tracing: Use __this_cpu_inc/dec operation instead of __get_cpu_var

__this_cpu_inc_return() or __this_cpu_dec generates a single instruction,
which is faster than __get_cpu_var operation.

Link: http://lkml.kernel.org/r/50A9C1BD.1060308@gmail.com
Reviewed-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Shan Wei <davidshan@tencent.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ca9b7dfed8ef59ee2f19e067f657e3f68b3639a4..07888e15c6943a7bd233b85ea40ec49dbeeb5677 100644 (file)
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1344,7 +1344,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
         */
        preempt_disable_notrace();
 
-       use_stack = ++__get_cpu_var(ftrace_stack_reserve);
+       use_stack = __this_cpu_inc_return(ftrace_stack_reserve);
        /*
         * We don't need any atomic variables, just a barrier.
         * If an interrupt comes in, we don't care, because it would
@@ -1398,7 +1398,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
  out:
        /* Again, don't let gcc optimize things here */
        barrier();
-       __get_cpu_var(ftrace_stack_reserve)--;
+       __this_cpu_dec(ftrace_stack_reserve);
        preempt_enable_notrace();
 
 }