percpu.c

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->vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
				       pcpu_nr_groups, pcpu_atom_size,
				       GFP_KERNEL);
	if (!chunk->vms) {
		free_pcpu_chunk(chunk);
		return NULL;
	}

	INIT_LIST_HEAD(&chunk->list);
	chunk->free_size = pcpu_unit_size;
	chunk->contig_hint = pcpu_unit_size;
	chunk->base_addr = chunk->vms[0]->addr - pcpu_group_offsets[0];

	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 address relative to base address */
	return __addr_to_pcpu_ptr(chunk->base_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);

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

	mutex_unlock(&pcpu_alloc_mutex);
}

/**
 * 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->base_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);

static inline size_t pcpu_calc_fc_sizes(size_t static_size,
					size_t reserved_size,
					ssize_t *dyn_sizep)
{
	size_t size_sum;

	size_sum = PFN_ALIGN(static_size + reserved_size +
			     (*dyn_sizep >= 0 ? *dyn_sizep : 0));
	if (*dyn_sizep != 0)
		*dyn_sizep = size_sum - static_size - reserved_size;

	return size_sum;
}

/**
 * pcpu_alloc_alloc_info - allocate percpu allocation info
 * @nr_groups: the number of groups
 * @nr_units: the number of units
 *
 * Allocate ai which is large enough for @nr_groups groups containing
 * @nr_units units.  The returned ai's groups[0].cpu_map points to the
 * cpu_map array which is long enough for @nr_units and filled with
 * NR_CPUS.  It's the caller's responsibility to initialize cpu_map
 * pointer of other groups.
 *
 * RETURNS:
 * Pointer to the allocated pcpu_alloc_info on success, NULL on
 * failure.
 */
struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
						      int nr_units)
{
	struct pcpu_alloc_info *ai;
	size_t base_size, ai_size;
	void *ptr;
	int unit;

	base_size = ALIGN(sizeof(*ai) + nr_groups * sizeof(ai->groups[0]),
			  __alignof__(ai->groups[0].cpu_map[0]));
	ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]);

	ptr = alloc_bootmem_nopanic(PFN_ALIGN(ai_size));
	if (!ptr)
		return NULL;
	ai = ptr;
	ptr += base_size;

	ai->groups[0].cpu_map = ptr;

	for (unit = 0; unit < nr_units; unit++)
		ai->groups[0].cpu_map[unit] = NR_CPUS;

	ai->nr_groups = nr_groups;
	ai->__ai_size = PFN_ALIGN(ai_size);

	return ai;
}

/**
 * pcpu_free_alloc_info - free percpu allocation info
 * @ai: pcpu_alloc_info to free
 *
 * Free @ai which was allocated by pcpu_alloc_alloc_info().
 */
void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
{
	free_bootmem(__pa(ai), ai->__ai_size);
}

/**
 * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
 * @atom_size: allocation atom size
 * @cpu_distance_fn: callback to determine distance between cpus, optional
 *
 * This function determines grouping of units, their mappings to cpus
 * and other parameters considering needed percpu size, allocation
 * atom size and distances between CPUs.
 *
 * Groups are always mutliples of atom size and CPUs which are of
 * LOCAL_DISTANCE both ways are grouped together and share space for
 * units in the same group.  The returned configuration is guaranteed
 * to have CPUs on different nodes on different groups and >=75% usage
 * of allocated virtual address space.
 *
 * RETURNS:
 * On success, pointer to the new allocation_info is returned.  On
 * failure, ERR_PTR value is returned.
 */
struct pcpu_alloc_info * __init pcpu_build_alloc_info(
				size_t reserved_size, ssize_t dyn_size,
				size_t atom_size,
				pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
{
	static int group_map[NR_CPUS] __initdata;
	static int group_cnt[NR_CPUS] __initdata;
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	int group_cnt_max = 0, nr_groups = 1, nr_units = 0;
	size_t size_sum, min_unit_size, alloc_size;
	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
	int last_allocs, group, unit;
	unsigned int cpu, tcpu;
	struct pcpu_alloc_info *ai;
	unsigned int *cpu_map;

