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

 * On the positive side, using __ia64_per_cpu_var() instead of __get_cpu_var() is slightly

 * more efficient.

 */

#define __ia64_per_cpu_var(var)	var

#define __ia64_per_cpu_var(var) (*({					\

	__verify_pcpu_ptr(&(var));					\

	((typeof(var) __kernel __force *)&(var));			\

}))

#include <asm-generic/percpu.h>

/*

 * mm/percpu-km.c - kernel memory based chunk allocation

 *

 * Copyright (C) 2010		SUSE Linux Products GmbH

 * Copyright (C) 2010		Tejun Heo <tj@kernel.org>

 *

 * This file is released under the GPLv2.

 *

 * Chunks are allocated as a contiguous kernel memory using gfp

 * allocation.  This is to be used on nommu architectures.

 *

 * To use percpu-km,

 *

 * - define CONFIG_NEED_PER_CPU_KM from the arch Kconfig.

 *

 * - CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK must not be defined.  It's

 *   not compatible with PER_CPU_KM.  EMBED_FIRST_CHUNK should work

 *   fine.

 *

 * - NUMA is not supported.  When setting up the first chunk,

 *   @cpu_distance_fn should be NULL or report all CPUs to be nearer

 *   than or at LOCAL_DISTANCE.

 *

 * - It's best if the chunk size is power of two multiple of

 *   PAGE_SIZE.  Because each chunk is allocated as a contiguous

 *   kernel memory block using alloc_pages(), memory will be wasted if

 *   chunk size is not aligned.  percpu-km code will whine about it.

 */

#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK

#error "contiguous percpu allocation is incompatible with paged first chunk"

#endif

#include <linux/log2.h>

static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)

{

	/* noop */

	return 0;

}

static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)

{

	/* nada */

}

static struct pcpu_chunk *pcpu_create_chunk(void)

{

	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;

	struct pcpu_chunk *chunk;

	struct page *pages;

	int i;

	chunk = pcpu_alloc_chunk();

	if (!chunk)

		return NULL;

	pages = alloc_pages(GFP_KERNEL, order_base_2(nr_pages));

	if (!pages) {

		pcpu_free_chunk(chunk);

		return NULL;

	}

	for (i = 0; i < nr_pages; i++)

		pcpu_set_page_chunk(nth_page(pages, i), chunk);

	chunk->data = pages;

	chunk->base_addr = page_address(pages) - pcpu_group_offsets[0];

	return chunk;

}

static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)

{

	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;

	if (chunk && chunk->data)

		__free_pages(chunk->data, order_base_2(nr_pages));

	pcpu_free_chunk(chunk);

}

static struct page *pcpu_addr_to_page(void *addr)

{

	return virt_to_page(addr);

}

static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)

{

	size_t nr_pages, alloc_pages;

	/* all units must be in a single group */

	if (ai->nr_groups != 1) {

		printk(KERN_CRIT "percpu: can't handle more than one groups\n");

		return -EINVAL;

	}

	nr_pages = (ai->groups[0].nr_units * ai->unit_size) >> PAGE_SHIFT;

	alloc_pages = roundup_pow_of_two(nr_pages);

	if (alloc_pages > nr_pages)

		printk(KERN_WARNING "percpu: wasting %zu pages per chunk\n",

		       alloc_pages - nr_pages);

	return 0;

}

/*

 * mm/percpu-vm.c - vmalloc area based chunk allocation

 *

 * Copyright (C) 2010		SUSE Linux Products GmbH

 * Copyright (C) 2010		Tejun Heo <tj@kernel.org>

 *

 * This file is released under the GPLv2.

 *

 * Chunks are mapped into vmalloc areas and populated page by page.

 * This is the default chunk allocator.

 */

static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,

				    unsigned int cpu, int page_idx)

{

	/* must not be used on pre-mapped chunk */

	WARN_ON(chunk->immutable);

	return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx));

}

/**

 * pcpu_get_pages_and_bitmap - get temp pages array and bitmap

 * @chunk: chunk of interest

 * @bitmapp: output parameter for bitmap

 * @may_alloc: may allocate the array

 *

 * Returns pointer to array of pointers to struct page and bitmap,

 * both of which can be indexed with pcpu_page_idx().  The returned

 * array is cleared to zero and *@bitmapp is copied from

 * @chunk->populated.  Note that there is only one array and bitmap

 * and access exclusion is the caller's responsibility.

 *

 * CONTEXT:

 * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc.

 * Otherwise, don't care.

 *

 * RETURNS:

 * Pointer to temp pages array on success, NULL on failure.

