percpu.c

		page_end = PFN_UP(off + size);

		pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
			WARN_ON(chunk->immutable);

			ret = pcpu_populate_chunk(chunk, rs, re);

			spin_lock_irqsave(&pcpu_lock, flags);
			if (ret) {
				mutex_unlock(&pcpu_alloc_mutex);
				pcpu_free_area(chunk, off, &occ_pages);
				err = "failed to populate";
				goto fail_unlock;
			}
			pcpu_chunk_populated(chunk, rs, re);
			spin_unlock_irqrestore(&pcpu_lock, flags);
		}

		mutex_unlock(&pcpu_alloc_mutex);
	}

	if (chunk != pcpu_reserved_chunk)
		pcpu_nr_empty_pop_pages -= occ_pages;

	if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
		pcpu_schedule_balance_work();

	/* clear the areas and return address relative to base address */
	for_each_possible_cpu(cpu)
		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);

	ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
	kmemleak_alloc_percpu(ptr, size);
	return ptr;

fail_unlock:
	spin_unlock_irqrestore(&pcpu_lock, flags);
fail:
	if (!is_atomic && warn_limit) {
		pr_warning("PERCPU: allocation failed, size=%zu align=%zu atomic=%d, %s\n",
			   size, align, is_atomic, err);
		dump_stack();
		if (!--warn_limit)
			pr_info("PERCPU: limit reached, disable warning\n");
	}
	if (is_atomic) {
		/* see the flag handling in pcpu_blance_workfn() */
		pcpu_atomic_alloc_failed = true;
		pcpu_schedule_balance_work();
	}
	return NULL;
}

/**
 * __alloc_percpu_gfp - allocate dynamic percpu area
 * @size: size of area to allocate in bytes
 * @align: alignment of area (max PAGE_SIZE)
 * @gfp: allocation flags
 *
 * Allocate zero-filled percpu area of @size bytes aligned at @align.  If
 * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can
 * be called from any context but is a lot more likely to fail.
 *
 * RETURNS:
 * Percpu pointer to the allocated area on success, NULL on failure.
 */
void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp)
{
	return pcpu_alloc(size, align, false, gfp);
}
EXPORT_SYMBOL_GPL(__alloc_percpu_gfp);

/**
 * __alloc_percpu - allocate dynamic percpu area
 * @size: size of area to allocate in bytes
 * @align: alignment of area (max PAGE_SIZE)
 *
 * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL).
 */
void __percpu *__alloc_percpu(size_t size, size_t align)
{
	return pcpu_alloc(size, align, false, GFP_KERNEL);
}
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 zero-filled 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 __percpu *__alloc_reserved_percpu(size_t size, size_t align)
{
	return pcpu_alloc(size, align, true, GFP_KERNEL);
}

/**
 * pcpu_balance_workfn - manage the amount of free chunks and populated pages
 * @work: unused
 *
 * Reclaim all fully free chunks except for the first one.
 */
static void pcpu_balance_workfn(struct work_struct *work)
{
	LIST_HEAD(to_free);
	struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
	struct pcpu_chunk *chunk, *next;
	int slot, nr_to_pop, ret;

	/*
	 * There's no reason to keep around multiple unused chunks and VM
	 * areas can be scarce.  Destroy all free chunks except for one.
	 */
	mutex_lock(&pcpu_alloc_mutex);
	spin_lock_irq(&pcpu_lock);

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

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

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

	spin_unlock_irq(&pcpu_lock);

	list_for_each_entry_safe(chunk, next, &to_free, list) {
		int rs, re;

		pcpu_for_each_pop_region(chunk, rs, re, 0, pcpu_unit_pages) {
			pcpu_depopulate_chunk(chunk, rs, re);
			spin_lock_irq(&pcpu_lock);
			pcpu_chunk_depopulated(chunk, rs, re);
			spin_unlock_irq(&pcpu_lock);
		}
		pcpu_destroy_chunk(chunk);
	}

	/*
	 * Ensure there are certain number of free populated pages for
	 * atomic allocs.  Fill up from the most packed so that atomic
	 * allocs don't increase fragmentation.  If atomic allocation
	 * failed previously, always populate the maximum amount.  This
	 * should prevent atomic allocs larger than PAGE_SIZE from keeping
	 * failing indefinitely; however, large atomic allocs are not
	 * something we support properly and can be highly unreliable and
	 * inefficient.
	 */
retry_pop:
	if (pcpu_atomic_alloc_failed) {
		nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH;
		/* best effort anyway, don't worry about synchronization */
		pcpu_atomic_alloc_failed = false;
	} else {
		nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
				  pcpu_nr_empty_pop_pages,
				  0, PCPU_EMPTY_POP_PAGES_HIGH);
	}

	for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) {
		int nr_unpop = 0, rs, re;

		if (!nr_to_pop)
			break;

		spin_lock_irq(&pcpu_lock);
		list_for_each_entry(chunk, &pcpu_slot[slot], list) {
			nr_unpop = pcpu_unit_pages - chunk->nr_populated;
			if (nr_unpop)
				break;
		}
		spin_unlock_irq(&pcpu_lock);

		if (!nr_unpop)
			continue;