	/* this function may be called multiple times */
	memset(group_map, 0, sizeof(group_map));
	memset(group_cnt, 0, sizeof(group_map));

	/*
	 * Determine min_unit_size, alloc_size and max_upa such that
	 * alloc_size is multiple of atom_size and is the smallest
	 * which can accomodate 4k aligned segments which are equal to
	 * or larger than min_unit_size.
	 */
	size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, &dyn_size);
	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);

	alloc_size = roundup(min_unit_size, atom_size);
	upa = alloc_size / min_unit_size;
	while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
		upa--;
	max_upa = upa;

	/* group cpus according to their proximity */
	for_each_possible_cpu(cpu) {
		group = 0;
	next_group:
		for_each_possible_cpu(tcpu) {
			if (cpu == tcpu)
				break;
			if (group_map[tcpu] == group && cpu_distance_fn &&
			    (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
				group++;
				nr_groups = max(nr_groups, group + 1);
				goto next_group;
			}
		}
		group_map[cpu] = group;
		group_cnt[group]++;
		group_cnt_max = max(group_cnt_max, group_cnt[group]);
	}

	/*
	 * Expand unit size until address space usage goes over 75%
	 * and then as much as possible without using more address
	 * space.
	 */
	last_allocs = INT_MAX;
	for (upa = max_upa; upa; upa--) {
		int allocs = 0, wasted = 0;

		if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
			continue;

		for (group = 0; group < nr_groups; group++) {
			int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
			allocs += this_allocs;
			wasted += this_allocs * upa - group_cnt[group];
		}

		/*
		 * Don't accept if wastage is over 25%.  The
		 * greater-than comparison ensures upa==1 always
		 * passes the following check.
		 */
		if (wasted > num_possible_cpus() / 3)
			continue;

		/* and then don't consume more memory */
		if (allocs > last_allocs)
			break;
		last_allocs = allocs;
		best_upa = upa;
	}
	upa = best_upa;

	/* allocate and fill alloc_info */
	for (group = 0; group < nr_groups; group++)
		nr_units += roundup(group_cnt[group], upa);

	ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
	if (!ai)
		return ERR_PTR(-ENOMEM);
	cpu_map = ai->groups[0].cpu_map;

	for (group = 0; group < nr_groups; group++) {
		ai->groups[group].cpu_map = cpu_map;
		cpu_map += roundup(group_cnt[group], upa);
	}

	ai->static_size = static_size;
	ai->reserved_size = reserved_size;
	ai->dyn_size = dyn_size;
	ai->unit_size = alloc_size / upa;
	ai->atom_size = atom_size;
	ai->alloc_size = alloc_size;

	for (group = 0, unit = 0; group_cnt[group]; group++) {
		struct pcpu_group_info *gi = &ai->groups[group];

		/*
		 * Initialize base_offset as if all groups are located
		 * back-to-back.  The caller should update this to
		 * reflect actual allocation.
		 */
		gi->base_offset = unit * ai->unit_size;

		for_each_possible_cpu(cpu)
			if (group_map[cpu] == group)
				gi->cpu_map[gi->nr_units++] = cpu;
		gi->nr_units = roundup(gi->nr_units, upa);
		unit += gi->nr_units;
	}
	BUG_ON(unit != nr_units);

	return ai;
}

/**
 * pcpu_dump_alloc_info - print out information about pcpu_alloc_info
 * @lvl: loglevel
 * @ai: allocation info to dump
 *
 * Print out information about @ai using loglevel @lvl.
 */
static void pcpu_dump_alloc_info(const char *lvl,
				 const struct pcpu_alloc_info *ai)
{
	int group_width = 1, cpu_width = 1, width;
	char empty_str[] = "--------";
	int alloc = 0, alloc_end = 0;
	int group, v;
	int upa, apl;	/* units per alloc, allocs per line */

	v = ai->nr_groups;
	while (v /= 10)
		group_width++;

	v = num_possible_cpus();
	while (v /= 10)
		cpu_width++;
	empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0';

	upa = ai->alloc_size / ai->unit_size;
	width = upa * (cpu_width + 1) + group_width + 3;
	apl = rounddown_pow_of_two(max(60 / width, 1));

	printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu",
	       lvl, ai->static_size, ai->reserved_size, ai->dyn_size,
	       ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size);

	for (group = 0; group < ai->nr_groups; group++) {
		const struct pcpu_group_info *gi = &ai->groups[group];
		int unit = 0, unit_end = 0;

		BUG_ON(gi->nr_units % upa);
		for (alloc_end += gi->nr_units / upa;
		     alloc < alloc_end; alloc++) {
			if (!(alloc % apl)) {
				printk("\n");
				printk("%spcpu-alloc: ", lvl);
			}
			printk("[%0*d] ", group_width, group);

			for (unit_end += upa; unit < unit_end; unit++)
				if (gi->cpu_map[unit] != NR_CPUS)
					printk("%0*d ", cpu_width,
					       gi->cpu_map[unit]);
				else
					printk("%s ", empty_str);
		}
	}
	printk("\n");
}

/**
 * pcpu_setup_first_chunk - initialize the first percpu chunk
 * @ai: pcpu_alloc_info describing how to percpu area is shaped
 * @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.
 *
 * @ai contains all information necessary to initialize the first
 * chunk and prime the dynamic percpu allocator.
 *
 * @ai->static_size is the size of static percpu area.
 *
 * @ai->reserved_size, if non-zero, specifies the amount of bytes to
 * reserve after the static area in the first chunk.  This reserves
 * the first chunk such that it's available only through reserved
 * percpu allocation.  This is primarily used to serve module percpu
 * static areas on architectures where the addressing model has
 * limited offset range for symbol relocations to guarantee module
 * percpu symbols fall inside the relocatable range.
 *
 * @ai->dyn_size determines the number of bytes available for dynamic
 * allocation in the first chunk.  The area between @ai->static_size +
 * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused.
 *
 * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE
 * and equal to or larger than @ai->static_size + @ai->reserved_size +
 * @ai->dyn_size.
 *
 * @ai->atom_size is the allocation atom size and used as alignment
 * for vm areas.
 *
 * @ai->alloc_size is the allocation size and always multiple of
 * @ai->atom_size.  This is larger than @ai->atom_size if
 * @ai->unit_size is larger than @ai->atom_size.
 *
 * @ai->nr_groups and @ai->groups describe virtual memory layout of
 * percpu areas.  Units which should be colocated are put into the
 * same group.  Dynamic VM areas will be allocated according to these
 * groupings.  If @ai->nr_groups is zero, a single group containing
 * all units is assumed.
 *
 * The caller should have mapped the first chunk at @base_addr and
 * copied static data to each unit.
 *
 * If the first chunk ends up with both reserved and dynamic areas, it
 * is served by two chunks - one to serve the core static and reserved
 * areas and the other for the dynamic area.  They share the same vm
 * and page map but uses different area allocation map to stay away
 * from each other.  The latter chunk is circulated in the chunk slots
 * and available for dynamic allocation like any other chunks.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
				  void *base_addr)
{
	static int smap[2], dmap[2];
	size_t dyn_size = ai->dyn_size;
	size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
	struct pcpu_chunk *schunk, *dchunk = NULL;
	unsigned long *group_offsets;
	size_t *group_sizes;
	unsigned long *unit_off;
	unsigned int cpu;
	int *unit_map;
	int group, unit, i;

	/* sanity checks */
	BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC ||
		     ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
	BUG_ON(ai->nr_groups <= 0);
	BUG_ON(!ai->static_size);
	BUG_ON(!base_addr);
	BUG_ON(ai->unit_size < size_sum);
	BUG_ON(ai->unit_size & ~PAGE_MASK);
	BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);

	pcpu_dump_alloc_info(KERN_DEBUG, ai);

	/* process group information and build config tables accordingly */
	group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));
	group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0]));
	unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0]));
	unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0]));