 */

static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,

					       unsigned long **bitmapp,

					       bool may_alloc)

{

	static struct page **pages;

	static unsigned long *bitmap;

	size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);

	size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) *

			     sizeof(unsigned long);

	if (!pages || !bitmap) {

		if (may_alloc && !pages)

			pages = pcpu_mem_alloc(pages_size);

		if (may_alloc && !bitmap)

			bitmap = pcpu_mem_alloc(bitmap_size);

		if (!pages || !bitmap)

			return NULL;

	}

	memset(pages, 0, pages_size);

	bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);

	*bitmapp = bitmap;

	return pages;

}

/**

 * pcpu_free_pages - free pages which were allocated for @chunk

 * @chunk: chunk pages were allocated for

 * @pages: array of pages to be freed, indexed by pcpu_page_idx()

 * @populated: populated bitmap

 * @page_start: page index of the first page to be freed

 * @page_end: page index of the last page to be freed + 1

 *

 * Free pages [@page_start and @page_end) in @pages for all units.

 * The pages were allocated for @chunk.

 */

static void pcpu_free_pages(struct pcpu_chunk *chunk,

			    struct page **pages, unsigned long *populated,

			    int page_start, int page_end)

{

	unsigned int cpu;

	int i;

	for_each_possible_cpu(cpu) {

		for (i = page_start; i < page_end; i++) {

			struct page *page = pages[pcpu_page_idx(cpu, i)];

			if (page)

				__free_page(page);

		}

	}

}

/**

 * pcpu_alloc_pages - allocates pages for @chunk

 * @chunk: target chunk

 * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()

 * @populated: populated bitmap

 * @page_start: page index of the first page to be allocated

 * @page_end: page index of the last page to be allocated + 1

 *

 * Allocate pages [@page_start,@page_end) into @pages for all units.

 * The allocation is for @chunk.  Percpu core doesn't care about the

 * content of @pages and will pass it verbatim to pcpu_map_pages().

 */

static int pcpu_alloc_pages(struct pcpu_chunk *chunk,

			    struct page **pages, unsigned long *populated,

			    int page_start, int page_end)

{

	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;

	unsigned int cpu;

	int i;

	for_each_possible_cpu(cpu) {

		for (i = page_start; i < page_end; i++) {

			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];

			*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);

			if (!*pagep) {

				pcpu_free_pages(chunk, pages, populated,

						page_start, page_end);

				return -ENOMEM;

			}

		}

	}

	return 0;

}

/**

 * pcpu_pre_unmap_flush - flush cache prior to unmapping

 * @chunk: chunk the regions to be flushed belongs to

 * @page_start: page index of the first page to be flushed

 * @page_end: page index of the last page to be flushed + 1

 *

 * Pages in [@page_start,@page_end) of @chunk are about to be

 * unmapped.  Flush cache.  As 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.

 */

static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,

				 int page_start, int page_end)

{

	flush_cache_vunmap(

		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),

		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));

}

static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)

{

	unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT);

}

/**

 * pcpu_unmap_pages - unmap pages out of a pcpu_chunk

 * @chunk: chunk of interest

 * @pages: pages array which can be used to pass information to free

 * @populated: populated bitmap

 * @page_start: page index of the first page to unmap

 * @page_end: page index of the last page to unmap + 1

 *

 * For each cpu, unmap pages [@page_start,@page_end) out of @chunk.

 * Corresponding elements in @pages were cleared by the caller and can

 * be used to carry information to pcpu_free_pages() which will be

 * called after all unmaps are finished.  The caller should call

 * proper pre/post flush functions.

 */

static void pcpu_unmap_pages(struct pcpu_chunk *chunk,

			     struct page **pages, unsigned long *populated,

			     int page_start, int page_end)

{

	unsigned int cpu;

	int i;

	for_each_possible_cpu(cpu) {

		for (i = page_start; i < page_end; i++) {

			struct page *page;

			page = pcpu_chunk_page(chunk, cpu, i);

			WARN_ON(!page);

			pages[pcpu_page_idx(cpu, i)] = page;

		}

		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start),

				   page_end - page_start);

	}

	for (i = page_start; i < page_end; i++)

		__clear_bit(i, populated);

}

/**

 * pcpu_post_unmap_tlb_flush - flush TLB after unmapping

 * @chunk: pcpu_chunk the regions to be flushed belong to

 * @page_start: page index of the first page to be flushed

 * @page_end: page index of the last page to be flushed + 1

 *

 * Pages [@page_start,@page_end) of @chunk have been unmapped.  Flush

 * TLB for the regions.  This can be skipped if the area is to be

 * returned to vmalloc as vmalloc will handle TLB flushing lazily.

 *

 * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once

 * for the whole region.

 */

static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,

				      int page_start, int page_end)

{

	flush_tlb_kernel_range(

		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),

		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));

}

static int __pcpu_map_pages(unsigned long addr, struct page **pages,

			    int nr_pages)

{

	return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT,

					PAGE_KERNEL, pages);

}

/**

 * pcpu_map_pages - map pages into a pcpu_chunk

 * @chunk: chunk of interest

 * @pages: pages array containing pages to be mapped

 * @populated: populated bitmap

 * @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.  The

 * caller is responsible for calling pcpu_post_map_flush() after all

 * mappings are complete.

 *

 * This function is responsible for setting corresponding bits in

 * @chunk->populated bitmap and whatever is necessary for reverse

 * lookup (addr -> chunk).

