diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 0420418f317a..e29b275e09e0 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -33,6 +33,7 @@
 #include <linux/unistd.h>
 #include <linux/serial.h>
 #include <linux/serial_8250.h>
+#include <linux/bootmem.h>
 #include <asm/io.h>
 #include <asm/kdump.h>
 #include <asm/prom.h>
@@ -654,3 +655,28 @@ void cpu_die(void)
 	if (ppc_md.cpu_die)
 		ppc_md.cpu_die();
 }
+
+#ifdef CONFIG_SMP
+void __init setup_per_cpu_areas(void)
+{
+	int i;
+	unsigned long size;
+	char *ptr;
+
+	/* Copy section for each CPU (we discard the original) */
+	size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES);
+#ifdef CONFIG_MODULES
+	if (size < PERCPU_ENOUGH_ROOM)
+		size = PERCPU_ENOUGH_ROOM;
+#endif
+
+	for_each_cpu(i) {
+		ptr = alloc_bootmem_node(NODE_DATA(cpu_to_node(i)), size);
+		if (!ptr)
+			panic("Cannot allocate cpu data for CPU %d\n", i);
+
+		paca[i].data_offset = ptr - __per_cpu_start;
+		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+	}
+}
+#endif
diff --git a/include/asm-powerpc/paca.h b/include/asm-powerpc/paca.h
index 3ae52d9dc9ff..a64b4d425dab 100644
--- a/include/asm-powerpc/paca.h
+++ b/include/asm-powerpc/paca.h
@@ -65,6 +65,7 @@ struct paca_struct {
 	u64 stab_real;			/* Absolute address of segment table */
 	u64 stab_addr;			/* Virtual address of segment table */
 	void *emergency_sp;		/* pointer to emergency stack */
+	u64 data_offset;		/* per cpu data offset */
 	s16 hw_cpu_id;			/* Physical processor number */
 	u8 cpu_start;			/* At startup, processor spins until */
 					/* this becomes non-zero. */
diff --git a/include/asm-powerpc/percpu.h b/include/asm-powerpc/percpu.h
index 06a959d67234..e31922c50e53 100644
--- a/include/asm-powerpc/percpu.h
+++ b/include/asm-powerpc/percpu.h
@@ -1 +1,57 @@
+#ifndef _ASM_POWERPC_PERCPU_H_
+#define _ASM_POWERPC_PERCPU_H_
+#ifdef __powerpc64__
+#include <linux/compiler.h>
+
+/*
+ * Same as asm-generic/percpu.h, except that we store the per cpu offset
+ * in the paca. Based on the x86-64 implementation.
+ */
+
+#ifdef CONFIG_SMP
+
+#include <asm/paca.h>
+
+#define __per_cpu_offset(cpu) (paca[cpu].data_offset)
+#define __my_cpu_offset() get_paca()->data_offset
+
+/* Separate out the type, so (int[3], foo) works. */
+#define DEFINE_PER_CPU(type, name) \
+    __attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
+
+/* var is in discarded region: offset to particular copy we want */
+#define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
+#define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()))
+
+/* A macro to avoid #include hell... */
+#define percpu_modcopy(pcpudst, src, size)			\
+do {								\
+	unsigned int __i;					\
+	for (__i = 0; __i < NR_CPUS; __i++)			\
+		if (cpu_possible(__i))				\
+			memcpy((pcpudst)+__per_cpu_offset(__i),	\
+			       (src), (size));			\
+} while (0)
+
+extern void setup_per_cpu_areas(void);
+
+#else /* ! SMP */
+
+#define DEFINE_PER_CPU(type, name) \
+    __typeof__(type) per_cpu__##name
+
+#define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu__##var))
+#define __get_cpu_var(var)			per_cpu__##var
+
+#endif	/* SMP */
+
+#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
+
+#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
+#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
+
+#else
 #include <asm-generic/percpu.h>
+#endif
+
+#endif /* _ASM_POWERPC_PERCPU_H_ */