Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (34 commits)
  m68k: rename global variable vmalloc_end to m68k_vmalloc_end
  percpu: add missing per_cpu_ptr_to_phys() definition for UP
  percpu: Fix kdump failure if booted with percpu_alloc=page
  percpu: make misc percpu symbols unique
  percpu: make percpu symbols in ia64 unique
  percpu: make percpu symbols in powerpc unique
  percpu: make percpu symbols in x86 unique
  percpu: make percpu symbols in xen unique
  percpu: make percpu symbols in cpufreq unique
  percpu: make percpu symbols in oprofile unique
  percpu: make percpu symbols in tracer unique
  percpu: make percpu symbols under kernel/ and mm/ unique
  percpu: remove some sparse warnings
  percpu: make alloc_percpu() handle array types
  vmalloc: fix use of non-existent percpu variable in put_cpu_var()
  this_cpu: Use this_cpu_xx in trace_functions_graph.c
  this_cpu: Use this_cpu_xx for ftrace
  this_cpu: Use this_cpu_xx in nmi handling
  this_cpu: Use this_cpu operations in RCU
  this_cpu: Use this_cpu ops for VM statistics
  ...

Fix up trivial (famous last words) global per-cpu naming conflicts in
	arch/x86/kvm/svm.c
	mm/slab.c

79 files changed, 1222 insertions, 978 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 1ee596cd942..2d7f56a98e0 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -87,9 +87,6 @@ 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/ia64/include/asm/meminit.h b/arch/ia64/include/asm/meminit.h
index 688a812c017..61c7b1750b1 100644
--- a/arch/ia64/include/asm/meminit.h
+++ b/arch/ia64/include/asm/meminit.h
@@ -61,7 +61,7 @@ extern int register_active_ranges(u64 start, u64 len, int nid);
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 # define LARGE_GAP	0x40000000 /* Use virtual mem map if hole is > than this */
-  extern unsigned long vmalloc_end;
+  extern unsigned long VMALLOC_END;
   extern struct page *vmem_map;
   extern int find_largest_hole(u64 start, u64 end, void *arg);
   extern int create_mem_map_page_table(u64 start, u64 end, void *arg);
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 8840a690d1e..69bf13857a9 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -228,8 +228,7 @@ ia64_phys_addr_valid (unsigned long addr)
 #define VMALLOC_START		(RGN_BASE(RGN_GATE) + 0x200000000UL)
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 # define VMALLOC_END_INIT	(RGN_BASE(RGN_GATE) + (1UL << (4*PAGE_SHIFT - 9)))
-# define VMALLOC_END		vmalloc_end
-  extern unsigned long vmalloc_end;
+extern unsigned long VMALLOC_END;
 #else
 #if defined(CONFIG_SPARSEMEM) && defined(CONFIG_SPARSEMEM_VMEMMAP)
 /* SPARSEMEM_VMEMMAP uses half of vmalloc... */
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 3eaeedf1aef..7fa90f73f6b 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -229,7 +229,7 @@ struct cpuinfo_ia64 {
 #endif
 };
 
-DECLARE_PER_CPU(struct cpuinfo_ia64, cpu_info);
+DECLARE_PER_CPU(struct cpuinfo_ia64, ia64_cpu_info);
 
 /*
  * The "local" data variable.  It refers to the per-CPU data of the currently executing
@@ -237,8 +237,8 @@ DECLARE_PER_CPU(struct cpuinfo_ia64, cpu_info);
  * Do not use the address of local_cpu_data, since it will be different from
  * cpu_data(smp_processor_id())!
  */
-#define local_cpu_data		(&__ia64_per_cpu_var(cpu_info))
-#define cpu_data(cpu)		(&per_cpu(cpu_info, cpu))
+#define local_cpu_data		(&__ia64_per_cpu_var(ia64_cpu_info))
+#define cpu_data(cpu)		(&per_cpu(ia64_cpu_info, cpu))
 
 extern void print_cpu_info (struct cpuinfo_ia64 *);
 
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index baec6f00f7f..40574ae1140 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -702,11 +702,23 @@ int __init early_acpi_boot_init(void)
 		printk(KERN_ERR PREFIX
 		       "Error parsing MADT - no LAPIC entries\n");
 
+#ifdef CONFIG_SMP
+	if (available_cpus == 0) {
+		printk(KERN_INFO "ACPI: Found 0 CPUS; assuming 1\n");
+		printk(KERN_INFO "CPU 0 (0x%04x)", hard_smp_processor_id());
+		smp_boot_data.cpu_phys_id[available_cpus] =
+		    hard_smp_processor_id();
+		available_cpus = 1;	/* We've got at least one of these, no? */
+	}
+	smp_boot_data.cpu_count = available_cpus;
+#endif
+	/* Make boot-up look pretty */
+	printk(KERN_INFO "%d CPUs available, %d CPUs total\n", available_cpus,
+	       total_cpus);
+
 	return 0;
 }
 
-
-
 int __init acpi_boot_init(void)
 {
 
@@ -769,18 +781,8 @@ int __init acpi_boot_init(void)
 	if (acpi_table_parse(ACPI_SIG_FADT, acpi_parse_fadt))
 		printk(KERN_ERR PREFIX "Can't find FADT\n");
 
+#ifdef CONFIG_ACPI_NUMA
 #ifdef CONFIG_SMP
-	if (available_cpus == 0) {
-		printk(KERN_INFO "ACPI: Found 0 CPUS; assuming 1\n");
-		printk(KERN_INFO "CPU 0 (0x%04x)", hard_smp_processor_id());
-		smp_boot_data.cpu_phys_id[available_cpus] =
-		    hard_smp_processor_id();
-		available_cpus = 1;	/* We've got at least one of these, no? */
-	}
-	smp_boot_data.cpu_count = available_cpus;
-
-	smp_build_cpu_map();
-# ifdef CONFIG_ACPI_NUMA
 	if (srat_num_cpus == 0) {
 		int cpu, i = 1;
 		for (cpu = 0; cpu < smp_boot_data.cpu_count; cpu++)
@@ -789,14 +791,9 @@ int __init acpi_boot_init(void)
 				node_cpuid[i++].phys_id =
 				    smp_boot_data.cpu_phys_id[cpu];
 	}
-# endif
 #endif
-#ifdef CONFIG_ACPI_NUMA
 	build_cpu_to_node_map();
 #endif
-	/* Make boot-up look pretty */
-	printk(KERN_INFO "%d CPUs available, %d CPUs total\n", available_cpus,
-	       total_cpus);
 	return 0;
 }
 
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 696eff28a0c..17a9fba3893 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -1051,7 +1051,7 @@ END(ia64_delay_loop)
  * intermediate precision so that we can produce a full 64-bit result.
  */
 GLOBAL_ENTRY(ia64_native_sched_clock)
-	addl r8=THIS_CPU(cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
+	addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
 	mov.m r9=ar.itc		// fetch cycle-counter				(35 cyc)
 	;;
 	ldf8 f8=[r8]
@@ -1077,7 +1077,7 @@ sched_clock = ia64_native_sched_clock
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 GLOBAL_ENTRY(cycle_to_cputime)
 	alloc r16=ar.pfs,1,0,0,0
-	addl r8=THIS_CPU(cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
+	addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
 	;;
 	ldf8 f8=[r8]
 	;;
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index 14d39e30062..461b99902bf 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/arch/ia64/kernel/ia64_ksyms.c
@@ -30,7 +30,7 @@ EXPORT_SYMBOL(max_low_pfn);	/* defined by bootmem.c, but not exported by generic
 #endif
 
 #include <asm/processor.h>
-EXPORT_SYMBOL(per_cpu__cpu_info);
+EXPORT_SYMBOL(per_cpu__ia64_cpu_info);
 #ifdef CONFIG_SMP
 EXPORT_SYMBOL(per_cpu__local_per_cpu_offset);
 #endif
diff --git a/arch/ia64/kernel/mca_asm.S b/arch/ia64/kernel/mca_asm.S
index 7461d2573d4..d5bdf9de36b 100644
--- a/arch/ia64/kernel/mca_asm.S
+++ b/arch/ia64/kernel/mca_asm.S
@@ -59,7 +59,7 @@
 ia64_do_tlb_purge:
 #define O(member)	IA64_CPUINFO_##member##_OFFSET
 
-	GET_THIS_PADDR(r2, cpu_info)	// load phys addr of cpu_info into r2
+	GET_THIS_PADDR(r2, ia64_cpu_info) // load phys addr of cpu_info into r2
 	;;
 	addl r17=O(PTCE_STRIDE),r2
 	addl r2=O(PTCE_BASE),r2
diff --git a/arch/ia64/kernel/relocate_kernel.S b/arch/ia64/kernel/relocate_kernel.S
index 32f6fc131fb..c370e02f006 100644
--- a/arch/ia64/kernel/relocate_kernel.S
+++ b/arch/ia64/kernel/relocate_kernel.S
@@ -61,7 +61,7 @@ GLOBAL_ENTRY(relocate_new_kernel)
 
 	// purge all TC entries
 #define O(member)       IA64_CPUINFO_##member##_OFFSET
-        GET_THIS_PADDR(r2, cpu_info)    // load phys addr of cpu_info into r2
+        GET_THIS_PADDR(r2, ia64_cpu_info) // load phys addr of cpu_info into r2
         ;;
         addl r17=O(PTCE_STRIDE),r2
         addl r2=O(PTCE_BASE),r2
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 1de86c96801..a1ea8791977 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -74,7 +74,7 @@ unsigned long __per_cpu_offset[NR_CPUS];
 EXPORT_SYMBOL(__per_cpu_offset);
 #endif
 
-DEFINE_PER_CPU(struct cpuinfo_ia64, cpu_info);
+DEFINE_PER_CPU(struct cpuinfo_ia64, ia64_cpu_info);
 DEFINE_PER_CPU(unsigned long, local_per_cpu_offset);
 unsigned long ia64_cycles_per_usec;
 struct ia64_boot_param *ia64_boot_param;
@@ -566,19 +566,18 @@ setup_arch (char **cmdline_p)
 	early_acpi_boot_init();
 # ifdef CONFIG_ACPI_NUMA
 	acpi_numa_init();
-#ifdef CONFIG_ACPI_HOTPLUG_CPU
+#  ifdef CONFIG_ACPI_HOTPLUG_CPU
 	prefill_possible_map();
-#endif
+#  endif
 	per_cpu_scan_finalize((cpus_weight(early_cpu_possible_map) == 0 ?
 		32 : cpus_weight(early_cpu_possible_map)),
 		additional_cpus > 0 ? additional_cpus : 0);
 # endif
-#else
-# ifdef CONFIG_SMP
-	smp_build_cpu_map();	/* happens, e.g., with the Ski simulator */
-# endif
 #endif /* CONFIG_APCI_BOOT */
 
+#ifdef CONFIG_SMP
+	smp_build_cpu_map();
+#endif
 	find_memory();
 
 	/* process SAL system table: */
@@ -856,18 +855,6 @@ identify_cpu (struct cpuinfo_ia64 *c)
 }
 
 /*
- * In UP configuration, setup_per_cpu_areas() is defined in
- * include/linux/percpu.h
- */
-#ifdef CONFIG_SMP
-void __init
-setup_per_cpu_areas (void)
-{
-	/* start_kernel() requires this... */
-}
-#endif
-
-/*
  * Do the following calculations:
  *
  * 1. the max. cache line size.
@@ -980,7 +967,7 @@ cpu_init (void)
 	 * depends on the data returned by identify_cpu().  We break the dependency by
 	 * accessing cpu_data() through the canonical per-CPU address.
 	 */
-	cpu_info = cpu_data + ((char *) &__ia64_per_cpu_var(cpu_info) - __per_cpu_start);
+	cpu_info = cpu_data + ((char *) &__ia64_per_cpu_var(ia64_cpu_info) - __per_cpu_start);
 	identify_cpu(cpu_info);
 
 #ifdef CONFIG_MCKINLEY
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 0a0c77b2c98..1295ba327f6 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -166,6 +166,12 @@ SECTIONS
 	}
 #endif
 
+#ifdef	CONFIG_SMP
+  . = ALIGN(PERCPU_PAGE_SIZE);
+  __cpu0_per_cpu = .;
+  . = . + PERCPU_PAGE_SIZE;	/* cpu0 per-cpu space */
+#endif
+
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
 
@@ -198,11 +204,6 @@ SECTIONS
   data : { } :data
   .data : AT(ADDR(.data) - LOAD_OFFSET)
 	{
-#ifdef	CONFIG_SMP
-  . = ALIGN(PERCPU_PAGE_SIZE);
-		__cpu0_per_cpu = .;
-  . = . + PERCPU_PAGE_SIZE;	/* cpu0 per-cpu space */
-#endif
 		INIT_TASK_DATA(PAGE_SIZE)
 		CACHELINE_ALIGNED_DATA(SMP_CACHE_BYTES)
 		READ_MOSTLY_DATA(SMP_CACHE_BYTES)
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 2f724d2bf29..54bf5405981 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -154,38 +154,99 @@ static void *cpu_data;
 void * __cpuinit
 per_cpu_init (void)
 {
-	int cpu;
-	static int first_time=1;
+	static bool first_time = true;
+	void *cpu0_data = __cpu0_per_cpu;
+	unsigned int cpu;
+
+	if (!first_time)
+		goto skip;
+	first_time = false;
 
 	/*
-	 * get_free_pages() cannot be used before cpu_init() done.  BSP
-	 * allocates "NR_CPUS" pages for all CPUs to avoid that AP calls
-	 * get_zeroed_page().
+	 * get_free_pages() cannot be used before cpu_init() done.
+	 * BSP allocates PERCPU_PAGE_SIZE bytes for all possible CPUs
+	 * to avoid that AP calls get_zeroed_page().
 	 */
-	if (first_time) {
-		void *cpu0_data = __cpu0_per_cpu;
+	for_each_possible_cpu(cpu) {
+		void *src = cpu == 0 ? cpu0_data : __phys_per_cpu_start;
 
-		first_time=0;
+		memcpy(cpu_data, src, __per_cpu_end - __per_cpu_start);
+		__per_cpu_offset[cpu] = (char *)cpu_data - __per_cpu_start;
+		per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
 
-		__per_cpu_offset[0] = (char *) cpu0_data - __per_cpu_start;
-		per_cpu(local_per_cpu_offset, 0) = __per_cpu_offset[0];
+		/*
+		 * percpu area for cpu0 is moved from the __init area
+		 * which is setup by head.S and used till this point.
+		 * Update ar.k3.  This move is ensures that percpu
+		 * area for cpu0 is on the correct node and its
+		 * virtual address isn't insanely far from other
+		 * percpu areas which is important for congruent
+		 * percpu allocator.
+		 */
+		if (cpu == 0)
+			ia64_set_kr(IA64_KR_PER_CPU_DATA, __pa(cpu_data) -
+				    (unsigned long)__per_cpu_start);
 
-		for (cpu = 1; cpu < NR_CPUS; cpu++) {
-			memcpy(cpu_data, __phys_per_cpu_start, __per_cpu_end - __per_cpu_start);
-			__per_cpu_offset[cpu] = (char *) cpu_data - __per_cpu_start;
-			cpu_data += PERCPU_PAGE_SIZE;
-			per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
-		}
+		cpu_data += PERCPU_PAGE_SIZE;
 	}
+skip:
 	return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
 }
 
 static inline void
 alloc_per_cpu_data(void)
 {
-	cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS-1,
+	cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * num_possible_cpus(),
 				   PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
 }
+
+/**
+ * setup_per_cpu_areas - setup percpu areas
+ *
+ * Arch code has already allocated and initialized percpu areas.  All
+ * this function has to do is to teach the determined layout to the
+ * dynamic percpu allocator, which happens to be more complex than
+ * creating whole new ones using helpers.
+ */
+void __init
+setup_per_cpu_areas(void)
+{
+	struct pcpu_alloc_info *ai;
+	struct pcpu_group_info *gi;
+	unsigned int cpu;
+	ssize_t static_size, reserved_size, dyn_size;
+	int rc;
+
+	ai = pcpu_alloc_alloc_info(1, num_possible_cpus());
+	if (!ai)
+		panic("failed to allocate pcpu_alloc_info");
+	gi = &ai->groups[0];
+
+	/* units are assigned consecutively to possible cpus */
+	for_each_possible_cpu(cpu)
+		gi->cpu_map[gi->nr_units++] = cpu;
+
+	/* set parameters */
+	static_size = __per_cpu_end - __per_cpu_start;
+	reserved_size = PERCPU_MODULE_RESERVE;
+	dyn_size = PERCPU_PAGE_SIZE - static_size - reserved_size;
+	if (dyn_size < 0)
+		panic("percpu area overflow static=%zd reserved=%zd\n",
+		      static_size, reserved_size);
+
+	ai->static_size		= static_size;
+	ai->reserved_size	= reserved_size;
+	ai->dyn_size		= dyn_size;
+	ai->unit_size		= PERCPU_PAGE_SIZE;
+	ai->atom_size		= PAGE_SIZE;
+	ai->alloc_size		= PERCPU_PAGE_SIZE;
+
+	rc = pcpu_setup_first_chunk(ai, __per_cpu_start + __per_cpu_offset[0]);
+	if (rc)
+		panic("failed to setup percpu area (err=%d)", rc);
+
+	pcpu_free_alloc_info(ai);
+}
 #else
 #define alloc_per_cpu_data() do { } while (0)
 #endif /* CONFIG_SMP */
@@ -270,8 +331,8 @@ paging_init (void)
 
 		map_size = PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
 			sizeof(struct page));
-		vmalloc_end -= map_size;
-		vmem_map = (struct page *) vmalloc_end;
+		VMALLOC_END -= map_size;
+		vmem_map = (struct page *) VMALLOC_END;
 		efi_memmap_walk(create_mem_map_page_table, NULL);
 
 		/*
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index d85ba98d900..19c4b2195dc 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -143,22 +143,120 @@ static void *per_cpu_node_setup(void *cpu_data, int node)
 	int cpu;
 
 	for_each_possible_early_cpu(cpu) {
-		if (cpu == 0) {
-			void *cpu0_data = __cpu0_per_cpu;
-			__per_cpu_offset[cpu] = (char*)cpu0_data -
-				__per_cpu_start;
-		} else if (node == node_cpuid[cpu].nid) {
-			memcpy(__va(cpu_data), __phys_per_cpu_start,
-			       __per_cpu_end - __per_cpu_start);
-			__per_cpu_offset[cpu] = (char*)__va(cpu_data) -
-				__per_cpu_start;
-			cpu_data += PERCPU_PAGE_SIZE;
-		}
+		void *src = cpu == 0 ? __cpu0_per_cpu : __phys_per_cpu_start;
+
+		if (node != node_cpuid[cpu].nid)
+			continue;
+
+		memcpy(__va(cpu_data), src, __per_cpu_end - __per_cpu_start);
+		__per_cpu_offset[cpu] = (char *)__va(cpu_data) -
+			__per_cpu_start;
+
+		/*
+		 * percpu area for cpu0 is moved from the __init area
+		 * which is setup by head.S and used till this point.
+		 * Update ar.k3.  This move is ensures that percpu
+		 * area for cpu0 is on the correct node and its
+		 * virtual address isn't insanely far from other
+		 * percpu areas which is important for congruent
+		 * percpu allocator.
+		 */
+		if (cpu == 0)
+			ia64_set_kr(IA64_KR_PER_CPU_DATA,
+				    (unsigned long)cpu_data -
+				    (unsigned long)__per_cpu_start);
+
+		cpu_data += PERCPU_PAGE_SIZE;
 	}
 #endif
 	return cpu_data;
 }
 
