percpu.c

		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->vm = get_vm_area(pcpu_chunk_size, VM_ALLOC);
	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 address relative to unit0 */
	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);

	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->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
 * @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
 * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE
 * @base_addr: mapped address
 * @unit_map: cpu -> unit map, NULL for sequential mapping
 *
 * Initialize the first percpu chunk which contains the kernel static
 * perpcu area.  This function is to be called from arch percpu area
 * setup path.
 *
 * @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.
 *
 * @dyn_size determines the number of bytes available for dynamic
 * allocation in the first chunk.  The area between @static_size +
 * @reserved_size + @dyn_size and @unit_size is unused.
 *
 * @unit_size specifies unit size and must be aligned to PAGE_SIZE and
 * equal to or larger than @static_size + @reserved_size + if
 * non-negative, @dyn_size.
 *
 * 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:
 * The determined pcpu_unit_size which can be used to initialize
 * percpu access.
 */
size_t __init pcpu_setup_first_chunk(size_t static_size, size_t reserved_size,
				     size_t dyn_size, size_t unit_size,
				     void *base_addr, const int *unit_map)
{
	static struct vm_struct first_vm;
	static int smap[2], dmap[2];
	size_t size_sum = static_size + reserved_size + dyn_size;
	struct pcpu_chunk *schunk, *dchunk = NULL;
	unsigned int cpu, tcpu;
	int i;

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

	/* determine number of units and verify and initialize pcpu_unit_map */
	if (unit_map) {
		int first_unit = INT_MAX, last_unit = INT_MIN;

		for_each_possible_cpu(cpu) {
			int unit = unit_map[cpu];

			BUG_ON(unit < 0);
			for_each_possible_cpu(tcpu) {
				if (tcpu == cpu)
					break;
				/* the mapping should be one-to-one */
				BUG_ON(unit_map[tcpu] == unit);
			}

			if (unit < first_unit) {
				pcpu_first_unit_cpu = cpu;
				first_unit = unit;
			}
			if (unit > last_unit) {
				pcpu_last_unit_cpu = cpu;
				last_unit = unit;
			}
		}
		pcpu_nr_units = last_unit + 1;
		pcpu_unit_map = unit_map;
	} else {
		int *identity_map;

		/* #units == #cpus, identity mapped */
		identity_map = alloc_bootmem(nr_cpu_ids *
					     sizeof(identity_map[0]));

		for_each_possible_cpu(cpu)
			identity_map[cpu] = cpu;

		pcpu_first_unit_cpu = 0;
		pcpu_last_unit_cpu = pcpu_nr_units - 1;
		pcpu_nr_units = nr_cpu_ids;
		pcpu_unit_map = identity_map;
	}

	/* determine basic parameters */
	pcpu_unit_pages = unit_size >> PAGE_SHIFT;
	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
	pcpu_chunk_size = pcpu_nr_units * pcpu_unit_size;
	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
		BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);

	first_vm.flags = VM_ALLOC;
	first_vm.size = pcpu_chunk_size;
	first_vm.addr = base_addr;

	/*
	 * 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->vm = &first_vm;
	schunk->map = smap;
	schunk->map_alloc = ARRAY_SIZE(smap);
	schunk->immutable = true;
	bitmap_fill(schunk->populated, pcpu_unit_pages);

	if (reserved_size) {
		schunk->free_size = reserved_size;
		pcpu_reserved_chunk = schunk;
		pcpu_reserved_chunk_limit = static_size + 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++] = -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->vm = &first_vm;
		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 = schunk->vm->addr;
	return pcpu_unit_size;
}

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

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
#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK
	else if (!strcmp(str, "lpage"))
		pcpu_chosen_fc = PCPU_FC_LPAGE;
#endif
	else
		pr_warning("PERCPU: unknown allocator %s specified\n", str);

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

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;
}

#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
 *
 * 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
 * as a contiguous area using bootmem allocator and used as-is without
 * being mapped into vmalloc area.  This enables the first chunk to
 * piggy back on the linear physical mapping which often uses larger
 * page size.
 *
 * 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 to the bootmem allocator.
 *
 * RETURNS:
 * The determined pcpu_unit_size which can be used to initialize
 * percpu access on success, -errno on failure.
 */
ssize_t __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size)
{
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	size_t size_sum, unit_size, chunk_size;
	void *base;
	unsigned int cpu;

	/* determine parameters and allocate */
	size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, &dyn_size);

	unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
	chunk_size = unit_size * nr_cpu_ids;

	base = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE,
				       __pa(MAX_DMA_ADDRESS));
	if (!base) {
		pr_warning("PERCPU: failed to allocate %zu bytes for "
			   "embedding\n", chunk_size);
		return -ENOMEM;
	}

	/* return the leftover and copy */
	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
		void *ptr = base + cpu * unit_size;

		if (cpu_possible(cpu)) {
			free_bootmem(__pa(ptr + size_sum),
				     unit_size - size_sum);
			memcpy(ptr, __per_cpu_load, static_size);
		} else
			free_bootmem(__pa(ptr), unit_size);
	}

	/* we're ready, commit */
	pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
		PFN_DOWN(size_sum), base, static_size, reserved_size, dyn_size,
		unit_size);

	return pcpu_setup_first_chunk(static_size, reserved_size, dyn_size,
				      unit_size, base, NULL);
}
#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:
 * The determined pcpu_unit_size which can be used to initialize
 * percpu access on success, -errno on failure.
 */
ssize_t __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;
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	ssize_t dyn_size = -1;
	size_t size_sum, unit_size;
	char psize_str[16];
	int unit_pages;
	size_t pages_size;
	struct page **pages;
	unsigned int cpu;
	int i, j;
	ssize_t ret;

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

	size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, &dyn_size);
	unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
	unit_pages = unit_size >> PAGE_SHIFT;

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

	/* allocate pages */
	j = 0;
	for_each_possible_cpu(cpu)
		for (i = 0; i < unit_pages; i++) {
			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 = nr_cpu_ids * unit_size;
	vm_area_register_early(&vm, PAGE_SIZE);

	for_each_possible_cpu(cpu) {
		unsigned long unit_addr =
			(unsigned long)vm.addr + cpu * 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 */
		ret = __pcpu_map_pages(unit_addr, &pages[cpu * unit_pages],
				       unit_pages);
		if (ret < 0)
			panic("failed to map percpu area, err=%zd\n", ret);

		/*
		 * 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, 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, static_size, reserved_size,
		dyn_size);

	ret = pcpu_setup_first_chunk(static_size, reserved_size, dyn_size,
				     unit_size, vm.addr, NULL);
	goto out_free_ar;

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

#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK
/**
 * pcpu_lpage_build_unit_map - build unit_map for large page remapping
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_sizep: in/out parameter for dynamic size, -1 for auto
 * @unit_sizep: out parameter for unit size
 * @unit_map: unit_map to be filled
 * @cpu_distance_fn: callback to determine distance between cpus
 *
 * This function builds cpu -> unit map and determine other parameters
 * considering needed percpu size, large page size and distances
 * between CPUs in NUMA.
 *
 * CPUs which are of LOCAL_DISTANCE both ways are grouped together and
 * may share units in the same large page.  The returned configuration
 * is guaranteed to have CPUs on different nodes on different large
 * pages and >=75% usage of allocated virtual address space.
 *
 * RETURNS:
 * On success, fills in @unit_map, sets *@dyn_sizep, *@unit_sizep and
 * returns the number of units to be allocated.  -errno on failure.
 */
int __init pcpu_lpage_build_unit_map(size_t reserved_size, ssize_t *dyn_sizep,
				     size_t *unit_sizep, size_t lpage_size,
				     int *unit_map,
				     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;
	size_t size_sum, min_unit_size, alloc_size;
	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
	int last_allocs;
	unsigned int cpu, tcpu;
	int group, unit;

	/*
	 * Determine min_unit_size, alloc_size and max_upa such that
	 * alloc_size is multiple of lpage_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_sizep);
	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);

	alloc_size = roundup(min_unit_size, lpage_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, tcpu) > LOCAL_DISTANCE ||
			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
				group++;
				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_cnt[group]; 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;
	}
	*unit_sizep = alloc_size / best_upa;

