diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 9fb8aae5c391..05d86407188c 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -70,6 +70,9 @@ config AUTO_IRQ_AFFINITY
 	depends on SMP
 	default y
 
+config HAVE_LEGACY_PER_CPU_AREA
+	def_bool y
+
 source "init/Kconfig"
 source "kernel/Kconfig.freezer"
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 170042b420d4..328d2f8b8c3f 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -89,6 +89,9 @@ config GENERIC_TIME_VSYSCALL
 	bool
 	default y
 
+config HAVE_LEGACY_PER_CPU_AREA
+	def_bool y
+
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index bf6cedfa05db..a774c2acbe69 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -46,6 +46,9 @@ config GENERIC_HARDIRQS_NO__DO_IRQ
 	bool
 	default y
 
+config HAVE_LEGACY_PER_CPU_AREA
+	def_bool PPC64
+
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool PPC64
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a14dba0e4d67..f4a3cc62d28f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -75,6 +75,9 @@ config VIRT_CPU_ACCOUNTING
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
+config HAVE_LEGACY_PER_CPU_AREA
+	def_bool y
+
 mainmenu "Linux Kernel Configuration"
 
 config S390
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 3f8b6a92eabd..7a8698b913fe 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -92,6 +92,9 @@ config AUDIT_ARCH
 	bool
 	default y
 
+config HAVE_LEGACY_PER_CPU_AREA
+	def_bool y if SPARC64
+
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y if SPARC64
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d1430ef6b4f9..a48a90076d83 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -149,9 +149,6 @@ config ARCH_HAS_CACHE_LINE_SIZE
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 
-config HAVE_DYNAMIC_PER_CPU_AREA
-	def_bool y
-
 config HAVE_CPUMASK_OF_CPU_MAP
 	def_bool X86_64_SMP
 
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 26fd9d12f050..e5000343dd61 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -34,7 +34,7 @@
 
 #ifdef CONFIG_SMP
 
-#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)
@@ -80,7 +80,7 @@ extern ssize_t __init pcpu_embed_first_chunk(
 
 extern void *__alloc_reserved_percpu(size_t size, size_t align);
 
-#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#else /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 struct percpu_data {
 	void *ptrs[1];
@@ -99,11 +99,15 @@ struct percpu_data {
         (__typeof__(ptr))__p->ptrs[(cpu)];				\
 })
 
-#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 extern void *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void *__pdata);
 
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+extern void __init setup_per_cpu_areas(void);
+#endif
+
 #else /* CONFIG_SMP */
 
 #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
@@ -124,6 +128,8 @@ static inline void free_percpu(void *p)
 	kfree(p);
 }
 
+static inline void __init setup_per_cpu_areas(void) { }
+
 #endif /* CONFIG_SMP */
 
 #define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type), \
diff --git a/init/main.c b/init/main.c
index 09131ec090c1..602d724afa5c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -357,7 +357,6 @@ static void __init smp_init(void)
 #define smp_init()	do { } while (0)
 #endif
 
-static inline void setup_per_cpu_areas(void) { }
 static inline void setup_nr_cpu_ids(void) { }
 static inline void smp_prepare_cpus(unsigned int maxcpus) { }
 
@@ -378,29 +377,6 @@ static void __init setup_nr_cpu_ids(void)
 	nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
 }
 
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-
-EXPORT_SYMBOL(__per_cpu_offset);
-
-static void __init setup_per_cpu_areas(void)
-{
-	unsigned long size, i;
-	char *ptr;
-	unsigned long nr_possible_cpus = num_possible_cpus();
-
-	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
-	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
-
-	for_each_possible_cpu(i) {
-		__per_cpu_offset[i] = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-		ptr += size;
-	}
-}
-#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
-
 /* Called by boot processor to activate the rest. */
 static void __init smp_init(void)
 {
diff --git a/kernel/module.c b/kernel/module.c
index 38928fcaff2b..f5934954fa99 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -364,7 +364,7 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 
 static void *percpu_modalloc(unsigned long size, unsigned long align,
 			     const char *name)
@@ -389,7 +389,7 @@ static void percpu_modfree(void *freeme)
 	free_percpu(freeme);
 }
 
-#else /* ... !CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 /* Number of blocks used and allocated. */
 static unsigned int pcpu_num_used, pcpu_num_allocated;
@@ -535,7 +535,7 @@ static int percpu_modinit(void)
 }
 __initcall(percpu_modinit);
 
-#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
 				 Elf_Shdr *sechdrs,
diff --git a/mm/Makefile b/mm/Makefile
index 5e0bd6426693..c77c6487552f 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -33,7 +33,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 obj-$(CONFIG_SMP) += percpu.o
 else
 obj-$(CONFIG_SMP) += allocpercpu.o
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
index dfdee6a47359..df34ceae0c67 100644
--- a/mm/allocpercpu.c
+++ b/mm/allocpercpu.c
@@ -5,6 +5,8 @@
  */
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/bootmem.h>
+#include <asm/sections.h>
 
 #ifndef cache_line_size
 #define cache_line_size()	L1_CACHE_BYTES
@@ -147,3 +149,29 @@ void free_percpu(void *__pdata)
 	kfree(__percpu_disguise(__pdata));
 }
 EXPORT_SYMBOL_GPL(free_percpu);
+
+/*
+ * Generic percpu area setup.
+ */
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+
+EXPORT_SYMBOL(__per_cpu_offset);
+
+void __init setup_per_cpu_areas(void)
+{
+	unsigned long size, i;
+	char *ptr;
+	unsigned long nr_possible_cpus = num_possible_cpus();
+
+	/* Copy section for each CPU (we discard the original) */
+	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
+	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
+
+	for_each_possible_cpu(i) {
+		__per_cpu_offset[i] = ptr - __per_cpu_start;
+		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+		ptr += size;
+	}
+}
+#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
diff --git a/mm/percpu.c b/mm/percpu.c
index b70f2acd8853..b14984566f5a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -43,7 +43,7 @@
  *
  * To use this allocator, arch code should do the followings.
  *
- * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+ * - drop CONFIG_HAVE_LEGACY_PER_CPU_AREA
  *
  * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
  *   regular address to percpu pointer and back if they need to be
@@ -1275,3 +1275,41 @@ ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
 				      reserved_size, dyn_size,
 				      pcpue_unit_size, pcpue_ptr, NULL);
 }
+
+/*
+ * Generic percpu area setup.
+ *
+ * The embedding helper is used because its behavior closely resembles
+ * the original non-dynamic generic percpu area setup.  This is
+ * important because many archs have addressing restrictions and might
+ * fail if the percpu area is located far away from the previous
+ * location.  As an added bonus, in non-NUMA cases, embedding is
+ * generally a good idea TLB-wise because percpu area can piggy back
+ * on the physical linear memory mapping which uses large page
+ * mappings on applicable archs.
+ */
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+void __init setup_per_cpu_areas(void)
+{
+	size_t static_size = __per_cpu_end - __per_cpu_start;
+	ssize_t unit_size;
+	unsigned long delta;
+	unsigned int cpu;
+
+	/*
+	 * Always reserve area for module percpu variables.  That's
+	 * what the legacy allocator did.
+	 */
+	unit_size = pcpu_embed_first_chunk(static_size, PERCPU_MODULE_RESERVE,
+					   PERCPU_DYNAMIC_RESERVE, -1);
+	if (unit_size < 0)
+		panic("Failed to initialized percpu areas.");
+
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+	for_each_possible_cpu(cpu)
+		__per_cpu_offset[cpu] = delta + cpu * unit_size;
+}
+#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */