (1-W)*true_avgidle + W*idle,
-		 * where W=2^{-ewma_log}. But cl->avgidle is scaled:
-		 * cl->avgidle == true_avgidle/W,
-		 * hence:
-		 */
-			avgidle += idle - (avgidle>>cl->ewma_log);
-		}
-
-		if (avgidle <= 0) {
-			/* Overlimit or at-limit */
-
-			if (avgidle < cl->minidle)
-				avgidle = cl->minidle;
-
-			cl->avgidle = avgidle;
-
-			/* Calculate expected time, when this class
-			 * will be allowed to send.
-			 * It will occur, when:
-			 * (1-W)*true_avgidle + W*delay = 0, i.e.
-			 * idle = (1/W - 1)*(-true_avgidle)
-			 * or
-			 * idle = (1 - W)*(-cl->avgidle);
-			 */
-			idle = (-avgidle) - ((-avgidle) >> cl->ewma_log);
-
-			/*
-			 * That is not all.
-			 * To maintain the rate allocated to the class,
-			 * we add to undertime virtual clock,
-			 * necessary to complete transmitted packet.
-			 * (len/phys_bandwidth has been already passed
-			 * to the moment of cbq_update)
-			 */
-
-			idle -= L2T(&q->link, len);
-			idle += L2T(cl, len);
-
-			cl->undertime = now + idle;
-		} else {
-			/* Underlimit */
-
-			cl->undertime = PSCHED_PASTPERFECT;
-			if (avgidle > cl->maxidle)
-				cl->avgidle = cl->maxidle;
-			else
-				cl->avgidle = avgidle;
-		}
-		if ((s64)(now - cl->last) > 0)
-			cl->last = now;
-	}
-
-	cbq_update_toplevel(q, this, q->tx_borrowed);
-}
-
-static inline struct cbq_class *
-cbq_under_limit(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-	struct cbq_class *this_cl = cl;
-
-	if (cl->tparent == NULL)
-		return cl;
-
-	if (cl->undertime == PSCHED_PASTPERFECT || q->now >= cl->undertime) {
-		cl->delayed = 0;
-		return cl;
-	}
-
-	do {
-		/* It is very suspicious place. Now overlimit
-		 * action is generated for not bounded classes
-		 * only if link is completely congested.
-		 * Though it is in agree with ancestor-only paradigm,
-		 * it looks very stupid. Particularly,
-		 * it means that this chunk of code will either
-		 * never be called or result in strong amplification
-		 * of burstiness. Dangerous, silly, and, however,
-		 * no another solution exists.
-		 */
-		cl = cl->borrow;
-		if (!cl) {
-			this_cl->qstats.overlimits++;
-			cbq_overlimit(this_cl);
-			return NULL;
-		}
-		if (cl->level > q->toplevel)
-			return NULL;
-	} while (cl->undertime != PSCHED_PASTPERFECT && q->now < cl->undertime);
-
-	cl->delayed = 0;
-	return cl;
-}
-
-static inline struct sk_buff *
-cbq_dequeue_prio(struct Qdisc *sch, int prio)
-{
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct cbq_class *cl_tail, *cl_prev, *cl;
-	struct sk_buff *skb;
-	int deficit;
-
-	cl_tail = cl_prev = q->active[prio];
-	cl = cl_prev->next_alive;
-
-	do {
-		deficit = 0;
-
-		/* Start round */
-		do {
-			struct cbq_class *borrow = cl;
-
-			if (cl->q->q.qlen &&
-			    (borrow = cbq_under_limit(cl)) == NULL)
-				goto skip_class;
-
-			if (cl->deficit <= 0) {
-				/* Class exhausted its allotment per
-				 * this round. Switch to the next one.