	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
		unit_map[cpu] = UINT_MAX;
	pcpu_first_unit_cpu = NR_CPUS;

	for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
		const struct pcpu_group_info *gi = &ai->groups[group];

		group_offsets[group] = gi->base_offset;
		group_sizes[group] = gi->nr_units * ai->unit_size;

		for (i = 0; i < gi->nr_units; i++) {
			cpu = gi->cpu_map[i];
			if (cpu == NR_CPUS)
				continue;

			BUG_ON(cpu > nr_cpu_ids || !cpu_possible(cpu));
			BUG_ON(unit_map[cpu] != UINT_MAX);

			unit_map[cpu] = unit + i;
			unit_off[cpu] = gi->base_offset + i * ai->unit_size;

			if (pcpu_first_unit_cpu == NR_CPUS)
				pcpu_first_unit_cpu = cpu;
		}
	}
	pcpu_last_unit_cpu = cpu;
	pcpu_nr_units = unit;

	for_each_possible_cpu(cpu)
		BUG_ON(unit_map[cpu] == UINT_MAX);

	pcpu_nr_groups = ai->nr_groups;
	pcpu_group_offsets = group_offsets;
	pcpu_group_sizes = group_sizes;
	pcpu_unit_map = unit_map;
	pcpu_unit_offsets = unit_off;

	/* determine basic parameters */
	pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
	pcpu_atom_size = ai->atom_size;
	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
		BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);

	/*
	 * 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]);

	/*
	 * Initialize static chunk.  If reserved_size is zero, the
	 * static chunk covers static area + dynamic allocation area
	 * in the first chunk.  If reserved_size is not zero, it
	 * covers static area + reserved area (mostly used for module
	 * static percpu allocation).
	 */
	schunk = alloc_bootmem(pcpu_chunk_struct_size);
	INIT_LIST_HEAD(&schunk->list);
	schunk->base_addr = base_addr;
	schunk->map = smap;
	schunk->map_alloc = ARRAY_SIZE(smap);
	schunk->immutable = true;
	bitmap_fill(schunk->populated, pcpu_unit_pages);

	if (ai->reserved_size) {
		schunk->free_size = ai->reserved_size;
		pcpu_reserved_chunk = schunk;
		pcpu_reserved_chunk_limit = ai->static_size + ai->reserved_size;
	} else {
		schunk->free_size = dyn_size;
		dyn_size = 0;			/* dynamic area covered */
	}
	schunk->contig_hint = schunk->free_size;

	schunk->map[schunk->map_used++] = -ai->static_size;
	if (schunk->free_size)
		schunk->map[schunk->map_used++] = schunk->free_size;

	/* init dynamic chunk if necessary */
	if (dyn_size) {
		dchunk = alloc_bootmem(pcpu_chunk_struct_size);
		INIT_LIST_HEAD(&dchunk->list);
		dchunk->base_addr = base_addr;
		dchunk->map = dmap;
		dchunk->map_alloc = ARRAY_SIZE(dmap);
		dchunk->immutable = true;
		bitmap_fill(dchunk->populated, pcpu_unit_pages);

		dchunk->contig_hint = dchunk->free_size = dyn_size;
		dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit;
		dchunk->map[dchunk->map_used++] = dchunk->free_size;
	}

	/* link the first chunk in */
	pcpu_first_chunk = dchunk ?: schunk;
	pcpu_chunk_relocate(pcpu_first_chunk, -1);

	/* we're done */
	pcpu_base_addr = base_addr;
	return 0;
}

const char *pcpu_fc_names[PCPU_FC_NR] __initdata = {
	[PCPU_FC_AUTO]	= "auto",
	[PCPU_FC_EMBED]	= "embed",
	[PCPU_FC_PAGE]	= "page",
};

enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;

static int __init percpu_alloc_setup(char *str)
{
	if (0)
		/* nada */;
#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
	else if (!strcmp(str, "embed"))
		pcpu_chosen_fc = PCPU_FC_EMBED;
#endif
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
	else if (!strcmp(str, "page"))
		pcpu_chosen_fc = PCPU_FC_PAGE;
#endif
	else
		pr_warning("PERCPU: unknown allocator %s specified\n", str);

	return 0;
}
early_param("percpu_alloc", percpu_alloc_setup);

