path: root/mm/percpu-vm.c

/*
 * 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)
{
	
	WARN_ON(chunk->immutable);

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

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_zalloc(pages_size);
		if (may_alloc && !bitmap)
			bitmap = pcpu_mem_zalloc(bitmap_size);
		if (!pages || !bitmap)
			return NULL;
	}

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

	*bitmapp = bitmap;
	return pages;
}

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);
		}
	}
}

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;
}

static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
				 int page_start, int page_end)
{
	flush_cache_vunmap(
		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}

static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
{
	unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT);
}

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);
	}

	bitmap_clear(populated, page_start, page_end - page_start);
}

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_low_unit_cpu, page_start),
		pcpu_chunk_addr(chunk, pcpu_high_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);
}

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;
	}

	
	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;
}

static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
				int page_start, int page_end)
{
	flush_cache_vmap(
		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}

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;

	
	rs = page_start;
	pcpu_next_pop(chunk, &rs, &re, page_end);
	if (rs == page_start && re == page_end)
		goto clear;

	
	WARN_ON(chunk->immutable);

	pages = pcpu_get_pages_and_bitmap(chunk, &populated, true);
	if (!pages)
		return -ENOMEM;

	
	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);

	
	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;
}

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;

	
	rs = page_start;
	pcpu_next_unpop(chunk, &rs, &re, page_end);
	if (rs == page_start && re == page_end)
		return;

	
	WARN_ON(chunk->immutable);

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

	
	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);

	

	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
		pcpu_free_pages(chunk, pages, populated, rs, re);

	
	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);
	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)
{
	
	return 0;
}