Merge remote branch 'percpu/for-next'

30 files changed, 767 insertions, 552 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 1ee596cd942f..2d7f56a98e0f 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 688a812c017d..61c7b1750b16 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 8840a690d1e7..69bf13857a9f 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/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index baec6f00f7f3..40574ae11401 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/setup.c b/arch/ia64/kernel/setup.c
index 1de86c96801d..bc1ef4ae828c 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -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.
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 0a0c77b2c988..1295ba327f6f 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 2f724d2bf299..54bf54059811 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 d85ba98d9008..40e4c1fbf76b 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.
@@ -666,9 +764,9 @@ 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 1857766a63c1..b9609c69343a 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/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index b65a36defeb7..8b5ec19bdef4 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -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/crypto/cryptd.c b/crypto/cryptd.c
index 35335825a4ef..3d7fe8306e2a 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/dma/dmaengine.c b/drivers/dma/dmaengine.c
index bd0b248de2cf..51d7480d3a92 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);
 
@@ -847,7 +840,6 @@ 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);
@@ -866,10 +858,10 @@ 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;
 }
@@ -896,7 +888,6 @@ 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);
@@ -913,10 +904,10 @@ 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;
 }
@@ -945,7 +936,6 @@ 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);
@@ -963,10 +953,10 @@ 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 4b89b791be6a..42be0b15084b 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/net/chelsio/sge.c b/drivers/net/chelsio/sge.c
index 8c658cf6f62f..109d2783e4d8 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 1bc654a73c47..8ebeb76a373d 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 ade5b344f75d..0c4a81124257 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -153,7 +153,7 @@ 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;
 
 	skb_orphan(skb);
 
@@ -161,9 +161,8 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *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/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index bba12824defa..d527fd384582 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3932,7 +3932,7 @@ 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 ceda50aad73c..46d779abafd3 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 8b6c9e807efb..ccafe8ef7ad5 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 90079c373f1c..8087b90d4673 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.h b/include/linux/percpu.h
index 878836ca999c..3d9ba92b104f 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)
 
@@ -130,28 +128,6 @@ 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);
 
@@ -243,4 +219,404 @@ 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 __size_call_return(stem, variable)				\
+({	typeof(variable) ret__;						\
+	switch(sizeof(variable)) {					\
+	case 1: ret__ = stem##1(variable);break;			\
+	case 2: ret__ = stem##2(variable);break;			\
+	case 4: ret__ = stem##4(variable);break;			\
+	case 8: ret__ = stem##8(variable);break;			\
+	default:							\
+		__bad_size_call_parameter();break;			\
+	}								\
+	ret__;								\
+})
+
+#define __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)	__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)	__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)		__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)		__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)		__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)		__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)	__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)	__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)	__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)	__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)	__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)	__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) __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) __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) __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) __size_call(irqsafe_cpu_xor_, (val))
+#endif
+
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 2d0f222388a8..d85889710f9b 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 3817fda82a80..f28403ff7648 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -90,12 +90,7 @@ 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
 {
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index cbdd6284996d..dde549779e42 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -295,11 +295,11 @@ 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 8c842e06bec8..f0d756f2ac99 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/module.c b/kernel/module.c
index 8b7d8805819d..64787cddeb5e 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 697c0a0229d4..5595214358f3 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -729,13 +729,13 @@ 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);
 }
@@ -784,13 +784,13 @@ 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/mm/Makefile b/mm/Makefile
index e3980c2126ec..1f6e10c384cc 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -35,11 +35,7 @@ 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 df34ceae0c67..000000000000
--- 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 4a048abad043..ec158bb5f86d 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
@@ -1870,13 +1868,14 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
 	max_distance = 0;
 	for (group = 0; group < ai->nr_groups; group++) {
 		ai->groups[group].base_offset = areas[group] - base;
-		max_distance = max(max_distance, ai->groups[group].base_offset);
+		max_distance = max_t(size_t, max_distance,
+				     ai->groups[group].base_offset);
 	}
 	max_distance += ai->unit_size;
 
 	/* warn if maximum distance is further than 75% of vmalloc space */
 	if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) {
-		pr_warning("PERCPU: max_distance=0x%lx too large for vmalloc "
+		pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc "
 			   "space 0x%lx\n",
 			   max_distance, VMALLOC_END - VMALLOC_START);
 #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK