arm64: barrier: Implement smp_cond_load_relaxed

We can provide an implementation of smp_cond_load_relaxed using READ_ONCE
and __cmpwait_relaxed.
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/include/asm/barrier.h

@@ -128,6 +128,19 @@ do {									\
 	__u.__val;							\
 })
 
+#define smp_cond_load_relaxed(ptr, cond_expr)				\
+({									\
+	typeof(ptr) __PTR = (ptr);					\
+	typeof(*ptr) VAL;						\
+	for (;;) {							\
+		VAL = READ_ONCE(*__PTR);				\
+		if (cond_expr)						\
+			break;						\
+		__cmpwait_relaxed(__PTR, VAL);				\
+	}								\
+	VAL;								\
+})
+
 #define smp_cond_load_acquire(ptr, cond_expr)				\
 ({									\
 	typeof(ptr) __PTR = (ptr);					\