Merge branch 'sch-accurate-backlog'

Cong Wang says:

====================
net_sched: update backlog for hierarchical qdisc's

For hierarchical qdisc like HTB, we currently only update its qlen
but leave its backlog as zero:

    qdisc htb 1: dev eth0 root refcnt 2 r2q 10 default 1 direct_packets_stat 0 ver 3.17
     Sent 172680457356 bytes 222469449 pkt (dropped 0, overlimits 123575834 requeues 0)
     backlog 0b 72p requeues 0

This patchset makes backlog as accurate as qlen.

v3: rebase and fix the n==0 case for qdisc_tree_reduce_backlog()
v2: rebase and update changelog, not code change
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/codel.h

@@ -162,12 +162,14 @@ struct codel_vars {
  * struct codel_stats - contains codel shared variables and stats
  * @maxpacket:	largest packet we've seen so far
  * @drop_count:	temp count of dropped packets in dequeue()
+ * @drop_len:	bytes of dropped packets in dequeue()
  * ecn_mark:	number of packets we ECN marked instead of dropping
  * ce_mark:	number of packets CE marked because sojourn time was above ce_threshold
  */
 struct codel_stats {
 	u32		maxpacket;
 	u32		drop_count;
+	u32		drop_len;
 	u32		ecn_mark;
 	u32		ce_mark;
 };
@@ -308,6 +310,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 								  vars->rec_inv_sqrt);
 					goto end;
 				}
+				stats->drop_len += qdisc_pkt_len(skb);
 				qdisc_drop(skb, sch);
 				stats->drop_count++;
 				skb = dequeue_func(vars, sch);
@@ -330,6 +333,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 		if (params->ecn && INET_ECN_set_ce(skb)) {
 			stats->ecn_mark++;
 		} else {
+			stats->drop_len += qdisc_pkt_len(skb);
 			qdisc_drop(skb, sch);
 			stats->drop_count++;
 

include/net/sch_generic.h

@@ -396,7 +396,8 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 			      struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
 void qdisc_destroy(struct Qdisc *qdisc);
-void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n);
+void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
+			       unsigned int len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops);
 struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
@@ -707,6 +708,23 @@ static inline void qdisc_reset_queue(struct Qdisc *sch)
 	sch->qstats.backlog = 0;
 }
 
+static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
+					  struct Qdisc **pold)
+{
+	struct Qdisc *old;
+
+	sch_tree_lock(sch);
+	old = *pold;
+	*pold = new;
+	if (old != NULL) {
+		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
+		qdisc_reset(old);
+	}
+	sch_tree_unlock(sch);
+
+	return old;
+}
+
 static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
 					      struct sk_buff_head *list)
 {

net/sched/sch_api.c

@@ -744,14 +744,15 @@ static u32 qdisc_alloc_handle(struct net_device *dev)
 	return 0;
 }
 
-void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
+void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n,
+			       unsigned int len)
 {
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
 	int drops;
 
-	if (n == 0)
+	if (n == 0 && len == 0)
 		return;
 	drops = max_t(int, n, 0);
 	rcu_read_lock();
@@ -774,11 +775,12 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 			cops->put(sch, cl);
 		}
 		sch->q.qlen -= n;
+		sch->qstats.backlog -= len;
 		__qdisc_qstats_drop(sch, drops);
 	}
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
+EXPORT_SYMBOL(qdisc_tree_reduce_backlog);
 
 static void notify_and_destroy(struct net *net, struct sk_buff *skb,
 			       struct nlmsghdr *n, u32 clid,

net/sched/sch_cbq.c

@@ -1624,13 +1624,8 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new->reshape_fail = cbq_reshape_fail;
 #endif
 	}
-	sch_tree_lock(sch);
-	*old = cl->q;
-	cl->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
 
