percpu: remove per_cpu__ prefix.

Now that the return from alloc_percpu is compatible with the address
of per-cpu vars, it makes sense to hand around the address of per-cpu
variables.  To make this sane, we remove the per_cpu__ prefix we used
created to stop people accidentally using these vars directly.

Now we have sparse, we can use that (next patch).

tj: * Updated to convert stuff which were missed by or added after the
      original patch.

    * Kill per_cpu_var() macro.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index d858897..3e489fd 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -76,22 +76,22 @@
 
 static inline void __count_vm_event(enum vm_event_item item)
 {
-	__this_cpu_inc(per_cpu_var(vm_event_states).event[item]);
+	__this_cpu_inc(vm_event_states.event[item]);
 }
 
 static inline void count_vm_event(enum vm_event_item item)
 {
-	this_cpu_inc(per_cpu_var(vm_event_states).event[item]);
+	this_cpu_inc(vm_event_states.event[item]);
 }
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
-	__this_cpu_add(per_cpu_var(vm_event_states).event[item], delta);
+	__this_cpu_add(vm_event_states.event[item], delta);
 }
 
 static inline void count_vm_events(enum vm_event_item item, long delta)
 {
-	this_cpu_add(per_cpu_var(vm_event_states).event[item], delta);
+	this_cpu_add(vm_event_states.event[item], delta);
 }
 
 extern void all_vm_events(unsigned long *);