this_cpu: Use this_cpu_xx for ftrace

this_cpu_xx can reduce the instruction count here and also
avoid address arithmetic.

Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Tejun Heo <tj@kernel.org>
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4506826..8439cdc 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -86,17 +86,17 @@
  */
 static int tracing_disabled = 1;
 
-DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(int, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
 {
 	preempt_disable();
-	local_inc(&__get_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
 }
 
 static inline void ftrace_enable_cpu(void)
 {
-	local_dec(&__get_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
 	preempt_enable();
 }
 
@@ -1085,7 +1085,7 @@
 	struct ftrace_entry *entry;
 
 	/* If we are reading the ring buffer, don't trace */
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
 		return;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),