+#ifdef CONFIG_SMP
+/**
+ * setup_per_cpu_areas - setup percpu areas
+ *
+ * Arch code has already allocated and initialized percpu areas.  All
+ * this function has to do is to teach the determined layout to the
+ * dynamic percpu allocator, which happens to be more complex than
+ * creating whole new ones using helpers.
+ */
+void __init setup_per_cpu_areas(void)
+{
+	struct pcpu_alloc_info *ai;
+	struct pcpu_group_info *uninitialized_var(gi);
+	unsigned int *cpu_map;
+	void *base;
+	unsigned long base_offset;
+	unsigned int cpu;
+	ssize_t static_size, reserved_size, dyn_size;
+	int node, prev_node, unit, nr_units, rc;
+
+	ai = pcpu_alloc_alloc_info(MAX_NUMNODES, nr_cpu_ids);
+	if (!ai)
+		panic("failed to allocate pcpu_alloc_info");
+	cpu_map = ai->groups[0].cpu_map;
+
+	/* determine base */
+	base = (void *)ULONG_MAX;
+	for_each_possible_cpu(cpu)
+		base = min(base,
+			   (void *)(__per_cpu_offset[cpu] + __per_cpu_start));
+	base_offset = (void *)__per_cpu_start - base;
+
+	/* build cpu_map, units are grouped by node */
+	unit = 0;
+	for_each_node(node)
+		for_each_possible_cpu(cpu)
+			if (node == node_cpuid[cpu].nid)
+				cpu_map[unit++] = cpu;
+	nr_units = unit;
+
+	/* set basic parameters */
+	static_size = __per_cpu_end - __per_cpu_start;
+	reserved_size = PERCPU_MODULE_RESERVE;
+	dyn_size = PERCPU_PAGE_SIZE - static_size - reserved_size;
+	if (dyn_size < 0)
+		panic("percpu area overflow static=%zd reserved=%zd\n",
+		      static_size, reserved_size);
+
+	ai->static_size		= static_size;
+	ai->reserved_size	= reserved_size;
+	ai->dyn_size		= dyn_size;
+	ai->unit_size		= PERCPU_PAGE_SIZE;
+	ai->atom_size		= PAGE_SIZE;
+	ai->alloc_size		= PERCPU_PAGE_SIZE;
+
+	/*
+	 * CPUs are put into groups according to node.  Walk cpu_map
+	 * and create new groups at node boundaries.
+	 */
+	prev_node = -1;
+	ai->nr_groups = 0;
+	for (unit = 0; unit < nr_units; unit++) {
+		cpu = cpu_map[unit];
+		node = node_cpuid[cpu].nid;
+
+		if (node == prev_node) {
+			gi->nr_units++;
+			continue;
+		}
+		prev_node = node;
+
+		gi = &ai->groups[ai->nr_groups++];
+		gi->nr_units		= 1;
+		gi->base_offset		= __per_cpu_offset[cpu] + base_offset;
+		gi->cpu_map		= &cpu_map[unit];
+	}
+
+	rc = pcpu_setup_first_chunk(ai, base);
+	if (rc)
+		panic("failed to setup percpu area (err=%d)", rc);
+
+	pcpu_free_alloc_info(ai);
+}
+#endif
+
 /**
  * fill_pernode - initialize pernode data.
  * @node: the node id.
@@ -352,7 +450,8 @@ static void __init initialize_pernode_data(void)
 	/* Set the node_data pointer for each per-cpu struct */
 	for_each_possible_early_cpu(cpu) {
 		node = node_cpuid[cpu].nid;
-		per_cpu(cpu_info, cpu).node_data = mem_data[node].node_data;
+		per_cpu(ia64_cpu_info, cpu).node_data =
+			mem_data[node].node_data;
 	}
 #else
 	{
@@ -360,7 +459,7 @@ static void __init initialize_pernode_data(void)
 		cpu = 0;
 		node = node_cpuid[cpu].nid;
 		cpu0_cpu_info = (struct cpuinfo_ia64 *)(__phys_per_cpu_start +
-			((char *)&per_cpu__cpu_info - __per_cpu_start));
+			((char *)&per_cpu__ia64_cpu_info - __per_cpu_start));
 		cpu0_cpu_info->node_data = mem_data[node].node_data;
 	}
 #endif /* CONFIG_SMP */
@@ -666,9 +765,9 @@ void __init paging_init(void)
 	sparse_init();
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-	vmalloc_end -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
+	VMALLOC_END -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
 		sizeof(struct page));
-	vmem_map = (struct page *) vmalloc_end;
+	vmem_map = (struct page *) VMALLOC_END;
 	efi_memmap_walk(create_mem_map_page_table, NULL);
 	printk("Virtual mem_map starts at 0x%p\n", vmem_map);
 #endif
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 1857766a63c..b9609c69343 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -44,8 +44,8 @@ extern void ia64_tlb_init (void);
 unsigned long MAX_DMA_ADDRESS = PAGE_OFFSET + 0x100000000UL;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-unsigned long vmalloc_end = VMALLOC_END_INIT;
-EXPORT_SYMBOL(vmalloc_end);
+unsigned long VMALLOC_END = VMALLOC_END_INIT;
+EXPORT_SYMBOL(VMALLOC_END);
 struct page *vmem_map;
 EXPORT_SYMBOL(vmem_map);
 #endif
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index 1176506b2ba..e884ba4e031 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -496,13 +496,13 @@ static int sn2_ptc_seq_show(struct seq_file *file, void *data)
 		seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", cpu, stat->ptc_l,
 				stat->change_rid, stat->shub_ptc_flushes, stat->nodes_flushed,
 				stat->deadlocks,
-				1000 * stat->lock_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec,
-				1000 * stat->shub_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec,
-				1000 * stat->shub_itc_clocks_max / per_cpu(cpu_info, cpu).cyc_per_usec,
+				1000 * stat->lock_itc_clocks / per_cpu(ia64_cpu_info, cpu).cyc_per_usec,
+				1000 * stat->shub_itc_clocks / per_cpu(ia64_cpu_info, cpu).cyc_per_usec,
+				1000 * stat->shub_itc_clocks_max / per_cpu(ia64_cpu_info, cpu).cyc_per_usec,
 				stat->shub_ptc_flushes_not_my_mm,
 				stat->deadlocks2,
 				stat->shub_ipi_flushes,
-				1000 * stat->shub_ipi_flushes_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec);
+				1000 * stat->shub_ipi_flushes_itc_clocks / per_cpu(ia64_cpu_info, cpu).cyc_per_usec);
 	}
 	return 0;
 }
diff --git a/arch/ia64/xen/irq_xen.c b/arch/ia64/xen/irq_xen.c
index f042e192d2f..a3fb7cf9ae1 100644
--- a/arch/ia64/xen/irq_xen.c
+++ b/arch/ia64/xen/irq_xen.c
@@ -63,19 +63,19 @@ xen_free_irq_vector(int vector)
 }
 
 
-static DEFINE_PER_CPU(int, timer_irq) = -1;
-static DEFINE_PER_CPU(int, ipi_irq) = -1;
-static DEFINE_PER_CPU(int, resched_irq) = -1;
-static DEFINE_PER_CPU(int, cmc_irq) = -1;
-static DEFINE_PER_CPU(int, cmcp_irq) = -1;
-static DEFINE_PER_CPU(int, cpep_irq) = -1;
+static DEFINE_PER_CPU(int, xen_timer_irq) = -1;
+static DEFINE_PER_CPU(int, xen_ipi_irq) = -1;
+static DEFINE_PER_CPU(int, xen_resched_irq) = -1;
+static DEFINE_PER_CPU(int, xen_cmc_irq) = -1;
+static DEFINE_PER_CPU(int, xen_cmcp_irq) = -1;
+static DEFINE_PER_CPU(int, xen_cpep_irq) = -1;
 #define NAME_SIZE	15
-static DEFINE_PER_CPU(char[NAME_SIZE], timer_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], ipi_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], resched_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], cmc_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], cmcp_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], cpep_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_timer_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_ipi_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_resched_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_cmc_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_cmcp_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_cpep_name);
 #undef NAME_SIZE
 
 struct saved_irq {
@@ -144,64 +144,64 @@ __xen_register_percpu_irq(unsigned int cpu, unsigned int vec,
 	if (xen_slab_ready) {
 		switch (vec) {
 		case IA64_TIMER_VECTOR:
-			snprintf(per_cpu(timer_name, cpu),
-				 sizeof(per_cpu(timer_name, cpu)),
+			snprintf(per_cpu(xen_timer_name, cpu),
+				 sizeof(per_cpu(xen_timer_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_virq_to_irqhandler(VIRQ_ITC, cpu,
 				action->handler, action->flags,
-				per_cpu(timer_name, cpu), action->dev_id);
-			per_cpu(timer_irq, cpu) = irq;
+				per_cpu(xen_timer_name, cpu), action->dev_id);
+			per_cpu(xen_timer_irq, cpu) = irq;
 			break;
 		case IA64_IPI_RESCHEDULE:
-			snprintf(per_cpu(resched_name, cpu),
-				 sizeof(per_cpu(resched_name, cpu)),
+			snprintf(per_cpu(xen_resched_name, cpu),
+				 sizeof(per_cpu(xen_resched_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu,
 				action->handler, action->flags,
-				per_cpu(resched_name, cpu), action->dev_id);
-			per_cpu(resched_irq, cpu) = irq;
+				per_cpu(xen_resched_name, cpu), action->dev_id);
+			per_cpu(xen_resched_irq, cpu) = irq;
 			break;
 		case IA64_IPI_VECTOR:
-			snprintf(per_cpu(ipi_name, cpu),
-				 sizeof(per_cpu(ipi_name, cpu)),
+			snprintf(per_cpu(xen_ipi_name, cpu),
+				 sizeof(per_cpu(xen_ipi_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_ipi_to_irqhandler(XEN_IPI_VECTOR, cpu,
 				action->handler, action->flags,
-				per_cpu(ipi_name, cpu), action->dev_id);
-			per_cpu(ipi_irq, cpu) = irq;
+				per_cpu(xen_ipi_name, cpu), action->dev_id);
+			per_cpu(xen_ipi_irq, cpu) = irq;
 			break;
 		case IA64_CMC_VECTOR:
-			snprintf(per_cpu(cmc_name, cpu),
-				 sizeof(per_cpu(cmc_name, cpu)),
+			snprintf(per_cpu(xen_cmc_name, cpu),
+				 sizeof(per_cpu(xen_cmc_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_virq_to_irqhandler(VIRQ_MCA_CMC, cpu,
-						      action->handler,
-						      action->flags,
-						      per_cpu(cmc_name, cpu),
-						      action->dev_id);
-			per_cpu(cmc_irq, cpu) = irq;
+						action->handler,
+						action->flags,
+						per_cpu(xen_cmc_name, cpu),
+						action->dev_id);
+			per_cpu(xen_cmc_irq, cpu) = irq;
 			break;
 		case IA64_CMCP_VECTOR:
-			snprintf(per_cpu(cmcp_name, cpu),
-				 sizeof(per_cpu(cmcp_name, cpu)),
+			snprintf(per_cpu(xen_cmcp_name, cpu),
+				 sizeof(per_cpu(xen_cmcp_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_ipi_to_irqhandler(XEN_CMCP_VECTOR, cpu,
-						     action->handler,
-						     action->flags,
-						     per_cpu(cmcp_name, cpu),
-						     action->dev_id);
-			per_cpu(cmcp_irq, cpu) = irq;
+						action->handler,
+						action->flags,
+						per_cpu(xen_cmcp_name, cpu),
+						action->dev_id);
+			per_cpu(xen_cmcp_irq, cpu) = irq;
 			break;
 		case IA64_CPEP_VECTOR:
-			snprintf(per_cpu(cpep_name, cpu),
-				 sizeof(per_cpu(cpep_name, cpu)),
+			snprintf(per_cpu(xen_cpep_name, cpu),
+				 sizeof(per_cpu(xen_cpep_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_ipi_to_irqhandler(XEN_CPEP_VECTOR, cpu,
-						     action->handler,
-						     action->flags,
-						     per_cpu(cpep_name, cpu),
-						     action->dev_id);
-			per_cpu(cpep_irq, cpu) = irq;
+						action->handler,
+						action->flags,
+						per_cpu(xen_cpep_name, cpu),
+						action->dev_id);
+			per_cpu(xen_cpep_irq, cpu) = irq;
 			break;
 		case IA64_CPE_VECTOR:
 		case IA64_MCA_RENDEZ_VECTOR:
@@ -275,30 +275,33 @@ unbind_evtchn_callback(struct notifier_block *nfb,
 
 	if (action == CPU_DEAD) {
 		/* Unregister evtchn.  */
-		if (per_cpu(cpep_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(cpep_irq, cpu), NULL);
-			per_cpu(cpep_irq, cpu) = -1;
+		if (per_cpu(xen_cpep_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_cpep_irq, cpu),
+					       NULL);
+			per_cpu(xen_cpep_irq, cpu) = -1;
 		}
-		if (per_cpu(cmcp_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(cmcp_irq, cpu), NULL);
-			per_cpu(cmcp_irq, cpu) = -1;
+		if (per_cpu(xen_cmcp_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_cmcp_irq, cpu),
+					       NULL);
+			per_cpu(xen_cmcp_irq, cpu) = -1;
 		}
-		if (per_cpu(cmc_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(cmc_irq, cpu), NULL);
-			per_cpu(cmc_irq, cpu) = -1;
+		if (per_cpu(xen_cmc_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_cmc_irq, cpu), NULL);
+			per_cpu(xen_cmc_irq, cpu) = -1;
 		}
-		if (per_cpu(ipi_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(ipi_irq, cpu), NULL);
-			per_cpu(ipi_irq, cpu) = -1;
+		if (per_cpu(xen_ipi_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_ipi_irq, cpu), NULL);
+			per_cpu(xen_ipi_irq, cpu) = -1;
 		}
-		if (per_cpu(resched_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(resched_irq, cpu),
-						NULL);
-			per_cpu(resched_irq, cpu) = -1;
+		if (per_cpu(xen_resched_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu),
+					       NULL);
+			per_cpu(xen_resched_irq, cpu) = -1;
 		}
-		if (per_cpu(timer_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(timer_irq, cpu), NULL);
-			per_cpu(timer_irq, cpu) = -1;
+		if (per_cpu(xen_timer_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_timer_irq, cpu),
+					       NULL);
+			per_cpu(xen_timer_irq, cpu) = -1;
 		}
 	}
 	return NOTIFY_OK;
diff --git a/arch/ia64/xen/time.c b/arch/ia64/xen/time.c
index dbeadb9c8e2..c1c544513e8 100644
--- a/arch/ia64/xen/time.c
+++ b/arch/ia64/xen/time.c
@@ -34,15 +34,15 @@
 
 #include "../kernel/fsyscall_gtod_data.h"
 
-DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
-DEFINE_PER_CPU(unsigned long, processed_stolen_time);
-DEFINE_PER_CPU(unsigned long, processed_blocked_time);
+static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
+static DEFINE_PER_CPU(unsigned long, xen_stolen_time);
+static DEFINE_PER_CPU(unsigned long, xen_blocked_time);
 
 /* taken from i386/kernel/time-xen.c */
 static void xen_init_missing_ticks_accounting(int cpu)
 {
 	struct vcpu_register_runstate_memory_area area;
-	struct vcpu_runstate_info *runstate = &per_cpu(runstate, cpu);
+	struct vcpu_runstate_info *runstate = &per_cpu(xen_runstate, cpu);
 	int rc;
 
 	memset(runstate, 0, sizeof(*runstate));
@@ -52,8 +52,8 @@ static void xen_init_missing_ticks_accounting(int cpu)
 				&area);
 	WARN_ON(rc && rc != -ENOSYS);
 
-	per_cpu(processed_blocked_time, cpu) = runstate->time[RUNSTATE_blocked];
-	per_cpu(processed_stolen_time, cpu) = runstate->time[RUNSTATE_runnable]
+	per_cpu(xen_blocked_time, cpu) = runstate->time[RUNSTATE_blocked];
+	per_cpu(xen_stolen_time, cpu) = runstate->time[RUNSTATE_runnable]
 					    + runstate->time[RUNSTATE_offline];
 }
 
@@ -68,7 +68,7 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
 
 	BUG_ON(preemptible());
 
-	state = &__get_cpu_var(runstate);
+	state = &__get_cpu_var(xen_runstate);
 
 	/*
 	 * The runstate info is always updated by the hypervisor on
@@ -103,12 +103,12 @@ consider_steal_time(unsigned long new_itm)
 	 * This function just checks and reject this effect.
 	 */
 	if (!time_after_eq(runstate.time[RUNSTATE_blocked],
-			   per_cpu(processed_blocked_time, cpu)))
+			   per_cpu(xen_blocked_time, cpu)))
 		blocked = 0;
 
 	if (!time_after_eq(runstate.time[RUNSTATE_runnable] +
 			   runstate.time[RUNSTATE_offline],
-			   per_cpu(processed_stolen_time, cpu)))
+			   per_cpu(xen_stolen_time, cpu)))
 		stolen = 0;
 
 	if (!time_after(delta_itm + new_itm, ia64_get_itc()))
@@ -147,8 +147,8 @@ consider_steal_time(unsigned long new_itm)
 		} else {
 			local_cpu_data->itm_next = delta_itm + new_itm;
 		}
-		per_cpu(processed_stolen_time, cpu) += NS_PER_TICK * stolen;
-		per_cpu(processed_blocked_time, cpu) += NS_PER_TICK * blocked;
+		per_cpu(xen_stolen_time, cpu) += NS_PER_TICK * stolen;
+		per_cpu(xen_blocked_time, cpu) += NS_PER_TICK * blocked;
 	}
 	return delta_itm;
 }
diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h
index fe60e1abaee..aca0e28581c 100644
--- a/arch/m68k/include/asm/pgtable_mm.h
+++ b/arch/m68k/include/asm/pgtable_mm.h
@@ -83,9 +83,9 @@
 #define VMALLOC_START (((unsigned long) high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
 #define VMALLOC_END KMAP_START
 #else
-extern unsigned long vmalloc_end;
+extern unsigned long m68k_vmalloc_end;
 #define VMALLOC_START 0x0f800000
-#define VMALLOC_END vmalloc_end
+#define VMALLOC_END m68k_vmalloc_end
 #endif /* CONFIG_SUN3 */
 
 /* zero page used for uninitialized stuff */
diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c
index 3cd19390aae..94f81ecfe3f 100644
--- a/arch/m68k/sun3/mmu_emu.c
+++ b/arch/m68k/sun3/mmu_emu.c
@@ -45,8 +45,8 @@
 ** Globals
 */
 
-unsigned long vmalloc_end;
-EXPORT_SYMBOL(vmalloc_end);
+unsigned long m68k_vmalloc_end;
+EXPORT_SYMBOL(m68k_vmalloc_end);
 
 unsigned long pmeg_vaddr[PMEGS_NUM];
 unsigned char pmeg_alloc[PMEGS_NUM];
@@ -172,8 +172,8 @@ void mmu_emu_init(unsigned long bootmem_end)
 #endif
 			// the lowest mapping here is the end of our
 			// vmalloc region
-			if(!vmalloc_end)
-				vmalloc_end = seg;
+			if (!m68k_vmalloc_end)
+				m68k_vmalloc_end = seg;
 
 			// mark the segmap alloc'd, and reserve any
 			// of the first 0xbff pages the hardware is
diff --git a/arch/mn10300/kernel/kprobes.c b/arch/mn10300/kernel/kprobes.c
index dacafab00eb..67e6389d625 100644
--- a/arch/mn10300/kernel/kprobes.c
+++ b/arch/mn10300/kernel/kprobes.c
@@ -31,13 +31,13 @@ const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
 #define KPROBE_HIT_ACTIVE	0x00000001
 #define KPROBE_HIT_SS		0x00000002
 
-static struct kprobe *current_kprobe;
-static unsigned long current_kprobe_orig_pc;
-static unsigned long current_kprobe_next_pc;
-static int current_kprobe_ss_flags;
+static struct kprobe *cur_kprobe;
+static unsigned long cur_kprobe_orig_pc;
+static unsigned long cur_kprobe_next_pc;
+static int cur_kprobe_ss_flags;
 static unsigned long kprobe_status;
-static kprobe_opcode_t current_kprobe_ss_buf[MAX_INSN_SIZE + 2];
-static unsigned long current_kprobe_bp_addr;
+static kprobe_opcode_t cur_kprobe_ss_buf[MAX_INSN_SIZE + 2];
+static unsigned long cur_kprobe_bp_addr;
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 
@@ -399,26 +399,25 @@ void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 {
 	unsigned long nextpc;
 
