Merge branch 'tj-percpu' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc into core/percpu

Conflicts:
	arch/x86/include/asm/pgtable.h

arch/alpha/mm/init.c

@@ -189,9 +189,21 @@ callback_init(void * kernel_end)
 
 	if (alpha_using_srm) {
 		static struct vm_struct console_remap_vm;
-		unsigned long vaddr = VMALLOC_START;
+		unsigned long nr_pages = 0;
+		unsigned long vaddr;
 		unsigned long i, j;
 
+		/* calculate needed size */
+		for (i = 0; i < crb->map_entries; ++i)
+			nr_pages += crb->map[i].count;
+
+		/* register the vm area */
+		console_remap_vm.flags = VM_ALLOC;
+		console_remap_vm.size = nr_pages << PAGE_SHIFT;
+		vm_area_register_early(&console_remap_vm, PAGE_SIZE);
+
+		vaddr = (unsigned long)consle_remap_vm.addr;
+
 		/* Set up the third level PTEs and update the virtual
 		   addresses of the CRB entries.  */
 		for (i = 0; i < crb->map_entries; ++i) {
@@ -213,12 +225,6 @@ callback_init(void * kernel_end)
 				vaddr += PAGE_SIZE;
 			}
 		}
-
-		/* Let vmalloc know that we've allocated some space.  */
-		console_remap_vm.flags = VM_ALLOC;
-		console_remap_vm.addr = (void *) VMALLOC_START;
-		console_remap_vm.size = vaddr - VMALLOC_START;
-		vmlist = &console_remap_vm;
 	}
 
 	callback_init_done = 1;

arch/avr32/Kconfig

@@ -181,7 +181,7 @@ source "kernel/Kconfig.preempt"
 config QUICKLIST
 	def_bool y
 
-config HAVE_ARCH_BOOTMEM_NODE
+config HAVE_ARCH_BOOTMEM
 	def_bool n
 
 config ARCH_HAVE_MEMORY_PRESENT

arch/x86/Kconfig

@@ -135,6 +135,9 @@ config ARCH_HAS_CACHE_LINE_SIZE
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 
+config HAVE_DYNAMIC_PER_CPU_AREA
+	def_bool y
+
 config HAVE_CPUMASK_OF_CPU_MAP
 	def_bool X86_64_SMP
 
@@ -1122,7 +1125,7 @@ config NODES_SHIFT
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accomodate various tables.
 
-config HAVE_ARCH_BOOTMEM_NODE
+config HAVE_ARCH_BOOTMEM
 	def_bool y
 	depends on X86_32 && NUMA
 

arch/x86/include/asm/mmzone_32.h

@@ -91,45 +91,12 @@ static inline int pfn_valid(int pfn)
 #endif /* CONFIG_DISCONTIGMEM */
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
-
+/* always use node 0 for bootmem on this numa platform */
-/*
+#define alloc_bootmem_core(__bdata, size, align, goal, limit)		\
- * Following are macros that are specific to this numa platform.
- */
-#define reserve_bootmem(addr, size, flags) \
-	reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags))
-#define alloc_bootmem(x) \
-	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_nopanic(x) \
-	__alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \
-				__pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low(x) \
-	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0)
-#define alloc_bootmem_pages(x) \
-	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_pages_nopanic(x) \
-	__alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \
-				__pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low_pages(x) \
-	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
-#define alloc_bootmem_node(pgdat, x)					\
 ({									\
-	struct pglist_data  __maybe_unused			\
+	bootmem_data_t __maybe_unused *	__abm_bdata_dummy = (__bdata);	\
-				*__alloc_bootmem_node__pgdat = (pgdat);	\
+	__alloc_bootmem_core(NODE_DATA(0)->bdata,			\
-	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES,	\
+			     (size), (align), (goal), (limit));		\
-						__pa(MAX_DMA_ADDRESS));	\
-})
-#define alloc_bootmem_pages_node(pgdat, x)				\
-({									\
-	struct pglist_data  __maybe_unused			\
-				*__alloc_bootmem_node__pgdat = (pgdat);	\
-	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE,		\
-						__pa(MAX_DMA_ADDRESS));	\
-})
-#define alloc_bootmem_low_pages_node(pgdat, x)				\
-({									\
-	struct pglist_data  __maybe_unused			\
-				*__alloc_bootmem_node__pgdat = (pgdat);	\
-	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0);		\
 })
 #endif /* CONFIG_NEED_MULTIPLE_NODES */
 

arch/x86/include/asm/percpu.h

@@ -43,6 +43,14 @@
 #else /* ...!ASSEMBLY */
 
 #include <linux/stringify.h>
+#include <asm/sections.h>
+
+#define __addr_to_pcpu_ptr(addr)					\
+	(void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr	\
+		 + (unsigned long)__per_cpu_start)
+#define __pcpu_ptr_to_addr(ptr)						\
+	(void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr	\
+		 - (unsigned long)__per_cpu_start)
 
 #ifdef CONFIG_SMP
 #define __percpu_arg(x)		"%%"__stringify(__percpu_seg)":%P" #x

arch/x86/include/asm/pgtable.h

@@ -288,6 +288,8 @@ static inline int is_new_memtype_allowed(unsigned long flags,
 	return 1;
 }
 
+pmd_t *populate_extra_pmd(unsigned long vaddr);
+pte_t *populate_extra_pte(unsigned long vaddr);
 #endif	/* __ASSEMBLY__ */
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c

@@ -601,7 +601,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (!data)
 		return -ENOMEM;
 
-	data->acpi_data = percpu_ptr(acpi_perf_data, cpu);
+	data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
 	per_cpu(drv_data, cpu) = data;
 
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))

arch/x86/kernel/irq_32.c

@@ -16,6 +16,7 @@
 #include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/uaccess.h>
+#include <linux/percpu.h>
 
 #include <asm/apic.h>
 
@@ -55,13 +56,13 @@ static inline void print_stack_overflow(void) { }
 union irq_ctx {
 	struct thread_info      tinfo;
 	u32                     stack[THREAD_SIZE/sizeof(u32)];
-};
+} __attribute__((aligned(PAGE_SIZE)));
 
-static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly;
+static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
-static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly;
+static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
 
-static char softirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss;
+static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, hardirq_stack);
-static char hardirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss;
+static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, softirq_stack);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -81,7 +82,7 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 	u32 *isp, arg1, arg2;
 
 	curctx = (union irq_ctx *) current_thread_info();
-	irqctx = hardirq_ctx[smp_processor_id()];
+	irqctx = __get_cpu_var(hardirq_ctx);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -125,34 +126,34 @@ void __cpuinit irq_ctx_init(int cpu)
 {
 	union irq_ctx *irqctx;
 
-	if (hardirq_ctx[cpu])
+	if (per_cpu(hardirq_ctx, cpu))
 		return;
 
-	irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE];
+	irqctx = &per_cpu(hardirq_stack, cpu);
 	irqctx->tinfo.task		= NULL;
 	irqctx->tinfo.exec_domain	= NULL;
 	irqctx->tinfo.cpu		= cpu;
 	irqctx->tinfo.preempt_count	= HARDIRQ_OFFSET;
 	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
 
-	hardirq_ctx[cpu] = irqctx;
+	per_cpu(hardirq_ctx, cpu) = irqctx;
 
-	irqctx = (union irq_ctx *) &softirq_stack[cpu*THREAD_SIZE];
+	irqctx = &per_cpu(softirq_stack, cpu);
 	irqctx->tinfo.task		= NULL;
 	irqctx->tinfo.exec_domain	= NULL;
 	irqctx->tinfo.cpu		= cpu;
 	irqctx->tinfo.preempt_count	= 0;
 	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
 
-	softirq_ctx[cpu] = irqctx;
+	per_cpu(softirq_ctx, cpu) = irqctx;
 
 	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
-	       cpu, hardirq_ctx[cpu], softirq_ctx[cpu]);
+	       cpu, per_cpu(hardirq_ctx, cpu),  per_cpu(softirq_ctx, cpu));
 }
 
 void irq_ctx_exit(int cpu)
 {
-	hardirq_ctx[cpu] = NULL;
+	per_cpu(hardirq_ctx, cpu) = NULL;
 }
 
 asmlinkage void do_softirq(void)
@@ -169,7 +170,7 @@ asmlinkage void do_softirq(void)
 
 	if (local_softirq_pending()) {
 		curctx = current_thread_info();
-		irqctx = softirq_ctx[smp_processor_id()];
+		irqctx = __get_cpu_var(softirq_ctx);
 		irqctx->tinfo.task = curctx->task;
 		irqctx->tinfo.previous_esp = current_stack_pointer;
 

arch/x86/kernel/setup_percpu.c

@@ -7,6 +7,7 @@
 #include <linux/crash_dump.h>
 #include <linux/smp.h>
 #include <linux/topology.h>
+#include <linux/pfn.h>
 #include <asm/sections.h>
 #include <asm/processor.h>
 #include <asm/setup.h>
@@ -41,6 +42,321 @@ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
 };
 EXPORT_SYMBOL(__per_cpu_offset);
 
