core: Replace __get_cpu_var with __this_cpu_read if not used for an address.

__get_cpu_var() can be replaced with this_cpu_read and will then use a
single read instruction with implied address calculation to access the
correct per cpu instance.

However, the address of a per cpu variable passed to __this_cpu_read()
cannot be determined (since it's an implied address conversion through
segment prefixes).  Therefore apply this only to uses of __get_cpu_var
where the address of the variable is not used.

Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Hugh Dickins <hughd@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
diff --git a/mm/slab.c b/mm/slab.c
index b1e40da..316d755 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -829,12 +829,12 @@
 
 static void next_reap_node(void)
 {
-	int node = __get_cpu_var(slab_reap_node);
+	int node = __this_cpu_read(slab_reap_node);
 
 	node = next_node(node, node_online_map);
 	if (unlikely(node >= MAX_NUMNODES))
 		node = first_node(node_online_map);
-	__get_cpu_var(slab_reap_node) = node;
+	__this_cpu_write(slab_reap_node, node);
 }
 
 #else
@@ -1012,7 +1012,7 @@
  */
 static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
 {
-	int node = __get_cpu_var(slab_reap_node);
+	int node = __this_cpu_read(slab_reap_node);
 
 	if (l3->alien) {
 		struct array_cache *ac = l3->alien[node];