#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
/**
 * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
 * @atom_size: allocation atom size
 * @cpu_distance_fn: callback to determine distance between cpus, optional
 * @alloc_fn: function to allocate percpu page
 * @free_fn: funtion to free percpu page
 *
 * This is a helper to ease setting up embedded first percpu chunk and
 * can be called where pcpu_setup_first_chunk() is expected.
 *
 * If this function is used to setup the first chunk, it is allocated
 * by calling @alloc_fn and used as-is without being mapped into
 * vmalloc area.  Allocations are always whole multiples of @atom_size
 * aligned to @atom_size.
 *
 * This enables the first chunk to piggy back on the linear physical
 * mapping which often uses larger page size.  Please note that this
 * can result in very sparse cpu->unit mapping on NUMA machines thus
 * requiring large vmalloc address space.  Don't use this allocator if
 * vmalloc space is not orders of magnitude larger than distances
 * between node memory addresses (ie. 32bit NUMA machines).
 *
 * When @dyn_size is positive, dynamic area might be larger than
 * specified to fill page alignment.  When @dyn_size is auto,
 * @dyn_size is just big enough to fill page alignment after static
 * and reserved areas.
 *
 * If the needed size is smaller than the minimum or specified unit
 * size, the leftover is returned using @free_fn.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
				  size_t atom_size,
				  pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
				  pcpu_fc_alloc_fn_t alloc_fn,
				  pcpu_fc_free_fn_t free_fn)
{
	void *base = (void *)ULONG_MAX;
	void **areas = NULL;
	struct pcpu_alloc_info *ai;
	size_t size_sum, areas_size;
	int group, i, rc;

	ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
				   cpu_distance_fn);
	if (IS_ERR(ai))
		return PTR_ERR(ai);

	size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
	areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *));

	areas = alloc_bootmem_nopanic(areas_size);
	if (!areas) {
		rc = -ENOMEM;
		goto out_free;
	}

	/* allocate, copy and determine base address */
	for (group = 0; group < ai->nr_groups; group++) {
		struct pcpu_group_info *gi = &ai->groups[group];
		unsigned int cpu = NR_CPUS;
		void *ptr;

		for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++)
			cpu = gi->cpu_map[i];
		BUG_ON(cpu == NR_CPUS);

		/* allocate space for the whole group */
		ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size);
		if (!ptr) {
			rc = -ENOMEM;
			goto out_free_areas;
		}
		areas[group] = ptr;

		base = min(ptr, base);

		for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
			if (gi->cpu_map[i] == NR_CPUS) {
				/* unused unit, free whole */
				free_fn(ptr, ai->unit_size);
				continue;
			}
			/* copy and return the unused part */
			memcpy(ptr, __per_cpu_load, ai->static_size);
			free_fn(ptr + size_sum, ai->unit_size - size_sum);
		}
	}

	/* base address is now known, determine group base offsets */
	for (group = 0; group < ai->nr_groups; group++)
		ai->groups[group].base_offset = areas[group] - base;

	pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
		PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,
		ai->dyn_size, ai->unit_size);

	rc = pcpu_setup_first_chunk(ai, base);
	goto out_free;

out_free_areas:
	for (group = 0; group < ai->nr_groups; group++)
		free_fn(areas[group],
			ai->groups[group].nr_units * ai->unit_size);
out_free:
	pcpu_free_alloc_info(ai);
	if (areas)
		free_bootmem(__pa(areas), areas_size);
	return rc;
}
#endif /* CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK ||
	  !CONFIG_HAVE_SETUP_PER_CPU_AREA */

