prefetch result for ARM64 atomic ops

index 0237f08..845f9be 100644
@@ -48,6 +48,7 @@ static inline void atomic_add(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	asm volatile("// atomic_add\n"
 "1:	ldxr	%w0, %2\n"
 "	add	%w0, %w0, %w3\n"

@@ -62,6 +63,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	asm volatile("// atomic_add_return\n"
 "1:	ldxr	%w0, %2\n"
 "	add	%w0, %w0, %w3\n"

@@ -80,6 +82,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	asm volatile("// atomic_sub\n"
 "1:	ldxr	%w0, %2\n"
 "	sub	%w0, %w0, %w3\n"

@@ -94,6 +97,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	asm volatile("// atomic_sub_return\n"
 "1:	ldxr	%w0, %2\n"
 "	sub	%w0, %w0, %w3\n"

@@ -113,6 +117,7 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 	int oldval;
 
 	smp_mb();
+	prefetchw(&ptr->counter);
 
 	asm volatile("// atomic_cmpxchg\n"
 "1:	ldxr	%w1, %2\n"

@@ -170,6 +175,7 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
 	long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	asm volatile("// atomic64_add\n"
 "1:	ldxr	%0, %2\n"
 "	add	%0, %0, %3\n"

@@ -184,6 +190,7 @@ static inline long atomic64_add_return(long i, atomic64_t *v)
 	long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	asm volatile("// atomic64_add_return\n"
 "1:	ldxr	%0, %2\n"
 "	add	%0, %0, %3\n"

@@ -202,6 +209,7 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
 	long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	asm volatile("// atomic64_sub\n"
 "1:	ldxr	%0, %2\n"
 "	sub	%0, %0, %3\n"

@@ -216,6 +224,7 @@ static inline long atomic64_sub_return(long i, atomic64_t *v)
 	long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	asm volatile("// atomic64_sub_return\n"
 "1:	ldxr	%0, %2\n"
 "	sub	%0, %0, %3\n"

@@ -235,6 +244,7 @@ static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new)
 	unsigned long res;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	asm volatile("// atomic64_cmpxchg\n"
 "1:	ldxr	%1, %2\n"

@@ -258,6 +268,7 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	asm volatile("// atomic64_dec_if_positive\n"
 "1:	ldxr	%0, %2\n"
 "	subs	%0, %0, #1\n"