-	current_kprobe_orig_pc = regs->pc;
-	memcpy(current_kprobe_ss_buf, &p->ainsn.insn[0], MAX_INSN_SIZE);
-	regs->pc = (unsigned long) current_kprobe_ss_buf;
+	cur_kprobe_orig_pc = regs->pc;
+	memcpy(cur_kprobe_ss_buf, &p->ainsn.insn[0], MAX_INSN_SIZE);
+	regs->pc = (unsigned long) cur_kprobe_ss_buf;
 
-	nextpc = find_nextpc(regs, &current_kprobe_ss_flags);
-	if (current_kprobe_ss_flags & SINGLESTEP_PCREL)
-		current_kprobe_next_pc =
-			current_kprobe_orig_pc + (nextpc - regs->pc);
+	nextpc = find_nextpc(regs, &cur_kprobe_ss_flags);
+	if (cur_kprobe_ss_flags & SINGLESTEP_PCREL)
+		cur_kprobe_next_pc = cur_kprobe_orig_pc + (nextpc - regs->pc);
 	else
-		current_kprobe_next_pc = nextpc;
+		cur_kprobe_next_pc = nextpc;
 
 	/* branching instructions need special handling */
-	if (current_kprobe_ss_flags & SINGLESTEP_BRANCH)
+	if (cur_kprobe_ss_flags & SINGLESTEP_BRANCH)
 		nextpc = singlestep_branch_setup(regs);
 
-	current_kprobe_bp_addr = nextpc;
+	cur_kprobe_bp_addr = nextpc;
 
 	*(u8 *) nextpc = BREAKPOINT_INSTRUCTION;
-	mn10300_dcache_flush_range2((unsigned) current_kprobe_ss_buf,
-				    sizeof(current_kprobe_ss_buf));
+	mn10300_dcache_flush_range2((unsigned) cur_kprobe_ss_buf,
+				    sizeof(cur_kprobe_ss_buf));
 	mn10300_icache_inv();
 }
 
@@ -440,7 +439,7 @@ static inline int __kprobes kprobe_handler(struct pt_regs *regs)
 			disarm_kprobe(p, regs);
 			ret = 1;
 		} else {
-			p = current_kprobe;
+			p = cur_kprobe;
 			if (p->break_handler && p->break_handler(p, regs))
 				goto ss_probe;
 		}
@@ -464,7 +463,7 @@ static inline int __kprobes kprobe_handler(struct pt_regs *regs)
 	}
 
 	kprobe_status = KPROBE_HIT_ACTIVE;
-	current_kprobe = p;
+	cur_kprobe = p;
 	if (p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
 		return 1;
@@ -491,8 +490,8 @@ no_kprobe:
 static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 {
 	/* we may need to fixup regs/stack after singlestepping a call insn */
-	if (current_kprobe_ss_flags & SINGLESTEP_BRANCH) {
-		regs->pc = current_kprobe_orig_pc;
+	if (cur_kprobe_ss_flags & SINGLESTEP_BRANCH) {
+		regs->pc = cur_kprobe_orig_pc;
 		switch (p->ainsn.insn[0]) {
 		case 0xcd:	/* CALL (d16,PC) */
 			*(unsigned *) regs->sp = regs->mdr = regs->pc + 5;
@@ -523,8 +522,8 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 		}
 	}
 
-	regs->pc = current_kprobe_next_pc;
-	current_kprobe_bp_addr = 0;
+	regs->pc = cur_kprobe_next_pc;
+	cur_kprobe_bp_addr = 0;
 }
 
 static inline int __kprobes post_kprobe_handler(struct pt_regs *regs)
@@ -532,10 +531,10 @@ static inline int __kprobes post_kprobe_handler(struct pt_regs *regs)
 	if (!kprobe_running())
 		return 0;
 
-	if (current_kprobe->post_handler)
-		current_kprobe->post_handler(current_kprobe, regs, 0);
+	if (cur_kprobe->post_handler)
+		cur_kprobe->post_handler(cur_kprobe, regs, 0);
 
-	resume_execution(current_kprobe, regs);
+	resume_execution(cur_kprobe, regs);
 	reset_current_kprobe();
 	preempt_enable_no_resched();
 	return 1;
@@ -545,12 +544,12 @@ static inline int __kprobes post_kprobe_handler(struct pt_regs *regs)
 static inline
 int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
-	if (current_kprobe->fault_handler &&
-	    current_kprobe->fault_handler(current_kprobe, regs, trapnr))
+	if (cur_kprobe->fault_handler &&
+	    cur_kprobe->fault_handler(cur_kprobe, regs, trapnr))
 		return 1;
 
 	if (kprobe_status & KPROBE_HIT_SS) {
-		resume_execution(current_kprobe, regs);
+		resume_execution(cur_kprobe, regs);
 		reset_current_kprobe();
 		preempt_enable_no_resched();
 	}
@@ -567,7 +566,7 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 
 	switch (val) {
 	case DIE_BREAKPOINT:
-		if (current_kprobe_bp_addr != args->regs->pc) {
+		if (cur_kprobe_bp_addr != args->regs->pc) {
 			if (kprobe_handler(args->regs))
 				return NOTIFY_STOP;
 		} else {
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index d9ea8d39c34..1d3b270d308 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -37,7 +37,7 @@ extern void cpu_die(void);
 extern void smp_send_debugger_break(int cpu);
 extern void smp_message_recv(int);
 
-DECLARE_PER_CPU(unsigned int, pvr);
+DECLARE_PER_CPU(unsigned int, cpu_pvr);
 
 #ifdef CONFIG_HOTPLUG_CPU
 extern void fixup_irqs(cpumask_t map);
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index 936f04dbfc6..a3c11cac3d7 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -487,11 +487,11 @@ static void perf_callchain_user_32(struct pt_regs *regs,
  * Since we can't get PMU interrupts inside a PMU interrupt handler,
  * we don't need separate irq and nmi entries here.
  */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
+static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain);
 
 struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
+	struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain);
 
 	entry->nr = 0;
 
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 845c72ab735..03dd6a24819 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -157,7 +157,7 @@ extern u32 cpu_temp_both(unsigned long cpu);
 #endif /* CONFIG_TAU */
 
 #ifdef CONFIG_SMP
-DEFINE_PER_CPU(unsigned int, pvr);
+DEFINE_PER_CPU(unsigned int, cpu_pvr);
 #endif
 
 static int show_cpuinfo(struct seq_file *m, void *v)
@@ -209,7 +209,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	}
 
 #ifdef CONFIG_SMP
-	pvr = per_cpu(pvr, cpu_id);
+	pvr = per_cpu(cpu_pvr, cpu_id);
 #else
 	pvr = mfspr(SPRN_PVR);
 #endif
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 97196eefef3..a521fb8a40e 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -235,7 +235,7 @@ struct thread_info *current_set[NR_CPUS];
 
 static void __devinit smp_store_cpu_info(int id)
 {
-	per_cpu(pvr, id) = mfspr(SPRN_PVR);
+	per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR);
 }
 
 static void __init smp_create_idle(unsigned int cpu)
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index f9dbf76a763..7267effc807 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -54,7 +54,7 @@ struct iic {
 	struct device_node *node;
 };
 
-static DEFINE_PER_CPU(struct iic, iic);
+static DEFINE_PER_CPU(struct iic, cpu_iic);
 #define IIC_NODE_COUNT	2
 static struct irq_host *iic_host;
 
@@ -82,7 +82,7 @@ static void iic_unmask(unsigned int irq)
 
 static void iic_eoi(unsigned int irq)
 {
-	struct iic *iic = &__get_cpu_var(iic);
+	struct iic *iic = &__get_cpu_var(cpu_iic);
 	out_be64(&iic->regs->prio, iic->eoi_stack[--iic->eoi_ptr]);
 	BUG_ON(iic->eoi_ptr < 0);
 }
@@ -146,7 +146,7 @@ static unsigned int iic_get_irq(void)
 	struct iic *iic;
 	unsigned int virq;
 
-	iic = &__get_cpu_var(iic);
+	iic = &__get_cpu_var(cpu_iic);
 	*(unsigned long *) &pending =
 		in_be64((u64 __iomem *) &iic->regs->pending_destr);
 	if (!(pending.flags & CBE_IIC_IRQ_VALID))
@@ -161,12 +161,12 @@ static unsigned int iic_get_irq(void)
 
 void iic_setup_cpu(void)
 {
-	out_be64(&__get_cpu_var(iic).regs->prio, 0xff);
+	out_be64(&__get_cpu_var(cpu_iic).regs->prio, 0xff);
 }
 
 u8 iic_get_target_id(int cpu)
 {
-	return per_cpu(iic, cpu).target_id;
+	return per_cpu(cpu_iic, cpu).target_id;
 }
 
 EXPORT_SYMBOL_GPL(iic_get_target_id);
@@ -181,7 +181,7 @@ static inline int iic_ipi_to_irq(int ipi)
 
 void iic_cause_IPI(int cpu, int mesg)
 {
-	out_be64(&per_cpu(iic, cpu).regs->generate, (0xf - mesg) << 4);
+	out_be64(&per_cpu(cpu_iic, cpu).regs->generate, (0xf - mesg) << 4);
 }
 
 struct irq_host *iic_get_irq_host(int node)
@@ -348,7 +348,7 @@ static void __init init_one_iic(unsigned int hw_cpu, unsigned long addr,
 	/* XXX FIXME: should locate the linux CPU number from the HW cpu
 	 * number properly. We are lucky for now
 	 */
-	struct iic *iic = &per_cpu(iic, hw_cpu);
+	struct iic *iic = &per_cpu(cpu_iic, hw_cpu);
 
 	iic->regs = ioremap(addr, sizeof(struct cbe_iic_thread_regs));
 	BUG_ON(iic->regs == NULL);
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 937a544a236..c5f3116b6ca 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -54,7 +54,7 @@ struct dtl {
 	int			buf_entries;
 	u64			last_idx;
 };
-static DEFINE_PER_CPU(struct dtl, dtl);
+static DEFINE_PER_CPU(struct dtl, cpu_dtl);
 
 /*
  * Dispatch trace log event mask:
@@ -261,7 +261,7 @@ static int dtl_init(void)
 
 	/* set up the per-cpu log structures */
 	for_each_possible_cpu(i) {
-		struct dtl *dtl = &per_cpu(dtl, i);
+		struct dtl *dtl = &per_cpu(cpu_dtl, i);
 		dtl->cpu = i;
 
 		rc = dtl_setup_file(dtl);
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index b129611590a..f30f4a1ead2 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -47,7 +47,7 @@ static DEFINE_PER_CPU(short, wd_enabled);
 static int endflag __initdata;
 
 static DEFINE_PER_CPU(unsigned int, last_irq_sum);
-static DEFINE_PER_CPU(local_t, alert_counter);
+static DEFINE_PER_CPU(long, alert_counter);
 static DEFINE_PER_CPU(int, nmi_touch);
 
 void touch_nmi_watchdog(void)
@@ -112,13 +112,13 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 		touched = 1;
 	}
 	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
-		local_inc(&__get_cpu_var(alert_counter));
-		if (local_read(&__get_cpu_var(alert_counter)) == 30 * nmi_hz)
+		__this_cpu_inc(per_cpu_var(alert_counter));
+		if (__this_cpu_read(per_cpu_var(alert_counter)) == 30 * nmi_hz)
 			die_nmi("BUG: NMI Watchdog detected LOCKUP",
 				regs, panic_on_timeout);
 	} else {
 		__get_cpu_var(last_irq_sum) = sum;
-		local_set(&__get_cpu_var(alert_counter), 0);
+		__this_cpu_write(per_cpu_var(alert_counter), 0);
 	}
 	if (__get_cpu_var(wd_enabled)) {
 		write_pic(picl_value(nmi_hz));
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index b65a36defeb..0c44196b78a 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -74,31 +74,31 @@ extern void __bad_percpu_size(void);
 
 #define percpu_to_op(op, var, val)			\
 do {							\
-	typedef typeof(var) T__;			\
+	typedef typeof(var) pto_T__;			\
 	if (0) {					\
-		T__ tmp__;				\
-		tmp__ = (val);				\
+		pto_T__ pto_tmp__;			\
+		pto_tmp__ = (val);			\
 	}						\
 	switch (sizeof(var)) {				\
 	case 1:						\
 		asm(op "b %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "qi" ((T__)(val)));		\
+		    : "qi" ((pto_T__)(val)));		\
 		break;					\
 	case 2:						\
 		asm(op "w %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "ri" ((T__)(val)));		\
+		    : "ri" ((pto_T__)(val)));		\
 		break;					\
 	case 4:						\
 		asm(op "l %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "ri" ((T__)(val)));		\
+		    : "ri" ((pto_T__)(val)));		\
 		break;					\
 	case 8:						\
 		asm(op "q %1,"__percpu_arg(0)		\
 		    : "+m" (var)			\
-		    : "re" ((T__)(val)));		\
+		    : "re" ((pto_T__)(val)));		\
 		break;					\
 	default: __bad_percpu_size();			\
 	}						\
@@ -106,31 +106,31 @@ do {							\
 
 #define percpu_from_op(op, var, constraint)		\
 ({							\
-	typeof(var) ret__;				\
+	typeof(var) pfo_ret__;				\
 	switch (sizeof(var)) {				\
 	case 1:						\
 		asm(op "b "__percpu_arg(1)",%0"		\
-		    : "=q" (ret__)			\
+		    : "=q" (pfo_ret__)			\
 		    : constraint);			\
 		break;					\
 	case 2:						\
 		asm(op "w "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
+		    : "=r" (pfo_ret__)			\
 		    : constraint);			\
 		break;					\
 	case 4:						\
 		asm(op "l "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
+		    : "=r" (pfo_ret__)			\
 		    : constraint);			\
 		break;					\
 	case 8:						\
 		asm(op "q "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
+		    : "=r" (pfo_ret__)			\
 		    : constraint);			\
 		break;					\
 	default: __bad_percpu_size();			\
 	}						\
-	ret__;						\
+	pfo_ret__;					\
 })
 
 /*
@@ -153,6 +153,84 @@ do {							\
 #define percpu_or(var, val)	percpu_to_op("or", per_cpu__##var, val)
 #define percpu_xor(var, val)	percpu_to_op("xor", per_cpu__##var, val)
 
+#define __this_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_read_4(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+
+#define __this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define __this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define __this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define __this_cpu_add_1(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_2(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_4(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
+#define __this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
+#define __this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
+#define __this_cpu_or_1(pcp, val)	percpu_to_op("or", (pcp), val)
+#define __this_cpu_or_2(pcp, val)	percpu_to_op("or", (pcp), val)
+#define __this_cpu_or_4(pcp, val)	percpu_to_op("or", (pcp), val)
+#define __this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define __this_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define __this_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#define this_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_4(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define this_cpu_add_1(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_add_2(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_add_4(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
+#define this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
+#define this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
+#define this_cpu_or_1(pcp, val)		percpu_to_op("or", (pcp), val)
+#define this_cpu_or_2(pcp, val)		percpu_to_op("or", (pcp), val)
+#define this_cpu_or_4(pcp, val)		percpu_to_op("or", (pcp), val)
+#define this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define this_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define this_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#define irqsafe_cpu_add_1(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_2(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_4(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_or_1(pcp, val)	percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_or_2(pcp, val)	percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_or_4(pcp, val)	percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+/*
+ * Per cpu atomic 64 bit operations are only available under 64 bit.
+ * 32 bit must fall back to generic operations.
+ */
+#ifdef CONFIG_X86_64
+#define __this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define __this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define __this_cpu_add_8(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
+#define __this_cpu_or_8(pcp, val)	percpu_to_op("or", (pcp), val)
+#define __this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#define this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define this_cpu_add_8(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
+#define this_cpu_or_8(pcp, val)		percpu_to_op("or", (pcp), val)
+#define this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#define irqsafe_cpu_add_8(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
+#define irqsafe_cpu_or_8(pcp, val)	percpu_to_op("or", (pcp), val)
+#define irqsafe_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
+
+#endif
+
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define x86_test_and_clear_bit_percpu(bit, var)				\
 ({									\
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index 6389432a9db..0159a69396c 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -361,7 +361,7 @@ void stop_apic_nmi_watchdog(void *unused)
  */
 
 static DEFINE_PER_CPU(unsigned, last_irq_sum);
-static DEFINE_PER_CPU(local_t, alert_counter);
+static DEFINE_PER_CPU(long, alert_counter);
 static DEFINE_PER_CPU(int, nmi_touch);
 
 void touch_nmi_watchdog(void)
@@ -438,8 +438,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 		 * Ayiee, looks like this CPU is stuck ...
 		 * wait a few IRQs (5 seconds) before doing the oops ...
 		 */
-		local_inc(&__get_cpu_var(alert_counter));
-		if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz)
+		__this_cpu_inc(per_cpu_var(alert_counter));
+		if (__this_cpu_read(per_cpu_var(alert_counter)) == 5 * nmi_hz)
 			/*
 			 * die_nmi will return ONLY if NOTIFY_STOP happens..
 			 */
@@ -447,7 +447,7 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 				regs, panic_on_timeout);
 	} else {
 		__get_cpu_var(last_irq_sum) = sum;
-		local_set(&__get_cpu_var(alert_counter), 0);
+		__this_cpu_write(per_cpu_var(alert_counter), 0);
 	}
 
 	/* see if the nmi watchdog went off */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c1afa990a6c..20399b7b0c3 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1093,7 +1093,7 @@ static void clear_all_debug_regs(void)
 
 void __cpuinit cpu_init(void)
 {
-	struct orig_ist *orig_ist;
+	struct orig_ist *oist;
 	struct task_struct *me;
 	struct tss_struct *t;
 	unsigned long v;
@@ -1102,7 +1102,7 @@ void __cpuinit cpu_init(void)
 
 	cpu = stack_smp_processor_id();
 	t = &per_cpu(init_tss, cpu);
-	orig_ist = &per_cpu(orig_ist, cpu);
+	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
 	if (cpu != 0 && percpu_read(node_number) == 0 &&
@@ -1143,12 +1143,12 @@ void __cpuinit cpu_init(void)
 	/*
 	 * set up and load the per-CPU TSS
 	 */
-	if (!orig_ist->ist[0]) {
+	if (!oist->ist[0]) {
 		char *estacks = per_cpu(exception_stacks, cpu);
 
 		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
 			estacks += exception_stack_sizes[v];
-			orig_ist->ist[v] = t->x86_tss.ist[v] =
+			oist->ist[v] = t->x86_tss.ist[v] =
 					(unsigned long)estacks;
 		}
 	}
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
index dca325c0399..b368cd86299 100644
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -30,9 +30,9 @@
 #include <asm/apic.h>
 #include <asm/desc.h>
 
-static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpu_arr);
-static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], priv_arr);
-static DEFINE_PER_CPU(int, cpu_priv_count);
+static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpud_arr);
+static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], cpud_priv_arr);
+static DEFINE_PER_CPU(int, cpud_priv_count);
 
 static DEFINE_MUTEX(cpu_debug_lock);
 
@@ -531,7 +531,7 @@ static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg,
 