+/**
+ * pcpu_need_numa - determine percpu allocation needs to consider NUMA
+ *
+ * If NUMA is not configured or there is only one NUMA node available,
+ * there is no reason to consider NUMA.  This function determines
+ * whether percpu allocation should consider NUMA or not.
+ *
+ * RETURNS:
+ * true if NUMA should be considered; otherwise, false.
+ */
+static bool __init pcpu_need_numa(void)
+{
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	pg_data_t *last = NULL;
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		int node = early_cpu_to_node(cpu);
+
+		if (node_online(node) && NODE_DATA(node) &&
+		    last && last != NODE_DATA(node))
+			return true;
+
+		last = NODE_DATA(node);
+	}
+#endif
+	return false;
+}
+
+/**
+ * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
+ * @cpu: cpu to allocate for
+ * @size: size allocation in bytes
+ * @align: alignment
+ *
+ * Allocate @size bytes aligned at @align for cpu @cpu.  This wrapper
+ * does the right thing for NUMA regardless of the current
+ * configuration.
+ *
+ * RETURNS:
+ * Pointer to the allocated area on success, NULL on failure.
+ */
+static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
+					unsigned long align)
+{
+	const unsigned long goal = __pa(MAX_DMA_ADDRESS);
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	int node = early_cpu_to_node(cpu);
+	void *ptr;
+
+	if (!node_online(node) || !NODE_DATA(node)) {
+		ptr = __alloc_bootmem_nopanic(size, align, goal);
+		pr_info("cpu %d has no node %d or node-local memory\n",
+			cpu, node);
+		pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
+			 cpu, size, __pa(ptr));
+	} else {
+		ptr = __alloc_bootmem_node_nopanic(NODE_DATA(node),
+						   size, align, goal);
+		pr_debug("per cpu data for cpu%d %lu bytes on node%d at "
+			 "%016lx\n", cpu, size, node, __pa(ptr));
+	}
+	return ptr;
+#else
+	return __alloc_bootmem_nopanic(size, align, goal);
+#endif
+}
+
+/*
+ * Remap allocator
+ *
+ * This allocator uses PMD page as unit.  A PMD page is allocated for
+ * each cpu and each is remapped into vmalloc area using PMD mapping.
+ * As PMD page is quite large, only part of it is used for the first
+ * chunk.  Unused part is returned to the bootmem allocator.
+ *
+ * So, the PMD pages are mapped twice - once to the physical mapping
+ * and to the vmalloc area for the first percpu chunk.  The double
+ * mapping does add one more PMD TLB entry pressure but still is much
+ * better than only using 4k mappings while still being NUMA friendly.
+ */
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+static size_t pcpur_size __initdata;
+static void **pcpur_ptrs __initdata;
+
+static struct page * __init pcpur_get_page(unsigned int cpu, int pageno)
+{
+	size_t off = (size_t)pageno << PAGE_SHIFT;
+
+	if (off >= pcpur_size)
+		return NULL;
+
+	return virt_to_page(pcpur_ptrs[cpu] + off);
+}
+
+static ssize_t __init setup_pcpu_remap(size_t static_size)
+{
+	static struct vm_struct vm;
+	pg_data_t *last;
+	size_t ptrs_size;
+	unsigned int cpu;
+	ssize_t ret;
+
+	/*
+	 * If large page isn't supported, there's no benefit in doing
+	 * this.  Also, on non-NUMA, embedding is better.
+	 */
+	if (!cpu_has_pse || pcpu_need_numa())
+		return -EINVAL;
+
+	last = NULL;
+	for_each_possible_cpu(cpu) {
+		int node = early_cpu_to_node(cpu);
+
+		if (node_online(node) && NODE_DATA(node) &&
+		    last && last != NODE_DATA(node))
+			goto proceed;
+
+		last = NODE_DATA(node);
+	}
+	return -EINVAL;
+
+proceed:
+	/*
+	 * Currently supports only single page.  Supporting multiple
+	 * pages won't be too difficult if it ever becomes necessary.
+	 */
+	pcpur_size = PFN_ALIGN(static_size + PERCPU_DYNAMIC_RESERVE);
+	if (pcpur_size > PMD_SIZE) {
+		pr_warning("PERCPU: static data is larger than large page, "
+			   "can't use large page\n");
+		return -EINVAL;
+	}
+
+	/* allocate pointer array and alloc large pages */
+	ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0]));
+	pcpur_ptrs = alloc_bootmem(ptrs_size);
+
+	for_each_possible_cpu(cpu) {
+		pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PMD_SIZE, PMD_SIZE);
+		if (!pcpur_ptrs[cpu])
+			goto enomem;
+
+		/*
+		 * Only use pcpur_size bytes and give back the rest.
+		 *
+		 * Ingo: The 2MB up-rounding bootmem is needed to make
+		 * sure the partial 2MB page is still fully RAM - it's
+		 * not well-specified to have a PAT-incompatible area
+		 * (unmapped RAM, device memory, etc.) in that hole.
+		 */
+		free_bootmem(__pa(pcpur_ptrs[cpu] + pcpur_size),
+			     PMD_SIZE - pcpur_size);
+
+		memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size);
+	}
+
+	/* allocate address and map */
+	vm.flags = VM_ALLOC;
+	vm.size = num_possible_cpus() * PMD_SIZE;
+	vm_area_register_early(&vm, PMD_SIZE);
+
+	for_each_possible_cpu(cpu) {
+		pmd_t *pmd;
+
+		pmd = populate_extra_pmd((unsigned long)vm.addr
+					 + cpu * PMD_SIZE);
+		set_pmd(pmd, pfn_pmd(page_to_pfn(virt_to_page(pcpur_ptrs[cpu])),
+				     PAGE_KERNEL_LARGE));
+	}
+
+	/* we're ready, commit */
+	pr_info("PERCPU: Remapped at %p with large pages, static data "
+		"%zu bytes\n", vm.addr, static_size);
+
+	ret = pcpu_setup_first_chunk(pcpur_get_page, static_size, PMD_SIZE,
+				     pcpur_size - static_size, vm.addr, NULL);
+	goto out_free_ar;
+
+enomem:
+	for_each_possible_cpu(cpu)
+		if (pcpur_ptrs[cpu])
+			free_bootmem(__pa(pcpur_ptrs[cpu]), PMD_SIZE);
+	ret = -ENOMEM;
+out_free_ar:
+	free_bootmem(__pa(pcpur_ptrs), ptrs_size);
+	return ret;
+}
+#else
+static ssize_t __init setup_pcpu_remap(size_t static_size)
+{
+	return -EINVAL;
+}
+#endif
+
+/*
+ * Embedding allocator
+ *
+ * The first chunk is sized to just contain the static area plus
+ * PERCPU_DYNAMIC_RESERVE and allocated as a contiguous area using
+ * bootmem allocator and used as-is without being mapped into vmalloc
+ * area.  This enables the first chunk to piggy back on the linear
+ * physical PMD mapping and doesn't add any additional pressure to
+ * TLB.
+ */
+static void *pcpue_ptr __initdata;
+static size_t pcpue_unit_size __initdata;
+
+static struct page * __init pcpue_get_page(unsigned int cpu, int pageno)
+{
+	return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size
+			    + ((size_t)pageno << PAGE_SHIFT));
+}
+
+static ssize_t __init setup_pcpu_embed(size_t static_size)
+{
+	unsigned int cpu;
+
+	/*
+	 * If large page isn't supported, there's no benefit in doing
+	 * this.  Also, embedding allocation doesn't play well with
+	 * NUMA.
+	 */
+	if (!cpu_has_pse || pcpu_need_numa())
+		return -EINVAL;
+
+	/* allocate and copy */
+	pcpue_unit_size = PFN_ALIGN(static_size + PERCPU_DYNAMIC_RESERVE);
+	pcpue_unit_size = max(pcpue_unit_size, PCPU_MIN_UNIT_SIZE);
+	pcpue_ptr = pcpu_alloc_bootmem(0, num_possible_cpus() * pcpue_unit_size,
+				       PAGE_SIZE);
+	if (!pcpue_ptr)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu)
+		memcpy(pcpue_ptr + cpu * pcpue_unit_size, __per_cpu_load,
+		       static_size);
+
+	/* we're ready, commit */
+	pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n",
+		pcpue_unit_size >> PAGE_SHIFT, pcpue_ptr, static_size);
+
+	return pcpu_setup_first_chunk(pcpue_get_page, static_size,
+				      pcpue_unit_size,
+				      pcpue_unit_size - static_size, pcpue_ptr,
+				      NULL);
+}
+
+/*
+ * 4k page allocator
+ *
+ * This is the basic allocator.  Static percpu area is allocated
+ * page-by-page and most of initialization is done by the generic
+ * setup function.
+ */
+static struct page **pcpu4k_pages __initdata;
+static int pcpu4k_nr_static_pages __initdata;
+
+static struct page * __init pcpu4k_get_page(unsigned int cpu, int pageno)
+{
+	if (pageno < pcpu4k_nr_static_pages)
+		return pcpu4k_pages[cpu * pcpu4k_nr_static_pages + pageno];
+	return NULL;
+}
+
+static void __init pcpu4k_populate_pte(unsigned long addr)
+{
+	populate_extra_pte(addr);
+}
+
+static ssize_t __init setup_pcpu_4k(size_t static_size)
+{
+	size_t pages_size;
+	unsigned int cpu;
+	int i, j;
+	ssize_t ret;
+
+	pcpu4k_nr_static_pages = PFN_UP(static_size);
+
+	/* unaligned allocations can't be freed, round up to page size */
+	pages_size = PFN_ALIGN(pcpu4k_nr_static_pages * num_possible_cpus()
+			       * sizeof(pcpu4k_pages[0]));
+	pcpu4k_pages = alloc_bootmem(pages_size);
+
+	/* allocate and copy */
+	j = 0;
+	for_each_possible_cpu(cpu)
+		for (i = 0; i < pcpu4k_nr_static_pages; i++) {
+			void *ptr;
+
+			ptr = pcpu_alloc_bootmem(cpu, PAGE_SIZE, PAGE_SIZE);
+			if (!ptr)
+				goto enomem;
+
+			memcpy(ptr, __per_cpu_load + i * PAGE_SIZE, PAGE_SIZE);
+			pcpu4k_pages[j++] = virt_to_page(ptr);
+		}
+
+	/* we're ready, commit */
+	pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n",
+		pcpu4k_nr_static_pages, static_size);
+
+	ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size, 0, 0, NULL,
+				     pcpu4k_populate_pte);
+	goto out_free_ar;
+
+enomem:
+	while (--j >= 0)
+		free_bootmem(__pa(page_address(pcpu4k_pages[j])), PAGE_SIZE);
+	ret = -ENOMEM;
+out_free_ar:
+	free_bootmem(__pa(pcpu4k_pages), pages_size);
+	return ret;
+}
+
 static inline void setup_percpu_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
@@ -61,38 +377,35 @@ static inline void setup_percpu_segment(int cpu)
  */
 void __init setup_per_cpu_areas(void)
 {
-	ssize_t size;
+	size_t static_size = __per_cpu_end - __per_cpu_start;
-	char *ptr;
+	unsigned int cpu;
-	int cpu;
+	unsigned long delta;
-
+	size_t pcpu_unit_size;
-	/* Copy section for each CPU (we discard the original) */
+	ssize_t ret;
-	size = roundup(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
 
