fq_codel: fix NET_XMIT_CN behavior

My prior attempt to fix the backlogs of parents failed.

If we return NET_XMIT_CN, our parents wont increase their backlog,
so our qdisc_tree_reduce_backlog() should take this into account.

v2: Florian Westphal pointed out that we could drop the packet,
so we need to save qdisc_pkt_len(skb) in a temp variable before
calling fq_codel_drop()

Fixes: 9d18562a ("fq_codel: add batch ability to fq_codel_drop()")
Fixes: 2ccccf5f ("net_sched: update hierarchical backlog too")
Reported-by: Stas Nichiporovich <stasn77@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/sched/sch_fq_codel.c

@@ -199,6 +199,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	unsigned int idx, prev_backlog, prev_qlen;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
+	unsigned int pkt_len;
 	bool memory_limited;
 
 	idx = fq_codel_classify(skb, sch, &ret);
@@ -230,6 +231,8 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	prev_backlog = sch->qstats.backlog;
 	prev_qlen = sch->q.qlen;
 
+	/* save this packet length as it might be dropped by fq_codel_drop() */
+	pkt_len = qdisc_pkt_len(skb);
 	/* fq_codel_drop() is quite expensive, as it performs a linear search
 	 * in q->backlogs[] to find a fat flow.
 	 * So instead of dropping a single packet, drop half of its backlog
@@ -237,14 +240,23 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	 */
 	ret = fq_codel_drop(sch, q->drop_batch_size);
 
-	q->drop_overlimit += prev_qlen - sch->q.qlen;
+	prev_qlen -= sch->q.qlen;
+	prev_backlog -= sch->qstats.backlog;
+	q->drop_overlimit += prev_qlen;
 	if (memory_limited)
-		q->drop_overmemory += prev_qlen - sch->q.qlen;
-	/* As we dropped packet(s), better let upper stack know this */
-	qdisc_tree_reduce_backlog(sch, prev_qlen - sch->q.qlen,
-				  prev_backlog - sch->qstats.backlog);
+		q->drop_overmemory += prev_qlen;
 
-	return ret == idx ? NET_XMIT_CN : NET_XMIT_SUCCESS;
+	/* As we dropped packet(s), better let upper stack know this.
+	 * If we dropped a packet for this flow, return NET_XMIT_CN,
+	 * but in this case, our parents wont increase their backlogs.
+	 */
+	if (ret == idx) {
+		qdisc_tree_reduce_backlog(sch, prev_qlen - 1,
+					  prev_backlog - pkt_len);
+		return NET_XMIT_CN;
+	}
+	qdisc_tree_reduce_backlog(sch, prev_qlen, prev_backlog);
+	return NET_XMIT_SUCCESS;
 }
 
 /* This is the specific function called from codel_dequeue()