 	/* Already intialized */
 	if (file == CPU_INDEX_BIT)
-		if (per_cpu(cpu_arr[type].init, cpu))
+		if (per_cpu(cpud_arr[type].init, cpu))
 			return 0;
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
@@ -543,8 +543,8 @@ static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg,
 	priv->reg = reg;
 	priv->file = file;
 	mutex_lock(&cpu_debug_lock);
-	per_cpu(priv_arr[type], cpu) = priv;
-	per_cpu(cpu_priv_count, cpu)++;
+	per_cpu(cpud_priv_arr[type], cpu) = priv;
+	per_cpu(cpud_priv_count, cpu)++;
 	mutex_unlock(&cpu_debug_lock);
 
 	if (file)
@@ -552,10 +552,10 @@ static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg,
 				    dentry, (void *)priv, &cpu_fops);
 	else {
 		debugfs_create_file(cpu_base[type].name, S_IRUGO,
-				    per_cpu(cpu_arr[type].dentry, cpu),
+				    per_cpu(cpud_arr[type].dentry, cpu),
 				    (void *)priv, &cpu_fops);
 		mutex_lock(&cpu_debug_lock);
-		per_cpu(cpu_arr[type].init, cpu) = 1;
+		per_cpu(cpud_arr[type].init, cpu) = 1;
 		mutex_unlock(&cpu_debug_lock);
 	}
 
@@ -615,7 +615,7 @@ static int cpu_init_allreg(unsigned cpu, struct dentry *dentry)
 		if (!is_typeflag_valid(cpu, cpu_base[type].flag))
 			continue;
 		cpu_dentry = debugfs_create_dir(cpu_base[type].name, dentry);
-		per_cpu(cpu_arr[type].dentry, cpu) = cpu_dentry;
+		per_cpu(cpud_arr[type].dentry, cpu) = cpu_dentry;
 
 		if (type < CPU_TSS_BIT)
 			err = cpu_init_msr(cpu, type, cpu_dentry);
@@ -647,11 +647,11 @@ static int cpu_init_cpu(void)
 		err = cpu_init_allreg(cpu, cpu_dentry);
 
 		pr_info("cpu%d(%d) debug files %d\n",
-			cpu, nr_cpu_ids, per_cpu(cpu_priv_count, cpu));
-		if (per_cpu(cpu_priv_count, cpu) > MAX_CPU_FILES) {
+			cpu, nr_cpu_ids, per_cpu(cpud_priv_count, cpu));
+		if (per_cpu(cpud_priv_count, cpu) > MAX_CPU_FILES) {
 			pr_err("Register files count %d exceeds limit %d\n",
-				per_cpu(cpu_priv_count, cpu), MAX_CPU_FILES);
-			per_cpu(cpu_priv_count, cpu) = MAX_CPU_FILES;
+				per_cpu(cpud_priv_count, cpu), MAX_CPU_FILES);
+			per_cpu(cpud_priv_count, cpu) = MAX_CPU_FILES;
 			err = -ENFILE;
 		}
 		if (err)
@@ -676,8 +676,8 @@ static void __exit cpu_debug_exit(void)
 		debugfs_remove_recursive(cpu_debugfs_dir);
 
 	for (cpu = 0; cpu <  nr_cpu_ids; cpu++)
-		for (i = 0; i < per_cpu(cpu_priv_count, cpu); i++)
-			kfree(per_cpu(priv_arr[i], cpu));
+		for (i = 0; i < per_cpu(cpud_priv_count, cpu); i++)
+			kfree(per_cpu(cpud_priv_arr[i], cpu));
 }
 
 module_init(cpu_debug_init);
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index d2e7c77c1ea..f28decf8dde 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -68,9 +68,9 @@ struct acpi_cpufreq_data {
 	unsigned int cpu_feature;
 };
 
-static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
+static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);
 
-static DEFINE_PER_CPU(struct aperfmperf, old_perf);
+static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
 
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance *acpi_perf_data;
@@ -214,14 +214,14 @@ static u32 get_cur_val(const struct cpumask *mask)
 	if (unlikely(cpumask_empty(mask)))
 		return 0;
 
-	switch (per_cpu(drv_data, cpumask_first(mask))->cpu_feature) {
+	switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
 		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
 		cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
 		break;
 	case SYSTEM_IO_CAPABLE:
 		cmd.type = SYSTEM_IO_CAPABLE;
-		perf = per_cpu(drv_data, cpumask_first(mask))->acpi_data;
+		perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
 		cmd.addr.io.port = perf->control_register.address;
 		cmd.addr.io.bit_width = perf->control_register.bit_width;
 		break;
@@ -268,8 +268,8 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 	if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
 		return 0;
 
-	ratio = calc_aperfmperf_ratio(&per_cpu(old_perf, cpu), &perf);
-	per_cpu(old_perf, cpu) = perf;
+	ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
+	per_cpu(acfreq_old_perf, cpu) = perf;
 
 	retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
 
@@ -278,7 +278,7 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 
 static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 {
-	struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
+	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
 	unsigned int freq;
 	unsigned int cached_freq;
 
@@ -322,7 +322,7 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
 static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 			       unsigned int target_freq, unsigned int relation)
 {
-	struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 	struct acpi_processor_performance *perf;
 	struct cpufreq_freqs freqs;
 	struct drv_cmd cmd;
@@ -416,7 +416,7 @@ out:
 
 static int acpi_cpufreq_verify(struct cpufreq_policy *policy)
 {
-	struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
 	dprintk("acpi_cpufreq_verify\n");
 
@@ -574,7 +574,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		return -ENOMEM;
 
 	data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
-	per_cpu(drv_data, cpu) = data;
+	per_cpu(acfreq_data, cpu) = data;
 
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
 		acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
@@ -725,20 +725,20 @@ err_unreg:
 	acpi_processor_unregister_performance(perf, cpu);
 err_free:
 	kfree(data);
-	per_cpu(drv_data, cpu) = NULL;
+	per_cpu(acfreq_data, cpu) = NULL;
 
 	return result;
 }
 
 static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
-	struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
 	dprintk("acpi_cpufreq_cpu_exit\n");
 
 	if (data) {
 		cpufreq_frequency_table_put_attr(policy->cpu);
-		per_cpu(drv_data, policy->cpu) = NULL;
+		per_cpu(acfreq_data, policy->cpu) = NULL;
 		acpi_processor_unregister_performance(data->acpi_data,
 						      policy->cpu);
 		kfree(data);
@@ -749,7 +749,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 
 static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 {
-	struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
 	dprintk("acpi_cpufreq_resume\n");
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6c40f6b5b34..0c06bca2a1d 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -499,8 +499,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SYSFS
 
 /* pointer to _cpuid4_info array (for each cache leaf) */
-static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
-#define CPUID4_INFO_IDX(x, y)	(&((per_cpu(cpuid4_info, x))[y]))
+static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info);
+#define CPUID4_INFO_IDX(x, y)	(&((per_cpu(ici_cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP
 static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
@@ -513,7 +513,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 	if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
 		struct cpuinfo_x86 *d;
 		for_each_online_cpu(i) {
-			if (!per_cpu(cpuid4_info, i))
+			if (!per_cpu(ici_cpuid4_info, i))
 				continue;
 			d = &cpu_data(i);
 			this_leaf = CPUID4_INFO_IDX(i, index);
@@ -535,7 +535,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 			    c->apicid >> index_msb) {
 				cpumask_set_cpu(i,
 					to_cpumask(this_leaf->shared_cpu_map));
-				if (i != cpu && per_cpu(cpuid4_info, i))  {
+				if (i != cpu && per_cpu(ici_cpuid4_info, i))  {
 					sibling_leaf =
 						CPUID4_INFO_IDX(i, index);
 					cpumask_set_cpu(cpu, to_cpumask(
@@ -574,8 +574,8 @@ static void __cpuinit free_cache_attributes(unsigned int cpu)
 	for (i = 0; i < num_cache_leaves; i++)
 		cache_remove_shared_cpu_map(cpu, i);
 
-	kfree(per_cpu(cpuid4_info, cpu));
-	per_cpu(cpuid4_info, cpu) = NULL;
+	kfree(per_cpu(ici_cpuid4_info, cpu));
+	per_cpu(ici_cpuid4_info, cpu) = NULL;
 }
 
 static int
@@ -614,15 +614,15 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 	if (num_cache_leaves == 0)
 		return -ENOENT;
 
-	per_cpu(cpuid4_info, cpu) = kzalloc(
+	per_cpu(ici_cpuid4_info, cpu) = kzalloc(
 	    sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL);
-	if (per_cpu(cpuid4_info, cpu) == NULL)
+	if (per_cpu(ici_cpuid4_info, cpu) == NULL)
 		return -ENOMEM;
 
 	smp_call_function_single(cpu, get_cpu_leaves, &retval, true);
 	if (retval) {
-		kfree(per_cpu(cpuid4_info, cpu));
-		per_cpu(cpuid4_info, cpu) = NULL;
+		kfree(per_cpu(ici_cpuid4_info, cpu));
+		per_cpu(ici_cpuid4_info, cpu) = NULL;
 	}
 
 	return retval;
@@ -634,7 +634,7 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */
 
 /* pointer to kobject for cpuX/cache */
-static DEFINE_PER_CPU(struct kobject *, cache_kobject);
+static DEFINE_PER_CPU(struct kobject *, ici_cache_kobject);
 
 struct _index_kobject {
 	struct kobject kobj;
@@ -643,8 +643,8 @@ struct _index_kobject {
 };
 
 /* pointer to array of kobjects for cpuX/cache/indexY */
-static DEFINE_PER_CPU(struct _index_kobject *, index_kobject);
-#define INDEX_KOBJECT_PTR(x, y)		(&((per_cpu(index_kobject, x))[y]))
+static DEFINE_PER_CPU(struct _index_kobject *, ici_index_kobject);
+#define INDEX_KOBJECT_PTR(x, y)		(&((per_cpu(ici_index_kobject, x))[y]))
 
 #define show_one_plus(file_name, object, val)				\
 static ssize_t show_##file_name						\
@@ -863,10 +863,10 @@ static struct kobj_type ktype_percpu_entry = {
 
 static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu)
 {
-	kfree(per_cpu(cache_kobject, cpu));
-	kfree(per_cpu(index_kobject, cpu));
-	per_cpu(cache_kobject, cpu) = NULL;
-	per_cpu(index_kobject, cpu) = NULL;
+	kfree(per_cpu(ici_cache_kobject, cpu));
+	kfree(per_cpu(ici_index_kobject, cpu));
+	per_cpu(ici_cache_kobject, cpu) = NULL;
+	per_cpu(ici_index_kobject, cpu) = NULL;
 	free_cache_attributes(cpu);
 }
 
@@ -882,14 +882,14 @@ static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu)
 		return err;
 
 	/* Allocate all required memory */
-	per_cpu(cache_kobject, cpu) =
+	per_cpu(ici_cache_kobject, cpu) =
 		kzalloc(sizeof(struct kobject), GFP_KERNEL);
-	if (unlikely(per_cpu(cache_kobject, cpu) == NULL))
+	if (unlikely(per_cpu(ici_cache_kobject, cpu) == NULL))
 		goto err_out;
 
-	per_cpu(index_kobject, cpu) = kzalloc(
+	per_cpu(ici_index_kobject, cpu) = kzalloc(
 	    sizeof(struct _index_kobject) * num_cache_leaves, GFP_KERNEL);
-	if (unlikely(per_cpu(index_kobject, cpu) == NULL))
+	if (unlikely(per_cpu(ici_index_kobject, cpu) == NULL))
 		goto err_out;
 
 	return 0;
@@ -913,7 +913,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 	if (unlikely(retval < 0))
 		return retval;
 
-	retval = kobject_init_and_add(per_cpu(cache_kobject, cpu),
+	retval = kobject_init_and_add(per_cpu(ici_cache_kobject, cpu),
 				      &ktype_percpu_entry,
 				      &sys_dev->kobj, "%s", "cache");
 	if (retval < 0) {
@@ -927,12 +927,12 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 		this_object->index = i;
 		retval = kobject_init_and_add(&(this_object->kobj),
 					      &ktype_cache,
-					      per_cpu(cache_kobject, cpu),
+					      per_cpu(ici_cache_kobject, cpu),
 					      "index%1lu", i);
 		if (unlikely(retval)) {
 			for (j = 0; j < i; j++)
 				kobject_put(&(INDEX_KOBJECT_PTR(cpu, j)->kobj));
-			kobject_put(per_cpu(cache_kobject, cpu));
+			kobject_put(per_cpu(ici_cache_kobject, cpu));
 			cpuid4_cache_sysfs_exit(cpu);
 			return retval;
 		}
@@ -940,7 +940,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 	}
 	cpumask_set_cpu(cpu, to_cpumask(cache_dev_map));
 
-	kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
+	kobject_uevent(per_cpu(ici_cache_kobject, cpu), KOBJ_ADD);
 	return 0;
 }
 
@@ -949,7 +949,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
 	unsigned int cpu = sys_dev->id;
 	unsigned long i;
 
-	if (per_cpu(cpuid4_info, cpu) == NULL)
+	if (per_cpu(ici_cpuid4_info, cpu) == NULL)
 		return;
 	if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map)))
 		return;
@@ -957,7 +957,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
 
 	for (i = 0; i < num_cache_leaves; i++)
 		kobject_put(&(INDEX_KOBJECT_PTR(cpu, i)->kobj));
-	kobject_put(per_cpu(cache_kobject, cpu));
+	kobject_put(per_cpu(ici_cache_kobject, cpu));
 	cpuid4_cache_sysfs_exit(cpu);
 }
 
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index ef42a038f1a..1c47390dd0e 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -265,13 +265,13 @@ struct ds_context {
 	int			cpu;
 };
 
-static DEFINE_PER_CPU(struct ds_context *, cpu_context);
+static DEFINE_PER_CPU(struct ds_context *, cpu_ds_context);
 
 
 static struct ds_context *ds_get_context(struct task_struct *task, int cpu)
 {
 	struct ds_context **p_context =
-		(task ? &task->thread.ds_ctx : &per_cpu(cpu_context, cpu));
+		(task ? &task->thread.ds_ctx : &per_cpu(cpu_ds_context, cpu));
 	struct ds_context *context = NULL;
 	struct ds_context *new_context = NULL;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 3de0b37ec03..1d9b33843c8 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -316,7 +316,7 @@ static void svm_hardware_disable(void *garbage)
 static int svm_hardware_enable(void *garbage)
 {
 
-	struct svm_cpu_data *svm_data;
+	struct svm_cpu_data *sd;
 	uint64_t efer;
 	struct descriptor_table gdt_descr;
 	struct desc_struct *gdt;
@@ -331,63 +331,61 @@ static int svm_hardware_enable(void *garbage)
 		       me);
 		return -EINVAL;
 	}
-	svm_data = per_cpu(svm_data, me);
+	sd = per_cpu(svm_data, me);
 
-	if (!svm_data) {
+	if (!sd) {
 		printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n",
 		       me);
 		return -EINVAL;
 	}
 
-	svm_data->asid_generation = 1;
-	svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
-	svm_data->next_asid = svm_data->max_asid + 1;
+	sd->asid_generation = 1;
+	sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
+	sd->next_asid = sd->max_asid + 1;
 
 	kvm_get_gdt(&gdt_descr);
 	gdt = (struct desc_struct *)gdt_descr.base;
-	svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
+	sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
 
 	wrmsrl(MSR_EFER, efer | EFER_SVME);
 
-	wrmsrl(MSR_VM_HSAVE_PA,
-	       page_to_pfn(svm_data->save_area) << PAGE_SHIFT);
+	wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
 
 	return 0;
 }
 
 static void svm_cpu_uninit(int cpu)
 {
-	struct svm_cpu_data *svm_data
-		= per_cpu(svm_data, raw_smp_processor_id());
+	struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id());
 
-	if (!svm_data)
+	if (!sd)
 		return;
 
 	per_cpu(svm_data, raw_smp_processor_id()) = NULL;
-	__free_page(svm_data->save_area);
-	kfree(svm_data);
+	__free_page(sd->save_area);
+	kfree(sd);
 }
 
 static int svm_cpu_init(int cpu)
 {
-	struct svm_cpu_data *svm_data;
+	struct svm_cpu_data *sd;
 	int r;
 
-	svm_data = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
-	if (!svm_data)
+	sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
+	if (!sd)
 		return -ENOMEM;
-	svm_data->cpu = cpu;
-	svm_data->save_area = alloc_page(GFP_KERNEL);
+	sd->cpu = cpu;
+	sd->save_area = alloc_page(GFP_KERNEL);
 	r = -ENOMEM;
-	if (!svm_data->save_area)
+	if (!sd->save_area)
 		goto err_1;
 
-	per_cpu(svm_data, cpu) = svm_data;
+	per_cpu(svm_data, cpu) = sd;
 
 	return 0;
 
 err_1:
-	kfree(svm_data);
+	kfree(sd);
 	return r;
 
 }
@@ -1092,16 +1090,16 @@ static void save_host_msrs(struct kvm_vcpu *vcpu)
 #endif
 }
 
-static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
+static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 {
-	if (svm_data->next_asid > svm_data->max_asid) {
-		++svm_data->asid_generation;
-		svm_data->next_asid = 1;
+	if (sd->next_asid > sd->max_asid) {
+		++sd->asid_generation;
+		sd->next_asid = 1;
 		svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
 	}
 
-	svm->asid_generation = svm_data->asid_generation;
-	svm->vmcb->control.asid = svm_data->next_asid++;
+	svm->asid_generation = sd->asid_generation;
+	svm->vmcb->control.asid = sd->next_asid++;
 }
 
 static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr)
@@ -2429,8 +2427,8 @@ static void reload_tss(struct kvm_vcpu *vcpu)
 {
 	int cpu = raw_smp_processor_id();
 
-	struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
-	svm_data->tss_desc->type = 9; /* available 32/64-bit TSS */
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+	sd->tss_desc->type = 9; /* available 32/64-bit TSS */
 	load_TR_desc();
 }
 
@@ -2438,12 +2436,12 @@ static void pre_svm_run(struct vcpu_svm *svm)
 {
 	int cpu = raw_smp_processor_id();
 
-	struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
 	/* FIXME: handle wraparound of asid_generation */
-	if (svm->asid_generation != svm_data->asid_generation)
-		new_asid(svm, svm_data);
+	if (svm->asid_generation != sd->asid_generation)
+		new_asid(svm, sd);
 }
 
 static void svm_inject_nmi(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 64757c0ba5f..563d2050498 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -35,10 +35,10 @@
 
 cpumask_var_t xen_cpu_initialized_map;
 
-static DEFINE_PER_CPU(int, resched_irq);
-static DEFINE_PER_CPU(int, callfunc_irq);
-static DEFINE_PER_CPU(int, callfuncsingle_irq);
-static DEFINE_PER_CPU(int, debug_irq) = -1;
+static DEFINE_PER_CPU(int, xen_resched_irq);
+static DEFINE_PER_CPU(int, xen_callfunc_irq);
+static DEFINE_PER_CPU(int, xen_callfuncsingle_irq);
+static DEFINE_PER_CPU(int, xen_debug_irq) = -1;
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
@@ -103,7 +103,7 @@ static int xen_smp_intr_init(unsigned int cpu)
 				    NULL);
 	if (rc < 0)
 		goto fail;
-	per_cpu(resched_irq, cpu) = rc;
+	per_cpu(xen_resched_irq, cpu) = rc;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
@@ -114,7 +114,7 @@ static int xen_smp_intr_init(unsigned int cpu)
 				    NULL);
 	if (rc < 0)
 		goto fail;
-	per_cpu(callfunc_irq, cpu) = rc;
+	per_cpu(xen_callfunc_irq, cpu) = rc;
 
 	debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
 	rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt,
@@ -122,7 +122,7 @@ static int xen_smp_intr_init(unsigned int cpu)
 				     debug_name, NULL);
 	if (rc < 0)
 		goto fail;
-	per_cpu(debug_irq, cpu) = rc;
+	per_cpu(xen_debug_irq, cpu) = rc;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
@@ -133,19 +133,20 @@ static int xen_smp_intr_init(unsigned int cpu)
 				    NULL);
 	if (rc < 0)
 		goto fail;
-	per_cpu(callfuncsingle_irq, cpu) = rc;
+	per_cpu(xen_callfuncsingle_irq, cpu) = rc;
 
 	return 0;
 
  fail:
-	if (per_cpu(resched_irq, cpu) >= 0)
-		unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL);
-	if (per_cpu(callfunc_irq, cpu) >= 0)
-		unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
-	if (per_cpu(debug_irq, cpu) >= 0)
-		unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
-	if (per_cpu(callfuncsingle_irq, cpu) >= 0)
-		unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL);
+	if (per_cpu(xen_resched_irq, cpu) >= 0)
+		unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
+	if (per_cpu(xen_callfunc_irq, cpu) >= 0)
+		unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
+	if (per_cpu(xen_debug_irq, cpu) >= 0)
+		unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
+	if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0)
+		unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu),
+				       NULL);
 
 	return rc;
 }
@@ -349,10 +350,10 @@ static void xen_cpu_die(unsigned int cpu)
 		current->state = TASK_UNINTERRUPTIBLE;
 		schedule_timeout(HZ/10);
 	}
-	unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL);
-	unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
-	unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
-	unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
 	xen_uninit_lock_cpu(cpu);
 	xen_teardown_timer(cpu);
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 9d1f853120d..0d3f07cd1b5 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -31,14 +31,14 @@
 #define NS_PER_TICK	(1000000000LL / HZ)
 
