this_cpu: Use this_cpu operations in RCU

RCU does not do dynamic allocations but it increments per cpu variables
a lot. These instructions results in a move to a register and then back
to memory. This patch will make it use the inc/dec instructions on x86
that do not need a register.
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Tejun Heo <tj@kernel.org>

kernel/rcutorture.c

@@ -731,13 +731,13 @@ static void rcu_torture_timer(unsigned long unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	++__get_cpu_var(rcu_torture_count)[pipe_count];
+	__this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
 	completed = cur_ops->completed() - completed;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
 	}
-	++__get_cpu_var(rcu_torture_batch)[completed];
+	__this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
 	preempt_enable();
 	cur_ops->readunlock(idx);
 }
@@ -786,13 +786,13 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		++__get_cpu_var(rcu_torture_count)[pipe_count];
+		__this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
 		completed = cur_ops->completed() - completed;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
 		}
-		++__get_cpu_var(rcu_torture_batch)[completed];
+		__this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();