percpu.c

/*
 * 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 pcpu_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 can be determined from the address using the index field
 * in the page struct. The index field contains a pointer to the chunk.
 *
 * To use this allocator, arch code should do the followings.
 *
 * - drop CONFIG_HAVE_LEGACY_PER_CPU_AREA
 *
 * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
 *   regular address to percpu pointer and back if they need to be
 *   different from the default
 *
 * - 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/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>

#include <asm/cacheflush.h>
#include <asm/sections.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 */

/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
#ifndef __addr_to_pcpu_ptr
#define __addr_to_pcpu_ptr(addr)					\
	(void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr	\
		 + (unsigned long)__per_cpu_start)
#endif
#ifndef __pcpu_ptr_to_addr
#define __pcpu_ptr_to_addr(ptr)						\
	(void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr	\
		 - (unsigned long)__per_cpu_start)
#endif

struct pcpu_chunk {
	struct list_head	list;		/* linked to pcpu_slot lists */
	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;		/* points to page array */
	struct page		*page_ar[];	/* #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 first chunk which always exists.  Note that unlike other
 * chunks, this one can be allocated and mapped in several different
 * ways and thus often doesn't live in the vmalloc area.
 */
static struct pcpu_chunk *pcpu_first_chunk;

/*
 * Optional reserved chunk.  This chunk reserves part of the first
 * chunk and serves it for reserved allocations.  The amount of
 * reserved offset is in pcpu_reserved_chunk_limit.  When reserved
 * area doesn't exist, the following variables contain NULL and 0
 * respectively.
 */
static struct pcpu_chunk *pcpu_reserved_chunk;
static int pcpu_reserved_chunk_limit;

/*
 * Synchronization rules.
 *
 * There are two locks - pcpu_alloc_mutex and pcpu_lock.  The former
 * protects allocation/reclaim paths, chunks and chunk->page arrays.
 * The latter is a spinlock and protects the index data structures -
 * chunk slots, chunks and area maps in chunks.
 *
 * During allocation, pcpu_alloc_mutex is kept locked all the time and
 * pcpu_lock is grabbed and released as necessary.  All actual memory
 * allocations are done using GFP_KERNEL with pcpu_lock released.
 *
 * Free path accesses and alters only the index data structures, so it
 * can be safely called from atomic context.  When memory needs to be
 * returned to the system, free path schedules reclaim_work which
 * grabs both pcpu_alloc_mutex and pcpu_lock, unlinks chunks to be
 * reclaimed, release both locks and frees the chunks.  Note that it's
 * necessary to grab both locks to remove a chunk from circulation as
 * allocation path might be referencing the chunk with only
 * pcpu_alloc_mutex locked.
 */
static DEFINE_MUTEX(pcpu_alloc_mutex);	/* protects whole alloc and reclaim */
static DEFINE_SPINLOCK(pcpu_lock);	/* protects index data structures */

static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */

/* reclaim work to release fully free chunks, scheduled from free path */
static void pcpu_reclaim(struct work_struct *work);
static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim);

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 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 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 bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk,
				     int page_idx)
{
	return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL;
}

/* set the pointer to a chunk in a page struct */
static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu)
{
	page->index = (unsigned long)pcpu;
}

/* obtain pointer to a chunk from a page struct */
static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page)
{
	return (struct pcpu_chunk *)page->index;
}

/**
 * pcpu_mem_alloc - allocate memory
 * @size: bytes to allocate
 *
 * Allocate @size bytes.  If @size is smaller than PAGE_SIZE,
 * kzalloc() is used; otherwise, vmalloc() is used.  The returned
 * memory is always zeroed.
 *
 * CONTEXT:
 * Does GFP_KERNEL allocation.
 *
 * RETURNS:
 * Pointer to the allocated area on success, NULL on failure.
 */
static void *pcpu_mem_alloc(size_t size)
{
	if (size <= PAGE_SIZE)
		return kzalloc(size, GFP_KERNEL);
	else {
		void *ptr = vmalloc(size);
		if (ptr)
			memset(ptr, 0, size);
		return ptr;
	}
}

/**
 * pcpu_mem_free - free memory
 * @ptr: memory to free
 * @size: size of the area
 *
 * Free @ptr.  @ptr should have been allocated using pcpu_mem_alloc().
 */
static void pcpu_mem_free(void *ptr, size_t size)
{
	if (size <= PAGE_SIZE)
		kfree(ptr);
	else
		vfree(ptr);
}

/**
 * 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.  Note that the reserved chunk is never put on
 * chunk slots.
 *
 * CONTEXT:
 * pcpu_lock.
 */
static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
{
	int nslot = pcpu_chunk_slot(chunk);

	if (chunk != pcpu_reserved_chunk && oslot != nslot) {
		if (oslot < nslot)
			list_move(&chunk->list, &pcpu_slot[nslot]);
		else
			list_move_tail(&chunk->list, &pcpu_slot[nslot]);
	}
}

