diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 0a456bef8c792d91a30a4c2caf24cb6fb96546e2..2fee2f59288c94d70814771ed06fced11ede369d 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -199,19 +199,19 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 #define _percpu_read(pcp)						\
 ({									\
 	typeof(pcp) __retval;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	__retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), 	\
 					      sizeof(pcp));		\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	__retval;							\
 })
 
 #define _percpu_write(pcp, val)						\
 do {									\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), 	\
 				sizeof(pcp));				\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 } while(0)								\
 
 #define _pcp_protect(operation, pcp, val)			\
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index e875a5a551d7debeab3c34ed2d52e9beae7c8f7d..89206b568cd42365090a8be788da1bbd35466f72 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -363,4 +363,14 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()
 
+/*
+ * Accesses appearing in program order before a spin_lock() operation
+ * can be reordered with accesses inside the critical section, by virtue
+ * of arch_spin_lock being constructed using acquire semantics.
+ *
+ * In cases where this is problematic (e.g. try_to_wake_up), an
+ * smp_mb__before_spinlock() can restore the required ordering.
+ */
+#define smp_mb__before_spinlock()	smp_mb()
+
 #endif /* __ASM_SPINLOCK_H */