Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Catalin Marinas:

 - smp_mb__before_spinlock() changed to smp_mb() on arm64 since the
   generic definition to smp_wmb() is not sufficient

 - avoid a recursive loop with the graph tracer by using using
   preempt_(enable|disable)_notrace in _percpu_(read|write)

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: use preempt_disable_notrace in _percpu_read/write
  arm64: spinlocks: implement smp_mb__before_spinlock() as smp_mb()

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)			\

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 */