 	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
 		NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
 
-	pr_info("PERCPU: Allocating %zd bytes of per cpu data\n", size);
+	/*
+	 * Allocate percpu area.  If PSE is supported, try to make use
+	 * of large page mappings.  Please read comments on top of
+	 * each allocator for details.
+	 */
+	ret = setup_pcpu_remap(static_size);
+	if (ret < 0)
+		ret = setup_pcpu_embed(static_size);
+	if (ret < 0)
+		ret = setup_pcpu_4k(static_size);
+	if (ret < 0)
+		panic("cannot allocate static percpu area (%zu bytes, err=%zd)",
+		      static_size, ret);
 
+	pcpu_unit_size = ret;
+
+	/* alrighty, percpu areas up and running */
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu) {
-#ifndef CONFIG_NEED_MULTIPLE_NODES
+		per_cpu_offset(cpu) = delta + cpu * pcpu_unit_size;
-		ptr = alloc_bootmem_pages(size);
-#else
-		int node = early_cpu_to_node(cpu);
-		if (!node_online(node) || !NODE_DATA(node)) {
-			ptr = alloc_bootmem_pages(size);
-			pr_info("cpu %d has no node %d or node-local memory\n",
-				cpu, node);
-			pr_debug("per cpu data for cpu%d at %016lx\n",
-				 cpu, __pa(ptr));
-		} else {
-			ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
-			pr_debug("per cpu data for cpu%d on node%d at %016lx\n",
-				cpu, node, __pa(ptr));
-		}
-#endif
-
-		memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start);
-		per_cpu_offset(cpu) = ptr - __per_cpu_start;
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
 		per_cpu(cpu_number, cpu) = cpu;
 		setup_percpu_segment(cpu);

arch/x86/mm/init_32.c

@@ -137,6 +137,23 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 	return pte_offset_kernel(pmd, 0);
 }
 
+pmd_t * __init populate_extra_pmd(unsigned long vaddr)
+{
+	int pgd_idx = pgd_index(vaddr);
+	int pmd_idx = pmd_index(vaddr);
+
+	return one_md_table_init(swapper_pg_dir + pgd_idx) + pmd_idx;
+}
+
+pte_t * __init populate_extra_pte(unsigned long vaddr)
+{
+	int pte_idx = pte_index(vaddr);
+	pmd_t *pmd;
+
+	pmd = populate_extra_pmd(vaddr);
+	return one_page_table_init(pmd) + pte_idx;
+}
+
 static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
 					   unsigned long vaddr, pte_t *lastpte)
 {

arch/x86/mm/init_64.c

@@ -168,34 +168,51 @@ static __ref void *spp_getpage(void)
 	return ptr;
 }
 
-void
+static pud_t * __init fill_pud(pgd_t *pgd, unsigned long vaddr)
-set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
+{
+	if (pgd_none(*pgd)) {
+		pud_t *pud = (pud_t *)spp_getpage();
+		pgd_populate(&init_mm, pgd, pud);
+		if (pud != pud_offset(pgd, 0))
+			printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n",
+			       pud, pud_offset(pgd, 0));
+	}
+	return pud_offset(pgd, vaddr);
+}
+
+static pmd_t * __init fill_pmd(pud_t *pud, unsigned long vaddr)
+{
+	if (pud_none(*pud)) {
+		pmd_t *pmd = (pmd_t *) spp_getpage();
+		pud_populate(&init_mm, pud, pmd);
+		if (pmd != pmd_offset(pud, 0))
+			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
+			       pmd, pmd_offset(pud, 0));
+	}
+	return pmd_offset(pud, vaddr);
+}
+
+static pte_t * __init fill_pte(pmd_t *pmd, unsigned long vaddr)
+{
+	if (pmd_none(*pmd)) {
+		pte_t *pte = (pte_t *) spp_getpage();
+		pmd_populate_kernel(&init_mm, pmd, pte);
+		if (pte != pte_offset_kernel(pmd, 0))
+			printk(KERN_ERR "PAGETABLE BUG #02!\n");
+	}
+	return pte_offset_kernel(pmd, vaddr);
+}
+
+void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
 {
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
 	pud = pud_page + pud_index(vaddr);
-	if (pud_none(*pud)) {
+	pmd = fill_pmd(pud, vaddr);
-		pmd = (pmd_t *) spp_getpage();
+	pte = fill_pte(pmd, vaddr);
-		pud_populate(&init_mm, pud, pmd);
-		if (pmd != pmd_offset(pud, 0)) {
-			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
-				pmd, pmd_offset(pud, 0));
-			return;
-		}
-	}
-	pmd = pmd_offset(pud, vaddr);
-	if (pmd_none(*pmd)) {
-		pte = (pte_t *) spp_getpage();
-		pmd_populate_kernel(&init_mm, pmd, pte);
-		if (pte != pte_offset_kernel(pmd, 0)) {
-			printk(KERN_ERR "PAGETABLE BUG #02!\n");
-			return;
-		}
-	}
 
-	pte = pte_offset_kernel(pmd, vaddr);
 	set_pte(pte, new_pte);
 
 	/*
@@ -205,8 +222,7 @@ set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
 	__flush_tlb_one(vaddr);
 }
 
-void
+void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
-set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 {
 	pgd_t *pgd;
 	pud_t *pud_page;
@@ -223,6 +239,24 @@ set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 	set_pte_vaddr_pud(pud_page, vaddr, pteval);
 }
 
+pmd_t * __init populate_extra_pmd(unsigned long vaddr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	pgd = pgd_offset_k(vaddr);
+	pud = fill_pud(pgd, vaddr);
+	return fill_pmd(pud, vaddr);
+}
+
+pte_t * __init populate_extra_pte(unsigned long vaddr)
+{
+	pmd_t *pmd;
+
+	pmd = populate_extra_pmd(vaddr);
+	return fill_pte(pmd, vaddr);
+}
+
 /*
  * Create large page table mappings for a range of physical addresses.
  */

block/blktrace.c

@@ -363,7 +363,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->sequence)
 		goto err;
 
-	bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG);
+	bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
 	if (!bt->msg_data)
 		goto err;
 

drivers/acpi/processor_perflib.c

@@ -516,12 +516,12 @@ int acpi_processor_preregister_performance(
 			continue;
 		}
 
-		if (!performance || !percpu_ptr(performance, i)) {
+		if (!performance || !per_cpu_ptr(performance, i)) {
 			retval = -EINVAL;
 			continue;
 		}
 
-		pr->performance = percpu_ptr(performance, i);
+		pr->performance = per_cpu_ptr(performance, i);
 		cpumask_set_cpu(i, pr->performance->shared_cpu_map);
 		if (acpi_processor_get_psd(pr)) {
 			retval = -EINVAL;

include/linux/bootmem.h

@@ -65,21 +65,18 @@ extern void free_bootmem(unsigned long addr, unsigned long size);
 #define BOOTMEM_DEFAULT		0
 #define BOOTMEM_EXCLUSIVE	(1<<0)
 
+extern int reserve_bootmem(unsigned long addr,
+			   unsigned long size,
+			   int flags);
 extern int reserve_bootmem_node(pg_data_t *pgdat,
 				unsigned long physaddr,
 				unsigned long size,
 				int flags);
-#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
-extern int reserve_bootmem(unsigned long addr, unsigned long size, int flags);
-#endif
 
-extern void *__alloc_bootmem_nopanic(unsigned long size,
-			     unsigned long align,
-			     unsigned long goal);
 extern void *__alloc_bootmem(unsigned long size,
 			     unsigned long align,
 			     unsigned long goal);
-extern void *__alloc_bootmem_low(unsigned long size,
+extern void *__alloc_bootmem_nopanic(unsigned long size,
 				     unsigned long align,
 				     unsigned long goal);
 extern void *__alloc_bootmem_node(pg_data_t *pgdat,
@@ -90,30 +87,35 @@ extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				  unsigned long size,
 				  unsigned long align,
 				  unsigned long goal);
+extern void *__alloc_bootmem_low(unsigned long size,
+				 unsigned long align,
+				 unsigned long goal);
 extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
 				      unsigned long size,
 				      unsigned long align,
 				      unsigned long goal);
-#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
+
 #define alloc_bootmem(x) \
 	__alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_nopanic(x) \
 	__alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low(x) \
-	__alloc_bootmem_low(x, SMP_CACHE_BYTES, 0)
 #define alloc_bootmem_pages(x) \
 	__alloc_bootmem(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_pages_nopanic(x) \
 	__alloc_bootmem_nopanic(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low_pages(x) \
-	__alloc_bootmem_low(x, PAGE_SIZE, 0)
 #define alloc_bootmem_node(pgdat, x) \
 	__alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_pages_node(pgdat, x) \
 	__alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_pages_node_nopanic(pgdat, x) \
+	__alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+
+#define alloc_bootmem_low(x) \
+	__alloc_bootmem_low(x, SMP_CACHE_BYTES, 0)
+#define alloc_bootmem_low_pages(x) \
+	__alloc_bootmem_low(x, PAGE_SIZE, 0)
 #define alloc_bootmem_low_pages_node(pgdat, x) \
 	__alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0)
-#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
 
 extern int reserve_bootmem_generic(unsigned long addr, unsigned long size,
 				   int flags);

include/linux/percpu.h

@@ -76,52 +76,98 @@
 
 #ifdef CONFIG_SMP
 
+#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+
+/* minimum unit size, also is the maximum supported allocation size */
+#define PCPU_MIN_UNIT_SIZE		(16UL << PAGE_SHIFT)
+
+/*
+ * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
+ * back on the first chunk if arch is manually allocating and mapping
+ * it for faster access (as a part of large page mapping for example).
+ * Note that dynamic percpu allocator covers both static and dynamic
+ * areas, so these values are bigger than PERCPU_MODULE_RESERVE.
+ *
+ * On typical configuration with modules, the following values leave
+ * about 8k of free space on the first chunk after boot on both x86_32
+ * and 64 when module support is enabled.  When module support is
+ * disabled, it's much tighter.
+ */
+#ifndef PERCPU_DYNAMIC_RESERVE
+#  if BITS_PER_LONG > 32
+#    ifdef CONFIG_MODULES
+#      define PERCPU_DYNAMIC_RESERVE	(6 << PAGE_SHIFT)
+#    else
+#      define PERCPU_DYNAMIC_RESERVE	(4 << PAGE_SHIFT)
+#    endif
+#  else
+#    ifdef CONFIG_MODULES
+#      define PERCPU_DYNAMIC_RESERVE	(4 << PAGE_SHIFT)
+#    else
+#      define PERCPU_DYNAMIC_RESERVE	(2 << PAGE_SHIFT)
+#    endif
+#  endif
+#endif	/* PERCPU_DYNAMIC_RESERVE */
+
+extern void *pcpu_base_addr;
+
+typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno);
+typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr);
+
+extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
+					size_t static_size, size_t unit_size,
+					size_t free_size, void *base_addr,
+					pcpu_populate_pte_fn_t populate_pte_fn);
+
+/*
+ * Use this to get to a cpu's version of the per-cpu object
+ * dynamically allocated. Non-atomic access to the current CPU's
+ * version should probably be combined with get_cpu()/put_cpu().
+ */
+#define per_cpu_ptr(ptr, cpu)	SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
+
+#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+
 struct percpu_data {
 	void *ptrs[1];
 };
 
 #define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
-/* 
+
- * Use this to get to a cpu's version of the per-cpu object dynamically
+#define per_cpu_ptr(ptr, cpu)						\
- * allocated. Non-atomic access to the current CPU's version should
- * probably be combined with get_cpu()/put_cpu().
- */ 
-#define percpu_ptr(ptr, cpu)                              \
 ({									\
         struct percpu_data *__p = __percpu_disguise(ptr);		\
         (__typeof__(ptr))__p->ptrs[(cpu)];				\
 })
 
-extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask);
+#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
-extern void percpu_free(void *__pdata);
+
+extern void *__alloc_percpu(size_t size, size_t align);
+extern void free_percpu(void *__pdata);
 
 #else /* CONFIG_SMP */
 
-#define percpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
+#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
 
-static __always_inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask)
+static inline void *__alloc_percpu(size_t size, size_t align)
 {
+	/*
+	 * 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 > __alignof__(unsigned long long));
 	return kzalloc(size, gfp);
 }
 
-static inline void percpu_free(void *__pdata)
+static inline void free_percpu(void *p)
 {
-	kfree(__pdata);
+	kfree(p);
 }
 
 #endif /* CONFIG_SMP */
 
-#define percpu_alloc_mask(size, gfp, mask) \
+#define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type), \
-	__percpu_alloc_mask((size), (gfp), &(mask))
+						       __alignof__(type))
-
-#define percpu_alloc(size, gfp) percpu_alloc_mask((size), (gfp), cpu_online_map)
-
-/* (legacy) interface for use without CPU hotplug handling */
-
-#define __alloc_percpu(size)	percpu_alloc_mask((size), GFP_KERNEL, \
-						  cpu_possible_map)
-#define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type))
-#define free_percpu(ptr)	percpu_free((ptr))
-#define per_cpu_ptr(ptr, cpu)	percpu_ptr((ptr), (cpu))
 
 #endif /* __LINUX_PERCPU_H */

include/linux/vmalloc.h

@@ -95,6 +95,9 @@ extern struct vm_struct *remove_vm_area(const void *addr);
 
 extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
 			struct page ***pages);
+extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
+				    pgprot_t prot, struct page **pages);
+extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
 extern void unmap_kernel_range(unsigned long addr, unsigned long size);
 
 /* Allocate/destroy a 'vmalloc' VM area. */
@@ -110,5 +113,6 @@ extern long vwrite(char *buf, char *addr, unsigned long count);
  */
 extern rwlock_t vmlist_lock;
 extern struct vm_struct *vmlist;
+extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
 
 #endif /* _LINUX_VMALLOC_H */

kernel/module.c

@@ -51,6 +51,7 @@
 #include <linux/tracepoint.h>
 #include <linux/ftrace.h>
 #include <linux/async.h>
+#include <linux/percpu.h>
 
 #if 0
 #define DEBUGP printk
@@ -366,6 +367,34 @@ static struct module *find_module(const char *name)
 }
 
 #ifdef CONFIG_SMP
+
+#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+
+static void *percpu_modalloc(unsigned long size, unsigned long align,
+			     const char *name)
+{
+	void *ptr;
+
+	if (align > PAGE_SIZE) {
+		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
+		       name, align, PAGE_SIZE);
+		align = PAGE_SIZE;
+	}
+
+	ptr = __alloc_percpu(size, align);
+	if (!ptr)
+		printk(KERN_WARNING
+		       "Could not allocate %lu bytes percpu data\n", size);
+	return ptr;
+}
+
+static void percpu_modfree(void *freeme)
+{
+	free_percpu(freeme);
+}
+
+#else /* ... !CONFIG_HAVE_DYNAMIC_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. */
@@ -480,21 +509,6 @@ static void percpu_modfree(void *freeme)
 	}
 }
 
-static unsigned int find_pcpusec(Elf_Ehdr *hdr,
-				 Elf_Shdr *sechdrs,
-				 const char *secstrings)
-{
-	return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
-}
-
-static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		memcpy(pcpudest + per_cpu_offset(cpu), from, size);
-}
-
 static int percpu_modinit(void)
 {
 	pcpu_num_used = 2;
@@ -513,7 +527,26 @@ static int percpu_modinit(void)
 	return 0;
 }
 __initcall(percpu_modinit);
+
+#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+
+static unsigned int find_pcpusec(Elf_Ehdr *hdr,
+				 Elf_Shdr *sechdrs,
+				 const char *secstrings)
+{
+	return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
+}
+
+static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		memcpy(pcpudest + per_cpu_offset(cpu), from, size);
+}
+
 #else /* ... !CONFIG_SMP */
+
 static inline void *percpu_modalloc(unsigned long size, unsigned long align,
 				    const char *name)
 {
@@ -535,6 +568,7 @@ static inline void percpu_modcopy(void *pcpudst, const void *src,
 	/* pcpusec should be 0, and size of that section should be 0. */
 	BUG_ON(size != 0);
 }
+
 #endif /* CONFIG_SMP */
 
 #define MODINFO_ATTR(field)	\

kernel/sched.c

@@ -9476,7 +9476,7 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 
 static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
 {
-	u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 	u64 data;
 
 #ifndef CONFIG_64BIT
@@ -9495,7 +9495,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
 
 static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
 {
-	u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 
 #ifndef CONFIG_64BIT
 	/*
@@ -9591,7 +9591,7 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 	ca = task_ca(tsk);
 
 	for (; ca; ca = ca->parent) {
-		u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 		*cpuusage += cputime;
 	}
 }

kernel/stop_machine.c

@@ -170,7 +170,7 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 	 * doesn't hit this CPU until we're ready. */
 	get_cpu();
 	for_each_online_cpu(i) {
-		sm_work = percpu_ptr(stop_machine_work, i);
+		sm_work = per_cpu_ptr(stop_machine_work, i);
 		INIT_WORK(sm_work, stop_cpu);
 		queue_work_on(i, stop_machine_wq, sm_work);
 	}

mm/Makefile

@@ -30,6 +30,10 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
+ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+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

mm/allocpercpu.c

@@ -99,45 +99,51 @@ static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
 	__percpu_populate_mask((__pdata), (size), (gfp), &(mask))
 
 /**
- * percpu_alloc_mask - initial setup of per-cpu data
+ * alloc_percpu - initial setup of per-cpu data
  * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
+ * @align: alignment
- * @mask: populate per-data for cpu's selected through mask bits
  *
- * Populating per-cpu data for all online cpu's would be a typical use case,
+ * Allocate dynamic percpu area.  Percpu objects are populated with
- * which is simplified by the percpu_alloc() wrapper.
+ * zeroed buffers.
- * Per-cpu objects are populated with zeroed buffers.
  */
-void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask)
+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);
+	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 > __alignof__(unsigned long long));
+
 	if (unlikely(!pdata))
 		return NULL;
-	if (likely(!__percpu_populate_mask(__pdata, size, gfp, mask)))
+	if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL,
+					   &cpu_possible_map)))
 		return __pdata;
 	kfree(pdata);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(__percpu_alloc_mask);
+EXPORT_SYMBOL_GPL(__alloc_percpu);
 
 /**
- * percpu_free - final cleanup of per-cpu data
+ * 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 percpu_free(void *__pdata)
+void free_percpu(void *__pdata)
 {
 	if (unlikely(!__pdata))
 		return;
 	__percpu_depopulate_mask(__pdata, &cpu_possible_map);
 	kfree(__percpu_disguise(__pdata));
 }
-EXPORT_SYMBOL_GPL(percpu_free);
+EXPORT_SYMBOL_GPL(free_percpu);

mm/bootmem.c

@@ -37,6 +37,16 @@ static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);
 
 static int bootmem_debug;
 
+/*
+ * If an arch needs to apply workarounds to bootmem allocation, it can
+ * set CONFIG_HAVE_ARCH_BOOTMEM and define a wrapper around
+ * __alloc_bootmem_core().
+ */
+#ifndef CONFIG_HAVE_ARCH_BOOTMEM
+#define alloc_bootmem_core(bdata, size, align, goal, limit)		\
+	__alloc_bootmem_core((bdata), (size), (align), (goal), (limit))
+#endif
+
 static int __init bootmem_debug_setup(char *buf)
 {
 	bootmem_debug = 1;
@@ -382,7 +392,6 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 	return mark_bootmem_node(pgdat->bdata, start, end, 1, flags);
 }
 
-#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
 /**
  * reserve_bootmem - mark a page range as usable
  * @addr: starting address of the range
@@ -403,7 +412,6 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size,
 
 	return mark_bootmem(start, end, 1, flags);
 }
-#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
 
 static unsigned long align_idx(struct bootmem_data *bdata, unsigned long idx,
 			unsigned long step)
@@ -428,7 +436,7 @@ static unsigned long align_off(struct bootmem_data *bdata, unsigned long off,
 	return ALIGN(base + off, align) - base;
 }
 
-static void * __init alloc_bootmem_core(struct bootmem_data *bdata,
+static void * __init __alloc_bootmem_core(struct bootmem_data *bdata,
 				unsigned long size, unsigned long align,
 				unsigned long goal, unsigned long limit)
 {

mm/percpu.c

@@ -0,0 +1,979 @@
+/*
+ * linux/mm/percpu.c - percpu memory allocator
+ *
+ * Copyright (C) 2009		SUSE Linux Products GmbH
+ * Copyright (C) 2009		Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ * This is percpu allocator which can handle both static and dynamic
+ * areas.  Percpu areas are allocated in chunks in vmalloc area.  Each
+ * chunk is consisted of num_possible_cpus() units and the first chunk
+ * is used for static percpu variables in the kernel image (special
+ * boot time alloc/init handling necessary as these areas need to be
+ * brought up before allocation services are running).  Unit grows as
+ * necessary and all units grow or shrink in unison.  When a chunk is
+ * filled up, another chunk is allocated.  ie. in vmalloc area
+ *
+ *  c0                           c1                         c2
+ *  -------------------          -------------------        ------------
+ * | u0 | u1 | u2 | u3 |        | u0 | u1 | u2 | u3 |      | u0 | u1 | u
+ *  -------------------  ......  -------------------  ....  ------------
+ *
+ * Allocation is done in offset-size areas of single unit space.  Ie,
+ * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0,
+ * c1:u1, c1:u2 and c1:u3.  Percpu access can be done by configuring
+ * percpu base registers UNIT_SIZE apart.
+ *
+ * There are usually many small percpu allocations many of them as
+ * small as 4 bytes.  The allocator organizes chunks into lists
+ * according to free size and tries to allocate from the fullest one.
+ * Each chunk keeps the maximum contiguous area size hint which is
+ * guaranteed to be eqaul to or larger than the maximum contiguous
+ * area in the chunk.  This helps the allocator not to iterate the
+ * chunk maps unnecessarily.
+ *
+ * Allocation state in each chunk is kept using an array of integers
+ * on chunk->map.  A positive value in the map represents a free
+ * region and negative allocated.  Allocation inside a chunk is done
+ * by scanning this map sequentially and serving the first matching
+ * entry.  This is mostly copied from the percpu_modalloc() allocator.
+ * Chunks are also linked into a rb tree to ease address to chunk
+ * mapping during free.
+ *
+ * To use this allocator, arch code should do the followings.
+ *
+ * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+ *
+ * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
+ *   regular address to percpu pointer and back
+ *
+ * - use pcpu_setup_first_chunk() during percpu area initialization to
+ *   setup the first chunk containing the kernel static percpu area
+ */
+
+#include <linux/bitmap.h>
+#include <linux/bootmem.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/pfn.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+#define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
+#define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */
+
+struct pcpu_chunk {
+	struct list_head	list;		/* linked to pcpu_slot lists */
+	struct rb_node		rb_node;	/* key is chunk->vm->addr */
+	int			free_size;	/* free bytes in the chunk */
+	int			contig_hint;	/* max contiguous size hint */
+	struct vm_struct	*vm;		/* mapped vmalloc region */
+	int			map_used;	/* # of map entries used */
+	int			map_alloc;	/* # of map entries allocated */
+	int			*map;		/* allocation map */
+	bool			immutable;	/* no [de]population allowed */
+	struct page		*page[];	/* #cpus * UNIT_PAGES */
+};
+
+static int pcpu_unit_pages __read_mostly;
+static int pcpu_unit_size __read_mostly;
+static int pcpu_chunk_size __read_mostly;
+static int pcpu_nr_slots __read_mostly;
+static size_t pcpu_chunk_struct_size __read_mostly;
+
+/* the address of the first chunk which starts with the kernel static area */
+void *pcpu_base_addr __read_mostly;
+EXPORT_SYMBOL_GPL(pcpu_base_addr);
+
+/* the size of kernel static area */
+static int pcpu_static_size __read_mostly;
+
+/*
+ * One mutex to rule them all.
+ *
+ * The following mutex is grabbed in the outermost public alloc/free
+ * interface functions and released only when the operation is
+ * complete.  As such, every function in this file other than the
+ * outermost functions are called under pcpu_mutex.
+ *
+ * It can easily be switched to use spinlock such that only the area
+ * allocation and page population commit are protected with it doing
+ * actual [de]allocation without holding any lock.  However, given
+ * what this allocator does, I think it's better to let them run
+ * sequentially.
+ */
+static DEFINE_MUTEX(pcpu_mutex);
+
+static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
+static struct rb_root pcpu_addr_root = RB_ROOT;	/* chunks by address */
+
+static int __pcpu_size_to_slot(int size)
+{
+	int highbit = fls(size);	/* size is in bytes */
+	return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1);
+}
+
+static int pcpu_size_to_slot(int size)
+{
+	if (size == pcpu_unit_size)
+		return pcpu_nr_slots - 1;
+	return __pcpu_size_to_slot(size);
+}
+
+static int pcpu_chunk_slot(const struct pcpu_chunk *chunk)
+{
+	if (chunk->free_size < sizeof(int) || chunk->contig_hint < sizeof(int))
+		return 0;
+
+	return pcpu_size_to_slot(chunk->free_size);
+}
+
+static int pcpu_page_idx(unsigned int cpu, int page_idx)
+{
+	return cpu * pcpu_unit_pages + page_idx;
+}
+
+static struct page **pcpu_chunk_pagep(struct pcpu_chunk *chunk,
+				      unsigned int cpu, int page_idx)
+{
+	return &chunk->page[pcpu_page_idx(cpu, page_idx)];
+}
+
+static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk,
+				     unsigned int cpu, int page_idx)
+{
+	return (unsigned long)chunk->vm->addr +
+		(pcpu_page_idx(cpu, page_idx) << PAGE_SHIFT);
+}
+
+static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk,
+				     int page_idx)
+{
+	return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL;
+}
+
+/**
+ * pcpu_realloc - versatile realloc
+ * @p: the current pointer (can be NULL for new allocations)
+ * @size: the current size in bytes (can be 0 for new allocations)
+ * @new_size: the wanted new size in bytes (can be 0 for free)
+ *
+ * More robust realloc which can be used to allocate, resize or free a
+ * memory area of arbitrary size.  If the needed size goes over
+ * PAGE_SIZE, kernel VM is used.
+ *
+ * RETURNS:
+ * The new pointer on success, NULL on failure.
+ */
+static void *pcpu_realloc(void *p, size_t size, size_t new_size)
+{
+	void *new;
+
+	if (new_size <= PAGE_SIZE)
+		new = kmalloc(new_size, GFP_KERNEL);
+	else
+		new = vmalloc(new_size);
+	if (new_size && !new)
+		return NULL;
+
+	memcpy(new, p, min(size, new_size));
+	if (new_size > size)
+		memset(new + size, 0, new_size - size);
+
+	if (size <= PAGE_SIZE)
+		kfree(p);
+	else
+		vfree(p);
+
+	return new;
+}
+
+/**
+ * pcpu_chunk_relocate - put chunk in the appropriate chunk slot
+ * @chunk: chunk of interest
+ * @oslot: the previous slot it was on
+ *
+ * This function is called after an allocation or free changed @chunk.
+ * New slot according to the changed state is determined and @chunk is
+ * moved to the slot.
+ */
+static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
+{
+	int nslot = pcpu_chunk_slot(chunk);
+
+	if (oslot != nslot) {
+		if (oslot < nslot)
+			list_move(&chunk->list, &pcpu_slot[nslot]);
+		else
+			list_move_tail(&chunk->list, &pcpu_slot[nslot]);
+	}
+}
+
+static struct rb_node **pcpu_chunk_rb_search(void *addr,
+					     struct rb_node **parentp)
+{
+	struct rb_node **p = &pcpu_addr_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct pcpu_chunk *chunk;
+
+	while (*p) {
+		parent = *p;
+		chunk = rb_entry(parent, struct pcpu_chunk, rb_node);
+
+		if (addr < chunk->vm->addr)
+			p = &(*p)->rb_left;
+		else if (addr > chunk->vm->addr)
+			p = &(*p)->rb_right;
+		else
+			break;
+	}
+
+	if (parentp)
+		*parentp = parent;
+	return p;
+}
+
+/**
+ * pcpu_chunk_addr_search - search for chunk containing specified address
+ * @addr: address to search for
+ *
+ * Look for chunk which might contain @addr.  More specifically, it
+ * searchs for the chunk with the highest start address which isn't
+ * beyond @addr.
+ *
+ * RETURNS:
+ * The address of the found chunk.
+ */
+static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
+{
+	struct rb_node *n, *parent;
+	struct pcpu_chunk *chunk;
+
+	n = *pcpu_chunk_rb_search(addr, &parent);
+	if (!n) {
+		/* no exactly matching chunk, the parent is the closest */
+		n = parent;
+		BUG_ON(!n);
+	}
+	chunk = rb_entry(n, struct pcpu_chunk, rb_node);
+
+	if (addr < chunk->vm->addr) {
+		/* the parent was the next one, look for the previous one */
+		n = rb_prev(n);
+		BUG_ON(!n);
+		chunk = rb_entry(n, struct pcpu_chunk, rb_node);
+	}
+
+	return chunk;
+}
+
+/**
+ * pcpu_chunk_addr_insert - insert chunk into address rb tree
+ * @new: chunk to insert
+ *
+ * Insert @new into address rb tree.
+ */
+static void pcpu_chunk_addr_insert(struct pcpu_chunk *new)
+{
+	struct rb_node **p, *parent;
+
+	p = pcpu_chunk_rb_search(new->vm->addr, &parent);
+	BUG_ON(*p);
+	rb_link_node(&new->rb_node, parent, p);
+	rb_insert_color(&new->rb_node, &pcpu_addr_root);
+}
+
+/**
+ * pcpu_split_block - split a map block
+ * @chunk: chunk of interest
+ * @i: index of map block to split
+ * @head: head size in bytes (can be 0)
+ * @tail: tail size in bytes (can be 0)
+ *
+ * Split the @i'th map block into two or three blocks.  If @head is
+ * non-zero, @head bytes block is inserted before block @i moving it
+ * to @i+1 and reducing its size by @head bytes.
+ *
+ * If @tail is non-zero, the target block, which can be @i or @i+1
+ * depending on @head, is reduced by @tail bytes and @tail byte block
+ * is inserted after the target block.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+static int pcpu_split_block(struct pcpu_chunk *chunk, int i, int head, int tail)
+{
+	int nr_extra = !!head + !!tail;
+	int target = chunk->map_used + nr_extra;
+
+	/* reallocation required? */
+	if (chunk->map_alloc < target) {
+		int new_alloc = chunk->map_alloc;
+		int *new;
+
+		while (new_alloc < target)
+			new_alloc *= 2;
+
+		new = pcpu_realloc(chunk->map,
+				   chunk->map_alloc * sizeof(new[0]),
+				   new_alloc * sizeof(new[0]));
+		if (!new)
+			return -ENOMEM;
+
+		chunk->map_alloc = new_alloc;
+		chunk->map = new;
+	}
+
+	/* insert a new subblock */
+	memmove(&chunk->map[i + nr_extra], &chunk->map[i],
+		sizeof(chunk->map[0]) * (chunk->map_used - i));
+	chunk->map_used += nr_extra;
+
+	if (head) {
+		chunk->map[i + 1] = chunk->map[i] - head;
+		chunk->map[i++] = head;
+	}
+	if (tail) {
+		chunk->map[i++] -= tail;
+		chunk->map[i] = tail;
+	}
+	return 0;
+}
+
+/**
+ * pcpu_alloc_area - allocate area from a pcpu_chunk
+ * @chunk: chunk of interest
+ * @size: wanted size in bytes
+ * @align: wanted align
+ *
+ * Try to allocate @size bytes area aligned at @align from @chunk.
+ * Note that this function only allocates the offset.  It doesn't
+ * populate or map the area.
+ *
+ * RETURNS:
+ * Allocated offset in @chunk on success, -errno on failure.
+ */
+static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
+{
+	int oslot = pcpu_chunk_slot(chunk);
+	int max_contig = 0;
+	int i, off;
+
+	/*
+	 * The static chunk initially doesn't have map attached
+	 * because kmalloc wasn't available during init.  Give it one.
+	 */
+	if (unlikely(!chunk->map)) {
+		chunk->map = pcpu_realloc(NULL, 0,
+				PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+		if (!chunk->map)
+			return -ENOMEM;
+
+		chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
+		chunk->map[chunk->map_used++] = -pcpu_static_size;
+		if (chunk->free_size)
+			chunk->map[chunk->map_used++] = chunk->free_size;
+	}
+
+	for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) {
+		bool is_last = i + 1 == chunk->map_used;
+		int head, tail;
+
+		/* extra for alignment requirement */
+		head = ALIGN(off, align) - off;
+		BUG_ON(i == 0 && head != 0);
+
+		if (chunk->map[i] < 0)
+			continue;
+		if (chunk->map[i] < head + size) {
+			max_contig = max(chunk->map[i], max_contig);
+			continue;
+		}
+
+		/*
+		 * If head is small or the previous block is free,
+		 * merge'em.  Note that 'small' is defined as smaller
+		 * than sizeof(int), which is very small but isn't too
+		 * uncommon for percpu allocations.
+		 */
+		if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) {
+			if (chunk->map[i - 1] > 0)
+				chunk->map[i - 1] += head;
+			else {
+				chunk->map[i - 1] -= head;
+				chunk->free_size -= head;
+			}
+			chunk->map[i] -= head;
+			off += head;
+			head = 0;
+		}
+
+		/* if tail is small, just keep it around */
+		tail = chunk->map[i] - head - size;
+		if (tail < sizeof(int))
+			tail = 0;
+
+		/* split if warranted */
+		if (head || tail) {
+			if (pcpu_split_block(chunk, i, head, tail))
+				return -ENOMEM;
+			if (head) {
+				i++;
+				off += head;
+				max_contig = max(chunk->map[i - 1], max_contig);
+			}
+			if (tail)
+				max_contig = max(chunk->map[i + 1], max_contig);
+		}
+
+		/* update hint and mark allocated */
+		if (is_last)
+			chunk->contig_hint = max_contig; /* fully scanned */
+		else
+			chunk->contig_hint = max(chunk->contig_hint,
+						 max_contig);
+
+		chunk->free_size -= chunk->map[i];
+		chunk->map[i] = -chunk->map[i];
+
+		pcpu_chunk_relocate(chunk, oslot);
+		return off;
+	}
+
+	chunk->contig_hint = max_contig;	/* fully scanned */
+	pcpu_chunk_relocate(chunk, oslot);
+
+	/*
+	 * Tell the upper layer that this chunk has no area left.
+	 * Note that this is not an error condition but a notification
+	 * to upper layer that it needs to look at other chunks.
+	 * -ENOSPC is chosen as it isn't used in memory subsystem and
+	 * matches the meaning in a way.
+	 */
+	return -ENOSPC;
+}
+
+/**
+ * pcpu_free_area - free area to a pcpu_chunk
+ * @chunk: chunk of interest
+ * @freeme: offset of area to free
+ *
+ * Free area starting from @freeme to @chunk.  Note that this function
+ * only modifies the allocation map.  It doesn't depopulate or unmap
+ * the area.
+ */
+static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
+{
+	int oslot = pcpu_chunk_slot(chunk);
+	int i, off;
+
+	for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++]))
+		if (off == freeme)
+			break;
+	BUG_ON(off != freeme);
+	BUG_ON(chunk->map[i] > 0);
+
+	chunk->map[i] = -chunk->map[i];
+	chunk->free_size += chunk->map[i];
+
+	/* merge with previous? */
+	if (i > 0 && chunk->map[i - 1] >= 0) {
+		chunk->map[i - 1] += chunk->map[i];
+		chunk->map_used--;
+		memmove(&chunk->map[i], &chunk->map[i + 1],
+			(chunk->map_used - i) * sizeof(chunk->map[0]));
+		i--;
+	}
+	/* merge with next? */
+	if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) {
+		chunk->map[i] += chunk->map[i + 1];
+		chunk->map_used--;
+		memmove(&chunk->map[i + 1], &chunk->map[i + 2],
+			(chunk->map_used - (i + 1)) * sizeof(chunk->map[0]));
+	}
+
+	chunk->contig_hint = max(chunk->map[i], chunk->contig_hint);
+	pcpu_chunk_relocate(chunk, oslot);
+}
+
+/**
+ * pcpu_unmap - unmap pages out of a pcpu_chunk
+ * @chunk: chunk of interest
+ * @page_start: page index of the first page to unmap
+ * @page_end: page index of the last page to unmap + 1
+ * @flush: whether to flush cache and tlb or not
+ *
+ * For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
+ * If @flush is true, vcache is flushed before unmapping and tlb
+ * after.
+ */
+static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end,
+		       bool flush)
+{
+	unsigned int last = num_possible_cpus() - 1;
+	unsigned int cpu;
+
+	/* unmap must not be done on immutable chunk */
+	WARN_ON(chunk->immutable);
+
+	/*
+	 * Each flushing trial can be very expensive, issue flush on
+	 * the whole region at once rather than doing it for each cpu.
+	 * This could be an overkill but is more scalable.
+	 */
+	if (flush)
+		flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start),
+				   pcpu_chunk_addr(chunk, last, page_end));
+
+	for_each_possible_cpu(cpu)
+		unmap_kernel_range_noflush(
+				pcpu_chunk_addr(chunk, cpu, page_start),
+				(page_end - page_start) << PAGE_SHIFT);
+
+	/* ditto as flush_cache_vunmap() */
+	if (flush)
+		flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start),
+				       pcpu_chunk_addr(chunk, last, page_end));
+}
+
+/**
+ * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk
+ * @chunk: chunk to depopulate
+ * @off: offset to the area to depopulate
+ * @size: size of the area to depopulate in bytes
+ * @flush: whether to flush cache and tlb or not
+ *
+ * For each cpu, depopulate and unmap pages [@page_start,@page_end)
+ * from @chunk.  If @flush is true, vcache is flushed before unmapping
+ * and tlb after.
+ */
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size,
+				  bool flush)
+{
+	int page_start = PFN_DOWN(off);
+	int page_end = PFN_UP(off + size);
+	int unmap_start = -1;
+	int uninitialized_var(unmap_end);
+	unsigned int cpu;
+	int i;
+
+	for (i = page_start; i < page_end; i++) {
+		for_each_possible_cpu(cpu) {
+			struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i);
+
+			if (!*pagep)
+				continue;
+
+			__free_page(*pagep);
+
+			/*
+			 * If it's partial depopulation, it might get
+			 * populated or depopulated again.  Mark the
+			 * page gone.
+			 */
+			*pagep = NULL;
+
+			unmap_start = unmap_start < 0 ? i : unmap_start;
+			unmap_end = i + 1;
+		}
+	}
+
+	if (unmap_start >= 0)
+		pcpu_unmap(chunk, unmap_start, unmap_end, flush);
+}
+
+/**
+ * pcpu_map - map pages into a pcpu_chunk
+ * @chunk: chunk of interest
+ * @page_start: page index of the first page to map
+ * @page_end: page index of the last page to map + 1
+ *
+ * For each cpu, map pages [@page_start,@page_end) into @chunk.
+ * vcache is flushed afterwards.
+ */
+static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end)
+{
+	unsigned int last = num_possible_cpus() - 1;
+	unsigned int cpu;
+	int err;
+
+	/* map must not be done on immutable chunk */
+	WARN_ON(chunk->immutable);
+
+	for_each_possible_cpu(cpu) {
+		err = map_kernel_range_noflush(
+				pcpu_chunk_addr(chunk, cpu, page_start),
+				(page_end - page_start) << PAGE_SHIFT,
+				PAGE_KERNEL,
+				pcpu_chunk_pagep(chunk, cpu, page_start));
+		if (err < 0)
+			return err;
+	}
+
+	/* flush at once, please read comments in pcpu_unmap() */
+	flush_cache_vmap(pcpu_chunk_addr(chunk, 0, page_start),
+			 pcpu_chunk_addr(chunk, last, page_end));
+	return 0;
+}
+
+/**
+ * pcpu_populate_chunk - populate and map an area of a pcpu_chunk
+ * @chunk: chunk of interest
+ * @off: offset to the area to populate
+ * @size: size of the area to populate in bytes
+ *
+ * For each cpu, populate and map pages [@page_start,@page_end) into
+ * @chunk.  The area is cleared on return.
+ */
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
+{
+	const gfp_t alloc_mask = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
+	int page_start = PFN_DOWN(off);
+	int page_end = PFN_UP(off + size);
+	int map_start = -1;
+	int map_end;
+	unsigned int cpu;
+	int i;
+
+	for (i = page_start; i < page_end; i++) {
+		if (pcpu_chunk_page_occupied(chunk, i)) {
+			if (map_start >= 0) {
+				if (pcpu_map(chunk, map_start, map_end))
+					goto err;
+				map_start = -1;
+			}
+			continue;
+		}
+
+		map_start = map_start < 0 ? i : map_start;
+		map_end = i + 1;
+
+		for_each_possible_cpu(cpu) {
+			struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i);
+
+			*pagep = alloc_pages_node(cpu_to_node(cpu),
+						  alloc_mask, 0);
+			if (!*pagep)
+				goto err;
+		}
+	}
+
+	if (map_start >= 0 && pcpu_map(chunk, map_start, map_end))
+		goto err;
+
+	for_each_possible_cpu(cpu)
+		memset(chunk->vm->addr + cpu * pcpu_unit_size + off, 0,
+		       size);
+
+	return 0;
+err:
+	/* likely under heavy memory pressure, give memory back */
+	pcpu_depopulate_chunk(chunk, off, size, true);
+	return -ENOMEM;
+}
+
+static void free_pcpu_chunk(struct pcpu_chunk *chunk)
+{
+	if (!chunk)
+		return;
+	if (chunk->vm)
+		free_vm_area(chunk->vm);
+	pcpu_realloc(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]), 0);
+	kfree(chunk);
+}
+
+static struct pcpu_chunk *alloc_pcpu_chunk(void)
+{
+	struct pcpu_chunk *chunk;
+
+	chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL);
+	if (!chunk)
+		return NULL;
+
+	chunk->map = pcpu_realloc(NULL, 0,
+				  PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+	chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
+	chunk->map[chunk->map_used++] = pcpu_unit_size;
+
+	chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL);
+	if (!chunk->vm) {
+		free_pcpu_chunk(chunk);
+		return NULL;
+	}
+
+	INIT_LIST_HEAD(&chunk->list);
+	chunk->free_size = pcpu_unit_size;
+	chunk->contig_hint = pcpu_unit_size;
+
+	return chunk;
+}
+
+/**
+ * __alloc_percpu - allocate percpu area
+ * @size: size of area to allocate in bytes
+ * @align: alignment of area (max PAGE_SIZE)
+ *
+ * Allocate percpu area of @size bytes aligned at @align.  Might
+ * sleep.  Might trigger writeouts.
+ *
+ * RETURNS:
+ * Percpu pointer to the allocated area on success, NULL on failure.
+ */
+void *__alloc_percpu(size_t size, size_t align)
+{
+	void *ptr = NULL;
+	struct pcpu_chunk *chunk;
+	int slot, off;
+
+	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
+		WARN(true, "illegal size (%zu) or align (%zu) for "
+		     "percpu allocation\n", size, align);
+		return NULL;
+	}
+
+	mutex_lock(&pcpu_mutex);
+
+	/* allocate area */
+	for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) {
+		list_for_each_entry(chunk, &pcpu_slot[slot], list) {
+			if (size > chunk->contig_hint)
+				continue;
+			off = pcpu_alloc_area(chunk, size, align);
+			if (off >= 0)
+				goto area_found;
+			if (off != -ENOSPC)
+				goto out_unlock;
+		}
+	}
+
+	/* hmmm... no space left, create a new chunk */
+	chunk = alloc_pcpu_chunk();
+	if (!chunk)
+		goto out_unlock;
+	pcpu_chunk_relocate(chunk, -1);
+	pcpu_chunk_addr_insert(chunk);
+
+	off = pcpu_alloc_area(chunk, size, align);
+	if (off < 0)
+		goto out_unlock;
+
+area_found:
+	/* populate, map and clear the area */
+	if (pcpu_populate_chunk(chunk, off, size)) {
+		pcpu_free_area(chunk, off);
+		goto out_unlock;
+	}
+
+	ptr = __addr_to_pcpu_ptr(chunk->vm->addr + off);
+out_unlock:
+	mutex_unlock(&pcpu_mutex);
+	return ptr;
+}
+EXPORT_SYMBOL_GPL(__alloc_percpu);
+
+static void pcpu_kill_chunk(struct pcpu_chunk *chunk)
+{
+	WARN_ON(chunk->immutable);
+	pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false);
+	list_del(&chunk->list);
+	rb_erase(&chunk->rb_node, &pcpu_addr_root);
+	free_pcpu_chunk(chunk);
+}
+
+/**
+ * free_percpu - free percpu area
+ * @ptr: pointer to area to free
+ *
+ * Free percpu area @ptr.  Might sleep.
+ */
+void free_percpu(void *ptr)
+{
+	void *addr = __pcpu_ptr_to_addr(ptr);
+	struct pcpu_chunk *chunk;
+	int off;
+
+	if (!ptr)
+		return;
+
+	mutex_lock(&pcpu_mutex);
+
+	chunk = pcpu_chunk_addr_search(addr);
+	off = addr - chunk->vm->addr;
+
+	pcpu_free_area(chunk, off);
+
+	/* the chunk became fully free, kill one if there are other free ones */
+	if (chunk->free_size == pcpu_unit_size) {
+		struct pcpu_chunk *pos;
+
+		list_for_each_entry(pos,
+				    &pcpu_slot[pcpu_chunk_slot(chunk)], list)
+			if (pos != chunk) {
+				pcpu_kill_chunk(pos);
+				break;
+			}
+	}
+
+	mutex_unlock(&pcpu_mutex);
+}
+EXPORT_SYMBOL_GPL(free_percpu);
+
+/**
+ * pcpu_setup_first_chunk - initialize the first percpu chunk
+ * @get_page_fn: callback to fetch page pointer
+ * @static_size: the size of static percpu area in bytes
+ * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, 0 for auto
+ * @free_size: free size in bytes, 0 for auto
+ * @base_addr: mapped address, NULL for auto
+ * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary
+ *
+ * Initialize the first percpu chunk which contains the kernel static
+ * perpcu area.  This function is to be called from arch percpu area
+ * setup path.  The first two parameters are mandatory.  The rest are
+ * optional.
+ *
+ * @get_page_fn() should return pointer to percpu page given cpu
+ * number and page number.  It should at least return enough pages to
+ * cover the static area.  The returned pages for static area should
+ * have been initialized with valid data.  If @unit_size is specified,
+ * it can also return pages after the static area.  NULL return
+ * indicates end of pages for the cpu.  Note that @get_page_fn() must
+ * return the same number of pages for all cpus.
+ *
+ * @unit_size, if non-zero, determines unit size and must be aligned
+ * to PAGE_SIZE and equal to or larger than @static_size + @free_size.
+ *
+ * @free_size determines the number of free bytes after the static
+ * area in the first chunk.  If zero, whatever left is available.
+ * Specifying non-zero value make percpu leave the area after
+ * @static_size + @free_size alone.
+ *
+ * Non-null @base_addr means that the caller already allocated virtual
+ * region for the first chunk and mapped it.  percpu must not mess
+ * with the chunk.  Note that @base_addr with 0 @unit_size or non-NULL
+ * @populate_pte_fn doesn't make any sense.
+ *
+ * @populate_pte_fn is used to populate the pagetable.  NULL means the
+ * caller already populated the pagetable.
+ *
+ * RETURNS:
+ * The determined pcpu_unit_size which can be used to initialize
+ * percpu access.
+ */
+size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
+				     size_t static_size, size_t unit_size,
+				     size_t free_size, void *base_addr,
+				     pcpu_populate_pte_fn_t populate_pte_fn)
+{
+	static struct vm_struct static_vm;
+	struct pcpu_chunk *static_chunk;
+	unsigned int cpu;
+	int nr_pages;
+	int err, i;
+
+	/* santiy checks */
+	BUG_ON(!static_size);
+	BUG_ON(!unit_size && free_size);
+	BUG_ON(unit_size && unit_size < static_size + free_size);
+	BUG_ON(unit_size & ~PAGE_MASK);
+	BUG_ON(base_addr && !unit_size);
+	BUG_ON(base_addr && populate_pte_fn);
+
+	if (unit_size)
+		pcpu_unit_pages = unit_size >> PAGE_SHIFT;
+	else
+		pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT,
+					PFN_UP(static_size));
+
+	pcpu_static_size = static_size;
+	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
+	pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size;
+	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk)
+		+ num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *);
+
+	/*
+	 * Allocate chunk slots.  The additional last slot is for
+	 * empty chunks.
+	 */
+	pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
+	pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0]));
+	for (i = 0; i < pcpu_nr_slots; i++)
+		INIT_LIST_HEAD(&pcpu_slot[i]);
+
+	/* init static_chunk */
+	static_chunk = alloc_bootmem(pcpu_chunk_struct_size);
+	INIT_LIST_HEAD(&static_chunk->list);
+	static_chunk->vm = &static_vm;
+
+	if (free_size)
+		static_chunk->free_size = free_size;
+	else
+		static_chunk->free_size = pcpu_unit_size - pcpu_static_size;
+
+	static_chunk->contig_hint = static_chunk->free_size;
+
+	/* allocate vm address */
+	static_vm.flags = VM_ALLOC;
+	static_vm.size = pcpu_chunk_size;
+
+	if (!base_addr)
+		vm_area_register_early(&static_vm, PAGE_SIZE);
+	else {
+		/*
+		 * Pages already mapped.  No need to remap into
+		 * vmalloc area.  In this case the static chunk can't
+		 * be mapped or unmapped by percpu and is marked
+		 * immutable.
+		 */
+		static_vm.addr = base_addr;
+		static_chunk->immutable = true;
+	}
+
+	/* assign pages */
+	nr_pages = -1;
+	for_each_possible_cpu(cpu) {
+		for (i = 0; i < pcpu_unit_pages; i++) {
+			struct page *page = get_page_fn(cpu, i);
+
+			if (!page)
+				break;
+			*pcpu_chunk_pagep(static_chunk, cpu, i) = page;
+		}
+
+		BUG_ON(i < PFN_UP(pcpu_static_size));
+
+		if (nr_pages < 0)
+			nr_pages = i;
+		else
+			BUG_ON(nr_pages != i);
+	}
+
+	/* map them */
+	if (populate_pte_fn) {
+		for_each_possible_cpu(cpu)
+			for (i = 0; i < nr_pages; i++)
+				populate_pte_fn(pcpu_chunk_addr(static_chunk,
+								cpu, i));
+
+		err = pcpu_map(static_chunk, 0, nr_pages);
+		if (err)
+			panic("failed to setup static percpu area, err=%d\n",
+			      err);
+	}
+
+	/* link static_chunk in */
+	pcpu_chunk_relocate(static_chunk, -1);
+	pcpu_chunk_addr_insert(static_chunk);
+
+	/* we're done */
+	pcpu_base_addr = (void *)pcpu_chunk_addr(static_chunk, 0, 0);
+	return pcpu_unit_size;
+}