-				 */
-				deficit = 1;
-				cl->deficit += cl->quantum;
-				goto next_class;
-			}
-
-			skb = cl->q->dequeue(cl->q);
-
-			/* Class did not give us any skb :-(
-			 * It could occur even if cl->q->q.qlen != 0
-			 * f.e. if cl->q == "tbf"
-			 */
-			if (skb == NULL)
-				goto skip_class;
-
-			cl->deficit -= qdisc_pkt_len(skb);
-			q->tx_class = cl;
-			q->tx_borrowed = borrow;
-			if (borrow != cl) {
-#ifndef CBQ_XSTATS_BORROWS_BYTES
-				borrow->xstats.borrows++;
-				cl->xstats.borrows++;
-#else
-				borrow->xstats.borrows += qdisc_pkt_len(skb);
-				cl->xstats.borrows += qdisc_pkt_len(skb);
-#endif
-			}
-			q->tx_len = qdisc_pkt_len(skb);
-
-			if (cl->deficit <= 0) {
-				q->active[prio] = cl;
-				cl = cl->next_alive;
-				cl->deficit += cl->quantum;
-			}
-			return skb;
-
-skip_class:
-			if (cl->q->q.qlen == 0 || prio != cl->cpriority) {
-				/* Class is empty or penalized.
-				 * Unlink it from active chain.
-				 */
-				cl_prev->next_alive = cl->next_alive;
-				cl->next_alive = NULL;
-
-				/* Did cl_tail point to it? */
-				if (cl == cl_tail) {
-					/* Repair it! */
-					cl_tail = cl_prev;
-
-					/* Was it the last class in this band? */
-					if (cl == cl_tail) {
-						/* Kill the band! */
-						q->active[prio] = NULL;
-						q->activemask &= ~(1<<prio);
-						if (cl->q->q.qlen)
-							cbq_activate_class(cl);
-						return NULL;
-					}
-
-					q->active[prio] = cl_tail;
-				}
-				if (cl->q->q.qlen)
-					cbq_activate_class(cl);
-
-				cl = cl_prev;
-			}
-
-next_class:
-			cl_prev = cl;
-			cl = cl->next_alive;
-		} while (cl_prev != cl_tail);
-	} while (deficit);
-
-	q->active[prio] = cl_prev;
-
-	return NULL;
-}
-
-static inline struct sk_buff *
-cbq_dequeue_1(struct Qdisc *sch)
-{
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct sk_buff *skb;
-	unsigned int activemask;
-
-	activemask = q->activemask & 0xFF;
-	while (activemask) {
-		int prio = ffz(~activemask);
-		activemask &= ~(1<<prio);
-		skb = cbq_dequeue_prio(sch, prio);
-		if (skb)
-			return skb;
-	}
-	return NULL;
-}
-
-static struct sk_buff *
-cbq_dequeue(struct Qdisc *sch)
-{
-	struct sk_buff *skb;
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	psched_time_t now;
-
-	now = psched_get_time();
-
-	if (q->tx_class)
-		cbq_update(q);
-
-	q->now = now;
-
-	for (;;) {
-		q->wd_expires = 0;
-
-		skb = cbq_dequeue_1(sch);
-		if (skb) {
-			qdisc_bstats_update(sch, skb);
-			sch->q.qlen--;
-			return skb;
-		}
-
-		/* All the classes are overlimit.
-		 *
-		 * It is possible, if:
-		 *
-		 * 1. Scheduler is empty.
-		 * 2. Toplevel cutoff inhibited borrowing.
-		 * 3. Root class is overlimit.
-		 *
-		 * Reset 2d and 3d conditions and retry.
-		 *
-		 * Note, that NS and cbq-2.0 are buggy, peeking
-		 * an arbitrary class is appropriate for ancestor-only
-		 * sharing, but not for toplevel algorithm.
-		 *
-		 * Our version is better, but slower, because it requires
-		 * two passes, but it is unavoidable with top-level sharing.
-		 */
-
-		if (q->toplevel == TC_CBQ_MAXLEVEL &&
-		    q->link.undertime == PSCHED_PASTPERFECT)
-			break;
-
-		q->toplevel = TC_CBQ_MAXLEVEL;
-		q->link.undertime = PSCHED_PASTPERFECT;
-	}
-
-	/* No packets in scheduler or nobody wants to give them to us :-(
-	 * Sigh... start watchdog timer in the last case.
