ARM: 7984/1: prefetch: add prefetchw invocations for barriered atomics

After a bunch of benchmarking on the interaction between dmb and pldw,
it turns out that issuing the pldw *after* the dmb instruction can
give modest performance gains (~3% atomic_add_return improvement on a
dual A15).

This patch adds prefetchw invocations to our barriered atomic operations
including cmpxchg, test_and_xxx and futexes.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 2aff798..53e69da 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -23,6 +23,7 @@
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	smp_mb();						\
+	prefetchw(uaddr);					\
 	__asm__ __volatile__(					\
 	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
@@ -46,6 +47,8 @@
 		return -EFAULT;
 
 	smp_mb();
+	/* Prefetching cannot fault */
+	prefetchw(uaddr);
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	ldrex	%1, [%4]\n"
 	"	teq	%1, %2\n"