/**
 * pcpu_chunk_addr_search - determine chunk containing specified address
 * @addr: address for which the chunk needs to be determined.
 *
 * RETURNS:
 * The address of the found chunk.
 */
static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
{
	void *first_start = pcpu_first_chunk->vm->addr;

	/* is it in the first chunk? */
	if (addr >= first_start && addr < first_start + pcpu_unit_size) {
		/* is it in the reserved area? */
		if (addr < first_start + pcpu_reserved_chunk_limit)
			return pcpu_reserved_chunk;
		return pcpu_first_chunk;
	}

	return pcpu_get_page_chunk(vmalloc_to_page(addr));
}

/**
 * pcpu_extend_area_map - extend area map for allocation
 * @chunk: target chunk
 *
 * Extend area map of @chunk so that it can accomodate an allocation.
 * A single allocation can split an area into three areas, so this
 * function makes sure that @chunk->map has at least two extra slots.
 *
 * CONTEXT:
 * pcpu_alloc_mutex, pcpu_lock.  pcpu_lock is released and reacquired
 * if area map is extended.
 *
 * RETURNS:
 * 0 if noop, 1 if successfully extended, -errno on failure.
 */
static int pcpu_extend_area_map(struct pcpu_chunk *chunk)
{
	int new_alloc;
	int *new;
	size_t size;

	/* has enough? */
	if (chunk->map_alloc >= chunk->map_used + 2)
		return 0;

	spin_unlock_irq(&pcpu_lock);

	new_alloc = PCPU_DFL_MAP_ALLOC;
	while (new_alloc < chunk->map_used + 2)
		new_alloc *= 2;

	new = pcpu_mem_alloc(new_alloc * sizeof(new[0]));
	if (!new) {
		spin_lock_irq(&pcpu_lock);
		return -ENOMEM;
	}

	/*
	 * Acquire pcpu_lock and switch to new area map.  Only free
	 * could have happened inbetween, so map_used couldn't have
	 * grown.
	 */
	spin_lock_irq(&pcpu_lock);
	BUG_ON(new_alloc < chunk->map_used + 2);

	size = chunk->map_alloc * sizeof(chunk->map[0]);
	memcpy(new, chunk->map, size);

	/*
	 * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is
	 * one of the first chunks and still using static map.
	 */
	if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC)
		pcpu_mem_free(chunk->map, size);

	chunk->map_alloc = new_alloc;
	chunk->map = new;
	return 0;
}

/**
 * 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.
 *
 * @chunk->map must have enough free slots to accomodate the split.
 *
 * CONTEXT:
 * pcpu_lock.
 */
static void pcpu_split_block(struct pcpu_chunk *chunk, int i,
			     int head, int tail)
{
	int nr_extra = !!head + !!tail;

	BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra);

	/* insert new subblocks */
	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;
	}
}

/**
 * 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.
 *
 * @chunk->map must have at least two free slots.
 *
 * CONTEXT:
 * pcpu_lock.
 *
 * RETURNS:
 * Allocated offset in @chunk on success, -1 if no matching area is
 * found.
 */
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;

	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) {
			pcpu_split_block(chunk, i, head, tail);
			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 matching area */
	return -1;
}

/**
 * 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.
 *
 * CONTEXT:
 * pcpu_lock.
 */
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_tlb: whether to flush 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_tlb)
{
	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.
	 */
	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_tlb)
		flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start),
				       pcpu_chunk_addr(chunk, last, 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 - 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 = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start),
				       pcpu_chunk_pagep(chunk, cpu, page_start),
				       page_end - 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_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,
				  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_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)
{
	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 uninitialized_var(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;
			pcpu_set_page_chunk(*pagep, chunk);
		}
	}

	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_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[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_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
	chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
	chunk->map[chunk->map_used++] = pcpu_unit_size;
	chunk->page = chunk->page_ar;

	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;
}

/**
 * pcpu_alloc - the percpu allocator
 * @size: size of area to allocate in bytes
 * @align: alignment of area (max PAGE_SIZE)
 * @reserved: allocate from the reserved chunk if available
 *
 * Allocate percpu area of @size bytes aligned at @align.
 *
 * CONTEXT:
 * Does GFP_KERNEL allocation.
 *
 * RETURNS:
 * Percpu pointer to the allocated area on success, NULL on failure.
 */
static void *pcpu_alloc(size_t size, size_t align, bool reserved)
{
	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_alloc_mutex);
	spin_lock_irq(&pcpu_lock);

	/* serve reserved allocations from the reserved chunk if available */
	if (reserved && pcpu_reserved_chunk) {
		chunk = pcpu_reserved_chunk;
		if (size > chunk->contig_hint ||
		    pcpu_extend_area_map(chunk) < 0)
			goto fail_unlock;
		off = pcpu_alloc_area(chunk, size, align);
		if (off >= 0)
			goto area_found;
		goto fail_unlock;
	}

restart:
	/* search through normal chunks */
	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;

			switch (pcpu_extend_area_map(chunk)) {
			case 0:
				break;
			case 1:
				goto restart;	/* pcpu_lock dropped, restart */
			default:
				goto fail_unlock;
			}

			off = pcpu_alloc_area(chunk, size, align);
			if (off >= 0)
				goto area_found;
		}
	}

	/* hmmm... no space left, create a new chunk */
	spin_unlock_irq(&pcpu_lock);

	chunk = alloc_pcpu_chunk();
	if (!chunk)
		goto fail_unlock_mutex;

	spin_lock_irq(&pcpu_lock);
	pcpu_chunk_relocate(chunk, -1);
	goto restart;

area_found:
	spin_unlock_irq(&pcpu_lock);

	/* populate, map and clear the area */
	if (pcpu_populate_chunk(chunk, off, size)) {
		spin_lock_irq(&pcpu_lock);
		pcpu_free_area(chunk, off);
		goto fail_unlock;
	}

	mutex_unlock(&pcpu_alloc_mutex);

	return __addr_to_pcpu_ptr(chunk->vm->addr + off);

fail_unlock:
	spin_unlock_irq(&pcpu_lock);
fail_unlock_mutex:
	mutex_unlock(&pcpu_alloc_mutex);
	return NULL;
}

/**
 * __alloc_percpu - allocate dynamic 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.
 *
 * CONTEXT:
 * Does GFP_KERNEL allocation.
 *
 * RETURNS:
 * Percpu pointer to the allocated area on success, NULL on failure.
 */
void *__alloc_percpu(size_t size, size_t align)
{
	return pcpu_alloc(size, align, false);
}
EXPORT_SYMBOL_GPL(__alloc_percpu);

/**
 * __alloc_reserved_percpu - allocate reserved 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 from reserved
 * percpu area if arch has set it up; otherwise, allocation is served
 * from the same dynamic area.  Might sleep.  Might trigger writeouts.
 *
 * CONTEXT:
 * Does GFP_KERNEL allocation.
 *
 * RETURNS:
 * Percpu pointer to the allocated area on success, NULL on failure.
 */
void *__alloc_reserved_percpu(size_t size, size_t align)
{
	return pcpu_alloc(size, align, true);
}

/**
 * pcpu_reclaim - reclaim fully free chunks, workqueue function
 * @work: unused
 *
 * Reclaim all fully free chunks except for the first one.
 *
 * CONTEXT:
 * workqueue context.
 */
static void pcpu_reclaim(struct work_struct *work)
{
	LIST_HEAD(todo);
	struct list_head *head = &pcpu_slot[pcpu_nr_slots - 1];
	struct pcpu_chunk *chunk, *next;

	mutex_lock(&pcpu_alloc_mutex);
	spin_lock_irq(&pcpu_lock);

	list_for_each_entry_safe(chunk, next, head, list) {
		WARN_ON(chunk->immutable);

		/* spare the first one */
		if (chunk == list_first_entry(head, struct pcpu_chunk, list))
			continue;

		list_move(&chunk->list, &todo);
	}

	spin_unlock_irq(&pcpu_lock);
	mutex_unlock(&pcpu_alloc_mutex);

	list_for_each_entry_safe(chunk, next, &todo, list) {
		pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false);
		free_pcpu_chunk(chunk);
	}
}

/**
 * free_percpu - free percpu area
 * @ptr: pointer to area to free
 *
 * Free percpu area @ptr.
 *
 * CONTEXT:
 * Can be called from atomic context.
 */
void free_percpu(void *ptr)
{
	void *addr = __pcpu_ptr_to_addr(ptr);
	struct pcpu_chunk *chunk;
	unsigned long flags;
	int off;

	if (!ptr)
		return;

	spin_lock_irqsave(&pcpu_lock, flags);

	chunk = pcpu_chunk_addr_search(addr);
	off = addr - chunk->vm->addr;

	pcpu_free_area(chunk, off);

	/* if there are more than one fully free chunks, wake up grim reaper */
	if (chunk->free_size == pcpu_unit_size) {
		struct pcpu_chunk *pos;

		list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list)
			if (pos != chunk) {
				schedule_work(&pcpu_reclaim_work);
				break;
			}
	}

	spin_unlock_irqrestore(&pcpu_lock, flags);
}
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
 * @reserved_size: the size of reserved percpu area in bytes, 0 for none
 * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
 * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE
 * @base_addr: mapped address
 *
 * Initialize the first percpu chunk which contains the kernel static
 * perpcu area.  This function is to be called from arch percpu area
 * setup path.
 *
 * @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.  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