mqprio: Correct stats in mqprio_dump_class_stats().

Introduction of lockless subqueues broke the class statistics.
Before the change stats were accumulated in `bstats' and `qstats'
on the stack which was then copied to struct gnet_dump.

After the change the `bstats' and `qstats' are initialized to 0
and never updated, yet still fed to gnet_dump. The code updates
the global qdisc->cpu_bstats and qdisc->cpu_qstats instead,
clobbering them. Most likely a copy-paste error from the code in
mqprio_dump().

__gnet_stats_copy_basic() and __gnet_stats_copy_queue() accumulate
the values for per-CPU case but for global stats they overwrite
the value, so only stats from the last loop iteration / tc end up
in sch->[bq]stats.

Use the on-stack [bq]stats variables again and add the stats manually
in the global case.

Fixes: ce679e8d ("net: sched: add support for TCQ_F_NOLOCK subqueues to sch_mqprio")
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
https://lore.kernel.org/all/20211007175000.2334713-2-bigeasy@linutronix.de/Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/sched/sch_mqprio.c

@@ -529,22 +529,28 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		for (i = tc.offset; i < tc.offset + tc.count; i++) {
 			struct netdev_queue *q = netdev_get_tx_queue(dev, i);
 			struct Qdisc *qdisc = rtnl_dereference(q->qdisc);
-			struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL;
-			struct gnet_stats_queue __percpu *cpu_qstats = NULL;
 
 			spin_lock_bh(qdisc_lock(qdisc));
+
 			if (qdisc_is_percpu_stats(qdisc)) {
-				cpu_bstats = qdisc->cpu_bstats;
-				cpu_qstats = qdisc->cpu_qstats;
+				qlen = qdisc_qlen_sum(qdisc);
+
+				__gnet_stats_copy_basic(NULL, &bstats,
+							qdisc->cpu_bstats,
+							&qdisc->bstats);
+				__gnet_stats_copy_queue(&qstats,
+							qdisc->cpu_qstats,
+							&qdisc->qstats,
+							qlen);
+			} else {
+				qlen		+= qdisc->q.qlen;
+				bstats.bytes	+= qdisc->bstats.bytes;
+				bstats.packets	+= qdisc->bstats.packets;
+				qstats.backlog	+= qdisc->qstats.backlog;
+				qstats.drops	+= qdisc->qstats.drops;
+				qstats.requeues	+= qdisc->qstats.requeues;
+				qstats.overlimits += qdisc->qstats.overlimits;
 			}
-
-			qlen = qdisc_qlen_sum(qdisc);
-			__gnet_stats_copy_basic(NULL, &sch->bstats,
-						cpu_bstats, &qdisc->bstats);
-			__gnet_stats_copy_queue(&sch->qstats,
-						cpu_qstats,
-						&qdisc->qstats,
-						qlen);
 			spin_unlock_bh(qdisc_lock(qdisc));
 		}