 /* runstate info updated by Xen */
-static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
+static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
 
 /* snapshots of runstate info */
-static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate_snapshot);
+static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot);
 
 /* unused ns of stolen and blocked time */
-static DEFINE_PER_CPU(u64, residual_stolen);
-static DEFINE_PER_CPU(u64, residual_blocked);
+static DEFINE_PER_CPU(u64, xen_residual_stolen);
+static DEFINE_PER_CPU(u64, xen_residual_blocked);
 
 /* return an consistent snapshot of 64-bit time/counter value */
 static u64 get64(const u64 *p)
@@ -79,7 +79,7 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
 
 	BUG_ON(preemptible());
 
-	state = &__get_cpu_var(runstate);
+	state = &__get_cpu_var(xen_runstate);
 
 	/*
 	 * The runstate info is always updated by the hypervisor on
@@ -97,14 +97,14 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
 /* return true when a vcpu could run but has no real cpu to run on */
 bool xen_vcpu_stolen(int vcpu)
 {
-	return per_cpu(runstate, vcpu).state == RUNSTATE_runnable;
+	return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable;
 }
 
 void xen_setup_runstate_info(int cpu)
 {
 	struct vcpu_register_runstate_memory_area area;
 
-	area.addr.v = &per_cpu(runstate, cpu);
+	area.addr.v = &per_cpu(xen_runstate, cpu);
 
 	if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area,
 			       cpu, &area))
@@ -122,7 +122,7 @@ static void do_stolen_accounting(void)
 
 	WARN_ON(state.state != RUNSTATE_running);
 
-	snap = &__get_cpu_var(runstate_snapshot);
+	snap = &__get_cpu_var(xen_runstate_snapshot);
 
 	/* work out how much time the VCPU has not been runn*ing*  */
 	blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked];
@@ -133,24 +133,24 @@ static void do_stolen_accounting(void)
 
 	/* Add the appropriate number of ticks of stolen time,
 	   including any left-overs from last time. */
-	stolen = runnable + offline + __get_cpu_var(residual_stolen);
+	stolen = runnable + offline + __get_cpu_var(xen_residual_stolen);
 
 	if (stolen < 0)
 		stolen = 0;
 
 	ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
-	__get_cpu_var(residual_stolen) = stolen;
+	__get_cpu_var(xen_residual_stolen) = stolen;
 	account_steal_ticks(ticks);
 
 	/* Add the appropriate number of ticks of blocked time,
 	   including any left-overs from last time. */
-	blocked += __get_cpu_var(residual_blocked);
+	blocked += __get_cpu_var(xen_residual_blocked);
 
 	if (blocked < 0)
 		blocked = 0;
 
 	ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
-	__get_cpu_var(residual_blocked) = blocked;
+	__get_cpu_var(xen_residual_blocked) = blocked;
 	account_idle_ticks(ticks);
 }
 
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index f8ae0d94a64..704c1411532 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -99,7 +99,7 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue,
 	struct cryptd_cpu_queue *cpu_queue;
 
 	cpu = get_cpu();
-	cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu);
+	cpu_queue = this_cpu_ptr(queue->cpu_queue);
 	err = crypto_enqueue_request(&cpu_queue->queue, request);
 	queue_work_on(cpu, kcrypto_wq, &cpu_queue->work);
 	put_cpu();
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 27fd775375b..958bd1540c3 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -131,7 +131,7 @@ static ssize_t show_crash_notes(struct sys_device *dev, struct sysdev_attribute
 	 * boot up and this data does not change there after. Hence this
 	 * operation should be safe. No locking required.
 	 */
-	addr = __pa(per_cpu_ptr(crash_notes, cpunum));
+	addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpunum));
 	rc = sprintf(buf, "%Lx\n", addr);
 	return rc;
 }
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f20668c09ce..67bc2ece7b4 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -64,14 +64,14 @@ static DEFINE_SPINLOCK(cpufreq_driver_lock);
  * - Lock should not be held across
  *     __cpufreq_governor(data, CPUFREQ_GOV_STOP);
  */
-static DEFINE_PER_CPU(int, policy_cpu);
+static DEFINE_PER_CPU(int, cpufreq_policy_cpu);
 static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);
 
 #define lock_policy_rwsem(mode, cpu)					\
 int lock_policy_rwsem_##mode						\
 (int cpu)								\
 {									\
-	int policy_cpu = per_cpu(policy_cpu, cpu);			\
+	int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);		\
 	BUG_ON(policy_cpu == -1);					\
 	down_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu));		\
 	if (unlikely(!cpu_online(cpu))) {				\
@@ -90,7 +90,7 @@ EXPORT_SYMBOL_GPL(lock_policy_rwsem_write);
 
 void unlock_policy_rwsem_read(int cpu)
 {
-	int policy_cpu = per_cpu(policy_cpu, cpu);
+	int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);
 	BUG_ON(policy_cpu == -1);
 	up_read(&per_cpu(cpu_policy_rwsem, policy_cpu));
 }
@@ -98,7 +98,7 @@ EXPORT_SYMBOL_GPL(unlock_policy_rwsem_read);
 
 void unlock_policy_rwsem_write(int cpu)
 {
-	int policy_cpu = per_cpu(policy_cpu, cpu);
+	int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);
 	BUG_ON(policy_cpu == -1);
 	up_write(&per_cpu(cpu_policy_rwsem, policy_cpu));
 }
@@ -818,7 +818,7 @@ static int cpufreq_add_dev_policy(unsigned int cpu,
 
 			/* Set proper policy_cpu */
 			unlock_policy_rwsem_write(cpu);
-			per_cpu(policy_cpu, cpu) = managed_policy->cpu;
+			per_cpu(cpufreq_policy_cpu, cpu) = managed_policy->cpu;
 
 			if (lock_policy_rwsem_write(cpu) < 0) {
 				/* Should not go through policy unlock path */
@@ -932,7 +932,7 @@ static int cpufreq_add_dev_interface(unsigned int cpu,
 	if (!cpu_online(j))
 		continue;
 		per_cpu(cpufreq_cpu_data, j) = policy;
-		per_cpu(policy_cpu, j) = policy->cpu;
+		per_cpu(cpufreq_policy_cpu, j) = policy->cpu;
 	}
 	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
@@ -1020,7 +1020,7 @@ static int cpufreq_add_dev(struct sys_device *sys_dev)
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
 
 	/* Initially set CPU itself as the policy_cpu */
-	per_cpu(policy_cpu, cpu) = cpu;
+	per_cpu(cpufreq_policy_cpu, cpu) = cpu;
 	ret = (lock_policy_rwsem_write(cpu) < 0);
 	WARN_ON(ret);
 
@@ -2002,7 +2002,7 @@ static int __init cpufreq_core_init(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		per_cpu(policy_cpu, cpu) = -1;
+		per_cpu(cpufreq_policy_cpu, cpu) = -1;
 		init_rwsem(&per_cpu(cpu_policy_rwsem, cpu));
 	}
 
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index a9bd3a05a68..05432216e22 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -174,7 +174,7 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_target);
 
-static DEFINE_PER_CPU(struct cpufreq_frequency_table *, show_table);
+static DEFINE_PER_CPU(struct cpufreq_frequency_table *, cpufreq_show_table);
 /**
  * show_available_freqs - show available frequencies for the specified CPU
  */
@@ -185,10 +185,10 @@ static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf)
 	ssize_t count = 0;
 	struct cpufreq_frequency_table *table;
 
-	if (!per_cpu(show_table, cpu))
+	if (!per_cpu(cpufreq_show_table, cpu))
 		return -ENODEV;
 
-	table = per_cpu(show_table, cpu);
+	table = per_cpu(cpufreq_show_table, cpu);
 
 	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
 		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
@@ -217,20 +217,20 @@ void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
 				      unsigned int cpu)
 {
 	dprintk("setting show_table for cpu %u to %p\n", cpu, table);
-	per_cpu(show_table, cpu) = table;
+	per_cpu(cpufreq_show_table, cpu) = table;
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_get_attr);
 
 void cpufreq_frequency_table_put_attr(unsigned int cpu)
 {
 	dprintk("clearing show_table for cpu %u\n", cpu);
-	per_cpu(show_table, cpu) = NULL;
+	per_cpu(cpufreq_show_table, cpu) = NULL;
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_put_attr);
 
 struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
 {
-	return per_cpu(show_table, cpu);
+	return per_cpu(cpufreq_show_table, cpu);
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
 
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 84c51e17726..8c2f3703ec8 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -64,7 +64,7 @@ struct aes_ctx {
 	u32 *D;
 };
 
-static DEFINE_PER_CPU(struct cword *, last_cword);
+static DEFINE_PER_CPU(struct cword *, paes_last_cword);
 
 /* Tells whether the ACE is capable to generate
    the extended key for a given key_len. */
@@ -152,9 +152,9 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 
 ok:
 	for_each_online_cpu(cpu)
-		if (&ctx->cword.encrypt == per_cpu(last_cword, cpu) ||
-		    &ctx->cword.decrypt == per_cpu(last_cword, cpu))
-			per_cpu(last_cword, cpu) = NULL;
+		if (&ctx->cword.encrypt == per_cpu(paes_last_cword, cpu) ||
+		    &ctx->cword.decrypt == per_cpu(paes_last_cword, cpu))
+			per_cpu(paes_last_cword, cpu) = NULL;
 
 	return 0;
 }
@@ -166,7 +166,7 @@ static inline void padlock_reset_key(struct cword *cword)
 {
 	int cpu = raw_smp_processor_id();
 
-	if (cword != per_cpu(last_cword, cpu))
+	if (cword != per_cpu(paes_last_cword, cpu))
 #ifndef CONFIG_X86_64
 		asm volatile ("pushfl; popfl");
 #else
@@ -176,7 +176,7 @@ static inline void padlock_reset_key(struct cword *cword)
 
 static inline void padlock_store_cword(struct cword *cword)
 {
-	per_cpu(last_cword, raw_smp_processor_id()) = cword;
+	per_cpu(paes_last_cword, raw_smp_processor_id()) = cword;
 }
 
 /*
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 8f99354082c..6f51a0a7a8b 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -326,14 +326,7 @@ arch_initcall(dma_channel_table_init);
  */
 struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type)
 {
-	struct dma_chan *chan;
-	int cpu;
-
-	cpu = get_cpu();
-	chan = per_cpu_ptr(channel_table[tx_type], cpu)->chan;
-	put_cpu();
-
-	return chan;
+	return this_cpu_read(channel_table[tx_type]->chan);
 }
 EXPORT_SYMBOL(dma_find_channel);
 
@@ -857,7 +850,6 @@ dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
 	struct dma_async_tx_descriptor *tx;
 	dma_addr_t dma_dest, dma_src;
 	dma_cookie_t cookie;
-	int cpu;
 	unsigned long flags;
 
 	dma_src = dma_map_single(dev->dev, src, len, DMA_TO_DEVICE);
@@ -876,10 +868,10 @@ dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
 	tx->callback = NULL;
 	cookie = tx->tx_submit(tx);
 
-	cpu = get_cpu();
-	per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
-	per_cpu_ptr(chan->local, cpu)->memcpy_count++;
-	put_cpu();
+	preempt_disable();
+	__this_cpu_add(chan->local->bytes_transferred, len);
+	__this_cpu_inc(chan->local->memcpy_count);
+	preempt_enable();
 
 	return cookie;
 }
@@ -906,7 +898,6 @@ dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
 	struct dma_async_tx_descriptor *tx;
 	dma_addr_t dma_dest, dma_src;
 	dma_cookie_t cookie;
-	int cpu;
 	unsigned long flags;
 
 	dma_src = dma_map_single(dev->dev, kdata, len, DMA_TO_DEVICE);
@@ -923,10 +914,10 @@ dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
 	tx->callback = NULL;
 	cookie = tx->tx_submit(tx);
 
-	cpu = get_cpu();
-	per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
-	per_cpu_ptr(chan->local, cpu)->memcpy_count++;
-	put_cpu();
+	preempt_disable();
+	__this_cpu_add(chan->local->bytes_transferred, len);
+	__this_cpu_inc(chan->local->memcpy_count);
+	preempt_enable();
 
 	return cookie;
 }
@@ -955,7 +946,6 @@ dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
 	struct dma_async_tx_descriptor *tx;
 	dma_addr_t dma_dest, dma_src;
 	dma_cookie_t cookie;
-	int cpu;
 	unsigned long flags;
 
 	dma_src = dma_map_page(dev->dev, src_pg, src_off, len, DMA_TO_DEVICE);
@@ -973,10 +963,10 @@ dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
 	tx->callback = NULL;
 	cookie = tx->tx_submit(tx);
 
-	cpu = get_cpu();
-	per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
-	per_cpu_ptr(chan->local, cpu)->memcpy_count++;
-	put_cpu();
+	preempt_disable();
+	__this_cpu_add(chan->local->bytes_transferred, len);
+	__this_cpu_inc(chan->local->memcpy_count);
+	preempt_enable();
 
 	return cookie;
 }
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c
index 4b89b791be6..42be0b15084 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -826,8 +826,7 @@ static void __cpuinit take_over_work(struct ehca_comp_pool *pool, int cpu)
 		cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
 
 		list_del(&cq->entry);
-		__queue_comp_task(cq, per_cpu_ptr(pool->cpu_comp_tasks,
-						  smp_processor_id()));
+		__queue_comp_task(cq, this_cpu_ptr(pool->cpu_comp_tasks));
 	}
 
 	spin_unlock_irqrestore(&cct->task_lock, flags_cct);
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 6ae388849a3..fb2b7ef7868 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -69,7 +69,7 @@ static struct lguest_pages *lguest_pages(unsigned int cpu)
 		  (SWITCHER_ADDR + SHARED_SWITCHER_PAGES*PAGE_SIZE))[cpu]);
 }
 
-static DEFINE_PER_CPU(struct lg_cpu *, last_cpu);
+static DEFINE_PER_CPU(struct lg_cpu *, lg_last_cpu);
 
 /*S:010
  * We approach the Switcher.
@@ -90,8 +90,8 @@ static void copy_in_guest_info(struct lg_cpu *cpu, struct lguest_pages *pages)
 	 * meanwhile).  If that's not the case, we pretend everything in the
 	 * Guest has changed.
 	 */
-	if (__get_cpu_var(last_cpu) != cpu || cpu->last_pages != pages) {
-		__get_cpu_var(last_cpu) = cpu;
+	if (__get_cpu_var(lg_last_cpu) != cpu || cpu->last_pages != pages) {
+		__get_cpu_var(lg_last_cpu) = cpu;
 		cpu->last_pages = pages;
 		cpu->changed = CHANGED_ALL;
 	}
diff --git a/drivers/net/chelsio/sge.c b/drivers/net/chelsio/sge.c
index 8c658cf6f62..109d2783e4d 100644
--- a/drivers/net/chelsio/sge.c
+++ b/drivers/net/chelsio/sge.c
@@ -1378,7 +1378,7 @@ static void sge_rx(struct sge *sge, struct freelQ *fl, unsigned int len)
 	}
 	__skb_pull(skb, sizeof(*p));
 
-	st = per_cpu_ptr(sge->port_stats[p->iff], smp_processor_id());
+	st = this_cpu_ptr(sge->port_stats[p->iff]);
 
 	skb->protocol = eth_type_trans(skb, adapter->port[p->iff].dev);
 	if ((adapter->flags & RX_CSUM_ENABLED) && p->csum == 0xffff &&
@@ -1780,8 +1780,7 @@ netdev_tx_t t1_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct adapter *adapter = dev->ml_priv;
 	struct sge *sge = adapter->sge;
-	struct sge_port_stats *st = per_cpu_ptr(sge->port_stats[dev->if_port],
-						smp_processor_id());
+	struct sge_port_stats *st = this_cpu_ptr(sge->port_stats[dev->if_port]);
 	struct cpl_tx_pkt *cpl;
 	struct sk_buff *orig_skb = skb;
 	int ret;
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index eae4ad749e9..b9fcc981983 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -81,7 +81,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
 
 	/* it's OK to use per_cpu_ptr() because BHs are off */
 	pcpu_lstats = dev->ml_priv;
-	lb_stats = per_cpu_ptr(pcpu_lstats, smp_processor_id());
+	lb_stats = this_cpu_ptr(pcpu_lstats);
 
 	len = skb->len;
 	if (likely(netif_rx(skb) == NET_RX_SUCCESS)) {
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 63099c58a6d..3a15de56df9 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -153,15 +153,14 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net_device *rcv = NULL;
 	struct veth_priv *priv, *rcv_priv;
 	struct veth_net_stats *stats, *rcv_stats;
-	int length, cpu;
+	int length;
 
 	priv = netdev_priv(dev);
 	rcv = priv->peer;
 	rcv_priv = netdev_priv(rcv);
 
-	cpu = smp_processor_id();
-	stats = per_cpu_ptr(priv->stats, cpu);
-	rcv_stats = per_cpu_ptr(rcv_priv->stats, cpu);
+	stats = this_cpu_ptr(priv->stats);
+	rcv_stats = this_cpu_ptr(rcv_priv->stats);
 
 	if (!(rcv->flags & IFF_UP))
 		goto tx_drop;
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index a7aae24f288..166b67ea622 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -47,7 +47,7 @@
  */
 static struct ring_buffer *op_ring_buffer_read;
 static struct ring_buffer *op_ring_buffer_write;
-DEFINE_PER_CPU(struct oprofile_cpu_buffer, cpu_buffer);
+DEFINE_PER_CPU(struct oprofile_cpu_buffer, op_cpu_buffer);
 
 static void wq_sync_buffer(struct work_struct *work);
 
@@ -61,8 +61,7 @@ unsigned long oprofile_get_cpu_buffer_size(void)
 
 void oprofile_cpu_buffer_inc_smpl_lost(void)
 {
-	struct oprofile_cpu_buffer *cpu_buf
-		= &__get_cpu_var(cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
 
 	cpu_buf->sample_lost_overflow++;
 }
@@ -95,7 +94,7 @@ int alloc_cpu_buffers(void)
 		goto fail;
 
 	for_each_possible_cpu(i) {
-		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
+		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);
 
 		b->last_task = NULL;
 		b->last_is_kernel = -1;
@@ -122,7 +121,7 @@ void start_cpu_work(void)
 	work_enabled = 1;
 
 	for_each_online_cpu(i) {
-		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
+		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);
 
 		/*
 		 * Spread the work by 1 jiffy per cpu so they dont all
@@ -139,7 +138,7 @@ void end_cpu_work(void)
 	work_enabled = 0;
 
 	for_each_online_cpu(i) {
-		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
+		struct oprofile_cpu_buffer *b = &per_cpu(op_cpu_buffer, i);
 
 		cancel_delayed_work(&b->work);
 	}
@@ -330,7 +329,7 @@ static inline void
 __oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 			  unsigned long event, int is_kernel)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
 	unsigned long backtrace = oprofile_backtrace_depth;
 