		/* @chunk can't go away while pcpu_alloc_mutex is held */
		pcpu_for_each_unpop_region(chunk, rs, re, 0, pcpu_unit_pages) {
			int nr = min(re - rs, nr_to_pop);

			ret = pcpu_populate_chunk(chunk, rs, rs + nr);
			if (!ret) {
				nr_to_pop -= nr;
				spin_lock_irq(&pcpu_lock);
				pcpu_chunk_populated(chunk, rs, rs + nr);
				spin_unlock_irq(&pcpu_lock);
			} else {
				nr_to_pop = 0;
			}

			if (!nr_to_pop)
				break;
		}
	}

	if (nr_to_pop) {
		/* ran out of chunks to populate, create a new one and retry */
		chunk = pcpu_create_chunk();
		if (chunk) {
			spin_lock_irq(&pcpu_lock);
			pcpu_chunk_relocate(chunk, -1);
			spin_unlock_irq(&pcpu_lock);
			goto retry_pop;
		}
	}

	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 __percpu *ptr)
{
	void *addr;
	struct pcpu_chunk *chunk;
	unsigned long flags;
	int off, occ_pages;

	if (!ptr)
		return;

	kmemleak_free_percpu(ptr);

	addr = __pcpu_ptr_to_addr(ptr);

	spin_lock_irqsave(&pcpu_lock, flags);

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

	pcpu_free_area(chunk, off, &occ_pages);

	if (chunk != pcpu_reserved_chunk)
		pcpu_nr_empty_pop_pages += occ_pages;

	/* 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) {
				pcpu_schedule_balance_work();
				break;
			}
	}

	spin_unlock_irqrestore(&pcpu_lock, flags);
}
EXPORT_SYMBOL_GPL(free_percpu);

/**
 * is_kernel_percpu_address - test whether address is from static percpu area
 * @addr: address to test
 *
 * Test whether @addr belongs to in-kernel static percpu area.  Module
 * static percpu areas are not considered.  For those, use
 * is_module_percpu_address().
 *
 * RETURNS:
 * %true if @addr is from in-kernel static percpu area, %false otherwise.
 */
bool is_kernel_percpu_address(unsigned long addr)
{
#ifdef CONFIG_SMP
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
	unsigned int cpu;

	for_each_possible_cpu(cpu) {
		void *start = per_cpu_ptr(base, cpu);

		if ((void *)addr >= start && (void *)addr < start + static_size)
			return true;
        }
#endif
	/* on UP, can't distinguish from other static vars, always false */
	return false;
}

/**
 * per_cpu_ptr_to_phys - convert translated percpu address to physical address
 * @addr: the address to be converted to physical address
 *
 * Given @addr which is dereferenceable address obtained via one of
 * percpu access macros, this function translates it into its physical
 * address.  The caller is responsible for ensuring @addr stays valid
 * until this function finishes.
 *
 * percpu allocator has special setup for the first chunk, which currently
 * supports either embedding in linear address space or vmalloc mapping,
 * and, from the second one, the backing allocator (currently either vm or
 * km) provides translation.
 *
 * The addr can be tranlated simply without checking if it falls into the
 * first chunk. But the current code reflects better how percpu allocator
 * actually works, and the verification can discover both bugs in percpu
 * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
 * code.
 *
 * RETURNS:
 * The physical address for @addr.
 */
phys_addr_t per_cpu_ptr_to_phys(void *addr)
{
	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
	bool in_first_chunk = false;
	unsigned long first_low, first_high;
	unsigned int cpu;

	/*
	 * The following test on unit_low/high isn't strictly
	 * necessary but will speed up lookups of addresses which
	 * aren't in the first chunk.
	 */
	first_low = pcpu_chunk_addr(pcpu_first_chunk, pcpu_low_unit_cpu, 0);
	first_high = pcpu_chunk_addr(pcpu_first_chunk, pcpu_high_unit_cpu,
				     pcpu_unit_pages);
	if ((unsigned long)addr >= first_low &&
	    (unsigned long)addr < first_high) {
		for_each_possible_cpu(cpu) {
			void *start = per_cpu_ptr(base, cpu);

			if (addr >= start && addr < start + pcpu_unit_size) {
				in_first_chunk = true;
				break;
			}
		}
	}

	if (in_first_chunk) {
		if (!is_vmalloc_addr(addr))
			return __pa(addr);
		else
			return page_to_phys(vmalloc_to_page(addr)) +
			       offset_in_page(addr);
	} else
		return page_to_phys(pcpu_addr_to_page(addr)) +
		       offset_in_page(addr);
}

/**
 * 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 = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), 0);
	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)
{
	memblock_free_early(__pa(ai), ai->__ai_size);
}

/**
 * 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(KERN_CONT "\n");
				printk("%spcpu-alloc: ", lvl);
			}
			printk(KERN_CONT "[%0*d] ", group_width, group);