mm/vmalloc.c

@@ -24,6 +24,7 @@
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
 #include <linux/bootmem.h>
+#include <linux/pfn.h>
 
 #include <asm/atomic.h>
 #include <asm/uaccess.h>
@@ -152,7 +153,7 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
  *
  * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
  */
-static int vmap_page_range(unsigned long start, unsigned long end,
+static int vmap_page_range_noflush(unsigned long start, unsigned long end,
 				   pgprot_t prot, struct page **pages)
 {
 	pgd_t *pgd;
@@ -169,13 +170,22 @@ static int vmap_page_range(unsigned long start, unsigned long end,
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
-	flush_cache_vmap(start, end);
 
 	if (unlikely(err))
 		return err;
 	return nr;
 }
 
+static int vmap_page_range(unsigned long start, unsigned long end,
+			   pgprot_t prot, struct page **pages)
+{
+	int ret;
+
+	ret = vmap_page_range_noflush(start, end, prot, pages);
+	flush_cache_vmap(start, end);
+	return ret;
+}
+
 static inline int is_vmalloc_or_module_addr(const void *x)
 {
 	/*
@@ -982,6 +992,32 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro
 }
 EXPORT_SYMBOL(vm_map_ram);
 
+/**
+ * vm_area_register_early - register vmap area early during boot
+ * @vm: vm_struct to register
+ * @align: requested alignment
+ *
+ * This function is used to register kernel vm area before
+ * vmalloc_init() is called.  @vm->size and @vm->flags should contain
+ * proper values on entry and other fields should be zero.  On return,
+ * vm->addr contains the allocated address.
+ *
+ * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
+ */
+void __init vm_area_register_early(struct vm_struct *vm, size_t align)
+{
+	static size_t vm_init_off __initdata;
+	unsigned long addr;
+
+	addr = ALIGN(VMALLOC_START + vm_init_off, align);
+	vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START;
+
+	vm->addr = (void *)addr;
+
+	vm->next = vmlist;
+	vmlist = vm;
+}
+
 void __init vmalloc_init(void)
 {
 	struct vmap_area *va;
@@ -1009,6 +1045,58 @@ void __init vmalloc_init(void)
 	vmap_initialized = true;
 }
 
+/**
+ * map_kernel_range_noflush - map kernel VM area with the specified pages
+ * @addr: start of the VM area to map
+ * @size: size of the VM area to map
+ * @prot: page protection flags to use
+ * @pages: pages to map
+ *
+ * Map PFN_UP(@size) pages at @addr.  The VM area @addr and @size
+ * specify should have been allocated using get_vm_area() and its
+ * friends.
+ *
+ * NOTE:
+ * This function does NOT do any cache flushing.  The caller is
+ * responsible for calling flush_cache_vmap() on to-be-mapped areas
+ * before calling this function.
+ *
+ * RETURNS:
+ * The number of pages mapped on success, -errno on failure.
+ */
+int map_kernel_range_noflush(unsigned long addr, unsigned long size,
+			     pgprot_t prot, struct page **pages)
+{
+	return vmap_page_range_noflush(addr, addr + size, prot, pages);
+}
+
+/**
+ * unmap_kernel_range_noflush - unmap kernel VM area
+ * @addr: start of the VM area to unmap
+ * @size: size of the VM area to unmap
+ *
+ * Unmap PFN_UP(@size) pages at @addr.  The VM area @addr and @size
+ * specify should have been allocated using get_vm_area() and its
+ * friends.
+ *
+ * NOTE:
+ * This function does NOT do any cache flushing.  The caller is
+ * responsible for calling flush_cache_vunmap() on to-be-mapped areas
+ * before calling this function and flush_tlb_kernel_range() after.
+ */
+void unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
+{
+	vunmap_page_range(addr, addr + size);
+}
+
+/**
+ * unmap_kernel_range - unmap kernel VM area and flush cache and TLB
+ * @addr: start of the VM area to unmap
+ * @size: size of the VM area to unmap
+ *
+ * Similar to unmap_kernel_range_noflush() but flushes vcache before
+ * the unmapping and tlb after.
+ */
 void unmap_kernel_range(unsigned long addr, unsigned long size)
 {
 	unsigned long end = addr + size;

net/ipv4/af_inet.c

@@ -1375,10 +1375,10 @@ EXPORT_SYMBOL_GPL(snmp_fold_field);
 int snmp_mib_init(void *ptr[2], size_t mibsize)
 {
 	BUG_ON(ptr == NULL);
-	ptr[0] = __alloc_percpu(mibsize);
+	ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long long));
 	if (!ptr[0])
 		goto err0;
-	ptr[1] = __alloc_percpu(mibsize);
+	ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long long));
 	if (!ptr[1])
 		goto err1;
 	return 0;