diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 5a710b9..87a03c7 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -93,14 +93,20 @@
 
 #else /* !CONFIG_PREEMPT_COUNT */
 
-#define preempt_disable()		do { } while (0)
-#define sched_preempt_enable_no_resched()	do { } while (0)
-#define preempt_enable_no_resched()	do { } while (0)
-#define preempt_enable()		do { } while (0)
+/*
+ * Even if we don't have any preemption, we need preempt disable/enable
+ * to be barriers, so that we don't have things like get_user/put_user
+ * that can cause faults and scheduling migrate into our preempt-protected
+ * region.
+ */
+#define preempt_disable()		barrier()
+#define sched_preempt_enable_no_resched()	barrier()
+#define preempt_enable_no_resched()	barrier()
+#define preempt_enable()		barrier()
 
-#define preempt_disable_notrace()		do { } while (0)
-#define preempt_enable_no_resched_notrace()	do { } while (0)
-#define preempt_enable_notrace()		do { } while (0)
+#define preempt_disable_notrace()		barrier()
+#define preempt_enable_no_resched_notrace()	barrier()
+#define preempt_enable_notrace()		barrier()
 
 #endif /* CONFIG_PREEMPT_COUNT */
 
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index a26e2fb..e2369c16 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -16,7 +16,10 @@
  * In the debug case, 1 means unlocked, 0 means locked. (the values
  * are inverted, to catch initialization bugs)
  *
- * No atomicity anywhere, we are on UP.
+ * No atomicity anywhere, we are on UP. However, we still need
+ * the compiler barriers, because we do not want the compiler to
+ * move potentially faulting instructions (notably user accesses)
+ * into the locked sequence, resulting in non-atomic execution.
  */
 
 #ifdef CONFIG_DEBUG_SPINLOCK
@@ -25,6 +28,7 @@
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	lock->slock = 0;
+	barrier();
 }
 
 static inline void
@@ -32,6 +36,7 @@
 {
 	local_irq_save(flags);
 	lock->slock = 0;
+	barrier();
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
@@ -39,32 +44,34 @@
 	char oldval = lock->slock;
 
 	lock->slock = 0;
+	barrier();
 
 	return oldval > 0;
 }
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
+	barrier();
 	lock->slock = 1;
 }
 
 /*
  * Read-write spinlocks. No debug version.
  */
-#define arch_read_lock(lock)		do { (void)(lock); } while (0)
-#define arch_write_lock(lock)		do { (void)(lock); } while (0)
-#define arch_read_trylock(lock)	({ (void)(lock); 1; })
-#define arch_write_trylock(lock)	({ (void)(lock); 1; })
-#define arch_read_unlock(lock)		do { (void)(lock); } while (0)
-#define arch_write_unlock(lock)	do { (void)(lock); } while (0)
+#define arch_read_lock(lock)		do { barrier(); (void)(lock); } while (0)
+#define arch_write_lock(lock)		do { barrier(); (void)(lock); } while (0)
+#define arch_read_trylock(lock)	({ barrier(); (void)(lock); 1; })
+#define arch_write_trylock(lock)	({ barrier(); (void)(lock); 1; })
+#define arch_read_unlock(lock)		do { barrier(); (void)(lock); } while (0)
+#define arch_write_unlock(lock)	do { barrier(); (void)(lock); } while (0)
 
 #else /* DEBUG_SPINLOCK */
 #define arch_spin_is_locked(lock)	((void)(lock), 0)
 /* for sched.c and kernel_lock.c: */
-# define arch_spin_lock(lock)		do { (void)(lock); } while (0)
-# define arch_spin_lock_flags(lock, flags)	do { (void)(lock); } while (0)
-# define arch_spin_unlock(lock)	do { (void)(lock); } while (0)
-# define arch_spin_trylock(lock)	({ (void)(lock); 1; })
+# define arch_spin_lock(lock)		do { barrier(); (void)(lock); } while (0)
+# define arch_spin_lock_flags(lock, flags)	do { barrier(); (void)(lock); } while (0)
+# define arch_spin_unlock(lock)	do { barrier(); (void)(lock); } while (0)
+# define arch_spin_trylock(lock)	({ barrier(); (void)(lock); 1; })
 #endif /* DEBUG_SPINLOCK */
 
 #define arch_spin_is_contended(lock)	(((void)(lock), 0))