	/* assign units to cpus accordingly */
	unit = 0;
	for (group = 0; group_cnt[group]; group++) {
		for_each_possible_cpu(cpu)
			if (group_map[cpu] == group)
				unit_map[cpu] = unit++;
		unit = roundup(unit, best_upa);
	}

	return unit;	/* unit contains aligned number of units */
}

struct pcpul_ent {
	void		*ptr;
	void		*map_addr;
};

static size_t pcpul_size;
static size_t pcpul_lpage_size;
static int pcpul_nr_lpages;
static struct pcpul_ent *pcpul_map;

static bool __init pcpul_unit_to_cpu(int unit, const int *unit_map,
				     unsigned int *cpup)
{
	unsigned int cpu;

	for_each_possible_cpu(cpu)
		if (unit_map[cpu] == unit) {
			if (cpup)
				*cpup = cpu;
			return true;
		}

	return false;
}

static void __init pcpul_lpage_dump_cfg(const char *lvl, size_t static_size,
					size_t reserved_size, size_t dyn_size,
					size_t unit_size, size_t lpage_size,
					const int *unit_map, int nr_units)
{
	int width = 1, v = nr_units;
	char empty_str[] = "--------";
	int upl, lpl;	/* units per lpage, lpage per line */
	unsigned int cpu;
	int lpage, unit;

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

	upl = max_t(int, lpage_size / unit_size, 1);
	lpl = rounddown_pow_of_two(max_t(int, 60 / (upl * (width + 1) + 2), 1));

	printk("%spcpu-lpage: sta/res/dyn=%zu/%zu/%zu unit=%zu lpage=%zu", lvl,
	       static_size, reserved_size, dyn_size, unit_size, lpage_size);

	for (lpage = 0, unit = 0; unit < nr_units; unit++) {
		if (!(unit % upl)) {
			if (!(lpage++ % lpl)) {
				printk("\n");
				printk("%spcpu-lpage: ", lvl);
			} else
				printk("| ");
		}
		if (pcpul_unit_to_cpu(unit, unit_map, &cpu))
			printk("%0*d ", width, cpu);
		else
			printk("%s ", empty_str);
	}
	printk("\n");
}

/**
 * pcpu_lpage_first_chunk - remap the first percpu chunk using large page
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_size: free size for dynamic allocation in bytes
 * @unit_size: unit size in bytes
 * @lpage_size: the size of a large page
 * @unit_map: cpu -> unit mapping
 * @nr_units: the number of units
 * @alloc_fn: function to allocate percpu lpage, always called with lpage_size
 * @free_fn: function to free percpu memory, @size <= lpage_size
 * @map_fn: function to map percpu lpage, always called with lpage_size
 *
 * This allocator uses large page to build and map the first chunk.
 * Unlike other helpers, the caller should always specify @dyn_size
 * and @unit_size.  These parameters along with @unit_map and
 * @nr_units can be determined using pcpu_lpage_build_unit_map().
 * This two stage initialization is to allow arch code to evaluate the
 * parameters before committing to it.
 *
 * Large pages are allocated as directed by @unit_map and other
 * parameters and mapped to vmalloc space.  Unused holes are returned
 * to the page allocator.  Note that these holes end up being actively
 * mapped twice - once to the physical mapping and to the vmalloc area
 * for the first percpu chunk.  Depending on architecture, this might
 * cause problem when changing page attributes of the returned area.
 * These double mapped areas can be detected using
 * pcpu_lpage_remapped().
 *
 * RETURNS:
 * The determined pcpu_unit_size which can be used to initialize
 * percpu access on success, -errno on failure.
 */
ssize_t __init pcpu_lpage_first_chunk(size_t reserved_size, size_t dyn_size,
				      size_t unit_size, size_t lpage_size,
				      const int *unit_map, int nr_units,
				      pcpu_fc_alloc_fn_t alloc_fn,
				      pcpu_fc_free_fn_t free_fn,
				      pcpu_fc_map_fn_t map_fn)
{
	static struct vm_struct vm;
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	size_t chunk_size = unit_size * nr_units;
	size_t map_size;
	unsigned int cpu;
	ssize_t ret;
	int i, j, unit;

	pcpul_lpage_dump_cfg(KERN_DEBUG, static_size, reserved_size, dyn_size,
			     unit_size, lpage_size, unit_map, nr_units);

	BUG_ON(chunk_size % lpage_size);

	pcpul_size = static_size + reserved_size + dyn_size;
	pcpul_lpage_size = lpage_size;
	pcpul_nr_lpages = chunk_size / lpage_size;

	/* allocate pointer array and alloc large pages */
	map_size = pcpul_nr_lpages * sizeof(pcpul_map[0]);
	pcpul_map = alloc_bootmem(map_size);

