diff --git a/arch/Kconfig b/arch/Kconfig
index dc81b34c5d8..78a35e9dc10 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -109,3 +109,6 @@ config HAVE_CLK
 
 config HAVE_DMA_API_DEBUG
 	bool
+
+config HAVE_DEFAULT_NO_SPIN_MUTEXES
+	bool
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index dcb667c4375..2eca5fe0e75 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -82,6 +82,7 @@ config S390
 	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_SYSCALL_WRAPPERS
 	select HAVE_FUNCTION_TRACER
+	select HAVE_DEFAULT_NO_SPIN_MUTEXES
 	select HAVE_OPROFILE
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 00f45ff081a..b0e63c672eb 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -80,56 +80,4 @@ extern void setup_per_cpu_areas(void);
 #define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \
 					__typeof__(type) per_cpu_var(name)
 
-/*
- * Optional methods for optimized non-lvalue per-cpu variable access.
- *
- * @var can be a percpu variable or a field of it and its size should
- * equal char, int or long.  percpu_read() evaluates to a lvalue and
- * all others to void.
- *
- * These operations are guaranteed to be atomic w.r.t. preemption.
- * The generic versions use plain get/put_cpu_var().  Archs are
- * encouraged to implement single-instruction alternatives which don't
- * require preemption protection.
- */
-#ifndef percpu_read
-# define percpu_read(var)						\
-  ({									\
-	typeof(per_cpu_var(var)) __tmp_var__;				\
-	__tmp_var__ = get_cpu_var(var);					\
-	put_cpu_var(var);						\
-	__tmp_var__;							\
-  })
-#endif
-
-#define __percpu_generic_to_op(var, val, op)				\
-do {									\
-	get_cpu_var(var) op val;					\
-	put_cpu_var(var);						\
-} while (0)
-
-#ifndef percpu_write
-# define percpu_write(var, val)		__percpu_generic_to_op(var, (val), =)
-#endif
-
-#ifndef percpu_add
-# define percpu_add(var, val)		__percpu_generic_to_op(var, (val), +=)
-#endif
-
-#ifndef percpu_sub
-# define percpu_sub(var, val)		__percpu_generic_to_op(var, (val), -=)
-#endif
-
-#ifndef percpu_and
-# define percpu_and(var, val)		__percpu_generic_to_op(var, (val), &=)
-#endif
-
-#ifndef percpu_or
-# define percpu_or(var, val)		__percpu_generic_to_op(var, (val), |=)
-#endif
-
-#ifndef percpu_xor
-# define percpu_xor(var, val)		__percpu_generic_to_op(var, (val), ^=)
-#endif
-
 #endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index ee5615d6521..cfda2d5ad31 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -168,4 +168,56 @@ static inline void free_percpu(void *p)
 #define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type), \
 						       __alignof__(type))
 
+/*
+ * Optional methods for optimized non-lvalue per-cpu variable access.
+ *
+ * @var can be a percpu variable or a field of it and its size should
+ * equal char, int or long.  percpu_read() evaluates to a lvalue and
+ * all others to void.
+ *
+ * These operations are guaranteed to be atomic w.r.t. preemption.
+ * The generic versions use plain get/put_cpu_var().  Archs are
+ * encouraged to implement single-instruction alternatives which don't
+ * require preemption protection.
+ */
+#ifndef percpu_read
+# define percpu_read(var)						\
+  ({									\
+	typeof(per_cpu_var(var)) __tmp_var__;				\
+	__tmp_var__ = get_cpu_var(var);					\
+	put_cpu_var(var);						\
+	__tmp_var__;							\
+  })
+#endif
+
+#define __percpu_generic_to_op(var, val, op)				\
+do {									\
+	get_cpu_var(var) op val;					\
+	put_cpu_var(var);						\
+} while (0)
+
+#ifndef percpu_write
+# define percpu_write(var, val)		__percpu_generic_to_op(var, (val), =)
+#endif
+
+#ifndef percpu_add
+# define percpu_add(var, val)		__percpu_generic_to_op(var, (val), +=)
+#endif
+
+#ifndef percpu_sub
+# define percpu_sub(var, val)		__percpu_generic_to_op(var, (val), -=)
+#endif
+
+#ifndef percpu_and
+# define percpu_and(var, val)		__percpu_generic_to_op(var, (val), &=)
+#endif
+
+#ifndef percpu_or
+# define percpu_or(var, val)		__percpu_generic_to_op(var, (val), |=)
+#endif
+
+#ifndef percpu_xor
+# define percpu_xor(var, val)		__percpu_generic_to_op(var, (val), ^=)
+#endif
+
 #endif /* __LINUX_PERCPU_H */
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 5d79781394a..507cf2b5e9f 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -148,7 +148,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 	preempt_disable();
 	mutex_acquire(&lock->dep_map, subclass, 0, ip);
-#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES)
+#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) && \
+    !defined(CONFIG_HAVE_DEFAULT_NO_SPIN_MUTEXES)
 	/*
 	 * Optimistic spinning.
 	 *