-	 */
-
-	if (sch->q.qlen) {
-		qdisc_qstats_overlimit(sch);
-		if (q->wd_expires)
-			qdisc_watchdog_schedule(&q->watchdog,
-						now + q->wd_expires);
-	}
-	return NULL;
-}
-
-/* CBQ class maintenance routines */
-
-static void cbq_adjust_levels(struct cbq_class *this)
-{
-	if (this == NULL)
-		return;
-
-	do {
-		int level = 0;
-		struct cbq_class *cl;
-
-		cl = this->children;
-		if (cl) {
-			do {
-				if (cl->level > level)
-					level = cl->level;
-			} while ((cl = cl->sibling) != this->children);
-		}
-		this->level = level + 1;
-	} while ((this = this->tparent) != NULL);
-}
-
-static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio)
-{
-	struct cbq_class *cl;
-	unsigned int h;
-
-	if (q->quanta[prio] == 0)
-		return;
-
-	for (h = 0; h < q->clhash.hashsize; h++) {
-		hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) {
-			/* BUGGGG... Beware! This expression suffer of
-			 * arithmetic overflows!
-			 */
-			if (cl->priority == prio) {
-				cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/
-					q->quanta[prio];
-			}
-			if (cl->quantum <= 0 ||
-			    cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) {
-				pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n",
-					cl->common.classid, cl->quantum);
-				cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1;
-			}
-		}
-	}
-}
-
-static void cbq_sync_defmap(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-	struct cbq_class *split = cl->split;
-	unsigned int h;
-	int i;
-
-	if (split == NULL)
-		return;
-
-	for (i = 0; i <= TC_PRIO_MAX; i++) {
-		if (split->defaults[i] == cl && !(cl->defmap & (1<<i)))
-			split->defaults[i] = NULL;
-	}
-
-	for (i = 0; i <= TC_PRIO_MAX; i++) {
-		int level = split->level;
-
-		if (split->defaults[i])
-			continue;
-
-		for (h = 0; h < q->clhash.hashsize; h++) {
-			struct cbq_class *c;
-
-			hlist_for_each_entry(c, &q->clhash.hash[h],
-					     common.hnode) {
-				if (c->split == split && c->level < level &&
-				    c->defmap & (1<<i)) {
-					split->defaults[i] = c;
-					level = c->level;
-				}
-			}
-		}
-	}
-}
-
-static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 mask)
-{
-	struct cbq_class *split = NULL;
-
-	if (splitid == 0) {
-		split = cl->split;
-		if (!split)
-			return;
-		splitid = split->common.classid;
-	}
-
-	if (split == NULL || split->common.classid != splitid) {
-		for (split = cl->tparent; split; split = split->tparent)
-			if (split->common.classid == splitid)
-				break;
-	}
-
-	if (split == NULL)
-		return;
-
-	if (cl->split != split) {
-		cl->defmap = 0;
-		cbq_sync_defmap(cl);
-		cl->split = split;
-		cl->defmap = def & mask;
-	} else
-		cl->defmap = (cl->defmap & ~mask) | (def & mask);
-
-	cbq_sync_defmap(cl);
-}
-
-static void cbq_unlink_class(struct cbq_class *this)
-{
-	struct cbq_class *cl, **clp;
-	struct cbq_sched_data *q = qdisc_priv(this->qdisc);
-
-	qdisc_class_hash_remove(&q->clhash, &this->common);
-
-	if (this->tparent) {
-		clp = &this->sibling;
-		cl = *clp;
-		do {
-			if (cl == this) {
-				*clp = cl->sibling;
-				break;
-			}
-			clp = &cl->sibling;
-		} while ((cl = *clp) != this->sibling);
-
-		if (this->tparent->children == this) {
-			this->tparent->children = this->sibling;
-			if (this->sibling == this)
-				this->tparent->children = NULL;
-		}
-	} else {
-		WARN_ON(this->sibling != this);
-	}
-}
-
-static void cbq_link_class(struct cbq_class *this)
-{
-	struct cbq_sched_data *q = qdisc_priv(this->qdisc);
-	struct cbq_class *parent = this->tparent;
-
-	this->sibling = this;
-	qdisc_class_hash_insert(&q->clhash, &this->common);
-
-	if (parent == NULL)
-		return;
-
-	if (parent->children == NULL) {
-		parent->children = this;
-	} else {
-		this->sibling = parent->children->sibling;
