Merge remote branch 'percpu/for-next'

10 files changed, 299 insertions, 81 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)				\
 ({									\