net: sched: fix `tc -s class show` no bstats on class with nolock subqueues

When a classful qdisc's child qdisc has set the flag
TCQ_F_CPUSTATS (pfifo_fast for example), the child qdisc's
cpu_bstats should be passed to gnet_stats_copy_basic(),
but many classful qdisc didn't do that. As a result,
`tc -s class show dev DEV` always return 0 for bytes and
packets in this case.

Pass the child qdisc's cpu_bstats to gnet_stats_copy_basic()
to fix this issue.

The qstats also has this problem, but it has been fixed
in 5dd431b6 ("net: sched: introduce and use qstats read...")
and bstats still remains buggy.

Fixes: 22e0f8b9 ("net: sched: make bstats per cpu and estimator RCU safe")
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/sched/sch_mq.c

@@ -245,7 +245,8 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
 
 	sch = dev_queue->qdisc_sleeping;
-	if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
+	if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats,
+				  &sch->bstats) < 0 ||
 	    qdisc_qstats_copy(d, sch) < 0)
 		return -1;
 	return 0;

net/sched/sch_mqprio.c

@@ -557,8 +557,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
 
 		sch = dev_queue->qdisc_sleeping;
-		if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
-					  d, NULL, &sch->bstats) < 0 ||
+		if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d,
+					  sch->cpu_bstats, &sch->bstats) < 0 ||
 		    qdisc_qstats_copy(d, sch) < 0)
 			return -1;
 	}

net/sched/sch_multiq.c

@@ -339,7 +339,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
-				  d, NULL, &cl_q->bstats) < 0 ||
+				  d, cl_q->cpu_bstats, &cl_q->bstats) < 0 ||
 	    qdisc_qstats_copy(d, cl_q) < 0)
 		return -1;
 

net/sched/sch_prio.c

@@ -356,7 +356,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
-				  d, NULL, &cl_q->bstats) < 0 ||
+				  d, cl_q->cpu_bstats, &cl_q->bstats) < 0 ||
 	    qdisc_qstats_copy(d, cl_q) < 0)
 		return -1;