-		parent->children->sibling = this;
-	}
-}
-
-static void
-cbq_reset(struct Qdisc *sch)
-{
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct cbq_class *cl;
-	int prio;
-	unsigned int h;
-
-	q->activemask = 0;
-	q->pmask = 0;
-	q->tx_class = NULL;
-	q->tx_borrowed = NULL;
-	qdisc_watchdog_cancel(&q->watchdog);
-	q->toplevel = TC_CBQ_MAXLEVEL;
-	q->now = psched_get_time();
-
-	for (prio = 0; prio <= TC_CBQ_MAXPRIO; prio++)
-		q->active[prio] = NULL;
-
-	for (h = 0; h < q->clhash.hashsize; h++) {
-		hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) {
-			qdisc_reset(cl->q);
-
-			cl->next_alive = NULL;
-			cl->undertime = PSCHED_PASTPERFECT;
-			cl->avgidle = cl->maxidle;
-			cl->deficit = cl->quantum;
-			cl->cpriority = cl->priority;
-		}
-	}
-}
-
-
-static void cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss)
-{
-	if (lss->change & TCF_CBQ_LSS_FLAGS) {
-		cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent;
-		cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent;
-	}
-	if (lss->change & TCF_CBQ_LSS_EWMA)
-		cl->ewma_log = lss->ewma_log;
-	if (lss->change & TCF_CBQ_LSS_AVPKT)
-		cl->avpkt = lss->avpkt;
-	if (lss->change & TCF_CBQ_LSS_MINIDLE)
-		cl->minidle = -(long)lss->minidle;
-	if (lss->change & TCF_CBQ_LSS_MAXIDLE) {
-		cl->maxidle = lss->maxidle;
-		cl->avgidle = lss->maxidle;
-	}
-	if (lss->change & TCF_CBQ_LSS_OFFTIME)
-		cl->offtime = lss->offtime;
-}
-
-static void cbq_rmprio(struct cbq_sched_data *q, struct cbq_class *cl)
-{
-	q->nclasses[cl->priority]--;
-	q->quanta[cl->priority] -= cl->weight;
-	cbq_normalize_quanta(q, cl->priority);
-}
-
-static void cbq_addprio(struct cbq_sched_data *q, struct cbq_class *cl)
-{
-	q->nclasses[cl->priority]++;
-	q->quanta[cl->priority] += cl->weight;
-	cbq_normalize_quanta(q, cl->priority);
-}
-
-static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-
-	if (wrr->allot)
-		cl->allot = wrr->allot;
-	if (wrr->weight)
-		cl->weight = wrr->weight;
-	if (wrr->priority) {
-		cl->priority = wrr->priority - 1;
-		cl->cpriority = cl->priority;
-		if (cl->priority >= cl->priority2)
-			cl->priority2 = TC_CBQ_MAXPRIO - 1;
-	}
-
-	cbq_addprio(q, cl);
-	return 0;
-}
-
-static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt)
-{
-	cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange);
-	return 0;
-}
-
-static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = {
-	[TCA_CBQ_LSSOPT]	= { .len = sizeof(struct tc_cbq_lssopt) },
-	[TCA_CBQ_WRROPT]	= { .len = sizeof(struct tc_cbq_wrropt) },
-	[TCA_CBQ_FOPT]		= { .len = sizeof(struct tc_cbq_fopt) },
-	[TCA_CBQ_OVL_STRATEGY]	= { .len = sizeof(struct tc_cbq_ovl) },
-	[TCA_CBQ_RATE]		= { .len = sizeof(struct tc_ratespec) },
-	[TCA_CBQ_RTAB]		= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
-	[TCA_CBQ_POLICE]	= { .len = sizeof(struct tc_cbq_police) },
-};
-
-static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1],
-			 struct nlattr *opt,
-			 struct netlink_ext_ack *extack)
-{
-	int err;
-
-	if (!opt) {
-		NL_SET_ERR_MSG(extack, "CBQ options are required for this operation");
-		return -EINVAL;
-	}
-
-	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt,
-					  cbq_policy, extack);
-	if (err < 0)
-		return err;
-
-	if (tb[TCA_CBQ_WRROPT]) {
-		const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]);
-
-		if (wrr->priority > TC_CBQ_MAXPRIO) {
-			NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO");
-			err = -EINVAL;
-		}
-	}
-	return err;
-}
-
-static int cbq_init(struct Qdisc *sch, struct nlattr *opt,
-		    struct netlink_ext_ack *extack)
-{
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct nlattr *tb[TCA_CBQ_MAX + 1];
-	struct tc_ratespec *r;
-	int err;
-
-	qdisc_watchdog_init(&q->watchdog, sch);
-