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 boot-time determined number of 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.  On UMA, units corresponds directly to
 * cpus.  On NUMA, the mapping can be non-linear and even sparse.
 * Percpu access can be done by configuring percpu base registers
 * according to cpu to unit mapping and pcpu_unit_size.
 *
 * There are usually many small percpu allocations many of them being
 * 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/err.h>
#include <linux/list.h>
#include <linux/log2.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 */
	void			*base_addr;	/* base address of this chunk */
	int			map_used;	/* # of map entries used */
	int			map_alloc;	/* # of map entries allocated */
	int			*map;		/* allocation map */
	struct vm_struct	**vms;		/* mapped vmalloc regions */
	bool			immutable;	/* no [de]population allowed */
	unsigned long		populated[];	/* populated bitmap */
};

static int pcpu_unit_pages __read_mostly;
static int pcpu_unit_size __read_mostly;
static int pcpu_nr_units __read_mostly;
static int pcpu_atom_size __read_mostly;
static int pcpu_nr_slots __read_mostly;
static size_t pcpu_chunk_struct_size __read_mostly;

/* cpus with the lowest and highest unit numbers */
static unsigned int pcpu_first_unit_cpu __read_mostly;
static unsigned int pcpu_last_unit_cpu __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);

static const int *pcpu_unit_map __read_mostly;		/* cpu -> unit */
const unsigned long *pcpu_unit_offsets __read_mostly;	/* cpu -> unit offset */

/* group information, used for vm allocation */
static int pcpu_nr_groups __read_mostly;
static const unsigned long *pcpu_group_offsets __read_mostly;
static const size_t *pcpu_group_sizes __read_mostly;

/*
 * 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, populated bitmap and
 * vmalloc mapping.  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.  In
 * general, percpu memory can't be allocated with irq off but
 * irqsave/restore are still used in alloc path so that it can be used
 * from early init path - sched_init() specifically.
 *
 * 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 pcpu_unit_map[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->base_addr + pcpu_unit_offsets[cpu] +
		(page_idx << PAGE_SHIFT);
}

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));
}

/* 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;
}

static void pcpu_next_unpop(struct pcpu_chunk *chunk, int *rs, int *re, int end)
{
	*rs = find_next_zero_bit(chunk->populated, end, *rs);
	*re = find_next_bit(chunk->populated, end, *rs + 1);
}

static void pcpu_next_pop(struct pcpu_chunk *chunk, int *rs, int *re, int end)
{
	*rs = find_next_bit(chunk->populated, end, *rs);
	*re = find_next_zero_bit(chunk->populated, end, *rs + 1);
}

/*
 * (Un)populated page region iterators.  Iterate over (un)populated
 * page regions betwen @start and @end in @chunk.  @rs and @re should
 * be integer variables and will be set to start and end page index of
 * the current region.
 */
#define pcpu_for_each_unpop_region(chunk, rs, re, start, end)		    \
	for ((rs) = (start), pcpu_next_unpop((chunk), &(rs), &(re), (end)); \
	     (rs) < (re);						    \
	     (rs) = (re) + 1, pcpu_next_unpop((chunk), &(rs), &(re), (end)))

#define pcpu_for_each_pop_region(chunk, rs, re, start, end)		    \
	for ((rs) = (start), pcpu_next_pop((chunk), &(rs), &(re), (end));   \
	     (rs) < (re);						    \
	     (rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end)))

/**
 * 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->base_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;
	}

	/*
	 * The address is relative to unit0 which might be unused and
	 * thus unmapped.  Offset the address to the unit space of the
	 * current processor before looking it up in the vmalloc
	 * space.  Note that any possible cpu id can be used here, so
	 * there's no need to worry about preemption or cpu hotplug.
	 */
	addr += pcpu_unit_offsets[raw_smp_processor_id()];
	return pcpu_get_page_chunk(vmalloc_to_page(addr));
}

/**
 * pcpu_need_to_extend - determine whether chunk area map needs to be extended
 * @chunk: chunk of interest
 *
 * Determine whether area map of @chunk needs to be extended to
 * accomodate a new allocation.
 *
 * CONTEXT:
 * pcpu_lock.
 *
 * RETURNS:
 * New target map allocation length if extension is necessary, 0
 * otherwise.
 */
static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
{
	int new_alloc;

	if (chunk->map_alloc >= chunk->map_used + 2)
		return 0;

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

	return new_alloc;
}

/**
 * pcpu_extend_area_map - extend area map of a chunk
 * @chunk: chunk of interest
 * @new_alloc: new target allocation length of the area map
 *
 * Extend area map of @chunk to have @new_alloc entries.
 *
 * CONTEXT:
 * Does GFP_KERNEL allocation.  Grabs and releases pcpu_lock.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
{
	int *old = NULL, *new = NULL;
	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
	unsigned long flags;

	new = pcpu_mem_alloc(new_size);
	if (!new)
		return -ENOMEM;

	/* acquire pcpu_lock and switch to new area map */
	spin_lock_irqsave(&pcpu_lock, flags);

	if (new_alloc <= chunk->map_alloc)
		goto out_unlock;

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

	chunk->map_alloc = new_alloc;
	chunk->map = new;
	new = NULL;

out_unlock:
	spin_unlock_irqrestore(&pcpu_lock, flags);

	/*
	 * pcpu_mem_free() might end up calling vfree() which uses
	 * IRQ-unsafe lock and thus can't be called under pcpu_lock.
	 */
	pcpu_mem_free(old, old_size);
	pcpu_mem_free(new, new_size);

	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_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_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 */
	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
		if (rs == page_start && re == page_end)
			return;
		break;
	}

	/* 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);
}

/**
 * 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 */
	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) {
		if (rs == page_start && re == page_end)
			goto clear;
		break;
	}

	/* 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);