 	/*
@@ -375,7 +374,7 @@ oprofile_write_reserve(struct op_entry *entry, struct pt_regs * const regs,
 {
 	struct op_sample *sample;
 	int is_kernel = !user_mode(regs);
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
 
 	cpu_buf->sample_received++;
 
@@ -430,13 +429,13 @@ int oprofile_write_commit(struct op_entry *entry)
 
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
 	log_sample(cpu_buf, pc, 0, is_kernel, event);
 }
 
 void oprofile_add_trace(unsigned long pc)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
 
 	if (!cpu_buf->tracing)
 		return;
diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h
index 272995d2029..68ea16ab645 100644
--- a/drivers/oprofile/cpu_buffer.h
+++ b/drivers/oprofile/cpu_buffer.h
@@ -50,7 +50,7 @@ struct oprofile_cpu_buffer {
 	struct delayed_work work;
 };
 
-DECLARE_PER_CPU(struct oprofile_cpu_buffer, cpu_buffer);
+DECLARE_PER_CPU(struct oprofile_cpu_buffer, op_cpu_buffer);
 
 /*
  * Resets the cpu buffer to a sane state.
@@ -60,7 +60,7 @@ DECLARE_PER_CPU(struct oprofile_cpu_buffer, cpu_buffer);
  */
 static inline void op_cpu_buffer_reset(int cpu)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu);
+	struct oprofile_cpu_buffer *cpu_buf = &per_cpu(op_cpu_buffer, cpu);
 
 	cpu_buf->last_is_kernel = -1;
 	cpu_buf->last_task = NULL;
diff --git a/drivers/oprofile/oprofile_stats.c b/drivers/oprofile/oprofile_stats.c
index 61689e814d4..917d28ebeac 100644
--- a/drivers/oprofile/oprofile_stats.c
+++ b/drivers/oprofile/oprofile_stats.c
@@ -23,7 +23,7 @@ void oprofile_reset_stats(void)
 	int i;
 
 	for_each_possible_cpu(i) {
-		cpu_buf = &per_cpu(cpu_buffer, i);
+		cpu_buf = &per_cpu(op_cpu_buffer, i);
 		cpu_buf->sample_received = 0;
 		cpu_buf->sample_lost_overflow = 0;
 		cpu_buf->backtrace_aborted = 0;
@@ -51,7 +51,7 @@ void oprofile_create_stats_files(struct super_block *sb, struct dentry *root)
 		return;
 
 	for_each_possible_cpu(i) {
-		cpu_buf = &per_cpu(cpu_buffer, i);
+		cpu_buf = &per_cpu(op_cpu_buffer, i);
 		snprintf(buf, 10, "cpu%d", i);
 		cpudir = oprofilefs_mkdir(sb, dir, buf);
 
diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c
index 395c04c2b00..98c04cac43c 100644
--- a/drivers/s390/net/netiucv.c
+++ b/drivers/s390/net/netiucv.c
@@ -113,11 +113,9 @@ static inline int iucv_dbf_passes(debug_info_t *dbf_grp, int level)
 #define IUCV_DBF_TEXT_(name, level, text...) \
 	do { \
 		if (iucv_dbf_passes(iucv_dbf_##name, level)) { \
-			char* iucv_dbf_txt_buf = \
-					get_cpu_var(iucv_dbf_txt_buf); \
-			sprintf(iucv_dbf_txt_buf, text); \
-			debug_text_event(iucv_dbf_##name, level, \
-						iucv_dbf_txt_buf); \
+			char* __buf = get_cpu_var(iucv_dbf_txt_buf); \
+			sprintf(__buf, text); \
+			debug_text_event(iucv_dbf_##name, level, __buf); \
 			put_cpu_var(iucv_dbf_txt_buf); \
 		} \
 	} while (0)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c1e19d5b598..b1fd3daadc9 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3955,7 +3955,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	 * per cpu locality group is to reduce the contention between block
 	 * request from multiple CPUs.
 	 */
-	ac->ac_lg = per_cpu_ptr(sbi->s_locality_groups, raw_smp_processor_id());
+	ac->ac_lg = __this_cpu_ptr(sbi->s_locality_groups);
 
 	/* we're going to use group allocation */
 	ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h
index ceda50aad73..46d779abafd 100644
--- a/fs/nfs/iostat.h
+++ b/fs/nfs/iostat.h
@@ -25,13 +25,7 @@ struct nfs_iostats {
 static inline void nfs_inc_server_stats(const struct nfs_server *server,
 					enum nfs_stat_eventcounters stat)
 {
-	struct nfs_iostats *iostats;
-	int cpu;
-
-	cpu = get_cpu();
-	iostats = per_cpu_ptr(server->io_stats, cpu);
-	iostats->events[stat]++;
-	put_cpu();
+	this_cpu_inc(server->io_stats->events[stat]);
 }
 
 static inline void nfs_inc_stats(const struct inode *inode,
@@ -44,13 +38,7 @@ static inline void nfs_add_server_stats(const struct nfs_server *server,
 					enum nfs_stat_bytecounters stat,
 					unsigned long addend)
 {
-	struct nfs_iostats *iostats;
-	int cpu;
-
-	cpu = get_cpu();
-	iostats = per_cpu_ptr(server->io_stats, cpu);
-	iostats->bytes[stat] += addend;
-	put_cpu();
+	this_cpu_add(server->io_stats->bytes[stat], addend);
 }
 
 static inline void nfs_add_stats(const struct inode *inode,
@@ -65,13 +53,7 @@ static inline void nfs_add_fscache_stats(struct inode *inode,
 					 enum nfs_stat_fscachecounters stat,
 					 unsigned long addend)
 {
-	struct nfs_iostats *iostats;
-	int cpu;
-
-	cpu = get_cpu();
-	iostats = per_cpu_ptr(NFS_SERVER(inode)->io_stats, cpu);
-	iostats->fscache[stat] += addend;
-	put_cpu();
+	this_cpu_add(NFS_SERVER(inode)->io_stats->fscache[stat], addend);
 }
 #endif
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 66a888a9ad6..bfffd6334ab 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -2389,12 +2389,12 @@ xfs_icsb_modify_counters(
 {
 	xfs_icsb_cnts_t	*icsbp;
 	long long	lcounter;	/* long counter for 64 bit fields */
-	int		cpu, ret = 0;
+	int		ret = 0;
 
 	might_sleep();
 again:
-	cpu = get_cpu();
-	icsbp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, cpu);
+	preempt_disable();
+	icsbp = this_cpu_ptr(mp->m_sb_cnts);
 
 	/*
 	 * if the counter is disabled, go to slow path
@@ -2438,11 +2438,11 @@ again:
 		break;
 	}
 	xfs_icsb_unlock_cntr(icsbp);
-	put_cpu();
+	preempt_enable();
 	return 0;
 
 slow_path:
-	put_cpu();
+	preempt_enable();
 
 	/*
 	 * serialise with a mutex so we don't burn lots of cpu on
@@ -2490,7 +2490,7 @@ slow_path:
 
 balance_counter:
 	xfs_icsb_unlock_cntr(icsbp);
-	put_cpu();
+	preempt_enable();
 
 	/*
 	 * We may have multiple threads here if multiple per-cpu
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 90079c373f1..8087b90d467 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -56,6 +56,9 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 #define __raw_get_cpu_var(var) \
 	(*SHIFT_PERCPU_PTR(&per_cpu_var(var), __my_cpu_offset))
 
+#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#define __this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
+
 
 #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void setup_per_cpu_areas(void);
@@ -66,6 +69,8 @@ extern void setup_per_cpu_areas(void);
 #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)
+#define this_cpu_ptr(ptr) per_cpu_ptr(ptr, 0)
+#define __this_cpu_ptr(ptr) this_cpu_ptr(ptr)
 
 #endif	/* SMP */
 
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 9bd03193ecd..5a5d6ce4bd5 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -60,6 +60,7 @@
 
 #define DEFINE_PER_CPU_SECTION(type, name, sec)				\
 	__PCPU_DUMMY_ATTRS char __pcpu_scope_##name;			\
+	extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name;		\
 	__PCPU_DUMMY_ATTRS char __pcpu_unique_##name;			\
 	__PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak			\
 	__typeof__(type) per_cpu__##name
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 878836ca999..cf5efbcf716 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -34,8 +34,6 @@
 
 #ifdef CONFIG_SMP
 
-#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)
 
@@ -130,30 +128,9 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
 #define per_cpu_ptr(ptr, cpu)	SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
 
 extern void *__alloc_reserved_percpu(size_t size, size_t align);
-
-#else /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
-struct percpu_data {
-	void *ptrs[1];
-};
-
-/* pointer disguising messes up the kmemleak objects tracking */
-#ifndef CONFIG_DEBUG_KMEMLEAK
-#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
-#else
-#define __percpu_disguise(pdata) (struct percpu_data *)(pdata)
-#endif
-
-#define per_cpu_ptr(ptr, cpu)						\
-({									\
-        struct percpu_data *__p = __percpu_disguise(ptr);		\
-        (__typeof__(ptr))__p->ptrs[(cpu)];				\
-})
-
-#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
 extern void *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void *__pdata);
+extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
 
 #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void __init setup_per_cpu_areas(void);
@@ -179,6 +156,11 @@ static inline void free_percpu(void *p)
 	kfree(p);
 }
 
+static inline phys_addr_t per_cpu_ptr_to_phys(void *addr)
+{
+	return __pa(addr);
+}
+
 static inline void __init setup_per_cpu_areas(void) { }
 
 static inline void *pcpu_lpage_remapped(void *kaddr)
@@ -188,8 +170,8 @@ static inline void *pcpu_lpage_remapped(void *kaddr)
 
 #endif /* CONFIG_SMP */
 
-#define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type), \
-						       __alignof__(type))
+#define alloc_percpu(type)	\
+	(typeof(type) *)__alloc_percpu(sizeof(type), __alignof__(type))
 
 /*
  * Optional methods for optimized non-lvalue per-cpu variable access.
@@ -243,4 +225,404 @@ do {									\
 # define percpu_xor(var, val)		__percpu_generic_to_op(var, (val), ^=)
 #endif
 
+/*
+ * Branching function to split up a function into a set of functions that
+ * are called for different scalar sizes of the objects handled.
+ */
+
+extern void __bad_size_call_parameter(void);
+
+#define __pcpu_size_call_return(stem, variable)				\
+({	typeof(variable) pscr_ret__;					\
+	switch(sizeof(variable)) {					\
+	case 1: pscr_ret__ = stem##1(variable);break;			\
+	case 2: pscr_ret__ = stem##2(variable);break;			\
+	case 4: pscr_ret__ = stem##4(variable);break;			\
+	case 8: pscr_ret__ = stem##8(variable);break;			\
+	default:							\
+		__bad_size_call_parameter();break;			\
+	}								\
+	pscr_ret__;							\
+})
+
+#define __pcpu_size_call(stem, variable, ...)				\
+do {									\
+	switch(sizeof(variable)) {					\
+		case 1: stem##1(variable, __VA_ARGS__);break;		\
+		case 2: stem##2(variable, __VA_ARGS__);break;		\
+		case 4: stem##4(variable, __VA_ARGS__);break;		\
+		case 8: stem##8(variable, __VA_ARGS__);break;		\
+		default: 						\
+			__bad_size_call_parameter();break;		\
+	}								\
+} while (0)
+
+/*
+ * Optimized manipulation for memory allocated through the per cpu
+ * allocator or for addresses of per cpu variables (can be determined
+ * using per_cpu_var(xx).
+ *
+ * These operation guarantee exclusivity of access for other operations
+ * on the *same* processor. The assumption is that per cpu data is only
+ * accessed by a single processor instance (the current one).
+ *
+ * The first group is used for accesses that must be done in a
+ * preemption safe way since we know that the context is not preempt
+ * safe. Interrupts may occur. If the interrupt modifies the variable
+ * too then RMW actions will not be reliable.
+ *
+ * The arch code can provide optimized functions in two ways:
+ *
+ * 1. Override the function completely. F.e. define this_cpu_add().
+ *    The arch must then ensure that the various scalar format passed
+ *    are handled correctly.
+ *
+ * 2. Provide functions for certain scalar sizes. F.e. provide
+ *    this_cpu_add_2() to provide per cpu atomic operations for 2 byte
+ *    sized RMW actions. If arch code does not provide operations for
+ *    a scalar size then the fallback in the generic code will be
+ *    used.
+ */
+
+#define _this_cpu_generic_read(pcp)					\
+({	typeof(pcp) ret__;						\
+	preempt_disable();						\
+	ret__ = *this_cpu_ptr(&(pcp));					\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_read
+# ifndef this_cpu_read_1
+#  define this_cpu_read_1(pcp)	_this_cpu_generic_read(pcp)
+# endif
+# ifndef this_cpu_read_2
+#  define this_cpu_read_2(pcp)	_this_cpu_generic_read(pcp)
+# endif
+# ifndef this_cpu_read_4
+#  define this_cpu_read_4(pcp)	_this_cpu_generic_read(pcp)
+# endif
+# ifndef this_cpu_read_8
+#  define this_cpu_read_8(pcp)	_this_cpu_generic_read(pcp)
+# endif
+# define this_cpu_read(pcp)	__pcpu_size_call_return(this_cpu_read_, (pcp))
+#endif
+
+#define _this_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	preempt_disable();						\
+	*__this_cpu_ptr(&pcp) op val;					\
+	preempt_enable();						\
+} while (0)
+
+#ifndef this_cpu_write
+# ifndef this_cpu_write_1
+#  define this_cpu_write_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef this_cpu_write_2
+#  define this_cpu_write_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef this_cpu_write_4
+#  define this_cpu_write_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef this_cpu_write_8
+#  define this_cpu_write_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# define this_cpu_write(pcp, val)	__pcpu_size_call(this_cpu_write_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_add
+# ifndef this_cpu_add_1
+#  define this_cpu_add_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef this_cpu_add_2
+#  define this_cpu_add_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef this_cpu_add_4
+#  define this_cpu_add_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef this_cpu_add_8
+#  define this_cpu_add_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# define this_cpu_add(pcp, val)		__pcpu_size_call(this_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_sub
+# define this_cpu_sub(pcp, val)		this_cpu_add((pcp), -(val))
+#endif
+
+#ifndef this_cpu_inc
+# define this_cpu_inc(pcp)		this_cpu_add((pcp), 1)
+#endif
+
+#ifndef this_cpu_dec
+# define this_cpu_dec(pcp)		this_cpu_sub((pcp), 1)
+#endif
+
+#ifndef this_cpu_and
+# ifndef this_cpu_and_1
+#  define this_cpu_and_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef this_cpu_and_2
+#  define this_cpu_and_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef this_cpu_and_4
+#  define this_cpu_and_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef this_cpu_and_8
+#  define this_cpu_and_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# define this_cpu_and(pcp, val)		__pcpu_size_call(this_cpu_and_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_or
+# ifndef this_cpu_or_1
+#  define this_cpu_or_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef this_cpu_or_2
+#  define this_cpu_or_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef this_cpu_or_4
+#  define this_cpu_or_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef this_cpu_or_8
+#  define this_cpu_or_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# define this_cpu_or(pcp, val)		__pcpu_size_call(this_cpu_or_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_xor
+# ifndef this_cpu_xor_1
+#  define this_cpu_xor_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef this_cpu_xor_2
+#  define this_cpu_xor_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef this_cpu_xor_4
+#  define this_cpu_xor_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef this_cpu_xor_8
+#  define this_cpu_xor_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# define this_cpu_xor(pcp, val)		__pcpu_size_call(this_cpu_or_, (pcp), (val))
+#endif
+
+/*
+ * Generic percpu operations that do not require preemption handling.
+ * Either we do not care about races or the caller has the
+ * responsibility of handling preemptions issues. Arch code can still
+ * override these instructions since the arch per cpu code may be more
+ * efficient and may actually get race freeness for free (that is the
+ * case for x86 for example).
+ *
+ * If there is no other protection through preempt disable and/or
+ * disabling interupts then one of these RMW operations can show unexpected
+ * behavior because the execution thread was rescheduled on another processor
+ * or an interrupt occurred and the same percpu variable was modified from
+ * the interrupt context.
+ */
+#ifndef __this_cpu_read
+# ifndef __this_cpu_read_1
+#  define __this_cpu_read_1(pcp)	(*__this_cpu_ptr(&(pcp)))
+# endif
+# ifndef __this_cpu_read_2
+#  define __this_cpu_read_2(pcp)	(*__this_cpu_ptr(&(pcp)))
+# endif
+# ifndef __this_cpu_read_4
+#  define __this_cpu_read_4(pcp)	(*__this_cpu_ptr(&(pcp)))
+# endif
+# ifndef __this_cpu_read_8
+#  define __this_cpu_read_8(pcp)	(*__this_cpu_ptr(&(pcp)))
+# endif
+# define __this_cpu_read(pcp)	__pcpu_size_call_return(__this_cpu_read_, (pcp))
+#endif
+
+#define __this_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	*__this_cpu_ptr(&(pcp)) op val;					\
+} while (0)
+
+#ifndef __this_cpu_write
+# ifndef __this_cpu_write_1
+#  define __this_cpu_write_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef __this_cpu_write_2
+#  define __this_cpu_write_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef __this_cpu_write_4
+#  define __this_cpu_write_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef __this_cpu_write_8
+#  define __this_cpu_write_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# define __this_cpu_write(pcp, val)	__pcpu_size_call(__this_cpu_write_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_add
+# ifndef __this_cpu_add_1
+#  define __this_cpu_add_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef __this_cpu_add_2
+#  define __this_cpu_add_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef __this_cpu_add_4
+#  define __this_cpu_add_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef __this_cpu_add_8
+#  define __this_cpu_add_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# define __this_cpu_add(pcp, val)	__pcpu_size_call(__this_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_sub
+# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(val))
+#endif
+
+#ifndef __this_cpu_inc
+# define __this_cpu_inc(pcp)		__this_cpu_add((pcp), 1)
+#endif
+
+#ifndef __this_cpu_dec
+# define __this_cpu_dec(pcp)		__this_cpu_sub((pcp), 1)
+#endif
+
+#ifndef __this_cpu_and
+# ifndef __this_cpu_and_1
+#  define __this_cpu_and_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef __this_cpu_and_2
+#  define __this_cpu_and_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef __this_cpu_and_4
+#  define __this_cpu_and_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef __this_cpu_and_8
+#  define __this_cpu_and_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# define __this_cpu_and(pcp, val)	__pcpu_size_call(__this_cpu_and_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_or
+# ifndef __this_cpu_or_1
+#  define __this_cpu_or_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef __this_cpu_or_2
+#  define __this_cpu_or_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef __this_cpu_or_4
+#  define __this_cpu_or_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef __this_cpu_or_8
+#  define __this_cpu_or_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# define __this_cpu_or(pcp, val)	__pcpu_size_call(__this_cpu_or_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_xor
+# ifndef __this_cpu_xor_1
+#  define __this_cpu_xor_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef __this_cpu_xor_2
+#  define __this_cpu_xor_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef __this_cpu_xor_4
+#  define __this_cpu_xor_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef __this_cpu_xor_8
+#  define __this_cpu_xor_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# define __this_cpu_xor(pcp, val)	__pcpu_size_call(__this_cpu_xor_, (pcp), (val))
+#endif
+
+/*
+ * IRQ safe versions of the per cpu RMW operations. Note that these operations
+ * are *not* safe against modification of the same variable from another
+ * processors (which one gets when using regular atomic operations)
+ . They are guaranteed to be atomic vs. local interrupts and
+ * preemption only.
+ */
+#define irqsafe_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
+	*__this_cpu_ptr(&(pcp)) op val;					\
+	local_irq_restore(flags);					\
+} while (0)
+
+#ifndef irqsafe_cpu_add
+# ifndef irqsafe_cpu_add_1
+#  define irqsafe_cpu_add_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef irqsafe_cpu_add_2
+#  define irqsafe_cpu_add_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef irqsafe_cpu_add_4
+#  define irqsafe_cpu_add_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef irqsafe_cpu_add_8
+#  define irqsafe_cpu_add_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# define irqsafe_cpu_add(pcp, val) __pcpu_size_call(irqsafe_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef irqsafe_cpu_sub
+# define irqsafe_cpu_sub(pcp, val)	irqsafe_cpu_add((pcp), -(val))
+#endif
+
+#ifndef irqsafe_cpu_inc
+# define irqsafe_cpu_inc(pcp)	irqsafe_cpu_add((pcp), 1)
+#endif
+
+#ifndef irqsafe_cpu_dec
+# define irqsafe_cpu_dec(pcp)	irqsafe_cpu_sub((pcp), 1)
+#endif
+
+#ifndef irqsafe_cpu_and
+# ifndef irqsafe_cpu_and_1
+#  define irqsafe_cpu_and_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef irqsafe_cpu_and_2
+#  define irqsafe_cpu_and_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef irqsafe_cpu_and_4
+#  define irqsafe_cpu_and_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef irqsafe_cpu_and_8
+#  define irqsafe_cpu_and_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# define irqsafe_cpu_and(pcp, val) __pcpu_size_call(irqsafe_cpu_and_, (val))
+#endif
+
+#ifndef irqsafe_cpu_or
+# ifndef irqsafe_cpu_or_1
+#  define irqsafe_cpu_or_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef irqsafe_cpu_or_2
+#  define irqsafe_cpu_or_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef irqsafe_cpu_or_4
+#  define irqsafe_cpu_or_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef irqsafe_cpu_or_8
+#  define irqsafe_cpu_or_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# define irqsafe_cpu_or(pcp, val) __pcpu_size_call(irqsafe_cpu_or_, (val))
+#endif
+
+#ifndef irqsafe_cpu_xor
+# ifndef irqsafe_cpu_xor_1
+#  define irqsafe_cpu_xor_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef irqsafe_cpu_xor_2
+#  define irqsafe_cpu_xor_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef irqsafe_cpu_xor_4
+#  define irqsafe_cpu_xor_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef irqsafe_cpu_xor_8
+#  define irqsafe_cpu_xor_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# define irqsafe_cpu_xor(pcp, val) __pcpu_size_call(irqsafe_cpu_xor_, (val))
+#endif
+
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 2d0f222388a..d85889710f9 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -76,24 +76,22 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
 
