percpu.c

		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 */
	max_distance = 0;
	for (group = 0; group < ai->nr_groups; group++) {
		ai->groups[group].base_offset = areas[group] - base;
		max_distance = max_t(size_t, max_distance,
				     ai->groups[group].base_offset);
	}
	max_distance += ai->unit_size;

	/* warn if maximum distance is further than 75% of vmalloc space */
	if (max_distance > VMALLOC_TOTAL * 3 / 4) {
		pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc "
			   "space 0x%lx\n", max_distance,
			   VMALLOC_TOTAL);
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
		/* and fail if we have fallback */
		rc = -EINVAL;
		goto out_free;
#endif
	}

	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++)
		if (areas[group])
			free_fn(areas[group],
				ai->groups[group].nr_units * ai->unit_size);
out_free:
	pcpu_free_alloc_info(ai);
	if (areas)
		memblock_free_early(__pa(areas), areas_size);
	return rc;
}
#endif /* BUILD_EMBED_FIRST_CHUNK */

#ifdef BUILD_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: function 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, 0, 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 = memblock_virt_alloc(pages_size, 0);

	/* 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;
			}
			/* kmemleak tracks the percpu allocations separately */
			kmemleak_free(ptr);
			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:
	memblock_free_early(__pa(pages), pages_size);
	pcpu_free_alloc_info(ai);
	return rc;
}
#endif /* BUILD_PAGE_FIRST_CHUNK */

#ifndef	CONFIG_HAVE_SETUP_PER_CPU_AREA
/*
 * Generic SMP 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.
 */
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  memblock_virt_alloc_from_nopanic(
			size, align, __pa(MAX_DMA_ADDRESS));
}

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

void __init setup_per_cpu_areas(void)
{
	unsigned long delta;
	unsigned int cpu;
	int rc;

	/*
	 * Always reserve area for module percpu variables.  That's
	 * what the legacy allocator did.
	 */
	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL,
				    pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
	if (rc < 0)
		panic("Failed to initialize percpu areas.");

	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
	for_each_possible_cpu(cpu)
		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
}
#endif	/* CONFIG_HAVE_SETUP_PER_CPU_AREA */

#else	/* CONFIG_SMP */

/*
 * UP percpu area setup.
 *
 * UP always uses km-based percpu allocator with identity mapping.
 * Static percpu variables are indistinguishable from the usual static
 * variables and don't require any special preparation.
 */
void __init setup_per_cpu_areas(void)
{
	const size_t unit_size =
		roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE,
					 PERCPU_DYNAMIC_RESERVE));
	struct pcpu_alloc_info *ai;
	void *fc;

	ai = pcpu_alloc_alloc_info(1, 1);
	fc = memblock_virt_alloc_from_nopanic(unit_size,
					      PAGE_SIZE,
					      __pa(MAX_DMA_ADDRESS));
	if (!ai || !fc)
		panic("Failed to allocate memory for percpu areas.");
	/* kmemleak tracks the percpu allocations separately */
	kmemleak_free(fc);

	ai->dyn_size = unit_size;
	ai->unit_size = unit_size;
	ai->atom_size = unit_size;
	ai->alloc_size = unit_size;
	ai->groups[0].nr_units = 1;
	ai->groups[0].cpu_map[0] = 0;

	if (pcpu_setup_first_chunk(ai, fc) < 0)
		panic("Failed to initialize percpu areas.");
}

#endif	/* CONFIG_SMP */

/*
 * First and reserved chunks are initialized with temporary allocation
 * map in initdata so that they can be used before slab is online.
 * This function is called after slab is brought up and replaces those
 * with properly allocated maps.
 */
void __init percpu_init_late(void)
{
	struct pcpu_chunk *target_chunks[] =
		{ pcpu_first_chunk, pcpu_reserved_chunk, NULL };
	struct pcpu_chunk *chunk;
	unsigned long flags;
	int i;

	for (i = 0; (chunk = target_chunks[i]); i++) {
		int *map;
		const size_t size = PERCPU_DYNAMIC_EARLY_SLOTS * sizeof(map[0]);

		BUILD_BUG_ON(size > PAGE_SIZE);

		map = pcpu_mem_zalloc(size);
		BUG_ON(!map);

		spin_lock_irqsave(&pcpu_lock, flags);
		memcpy(map, chunk->map, size);
		chunk->map = map;
		spin_unlock_irqrestore(&pcpu_lock, flags);
	}
}

/*
 * Percpu allocator is initialized early during boot when neither slab or
 * workqueue is available.  Plug async management until everything is up
 * and running.
 */
static int __init percpu_enable_async(void)
{
	pcpu_async_enabled = true;
	return 0;
}
subsys_initcall(percpu_enable_async);