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

#define PCPU_SETUP_BUG_ON(cond)	do {					\
	if (unlikely(cond)) {						\
		pr_emerg("PERCPU: failed to initialize, %s", #cond);	\
		pr_emerg("PERCPU: cpu_possible_mask=%*pb\n",		\
			 cpumask_pr_args(cpu_possible_mask));		\
		pcpu_dump_alloc_info(KERN_EMERG, ai);			\
		BUG();							\
	}								\
} while (0)

	/* sanity checks */
	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
#ifdef CONFIG_SMP
	PCPU_SETUP_BUG_ON(!ai->static_size);
	PCPU_SETUP_BUG_ON((unsigned long)__per_cpu_start & ~PAGE_MASK);
#endif
	PCPU_SETUP_BUG_ON(!base_addr);
	PCPU_SETUP_BUG_ON((unsigned long)base_addr & ~PAGE_MASK);
	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
	PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
	PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
	PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE);
	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);

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

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

	pcpu_low_unit_cpu = NR_CPUS;
	pcpu_high_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;

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

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

			/* determine low/high unit_cpu */
			if (pcpu_low_unit_cpu == NR_CPUS ||
			    unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
				pcpu_low_unit_cpu = cpu;
			if (pcpu_high_unit_cpu == NR_CPUS ||
			    unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
				pcpu_high_unit_cpu = cpu;
		}
	}
	pcpu_nr_units = unit;

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

	/* we're done parsing the input, undefine BUG macro and dump config */
#undef PCPU_SETUP_BUG_ON
	pcpu_dump_alloc_info(KERN_DEBUG, ai);

	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 = memblock_virt_alloc(
			pcpu_nr_slots * sizeof(pcpu_slot[0]), 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 = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
	INIT_LIST_HEAD(&schunk->list);
	INIT_WORK(&schunk->map_extend_work, pcpu_map_extend_workfn);
	schunk->base_addr = base_addr;
	schunk->map = smap;
	schunk->map_alloc = ARRAY_SIZE(smap);
	schunk->immutable = true;
	bitmap_fill(schunk->populated, pcpu_unit_pages);
	schunk->nr_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[0] = 1;
	schunk->map[1] = ai->static_size;
	schunk->map_used = 1;
	if (schunk->free_size)
		schunk->map[++schunk->map_used] = 1 | (ai->static_size + schunk->free_size);
	else
		schunk->map[1] |= 1;

	/* init dynamic chunk if necessary */
	if (dyn_size) {
		dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
		INIT_LIST_HEAD(&dchunk->list);
		INIT_WORK(&dchunk->map_extend_work, pcpu_map_extend_workfn);
		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->nr_populated = pcpu_unit_pages;

		dchunk->contig_hint = dchunk->free_size = dyn_size;
		dchunk->map[0] = 1;
		dchunk->map[1] = pcpu_reserved_chunk_limit;
		dchunk->map[2] = (pcpu_reserved_chunk_limit + dchunk->free_size) | 1;
		dchunk->map_used = 2;
	}

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

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

#ifdef CONFIG_SMP

const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = {
	[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 (!str)
		return -EINVAL;

	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);

/*
 * pcpu_embed_first_chunk() is used by the generic percpu setup.
 * Build it if needed by the arch config or the generic setup is going
 * to be used.
 */
#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
#define BUILD_EMBED_FIRST_CHUNK
#endif

/* build pcpu_page_first_chunk() iff needed by the arch config */
#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
#define BUILD_PAGE_FIRST_CHUNK
#endif

/* pcpu_build_alloc_info() is used by both embed and page first chunk */
#if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK)
/**
 * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_size: minimum free size for dynamic allocation in bytes
 * @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.
 */
static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
				size_t reserved_size, size_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 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_cnt));

	/* calculate size_sum and ensure dyn_size is enough for early alloc */
	size_sum = PFN_ALIGN(static_size + reserved_size +
			    max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
	dyn_size = size_sum - static_size - reserved_size;

	/*
	 * Determine min_unit_size, alloc_size and max_upa such that
	 * alloc_size is multiple of atom_size and is the smallest
	 * which can accommodate 4k aligned segments which are equal to
	 * or larger than min_unit_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]++;
	}

	/*
	 * 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 1/3.  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;
}
#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */

#if defined(BUILD_EMBED_FIRST_CHUNK)
/**
 * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_size: minimum free size for dynamic allocation in bytes
 * @atom_size: allocation atom size
 * @cpu_distance_fn: callback to determine distance between cpus, optional
 * @alloc_fn: function to allocate percpu page
 * @free_fn: function 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).
 *
 * @dyn_size specifies the minimum dynamic area size.
 *
 * 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, size_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, max_distance;
	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 = memblock_virt_alloc_nopanic(areas_size, 0);
	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;
		}
		/* kmemleak tracks the percpu allocations separately */
		kmemleak_free(ptr);
		areas[group] = ptr;

		base = min(ptr, base);
	}

	/*
	 * Copy data and free unused parts.  This should happen after all
	 * allocations are complete; otherwise, we may end up with
	 * overlapping groups.
	 */
	for (group = 0; group < ai->nr_groups; group++) {
		struct pcpu_group_info *gi = &ai->groups[group];
		void *ptr = areas[group];