 */

static int pcpu_map_pages(struct pcpu_chunk *chunk,

			  struct page **pages, unsigned long *populated,

			  int page_start, int page_end)

{

	unsigned int cpu, tcpu;

	int i, err;

	for_each_possible_cpu(cpu) {

		err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start),

				       &pages[pcpu_page_idx(cpu, page_start)],

				       page_end - page_start);

		if (err < 0)

			goto err;

	}

	/* mapping successful, link chunk and mark populated */

	for (i = page_start; i < page_end; i++) {

		for_each_possible_cpu(cpu)

			pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)],

					    chunk);

		__set_bit(i, populated);

	}

	return 0;

err:

	for_each_possible_cpu(tcpu) {

		if (tcpu == cpu)

			break;

		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),

				   page_end - page_start);

	}

	return err;

}

/**

 * pcpu_post_map_flush - flush cache after mapping

 * @chunk: pcpu_chunk the regions to be flushed belong to

 * @page_start: page index of the first page to be flushed

 * @page_end: page index of the last page to be flushed + 1

 *

 * Pages [@page_start,@page_end) of @chunk have been mapped.  Flush

 * cache.

 *

 * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once

 * for the whole region.

 */

static void pcpu_post_map_flush(struct pcpu_chunk *chunk,

				int page_start, int page_end)

{

	flush_cache_vmap(

		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),

		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));

}

/**

 * 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.

 *

 * CONTEXT:

 * pcpu_alloc_mutex, does GFP_KERNEL allocation.

 */

static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)

{

	int page_start = PFN_DOWN(off);

	int page_end = PFN_UP(off + size);

	int free_end = page_start, unmap_end = page_start;

	struct page **pages;

	unsigned long *populated;

	unsigned int cpu;

	int rs, re, rc;

	/* quick path, check whether all pages are already there */

	rs = page_start;

	pcpu_next_pop(chunk, &rs, &re, page_end);

	if (rs == page_start && re == page_end)

		goto clear;

	/* need to allocate and map pages, this chunk can't be immutable */

	WARN_ON(chunk->immutable);

	pages = pcpu_get_pages_and_bitmap(chunk, &populated, true);

	if (!pages)

		return -ENOMEM;

	/* alloc and map */

	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {

		rc = pcpu_alloc_pages(chunk, pages, populated, rs, re);

		if (rc)

			goto err_free;

		free_end = re;

	}

	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {

		rc = pcpu_map_pages(chunk, pages, populated, rs, re);

		if (rc)

			goto err_unmap;

		unmap_end = re;

	}

	pcpu_post_map_flush(chunk, page_start, page_end);

	/* commit new bitmap */

	bitmap_copy(chunk->populated, populated, pcpu_unit_pages);

clear:

	for_each_possible_cpu(cpu)

		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);

	return 0;

err_unmap:

	pcpu_pre_unmap_flush(chunk, page_start, unmap_end);

	pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end)

		pcpu_unmap_pages(chunk, pages, populated, rs, re);

	pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end);

err_free:

	pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end)

		pcpu_free_pages(chunk, pages, populated, rs, re);

	return rc;

}

/**

 * 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.

 *

 * CONTEXT:

 * pcpu_alloc_mutex.

 */

static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)

{

	int page_start = PFN_DOWN(off);

	int page_end = PFN_UP(off + size);

	struct page **pages;

	unsigned long *populated;

	int rs, re;

	/* quick path, check whether it's empty already */

	rs = page_start;

	pcpu_next_unpop(chunk, &rs, &re, page_end);

	if (rs == page_start && re == page_end)

		return;

	/* immutable chunks can't be depopulated */

	WARN_ON(chunk->immutable);

	/*

	 * If control reaches here, there must have been at least one

	 * successful population attempt so the temp pages array must

	 * be available now.

	 */

	pages = pcpu_get_pages_and_bitmap(chunk, &populated, false);

	BUG_ON(!pages);

	/* unmap and free */

	pcpu_pre_unmap_flush(chunk, page_start, page_end);

	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)

		pcpu_unmap_pages(chunk, pages, populated, rs, re);

	/* no need to flush tlb, vmalloc will handle it lazily */

	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)

		pcpu_free_pages(chunk, pages, populated, rs, re);

	/* commit new bitmap */

	bitmap_copy(chunk->populated, populated, pcpu_unit_pages);

}

static struct pcpu_chunk *pcpu_create_chunk(void)

{

	struct pcpu_chunk *chunk;

	struct vm_struct **vms;

	chunk = pcpu_alloc_chunk();

	if (!chunk)

		return NULL;

	vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,

				pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL);

	if (!vms) {

		pcpu_free_chunk(chunk);

		return NULL;

	}

	chunk->data = vms;

	chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0];

	return chunk;

}

static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)

{

	if (chunk && chunk->data)

		pcpu_free_vm_areas(chunk->data, pcpu_nr_groups);

	pcpu_free_chunk(chunk);

}

static struct page *pcpu_addr_to_page(void *addr)

{

	return vmalloc_to_page(addr);

}

static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)

{

	/* no extra restriction */

	return 0;

}