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

37 files changed, 592 insertions, 372 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);
 }