 static inline void __count_vm_event(enum vm_event_item item)
 {
-	__get_cpu_var(vm_event_states).event[item]++;
+	__this_cpu_inc(per_cpu_var(vm_event_states).event[item]);
 }
 
 static inline void count_vm_event(enum vm_event_item item)
 {
-	get_cpu_var(vm_event_states).event[item]++;
-	put_cpu();
+	this_cpu_inc(per_cpu_var(vm_event_states).event[item]);
 }
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
-	__get_cpu_var(vm_event_states).event[item] += delta;
+	__this_cpu_add(per_cpu_var(vm_event_states).event[item], delta);
 }
 
 static inline void count_vm_events(enum vm_event_item item, long delta)
 {
-	get_cpu_var(vm_event_states).event[item] += delta;
-	put_cpu();
+	this_cpu_add(per_cpu_var(vm_event_states).event[item], delta);
 }
 
 extern void all_vm_events(unsigned long *);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 0302f31a2fb..b0173202cad 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -88,12 +88,7 @@ struct neigh_statistics {
 	unsigned long unres_discards;	/* number of unresolved drops */
 };
 
-#define NEIGH_CACHE_STAT_INC(tbl, field)				\
-	do {								\
-		preempt_disable();					\
-		(per_cpu_ptr((tbl)->stats, smp_processor_id())->field)++; \
-		preempt_enable();					\
-	} while (0)
+#define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field)
 
 struct neighbour {
 	struct neighbour	*next;
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 5cf7270e3ff..a0904adfb8f 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -293,11 +293,11 @@ extern unsigned int nf_conntrack_htable_size;
 extern unsigned int nf_conntrack_max;
 
 #define NF_CT_STAT_INC(net, count)	\
-	(per_cpu_ptr((net)->ct.stat, raw_smp_processor_id())->count++)
+	__this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count)		\
 do {							\
 	local_bh_disable();				\
-	per_cpu_ptr((net)->ct.stat, raw_smp_processor_id())->count++;	\
+	__this_cpu_inc((net)->ct.stat->count);		\
 	local_bh_enable();				\
 } while (0)
 
diff --git a/include/net/snmp.h b/include/net/snmp.h
index 8c842e06bec..f0d756f2ac9 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -136,45 +136,31 @@ struct linux_xfrm_mib {
 #define SNMP_STAT_BHPTR(name)	(name[0])
 #define SNMP_STAT_USRPTR(name)	(name[1])
 
-#define SNMP_INC_STATS_BH(mib, field) 	\
-	(per_cpu_ptr(mib[0], raw_smp_processor_id())->mibs[field]++)
-#define SNMP_INC_STATS_USER(mib, field) \
-	do { \
-		per_cpu_ptr(mib[1], get_cpu())->mibs[field]++; \
-		put_cpu(); \
-	} while (0)
-#define SNMP_INC_STATS(mib, field) 	\
-	do { \
-		per_cpu_ptr(mib[!in_softirq()], get_cpu())->mibs[field]++; \
-		put_cpu(); \
-	} while (0)
-#define SNMP_DEC_STATS(mib, field) 	\
-	do { \
-		per_cpu_ptr(mib[!in_softirq()], get_cpu())->mibs[field]--; \
-		put_cpu(); \
-	} while (0)
-#define SNMP_ADD_STATS(mib, field, addend) 	\
-	do { \
-		per_cpu_ptr(mib[!in_softirq()], get_cpu())->mibs[field] += addend; \
-		put_cpu(); \
-	} while (0)
-#define SNMP_ADD_STATS_BH(mib, field, addend) 	\
-	(per_cpu_ptr(mib[0], raw_smp_processor_id())->mibs[field] += addend)
-#define SNMP_ADD_STATS_USER(mib, field, addend) 	\
-	do { \
-		per_cpu_ptr(mib[1], get_cpu())->mibs[field] += addend; \
-		put_cpu(); \
-	} while (0)
+#define SNMP_INC_STATS_BH(mib, field)	\
+			__this_cpu_inc(mib[0]->mibs[field])
+#define SNMP_INC_STATS_USER(mib, field)	\
+			this_cpu_inc(mib[1]->mibs[field])
+#define SNMP_INC_STATS(mib, field)	\
+			this_cpu_inc(mib[!in_softirq()]->mibs[field])
+#define SNMP_DEC_STATS(mib, field)	\
+			this_cpu_dec(mib[!in_softirq()]->mibs[field])
+#define SNMP_ADD_STATS_BH(mib, field, addend)	\
+			__this_cpu_add(mib[0]->mibs[field], addend)
+#define SNMP_ADD_STATS_USER(mib, field, addend)	\
+			this_cpu_add(mib[1]->mibs[field], addend)
 #define SNMP_UPD_PO_STATS(mib, basefield, addend)	\
 	do { \
-		__typeof__(mib[0]) ptr = per_cpu_ptr(mib[!in_softirq()], get_cpu());\
+		__typeof__(mib[0]) ptr; \
+		preempt_disable(); \
+		ptr = this_cpu_ptr((mib)[!in_softirq()]); \
 		ptr->mibs[basefield##PKTS]++; \
 		ptr->mibs[basefield##OCTETS] += addend;\
-		put_cpu(); \
+		preempt_enable(); \
 	} while (0)
 #define SNMP_UPD_PO_STATS_BH(mib, basefield, addend)	\
 	do { \
-		__typeof__(mib[0]) ptr = per_cpu_ptr(mib[!in_softirq()], raw_smp_processor_id());\
+		__typeof__(mib[0]) ptr = \
+			__this_cpu_ptr((mib)[!in_softirq()]); \
 		ptr->mibs[basefield##PKTS]++; \
 		ptr->mibs[basefield##OCTETS] += addend;\
 	} while (0)
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 4f8df01dbe5..429540c70d3 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -140,7 +140,8 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
 }
 
 #ifdef CONFIG_LOCK_STAT
-static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
+static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS],
+		      cpu_lock_stats);
 
 static inline u64 lockstat_clock(void)
 {
@@ -198,7 +199,7 @@ struct lock_class_stats lock_stats(struct lock_class *class)
 	memset(&stats, 0, sizeof(struct lock_class_stats));
 	for_each_possible_cpu(cpu) {
 		struct lock_class_stats *pcs =
-			&per_cpu(lock_stats, cpu)[class - lock_classes];
+			&per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
 
 		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
 			stats.contention_point[i] += pcs->contention_point[i];
@@ -225,7 +226,7 @@ void clear_lock_stats(struct lock_class *class)
 
 	for_each_possible_cpu(cpu) {
 		struct lock_class_stats *cpu_stats =
-			&per_cpu(lock_stats, cpu)[class - lock_classes];
+			&per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
 
 		memset(cpu_stats, 0, sizeof(struct lock_class_stats));
 	}
@@ -235,12 +236,12 @@ void clear_lock_stats(struct lock_class *class)
 
 static struct lock_class_stats *get_lock_stats(struct lock_class *class)
 {
-	return &get_cpu_var(lock_stats)[class - lock_classes];
+	return &get_cpu_var(cpu_lock_stats)[class - lock_classes];
 }
 
 static void put_lock_stats(struct lock_class_stats *stats)
 {
-	put_cpu_var(lock_stats);
+	put_cpu_var(cpu_lock_stats);
 }
 
 static void lock_release_holdtime(struct held_lock *hlock)
diff --git a/kernel/module.c b/kernel/module.c
index 5842a71cf05..12afc5a3ddd 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -370,8 +370,6 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
-
 static void *percpu_modalloc(unsigned long size, unsigned long align,
 			     const char *name)
 {
@@ -395,154 +393,6 @@ static void percpu_modfree(void *freeme)
 	free_percpu(freeme);
 }
 
-#else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
-/* Number of blocks used and allocated. */
-static unsigned int pcpu_num_used, pcpu_num_allocated;
-/* Size of each block.  -ve means used. */
-static int *pcpu_size;
-
-static int split_block(unsigned int i, unsigned short size)
-{
-	/* Reallocation required? */
-	if (pcpu_num_used + 1 > pcpu_num_allocated) {
-		int *new;
-
-		new = krealloc(pcpu_size, sizeof(new[0])*pcpu_num_allocated*2,
-			       GFP_KERNEL);
-		if (!new)
-			return 0;
-
-		pcpu_num_allocated *= 2;
-		pcpu_size = new;
-	}
-
-	/* Insert a new subblock */
-	memmove(&pcpu_size[i+1], &pcpu_size[i],
-		sizeof(pcpu_size[0]) * (pcpu_num_used - i));
-	pcpu_num_used++;
-
-	pcpu_size[i+1] -= size;
-	pcpu_size[i] = size;
-	return 1;
-}
-
-static inline unsigned int block_size(int val)
-{
-	if (val < 0)
-		return -val;
-	return val;
-}
-
-static void *percpu_modalloc(unsigned long size, unsigned long align,
-			     const char *name)
-{
-	unsigned long extra;
-	unsigned int i;
-	void *ptr;
-	int cpu;
-
-	if (align > PAGE_SIZE) {
-		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
-		       name, align, PAGE_SIZE);
-		align = PAGE_SIZE;
-	}
-
-	ptr = __per_cpu_start;
-	for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
-		/* Extra for alignment requirement. */
-		extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr;
-		BUG_ON(i == 0 && extra != 0);
-
-		if (pcpu_size[i] < 0 || pcpu_size[i] < extra + size)
-			continue;
-
-		/* Transfer extra to previous block. */
-		if (pcpu_size[i-1] < 0)
-			pcpu_size[i-1] -= extra;
-		else
-			pcpu_size[i-1] += extra;
-		pcpu_size[i] -= extra;
-		ptr += extra;
-
-		/* Split block if warranted */
-		if (pcpu_size[i] - size > sizeof(unsigned long))
-			if (!split_block(i, size))
-				return NULL;
-
-		/* add the per-cpu scanning areas */
-		for_each_possible_cpu(cpu)
-			kmemleak_alloc(ptr + per_cpu_offset(cpu), size, 0,
-				       GFP_KERNEL);
-
-		/* Mark allocated */
-		pcpu_size[i] = -pcpu_size[i];
-		return ptr;
-	}
-
-	printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n",
-	       size);
-	return NULL;
-}
-
-static void percpu_modfree(void *freeme)
-{
-	unsigned int i;
-	void *ptr = __per_cpu_start + block_size(pcpu_size[0]);
-	int cpu;
-
-	/* First entry is core kernel percpu data. */
-	for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
-		if (ptr == freeme) {
-			pcpu_size[i] = -pcpu_size[i];
-			goto free;
-		}
-	}
-	BUG();
-
- free:
-	/* remove the per-cpu scanning areas */
-	for_each_possible_cpu(cpu)
-		kmemleak_free(freeme + per_cpu_offset(cpu));
-
-	/* Merge with previous? */
-	if (pcpu_size[i-1] >= 0) {
-		pcpu_size[i-1] += pcpu_size[i];
-		pcpu_num_used--;
-		memmove(&pcpu_size[i], &pcpu_size[i+1],
-			(pcpu_num_used - i) * sizeof(pcpu_size[0]));
-		i--;
-	}
-	/* Merge with next? */
-	if (i+1 < pcpu_num_used && pcpu_size[i+1] >= 0) {
-		pcpu_size[i] += pcpu_size[i+1];
-		pcpu_num_used--;
-		memmove(&pcpu_size[i+1], &pcpu_size[i+2],
-			(pcpu_num_used - (i+1)) * sizeof(pcpu_size[0]));
-	}
-}
-
-static int percpu_modinit(void)
-{
-	pcpu_num_used = 2;
-	pcpu_num_allocated = 2;
-	pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated,
-			    GFP_KERNEL);
-	/* Static in-kernel percpu data (used). */
-	pcpu_size[0] = -(__per_cpu_end-__per_cpu_start);
-	/* Free room. */
-	pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0];
-	if (pcpu_size[1] < 0) {
-		printk(KERN_ERR "No per-cpu room for modules.\n");
-		pcpu_num_used = 1;
-	}
-
-	return 0;
-}
-__initcall(percpu_modinit);
-
-#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
 				 Elf_Shdr *sechdrs,
 				 const char *secstrings)
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index a621a67ef4e..9bb52177af0 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -763,13 +763,13 @@ static void rcu_torture_timer(unsigned long unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	++__get_cpu_var(rcu_torture_count)[pipe_count];
+	__this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
 	completed = cur_ops->completed() - completed;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
 	}
-	++__get_cpu_var(rcu_torture_batch)[completed];
+	__this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
 	preempt_enable();
 	cur_ops->readunlock(idx);
 }
@@ -818,13 +818,13 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		++__get_cpu_var(rcu_torture_count)[pipe_count];
+		__this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
 		completed = cur_ops->completed() - completed;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
 		}
-		++__get_cpu_var(rcu_torture_batch)[completed];
+		__this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();
diff --git a/kernel/sched.c b/kernel/sched.c
index ff39cadf621..fd05861b211 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -298,7 +298,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq);
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var);
 #endif /* CONFIG_RT_GROUP_SCHED */
 #else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group
@@ -8286,14 +8286,14 @@ enum s_alloc {
  */
 #ifdef CONFIG_SCHED_SMT
 static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
+static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
 
 static int
 cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
 		 struct sched_group **sg, struct cpumask *unused)
 {
 	if (sg)
-		*sg = &per_cpu(sched_group_cpus, cpu).sg;
+		*sg = &per_cpu(sched_groups, cpu).sg;
 	return cpu;
 }
 #endif /* CONFIG_SCHED_SMT */
@@ -9583,7 +9583,7 @@ void __init sched_init(void)
 #elif defined CONFIG_USER_SCHED
 		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
 		init_tg_rt_entry(&init_task_group,
-				&per_cpu(init_rt_rq, i),
+				&per_cpu(init_rt_rq_var, i),
 				&per_cpu(init_sched_rt_entity, i), i, 1,
 				root_task_group.rt_se[i]);
 #endif
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 21939d9e830..a09502e2ef7 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -697,7 +697,7 @@ void __init softirq_init(void)
 	open_softirq(HI_SOFTIRQ, tasklet_hi_action);
 }
 
-static int ksoftirqd(void * __bind_cpu)
+static int run_ksoftirqd(void * __bind_cpu)
 {
 	set_current_state(TASK_INTERRUPTIBLE);
 
@@ -810,7 +810,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
+		p = kthread_create(run_ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
 		if (IS_ERR(p)) {
 			printk("ksoftirqd for %i failed\n", hotcpu);
 			return NOTIFY_BAD;
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 81324d12eb3..d22579087e2 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -22,9 +22,9 @@
 
 static DEFINE_SPINLOCK(print_lock);
 
-static DEFINE_PER_CPU(unsigned long, touch_timestamp);
-static DEFINE_PER_CPU(unsigned long, print_timestamp);
-static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
+static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */
+static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */
+static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
 
 static int __read_mostly did_panic;
 int __read_mostly softlockup_thresh = 60;
@@ -70,12 +70,12 @@ static void __touch_softlockup_watchdog(void)
 {
 	int this_cpu = raw_smp_processor_id();
 
-	__raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu);
+	__raw_get_cpu_var(softlockup_touch_ts) = get_timestamp(this_cpu);
 }
 
 void touch_softlockup_watchdog(void)
 {
-	__raw_get_cpu_var(touch_timestamp) = 0;
+	__raw_get_cpu_var(softlockup_touch_ts) = 0;
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
@@ -85,7 +85,7 @@ void touch_all_softlockup_watchdogs(void)
 
 	/* Cause each CPU to re-update its timestamp rather than complain */
 	for_each_online_cpu(cpu)
-		per_cpu(touch_timestamp, cpu) = 0;
+		per_cpu(softlockup_touch_ts, cpu) = 0;
 }
 EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
 
@@ -104,28 +104,28 @@ int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
 void softlockup_tick(void)
 {
 	int this_cpu = smp_processor_id();
-	unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
-	unsigned long print_timestamp;
+	unsigned long touch_ts = per_cpu(softlockup_touch_ts, this_cpu);
+	unsigned long print_ts;
 	struct pt_regs *regs = get_irq_regs();
 	unsigned long now;
 
 	/* Is detection switched off? */
-	if (!per_cpu(watchdog_task, this_cpu) || softlockup_thresh <= 0) {
+	if (!per_cpu(softlockup_watchdog, this_cpu) || softlockup_thresh <= 0) {
 		/* Be sure we don't false trigger if switched back on */
-		if (touch_timestamp)
-			per_cpu(touch_timestamp, this_cpu) = 0;
+		if (touch_ts)
+			per_cpu(softlockup_touch_ts, this_cpu) = 0;
 		return;
 	}
 
-	if (touch_timestamp == 0) {
+	if (touch_ts == 0) {
 		__touch_softlockup_watchdog();
 		return;
 	}
 
-	print_timestamp = per_cpu(print_timestamp, this_cpu);
+	print_ts = per_cpu(softlockup_print_ts, this_cpu);
 
 	/* report at most once a second */
-	if (print_timestamp == touch_timestamp || did_panic)
+	if (print_ts == touch_ts || did_panic)
 		return;
 
 	/* do not print during early bootup: */
@@ -140,18 +140,18 @@ void softlockup_tick(void)
 	 * Wake up the high-prio watchdog task twice per
 	 * threshold timespan.
 	 */
-	if (now > touch_timestamp + softlockup_thresh/2)
-		wake_up_process(per_cpu(watchdog_task, this_cpu));
+	if (now > touch_ts + softlockup_thresh/2)
+		wake_up_process(per_cpu(softlockup_watchdog, this_cpu));
 