	/* allocate all pages */
	for (i = 0; i < pcpul_nr_lpages; i++) {
		size_t offset = i * lpage_size;
		int first_unit = offset / unit_size;
		int last_unit = (offset + lpage_size - 1) / unit_size;
		void *ptr;

		/* find out which cpu is mapped to this unit */
		for (unit = first_unit; unit <= last_unit; unit++)
			if (pcpul_unit_to_cpu(unit, unit_map, &cpu))
				goto found;
		continue;
	found:
		ptr = alloc_fn(cpu, lpage_size, lpage_size);
		if (!ptr) {
			pr_warning("PERCPU: failed to allocate large page "
				   "for cpu%u\n", cpu);
			goto enomem;
		}

		pcpul_map[i].ptr = ptr;
	}

	/* return unused holes */
	for (unit = 0; unit < nr_units; unit++) {
		size_t start = unit * unit_size;
		size_t end = start + unit_size;
		size_t off, next;

		/* don't free used part of occupied unit */
		if (pcpul_unit_to_cpu(unit, unit_map, NULL))
			start += pcpul_size;

		/* unit can span more than one page, punch the holes */
		for (off = start; off < end; off = next) {
			void *ptr = pcpul_map[off / lpage_size].ptr;
			next = min(roundup(off + 1, lpage_size), end);
			if (ptr)
				free_fn(ptr + off % lpage_size, next - off);
		}
	}

	/* allocate address, map and copy */
	vm.flags = VM_ALLOC;
	vm.size = chunk_size;
	vm_area_register_early(&vm, unit_size);

	for (i = 0; i < pcpul_nr_lpages; i++) {
		if (!pcpul_map[i].ptr)
			continue;
		pcpul_map[i].map_addr = vm.addr + i * lpage_size;
		map_fn(pcpul_map[i].ptr, lpage_size, pcpul_map[i].map_addr);
	}

	for_each_possible_cpu(cpu)
		memcpy(vm.addr + unit_map[cpu] * unit_size, __per_cpu_load,
		       static_size);

	/* we're ready, commit */
	pr_info("PERCPU: large pages @%p s%zu r%zu d%zu u%zu\n",
		vm.addr, static_size, reserved_size, dyn_size, unit_size);

	ret = pcpu_setup_first_chunk(static_size, reserved_size, dyn_size,
				     unit_size, vm.addr, unit_map);

	/*
	 * Sort pcpul_map array for pcpu_lpage_remapped().  Unmapped
	 * lpages are pushed to the end and trimmed.
	 */
	for (i = 0; i < pcpul_nr_lpages - 1; i++)
		for (j = i + 1; j < pcpul_nr_lpages; j++) {
			struct pcpul_ent tmp;

			if (!pcpul_map[j].ptr)
				continue;
			if (pcpul_map[i].ptr &&
			    pcpul_map[i].ptr < pcpul_map[j].ptr)
				continue;

			tmp = pcpul_map[i];
			pcpul_map[i] = pcpul_map[j];
			pcpul_map[j] = tmp;
		}

	while (pcpul_nr_lpages && !pcpul_map[pcpul_nr_lpages - 1].ptr)
		pcpul_nr_lpages--;

	return ret;

enomem:
	for (i = 0; i < pcpul_nr_lpages; i++)
		if (pcpul_map[i].ptr)
			free_fn(pcpul_map[i].ptr, lpage_size);
	free_bootmem(__pa(pcpul_map), map_size);
	return -ENOMEM;
}

/**
 * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area
 * @kaddr: the kernel address in question
 *
 * Determine whether @kaddr falls in the pcpul recycled area.  This is
 * used by pageattr to detect VM aliases and break up the pcpu large
 * page mapping such that the same physical page is not mapped under
 * different attributes.
 *
 * The recycled area is always at the tail of a partially used large
 * page.
 *
 * RETURNS:
 * Address of corresponding remapped pcpu address if match is found;
 * otherwise, NULL.
 */
void *pcpu_lpage_remapped(void *kaddr)
{
	unsigned long lpage_mask = pcpul_lpage_size - 1;
	void *lpage_addr = (void *)((unsigned long)kaddr & ~lpage_mask);
	unsigned long offset = (unsigned long)kaddr & lpage_mask;
	int left = 0, right = pcpul_nr_lpages - 1;
	int pos;

	/* pcpul in use at all? */
	if (!pcpul_map)