net: sched: shrink struct Qdisc

The struct Qdisc has a lot of holes, especially after commit
a53851e2 ("net: sched: explicit locking in gso_cpu fallback"),
which as a side effect, moved the fields just after 'busylock'
on a new cacheline.

Since both 'padded' and 'refcnt' are not updated frequently, and
there is a hole before 'gso_skb', we can move such fields there,
saving a cacheline without any performance side effect.

Before this commit:

pahole -C Qdisc net/sche/sch_generic.o
	# ...
        /* size: 384, cachelines: 6, members: 25 */
        /* sum members: 236, holes: 3, sum holes: 92 */
        /* padding: 56 */

After this commit:
pahole -C Qdisc net/sche/sch_generic.o
	# ...
	/* size: 320, cachelines: 5, members: 25 */
	/* sum members: 236, holes: 2, sum holes: 28 */
	/* padding: 56 */
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/sch_generic.h

@@ -85,6 +85,8 @@ struct Qdisc {
 	struct net_rate_estimator __rcu *rate_est;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
 	struct gnet_stats_queue	__percpu *cpu_qstats;
+	int			padded;
+	refcount_t		refcnt;
 
 	/*
 	 * For performance sake on SMP, we put highly modified fields at the end
@@ -97,8 +99,6 @@ struct Qdisc {
 	unsigned long		state;
 	struct Qdisc            *next_sched;
 	struct sk_buff_head	skb_bad_txq;
-	int			padded;
-	refcount_t		refcnt;
 
 	spinlock_t		busylock ____cacheline_aligned_in_smp;
 	spinlock_t		seqlock;