diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index 196287928bae..e699eb6c44be 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -947,7 +947,7 @@ percpu_modcopy (void *pcpudst, const void *src, unsigned long size)
 {
 	unsigned int i;
 	for_each_possible_cpu(i) {
-		memcpy(pcpudst + __per_cpu_offset[i], src, size);
+		memcpy(pcpudst + per_cpu_offset(i), src, size);
 	}
 }
 #endif /* CONFIG_SMP */
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index e038f13594e5..c41b1a731129 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -3,35 +3,87 @@
 #include <linux/compiler.h>
 #include <linux/threads.h>
 
+/*
+ * Determine the real variable name from the name visible in the
+ * kernel sources.
+ */
+#define per_cpu_var(var) per_cpu__##var
+
 #ifdef CONFIG_SMP
 
+/*
+ * per_cpu_offset() is the offset that has to be added to a
+ * percpu variable to get to the instance for a certain processor.
+ *
+ * Most arches use the __per_cpu_offset array for those offsets but
+ * some arches have their own ways of determining the offset (x86_64, s390).
+ */
+#ifndef __per_cpu_offset
 extern unsigned long __per_cpu_offset[NR_CPUS];
 
 #define per_cpu_offset(x) (__per_cpu_offset[x])
+#endif
 
-/* var is in discarded region: offset to particular copy we want */
-#define per_cpu(var, cpu) (*({				\
-	extern int simple_identifier_##var(void);	\
-	RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]); }))
-#define __get_cpu_var(var) per_cpu(var, smp_processor_id())
-#define __raw_get_cpu_var(var) per_cpu(var, raw_smp_processor_id())
+/*
+ * Determine the offset for the currently active processor.
+ * An arch may define __my_cpu_offset to provide a more effective
+ * means of obtaining the offset to the per cpu variables of the
+ * current processor.
+ */
+#ifndef __my_cpu_offset
+#define __my_cpu_offset per_cpu_offset(raw_smp_processor_id())
+#define my_cpu_offset per_cpu_offset(smp_processor_id())
+#else
+#define my_cpu_offset __my_cpu_offset
+#endif
+
+/*
+ * Add a offset to a pointer but keep the pointer as is.
+ *
+ * Only S390 provides its own means of moving the pointer.
+ */
+#ifndef SHIFT_PERCPU_PTR
+#define SHIFT_PERCPU_PTR(__p, __offset)	RELOC_HIDE((__p), (__offset))
+#endif
+
+/*
+ * A percpu variable may point to a discarded reghions. The following are
+ * established ways to produce a usable pointer from the percpu variable
+ * offset.
+ */
+#define per_cpu(var, cpu) \
+	(*SHIFT_PERCPU_PTR(&per_cpu_var(var), per_cpu_offset(cpu)))
+#define __get_cpu_var(var) \
+	(*SHIFT_PERCPU_PTR(&per_cpu_var(var), my_cpu_offset))
+#define __raw_get_cpu_var(var) \
+	(*SHIFT_PERCPU_PTR(&per_cpu_var(var), __my_cpu_offset))
+
+
+#ifdef CONFIG_ARCH_SETS_UP_PER_CPU_AREA
+extern void setup_per_cpu_areas(void);
+#endif
 
 /* A macro to avoid #include hell... */
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
 	for_each_possible_cpu(__i)				\
-		memcpy((pcpudst)+__per_cpu_offset[__i],		\
+		memcpy((pcpudst)+per_cpu_offset(__i),		\
 		       (src), (size));				\
 } while (0)
 #else /* ! SMP */
 
-#define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu__##var))
-#define __get_cpu_var(var)			per_cpu__##var
-#define __raw_get_cpu_var(var)			per_cpu__##var
+#define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu_var(var)))
+#define __get_cpu_var(var)			per_cpu_var(var)
+#define __raw_get_cpu_var(var)			per_cpu_var(var)
 
 #endif	/* SMP */
 
-#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
+#ifndef PER_CPU_ATTRIBUTES
+#define PER_CPU_ATTRIBUTES
+#endif
+
+#define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \
+					__typeof__(type) per_cpu_var(name)
 
 #endif /* _ASM_GENERIC_PERCPU_H_ */