#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
/**
 * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
 * @reserved_size: the size of reserved percpu area in bytes
 * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE
 * @free_fn: funtion to free percpu page, always called with PAGE_SIZE
 * @populate_pte_fn: function to populate pte
 *
 * This is a helper to ease setting up page-remapped first percpu
 * chunk and can be called where pcpu_setup_first_chunk() is expected.
 *
 * This is the basic allocator.  Static percpu area is allocated
 * page-by-page into vmalloc area.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int __init pcpu_page_first_chunk(size_t reserved_size,
				 pcpu_fc_alloc_fn_t alloc_fn,
				 pcpu_fc_free_fn_t free_fn,
				 pcpu_fc_populate_pte_fn_t populate_pte_fn)
{
	static struct vm_struct vm;
	struct pcpu_alloc_info *ai;
	char psize_str[16];
	int unit_pages;
	size_t pages_size;
	struct page **pages;
	int unit, i, j, rc;

	snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10);

	ai = pcpu_build_alloc_info(reserved_size, -1, PAGE_SIZE, NULL);
	if (IS_ERR(ai))
		return PTR_ERR(ai);
	BUG_ON(ai->nr_groups != 1);
	BUG_ON(ai->groups[0].nr_units != num_possible_cpus());

	unit_pages = ai->unit_size >> PAGE_SHIFT;

	/* unaligned allocations can't be freed, round up to page size */
	pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() *
			       sizeof(pages[0]));
	pages = alloc_bootmem(pages_size);

	/* allocate pages */
	j = 0;
	for (unit = 0; unit < num_possible_cpus(); unit++)
		for (i = 0; i < unit_pages; i++) {
			unsigned int cpu = ai->groups[0].cpu_map[unit];
			void *ptr;

			ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE);
			if (!ptr) {
				pr_warning("PERCPU: failed to allocate %s page "
					   "for cpu%u\n", psize_str, cpu);
				goto enomem;
			}
			pages[j++] = virt_to_page(ptr);
		}

	/* allocate vm area, map the pages and copy static data */
	vm.flags = VM_ALLOC;
	vm.size = num_possible_cpus() * ai->unit_size;
	vm_area_register_early(&vm, PAGE_SIZE);

	for (unit = 0; unit < num_possible_cpus(); unit++) {
		unsigned long unit_addr =
			(unsigned long)vm.addr + unit * ai->unit_size;

		for (i = 0; i < unit_pages; i++)
			populate_pte_fn(unit_addr + (i << PAGE_SHIFT));

		/* pte already populated, the following shouldn't fail */
		rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages],
				      unit_pages);
		if (rc < 0)
			panic("failed to map percpu area, err=%d\n", rc);

		/*
		 * FIXME: Archs with virtual cache should flush local
		 * cache for the linear mapping here - something
		 * equivalent to flush_cache_vmap() on the local cpu.
		 * flush_cache_vmap() can't be used as most supporting
		 * data structures are not set up yet.
		 */

		/* copy static data */
		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
	}

	/* we're ready, commit */
	pr_info("PERCPU: %d %s pages/cpu @%p s%zu r%zu d%zu\n",
		unit_pages, psize_str, vm.addr, ai->static_size,
		ai->reserved_size, ai->dyn_size);

	rc = pcpu_setup_first_chunk(ai, vm.addr);
	goto out_free_ar;

enomem:
	while (--j >= 0)
		free_fn(page_address(pages[j]), PAGE_SIZE);
	rc = -ENOMEM;
out_free_ar:
	free_bootmem(__pa(pages), pages_size);
	pcpu_free_alloc_info(ai);
	return rc;
}
#endif /* CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK */

/*
 * Generic percpu area setup.
 *
 * The embedding helper is used because its behavior closely resembles
 * the original non-dynamic generic percpu area setup.  This is
 * important because many archs have addressing restrictions and might
 * fail if the percpu area is located far away from the previous
 * location.  As an added bonus, in non-NUMA cases, embedding is
 * generally a good idea TLB-wise because percpu area can piggy back
 * on the physical linear memory mapping which uses large page
 * mappings on applicable archs.
 */
#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);

static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size,
				       size_t align)
{
	return __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
}

static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
{
	free_bootmem(__pa(ptr), size);
}

void __init setup_per_cpu_areas(void)
{