net: sched: a dflt qdisc may be used with per cpu stats

Enable dflt qdisc support for per cpu stats before this patch a dflt
qdisc was required to use the global statistics qstats and bstats.

This adds a static flags field to qdisc_ops that is propagated
into qdisc->flags in qdisc allocate call. This allows the allocation
block to completely allocate the qdisc object so we don't have
dangling allocations after qdisc init.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/sch_generic.h

@@ -180,6 +180,7 @@ struct Qdisc_ops {
 	const struct Qdisc_class_ops	*cl_ops;
 	char			id[IFNAMSIZ];
 	int			priv_size;
+	unsigned int		static_flags;
 
 	int 			(*enqueue)(struct sk_buff *skb,
 					   struct Qdisc *sch,

net/sched/sch_generic.c

@@ -632,6 +632,19 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	qdisc_skb_head_init(&sch->q);
 	spin_lock_init(&sch->q.lock);
 
+	if (ops->static_flags & TCQ_F_CPUSTATS) {
+		sch->cpu_bstats =
+			netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
+		if (!sch->cpu_bstats)
+			goto errout1;
+
+		sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
+		if (!sch->cpu_qstats) {
+			free_percpu(sch->cpu_bstats);
+			goto errout1;
+		}
+	}
+
 	spin_lock_init(&sch->busylock);
 	lockdep_set_class(&sch->busylock,
 			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
@@ -641,6 +654,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  dev->qdisc_running_key ?: &qdisc_running_key);
 
 	sch->ops = ops;
+	sch->flags = ops->static_flags;
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;
 	sch->dev_queue = dev_queue;
@@ -648,6 +662,8 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	refcount_set(&sch->refcnt, 1);
 
 	return sch;
+errout1:
+	kfree(p);
 errout:
 	return ERR_PTR(err);
 }