ARM: 6998/2: kernel: use proper memory barriers for bitops

Improve scalability by avoiding costly and unnecessary L2 cache sync
in handling bitops.
Signed-off-by: NHeechul Yun <hyun@nvidia.com>
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

arch/arm/include/asm/bitops.h

@@ -26,8 +26,8 @@
 #include <linux/compiler.h>
 #include <asm/system.h>
 
-#define smp_mb__before_clear_bit()	mb()
-#define smp_mb__after_clear_bit()	mb()
+#define smp_mb__before_clear_bit()	smp_mb()
+#define smp_mb__after_clear_bit()	smp_mb()
 
 /*
  * These functions are the basis of our bit ops.