[PATCH] tracing/function-return-tracer: Add a barrier to ensure return stack index is incremented in memory

[Frederic Weisbecker <fweisbec@gmail.com>]

Impact: Fix possible race condition in ftrace function return tracer

This fixes a possible race condition if index incrementation
is not immediately flushed in memory.

Thanks for Andi Kleen and Steven Rostedt for pointing out this issue
and give me this solution.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Andi Kleen <andi@firstfloor.org>
---
 arch/x86/kernel/ftrace.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index fe83273..db25236 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -56,6 +56,7 @@ static int push_return_trace(unsigned long ret, unsigned long long time,
 		return -EBUSY;
 
 	index = ++ti->curr_ret_stack;
+	barrier();
 	ti->ret_stack[index].ret = ret;
 	ti->ret_stack[index].func = func;
 	ti->ret_stack[index].calltime = time;
-- 
1.5.2.5