+	*old = qdisc_replace(sch, new, &cl->q);
 	return 0;
 }
 
@@ -1914,16 +1909,17 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
-	unsigned int qlen;
+	unsigned int qlen, backlog;
 
 	if (cl->filters || cl->children || cl == &q->link)
 		return -EBUSY;
 
 	sch_tree_lock(sch);
 
 	qlen = cl->q->q.qlen;
+	backlog = cl->q->qstats.backlog;
 	qdisc_reset(cl->q);
-	qdisc_tree_decrease_qlen(cl->q, qlen);
+	qdisc_tree_reduce_backlog(cl->q, qlen, backlog);
 
 	if (cl->next_alive)
 		cbq_deactivate_class(cl);

net/sched/sch_choke.c

@@ -128,8 +128,8 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 		choke_zap_tail_holes(q);
 
 	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
 	qdisc_drop(skb, sch);
-	qdisc_tree_decrease_qlen(sch, 1);
 	--sch->q.qlen;
 }
 
@@ -456,6 +456,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 		old = q->tab;
 		if (old) {
 			unsigned int oqlen = sch->q.qlen, tail = 0;
+			unsigned dropped = 0;
 
 			while (q->head != q->tail) {
 				struct sk_buff *skb = q->tab[q->head];
@@ -467,11 +468,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 					ntab[tail++] = skb;
 					continue;
 				}
+				dropped += qdisc_pkt_len(skb);
 				qdisc_qstats_backlog_dec(sch, skb);
 				--sch->q.qlen;
 				qdisc_drop(skb, sch);
 			}
-			qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen);
+			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
 			q->head = 0;
 			q->tail = tail;
 		}

net/sched/sch_codel.c

@@ -79,12 +79,13 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 
 	skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue);
 
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->stats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->stats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
 		q->stats.drop_count = 0;
+		q->stats.drop_len = 0;
 	}
 	if (skb)
 		qdisc_bstats_update(sch, skb);
@@ -116,7 +117,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_CODEL_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -156,10 +157,11 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;

net/sched/sch_drr.c

@@ -53,9 +53,10 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
 static void drr_purge_queue(struct drr_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
@@ -226,11 +227,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	drr_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 

net/sched/sch_dsmark.c

@@ -73,13 +73,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	*old = p->q;
-	p->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &p->q);
 	return 0;
 }
 
@@ -264,6 +258,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -286,6 +281,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		return NULL;
 
 	qdisc_bstats_update(sch, skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
 
 	index = skb->tc_index & (p->indices - 1);
@@ -401,6 +397,7 @@ static void dsmark_reset(struct Qdisc *sch)
 
 	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 	qdisc_reset(p->q);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 

net/sched/sch_fq.c

@@ -662,6 +662,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_MAX + 1];
 	int err, drop_count = 0;
+	unsigned drop_len = 0;
 	u32 fq_log;
 
 	if (!opt)
@@ -736,10 +737,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 
 		if (!skb)
 			break;
+		drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, drop_count);
+	qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
 
 	sch_tree_unlock(sch);
 	return err;

net/sched/sch_fq_codel.c

@@ -175,7 +175,7 @@ static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch)
 static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
-	unsigned int idx;
+	unsigned int idx, prev_backlog;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
 
@@ -203,6 +203,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
@@ -211,7 +212,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -241,6 +242,7 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	struct fq_codel_flow *flow;
 	struct list_head *head;
 	u32 prev_drop_count, prev_ecn_mark;
+	unsigned int prev_backlog;
 
 begin:
 	head = &q->new_flows;
@@ -259,6 +261,7 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 
 	prev_drop_count = q->cstats.drop_count;
 	prev_ecn_mark = q->cstats.ecn_mark;
+	prev_backlog = sch->qstats.backlog;
 
 	skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats,
 			    dequeue);
@@ -276,12 +279,14 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	}
 	qdisc_bstats_update(sch, skb);
 	flow->deficit -= qdisc_pkt_len(skb);
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->cstats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
+					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;
+		q->cstats.drop_len = 0;
 	}
 	return skb;
 }
@@ -372,11 +377,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = fq_codel_dequeue(sch);
 
+		q->cstats.drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		q->cstats.drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
 	q->cstats.drop_count = 0;
+	q->cstats.drop_len = 0;
 
 	sch_tree_unlock(sch);
 	return 0;

net/sched/sch_hfsc.c

@@ -895,9 +895,10 @@ static void
 hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static void
@@ -1215,11 +1216,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	hfsc_purge_queue(sch, cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }