diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 8b97308e65df..9ca008f0c542 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -259,6 +259,9 @@ extern void __bad_size_call_parameter(void);
  * Special handling for cmpxchg_double.  cmpxchg_double is passed two
  * percpu variables.  The first has to be aligned to a double word
  * boundary and the second has to follow directly thereafter.
+ * We enforce this on all architectures even if they don't support
+ * a double cmpxchg instruction, since it's a cheap requirement, and it
+ * avoids breaking the requirement for architectures with the instruction.
  */
 #define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...)		\
 ({									\
diff --git a/mm/slub.c b/mm/slub.c
index 7be0223531b0..35f351f26193 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2320,16 +2320,12 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
 	BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
 			SLUB_PAGE_SHIFT * sizeof(struct kmem_cache_cpu));
 
-#ifdef CONFIG_CMPXCHG_LOCAL
 	/*
-	 * Must align to double word boundary for the double cmpxchg instructions
-	 * to work.
+	 * Must align to double word boundary for the double cmpxchg
+	 * instructions to work; see __pcpu_double_call_return_bool().
 	 */
-	s->cpu_slab = __alloc_percpu(sizeof(struct kmem_cache_cpu), 2 * sizeof(void *));
-#else
-	/* Regular alignment is sufficient */
-	s->cpu_slab = alloc_percpu(struct kmem_cache_cpu);
-#endif
+	s->cpu_slab = __alloc_percpu(sizeof(struct kmem_cache_cpu),
+				     2 * sizeof(void *));
 
 	if (!s->cpu_slab)
 		return 0;