 	/* Warn about unreasonable delays: */
-	if (now <= (touch_timestamp + softlockup_thresh))
+	if (now <= (touch_ts + softlockup_thresh))
 		return;
 
-	per_cpu(print_timestamp, this_cpu) = touch_timestamp;
+	per_cpu(softlockup_print_ts, this_cpu) = touch_ts;
 
 	spin_lock(&print_lock);
 	printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n",
-			this_cpu, now - touch_timestamp,
+			this_cpu, now - touch_ts,
 			current->comm, task_pid_nr(current));
 	print_modules();
 	print_irqtrace_events(current);
@@ -209,32 +209,32 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		BUG_ON(per_cpu(watchdog_task, hotcpu));
+		BUG_ON(per_cpu(softlockup_watchdog, hotcpu));
 		p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
 		if (IS_ERR(p)) {
 			printk(KERN_ERR "watchdog for %i failed\n", hotcpu);
 			return NOTIFY_BAD;
 		}
-		per_cpu(touch_timestamp, hotcpu) = 0;
-		per_cpu(watchdog_task, hotcpu) = p;
+		per_cpu(softlockup_touch_ts, hotcpu) = 0;
+		per_cpu(softlockup_watchdog, hotcpu) = p;
 		kthread_bind(p, hotcpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		wake_up_process(per_cpu(watchdog_task, hotcpu));
+		wake_up_process(per_cpu(softlockup_watchdog, hotcpu));
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
-		if (!per_cpu(watchdog_task, hotcpu))
+		if (!per_cpu(softlockup_watchdog, hotcpu))
 			break;
 		/* Unbind so it can run.  Fall thru. */
-		kthread_bind(per_cpu(watchdog_task, hotcpu),
+		kthread_bind(per_cpu(softlockup_watchdog, hotcpu),
 			     cpumask_any(cpu_online_mask));
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		p = per_cpu(watchdog_task, hotcpu);
-		per_cpu(watchdog_task, hotcpu) = NULL;
+		p = per_cpu(softlockup_watchdog, hotcpu);
+		per_cpu(softlockup_watchdog, hotcpu) = NULL;
 		kthread_stop(p);
 		break;
 #endif /* CONFIG_HOTPLUG_CPU */
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index ee5681f8d7e..63b117e9eba 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -86,7 +86,7 @@ static DEFINE_SPINLOCK(table_lock);
 /*
  * Per-CPU lookup locks for fast hash lookup:
  */
-static DEFINE_PER_CPU(spinlock_t, lookup_lock);
+static DEFINE_PER_CPU(spinlock_t, tstats_lookup_lock);
 
 /*
  * Mutex to serialize state changes with show-stats activities:
@@ -245,7 +245,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	if (likely(!timer_stats_active))
 		return;
 
-	lock = &per_cpu(lookup_lock, raw_smp_processor_id());
+	lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id());
 
 	input.timer = timer;
 	input.start_func = startf;
@@ -348,9 +348,10 @@ static void sync_access(void)
 	int cpu;
 
 	for_each_online_cpu(cpu) {
-		spin_lock_irqsave(&per_cpu(lookup_lock, cpu), flags);
+		spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu);
+		spin_lock_irqsave(lock, flags);
 		/* nothing */
-		spin_unlock_irqrestore(&per_cpu(lookup_lock, cpu), flags);
+		spin_unlock_irqrestore(lock, flags);
 	}
 }
 
@@ -408,7 +409,7 @@ void __init init_timer_stats(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		spin_lock_init(&per_cpu(lookup_lock, cpu));
+		spin_lock_init(&per_cpu(tstats_lookup_lock, cpu));
 }
 
 static int __init init_tstats_procfs(void)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 88bd9ae2a9e..c82dfd92fdf 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -86,17 +86,17 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
  */
 static int tracing_disabled = 1;
 
-DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(int, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
 {
 	preempt_disable();
-	local_inc(&__get_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
 }
 
 static inline void ftrace_enable_cpu(void)
 {
-	local_dec(&__get_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
 	preempt_enable();
 }
 
@@ -203,7 +203,7 @@ cycle_t ftrace_now(int cpu)
  */
 static struct trace_array	max_tr;
 
-static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
+static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
 
 /* tracer_enabled is used to toggle activation of a tracer */
 static int			tracer_enabled = 1;
@@ -1085,7 +1085,7 @@ trace_function(struct trace_array *tr,
 	struct ftrace_entry *entry;
 
 	/* If we are reading the ring buffer, don't trace */
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
 		return;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
@@ -4454,7 +4454,7 @@ __init static int tracer_alloc_buffers(void)
 	/* Allocate the first page for all buffers */
 	for_each_tracing_cpu(i) {
 		global_trace.data[i] = &per_cpu(global_trace_cpu, i);
-		max_tr.data[i] = &per_cpu(max_data, i);
+		max_tr.data[i] = &per_cpu(max_tr_data, i);
 	}
 
 	trace_init_cmdlines();
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 7fa33cab696..a52bed2eedd 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -443,7 +443,7 @@ extern int DYN_FTRACE_TEST_NAME(void);
 
 extern int ring_buffer_expanded;
 extern bool tracing_selftest_disabled;
-DECLARE_PER_CPU(local_t, ftrace_cpu_disabled);
+DECLARE_PER_CPU(int, ftrace_cpu_disabled);
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 extern int trace_selftest_startup_function(struct tracer *trace,
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index a43d009c561..b1342c5d37c 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -187,7 +187,7 @@ static int __trace_graph_entry(struct trace_array *tr,
 	struct ring_buffer *buffer = tr->buffer;
 	struct ftrace_graph_ent_entry *entry;
 
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
 		return 0;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
@@ -251,7 +251,7 @@ static void __trace_graph_return(struct trace_array *tr,
 	struct ring_buffer *buffer = tr->buffer;
 	struct ftrace_graph_ret_entry *entry;
 
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
 		return;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index 69543a905cd..7b97000745f 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -20,10 +20,10 @@
 
 #define BTS_BUFFER_SIZE (1 << 13)
 
-static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], buffer);
+static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
+static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
 
-#define this_tracer per_cpu(tracer, smp_processor_id())
+#define this_tracer per_cpu(hwb_tracer, smp_processor_id())
 
 static int trace_hw_branches_enabled __read_mostly;
 static int trace_hw_branches_suspended __read_mostly;
@@ -32,12 +32,13 @@ static struct trace_array *hw_branch_trace __read_mostly;
 
 static void bts_trace_init_cpu(int cpu)
 {
-	per_cpu(tracer, cpu) =
-		ds_request_bts_cpu(cpu, per_cpu(buffer, cpu), BTS_BUFFER_SIZE,
-				   NULL, (size_t)-1, BTS_KERNEL);
+	per_cpu(hwb_tracer, cpu) =
+		ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
+				   BTS_BUFFER_SIZE, NULL, (size_t)-1,
+				   BTS_KERNEL);
 
-	if (IS_ERR(per_cpu(tracer, cpu)))
-		per_cpu(tracer, cpu) = NULL;
+	if (IS_ERR(per_cpu(hwb_tracer, cpu)))
+		per_cpu(hwb_tracer, cpu) = NULL;
 }
 
 static int bts_trace_init(struct trace_array *tr)
@@ -51,7 +52,7 @@ static int bts_trace_init(struct trace_array *tr)
 	for_each_online_cpu(cpu) {
 		bts_trace_init_cpu(cpu);
 
-		if (likely(per_cpu(tracer, cpu)))
+		if (likely(per_cpu(hwb_tracer, cpu)))
 			trace_hw_branches_enabled = 1;
 	}
 	trace_hw_branches_suspended = 0;
@@ -67,9 +68,9 @@ static void bts_trace_reset(struct trace_array *tr)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
-		if (likely(per_cpu(tracer, cpu))) {
-			ds_release_bts(per_cpu(tracer, cpu));
-			per_cpu(tracer, cpu) = NULL;
+		if (likely(per_cpu(hwb_tracer, cpu))) {
+			ds_release_bts(per_cpu(hwb_tracer, cpu));
+			per_cpu(hwb_tracer, cpu) = NULL;
 		}
 	}
 	trace_hw_branches_enabled = 0;
@@ -83,8 +84,8 @@ static void bts_trace_start(struct trace_array *tr)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu)
-		if (likely(per_cpu(tracer, cpu)))
-			ds_resume_bts(per_cpu(tracer, cpu));
+		if (likely(per_cpu(hwb_tracer, cpu)))
+			ds_resume_bts(per_cpu(hwb_tracer, cpu));
 	trace_hw_branches_suspended = 0;
 	put_online_cpus();
 }
@@ -95,8 +96,8 @@ static void bts_trace_stop(struct trace_array *tr)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu)
-		if (likely(per_cpu(tracer, cpu)))
-			ds_suspend_bts(per_cpu(tracer, cpu));
+		if (likely(per_cpu(hwb_tracer, cpu)))
+			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
 	trace_hw_branches_suspended = 1;
 	put_online_cpus();
 }
@@ -114,16 +115,16 @@ static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
 			bts_trace_init_cpu(cpu);
 
 			if (trace_hw_branches_suspended &&
-			    likely(per_cpu(tracer, cpu)))
-				ds_suspend_bts(per_cpu(tracer, cpu));
+			    likely(per_cpu(hwb_tracer, cpu)))
+				ds_suspend_bts(per_cpu(hwb_tracer, cpu));
 		}
 		break;
 
 	case CPU_DOWN_PREPARE:
 		/* The notification is sent with interrupts enabled. */
-		if (likely(per_cpu(tracer, cpu))) {
-			ds_release_bts(per_cpu(tracer, cpu));
-			per_cpu(tracer, cpu) = NULL;
+		if (likely(per_cpu(hwb_tracer, cpu))) {
+			ds_release_bts(per_cpu(hwb_tracer, cpu));
+			per_cpu(hwb_tracer, cpu) = NULL;
 		}
 	}
 
@@ -258,8 +259,8 @@ static void trace_bts_prepare(struct trace_iterator *iter)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu)
-		if (likely(per_cpu(tracer, cpu)))
-			ds_suspend_bts(per_cpu(tracer, cpu));
+		if (likely(per_cpu(hwb_tracer, cpu)))
+			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
 	/*
 	 * We need to collect the trace on the respective cpu since ftrace
 	 * implicitly adds the record for the current cpu.
@@ -268,8 +269,8 @@ static void trace_bts_prepare(struct trace_iterator *iter)
 	on_each_cpu(trace_bts_cpu, iter->tr, 1);
 
 	for_each_online_cpu(cpu)
-		if (likely(per_cpu(tracer, cpu)))
-			ds_resume_bts(per_cpu(tracer, cpu));
+		if (likely(per_cpu(hwb_tracer, cpu)))
+			ds_resume_bts(per_cpu(hwb_tracer, cpu));
 	put_online_cpus();
 }
 
diff --git a/mm/Makefile b/mm/Makefile
index ebf849042ed..82131d0f8d8 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -34,11 +34,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 obj-$(CONFIG_SMP) += percpu.o
-else
-obj-$(CONFIG_SMP) += allocpercpu.o
-endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
deleted file mode 100644
index df34ceae0c6..00000000000
--- a/mm/allocpercpu.c
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * linux/mm/allocpercpu.c
- *
- * Separated from slab.c August 11, 2006 Christoph Lameter
- */
-#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
-#endif
-
-/**
- * percpu_depopulate - depopulate per-cpu data for given cpu
- * @__pdata: per-cpu data to depopulate
- * @cpu: depopulate per-cpu data for this cpu
- *
- * Depopulating per-cpu data for a cpu going offline would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- */
-static void percpu_depopulate(void *__pdata, int cpu)
-{
-	struct percpu_data *pdata = __percpu_disguise(__pdata);
-
-	kfree(pdata->ptrs[cpu]);
-	pdata->ptrs[cpu] = NULL;
-}
-
-/**
- * percpu_depopulate_mask - depopulate per-cpu data for some cpu's
- * @__pdata: per-cpu data to depopulate
- * @mask: depopulate per-cpu data for cpu's selected through mask bits
- */
-static void __percpu_depopulate_mask(void *__pdata, const cpumask_t *mask)
-{
-	int cpu;
-	for_each_cpu_mask_nr(cpu, *mask)
-		percpu_depopulate(__pdata, cpu);
-}
-
-#define percpu_depopulate_mask(__pdata, mask) \
-	__percpu_depopulate_mask((__pdata), &(mask))
-
-/**
- * percpu_populate - populate per-cpu data for given cpu
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @cpu: populate per-data for this cpu
- *
- * Populating per-cpu data for a cpu coming online would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- * Per-cpu object is populated with zeroed buffer.
- */
-static void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
-{
-	struct percpu_data *pdata = __percpu_disguise(__pdata);
-	int node = cpu_to_node(cpu);
-
-	/*
-	 * We should make sure each CPU gets private memory.
-	 */
-	size = roundup(size, cache_line_size());
-
-	BUG_ON(pdata->ptrs[cpu]);
-	if (node_online(node))
-		pdata->ptrs[cpu] = kmalloc_node(size, gfp|__GFP_ZERO, node);
-	else
-		pdata->ptrs[cpu] = kzalloc(size, gfp);
-	return pdata->ptrs[cpu];
-}
-
-/**
- * percpu_populate_mask - populate per-cpu data for more cpu's
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @mask: populate per-cpu data for cpu's selected through mask bits
- *
- * Per-cpu objects are populated with zeroed buffers.
- */
-static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
-				  cpumask_t *mask)
-{
-	cpumask_t populated;
-	int cpu;
-
-	cpus_clear(populated);
-	for_each_cpu_mask_nr(cpu, *mask)
-		if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) {
-			__percpu_depopulate_mask(__pdata, &populated);
-			return -ENOMEM;
-		} else
-			cpu_set(cpu, populated);
-	return 0;
-}
-
-#define percpu_populate_mask(__pdata, size, gfp, mask) \
-	__percpu_populate_mask((__pdata), (size), (gfp), &(mask))
-
-/**
- * alloc_percpu - initial setup of per-cpu data
- * @size: size of per-cpu object
- * @align: alignment
- *
- * Allocate dynamic percpu area.  Percpu objects are populated with
- * zeroed buffers.
- */
-void *__alloc_percpu(size_t size, size_t align)
-{
-	/*
-	 * We allocate whole cache lines to avoid false sharing
-	 */
-	size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size());
-	void *pdata = kzalloc(sz, GFP_KERNEL);
-	void *__pdata = __percpu_disguise(pdata);
-
-	/*
-	 * Can't easily make larger alignment work with kmalloc.  WARN
-	 * on it.  Larger alignment should only be used for module
-	 * percpu sections on SMP for which this path isn't used.
-	 */
-	WARN_ON_ONCE(align > SMP_CACHE_BYTES);
-
-	if (unlikely(!pdata))
-		return NULL;
-	if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL,
-					   &cpu_possible_map)))
-		return __pdata;
-	kfree(pdata);
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-/**
- * free_percpu - final cleanup of per-cpu data
- * @__pdata: object to clean up
- *
- * We simply clean up any per-cpu object left. No need for the client to
- * track and specify through a bis mask which per-cpu objects are to free.
- */
-void free_percpu(void *__pdata)
-{
-	if (unlikely(!__pdata))
-		return;
-	__percpu_depopulate_mask(__pdata, cpu_possible_mask);
-	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 5adfc268b40..442010cc91c 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -46,8 +46,6 @@
  *
  * To use this allocator, arch code should do the followings.
  *
- * - 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
  *   different from the default
@@ -74,6 +72,7 @@
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
+#include <asm/io.h>
 
 #define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
 #define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */
@@ -1302,6 +1301,27 @@ void free_percpu(void *ptr)
 }
 EXPORT_SYMBOL_GPL(free_percpu);
 
+/**
+ * per_cpu_ptr_to_phys - convert translated percpu address to physical address
+ * @addr: the address to be converted to physical address
+ *
+ * Given @addr which is dereferenceable address obtained via one of
+ * percpu access macros, this function translates it into its physical
+ * address.  The caller is responsible for ensuring @addr stays valid
+ * until this function finishes.
+ *
+ * RETURNS:
+ * The physical address for @addr.
+ */
+phys_addr_t per_cpu_ptr_to_phys(void *addr)
+{
+	if ((unsigned long)addr < VMALLOC_START ||
+			(unsigned long)addr >= VMALLOC_END)
+		return __pa(addr);
+	else
+		return page_to_phys(vmalloc_to_page(addr));
+}
+
 static inline size_t pcpu_calc_fc_sizes(size_t static_size,
 					size_t reserved_size,
 					ssize_t *dyn_sizep)
diff --git a/mm/slab.c b/mm/slab.c
index a6c9166996a..29b09599af7 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -697,7 +697,7 @@ static inline void init_lock_keys(void)
 static DEFINE_MUTEX(cache_chain_mutex);
 static struct list_head cache_chain;
 
-static DEFINE_PER_CPU(struct delayed_work, reap_work);
+static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
 
 static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {
@@ -838,7 +838,7 @@ __setup("noaliencache", noaliencache_setup);
  * objects freed on different nodes from which they were allocated) and the
  * flushing of remote pcps by calling drain_node_pages.
  */
-static DEFINE_PER_CPU(unsigned long, reap_node);
+static DEFINE_PER_CPU(unsigned long, slab_reap_node);
 
 static void init_reap_node(int cpu)
 {
@@ -848,17 +848,17 @@ static void init_reap_node(int cpu)
 	if (node == MAX_NUMNODES)
 		node = first_node(node_online_map);
 
-	per_cpu(reap_node, cpu) = node;
+	per_cpu(slab_reap_node, cpu) = node;
 }
 
 static void next_reap_node(void)
 {
-	int node = __get_cpu_var(reap_node);
+	int node = __get_cpu_var(slab_reap_node);
 
 	node = next_node(node, node_online_map);
 	if (unlikely(node >= MAX_NUMNODES))
 		node = first_node(node_online_map);
-	__get_cpu_var(reap_node) = node;
+	__get_cpu_var(slab_reap_node) = node;
 }
 
 #else
@@ -875,7 +875,7 @@ static void next_reap_node(void)
  */
 static void __cpuinit start_cpu_timer(int cpu)
 {
-	struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
+	struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
 
 	/*
 	 * When this gets called from do_initcalls via cpucache_init(),
@@ -1039,7 +1039,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
  */
 static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
 {
-	int node = __get_cpu_var(reap_node);
+	int node = __get_cpu_var(slab_reap_node);
 
 	if (l3->alien) {
 		struct array_cache *ac = l3->alien[node];
@@ -1300,9 +1300,9 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 		 * anything expensive but will only modify reap_work
 		 * and reschedule the timer.
 		*/
-		cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
+		cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu));
 		/* Now the cache_reaper is guaranteed to be not running. */
-		per_cpu(reap_work, cpu).work.func = NULL;
+		per_cpu(slab_reap_work, cpu).work.func = NULL;
   		break;
   	case CPU_DOWN_FAILED:
   	case CPU_DOWN_FAILED_FROZEN:
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 0f551a4a44c..9b08d790df6 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -761,7 +761,7 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask)
 	spin_lock(&vbq->lock);
 	list_add(&vb->free_list, &vbq->free);
 	spin_unlock(&vbq->lock);
-	put_cpu_var(vmap_cpu_blocks);
+	put_cpu_var(vmap_block_queue);
 
 	return vb;
 }
@@ -826,7 +826,7 @@ again:
 		}
 		spin_unlock(&vb->lock);
 	}
-	put_cpu_var(vmap_cpu_blocks);
+	put_cpu_var(vmap_block_queue);
 	rcu_read_unlock();
 
 	if (!addr) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c81321f9fee..dad2327e458 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -883,11 +883,10 @@ static void vmstat_update(struct work_struct *w)
 
 static void __cpuinit start_cpu_timer(int cpu)
 {
-	struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
+	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
 
-	INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
-	schedule_delayed_work_on(cpu, vmstat_work,
-				 __round_jiffies_relative(HZ, cpu));
+	INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update);
+	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
 }
 
 /*