page_alloc.c

	int i, bad = 0;

	VM_BUG_ON_PAGE(PageTail(page), page);
	VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);

	trace_mm_page_free(page, order);
	kmemcheck_free_shadow(page, order);
	kasan_free_pages(page, order);

	if (PageAnon(page))
		page->mapping = NULL;
	bad += free_pages_check(page);
	for (i = 1; i < (1 << order); i++) {
		if (compound)
			bad += free_tail_pages_check(page, page + i);
		bad += free_pages_check(page + i);
	}
	if (bad)
		return false;

	reset_page_owner(page, order);

	if (!PageHighMem(page)) {
		debug_check_no_locks_freed(page_address(page),
					   PAGE_SIZE << order);
		debug_check_no_obj_freed(page_address(page),
					   PAGE_SIZE << order);
	}
	arch_free_page(page, order);
	kernel_poison_pages(page, 1 << order, 0);
	kernel_map_pages(page, 1 << order, 0);

	return true;
}

static void __free_pages_ok(struct page *page, unsigned int order)
{
	unsigned long flags;
	int migratetype;
	unsigned long pfn = page_to_pfn(page);

	if (!free_pages_prepare(page, order))
		return;

	migratetype = get_pfnblock_migratetype(page, pfn);
	local_irq_save(flags);
	__count_vm_events(PGFREE, 1 << order);
	free_one_page(page_zone(page), page, pfn, order, migratetype);
	local_irq_restore(flags);
}

static void __init __free_pages_boot_core(struct page *page,
					unsigned long pfn, unsigned int order)
{
	unsigned int nr_pages = 1 << order;
	struct page *p = page;
	unsigned int loop;

	prefetchw(p);
	for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
		prefetchw(p + 1);
		__ClearPageReserved(p);
		set_page_count(p, 0);
	}
	__ClearPageReserved(p);
	set_page_count(p, 0);

	page_zone(page)->managed_pages += nr_pages;
	set_page_refcounted(page);
	__free_pages(page, order);
}

#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
	defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)

static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;

int __meminit early_pfn_to_nid(unsigned long pfn)
{
	static DEFINE_SPINLOCK(early_pfn_lock);
	int nid;

	spin_lock(&early_pfn_lock);
	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
	if (nid < 0)
		nid = 0;
	spin_unlock(&early_pfn_lock);

	return nid;
}
#endif

#ifdef CONFIG_NODES_SPAN_OTHER_NODES
static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node,
					struct mminit_pfnnid_cache *state)
{
	int nid;

	nid = __early_pfn_to_nid(pfn, state);
	if (nid >= 0 && nid != node)
		return false;
	return true;
}

/* Only safe to use early in boot when initialisation is single-threaded */
static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
	return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache);
}

#else

static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
	return true;
}
static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node,
					struct mminit_pfnnid_cache *state)
{
	return true;
}
#endif


void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
							unsigned int order)
{
	if (early_page_uninitialised(pfn))
		return;
	return __free_pages_boot_core(page, pfn, order);
}

/*
 * Check that the whole (or subset of) a pageblock given by the interval of
 * [start_pfn, end_pfn) is valid and within the same zone, before scanning it
 * with the migration of free compaction scanner. The scanners then need to
 * use only pfn_valid_within() check for arches that allow holes within
 * pageblocks.
 *
 * Return struct page pointer of start_pfn, or NULL if checks were not passed.
 *
 * It's possible on some configurations to have a setup like node0 node1 node0
 * i.e. it's possible that all pages within a zones range of pages do not
 * belong to a single zone. We assume that a border between node0 and node1
 * can occur within a single pageblock, but not a node0 node1 node0
 * interleaving within a single pageblock. It is therefore sufficient to check
 * the first and last page of a pageblock and avoid checking each individual
 * page in a pageblock.
 */
struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
				     unsigned long end_pfn, struct zone *zone)
{
	struct page *start_page;
	struct page *end_page;

	/* end_pfn is one past the range we are checking */
	end_pfn--;

	if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
		return NULL;

	start_page = pfn_to_page(start_pfn);

	if (page_zone(start_page) != zone)
		return NULL;

	end_page = pfn_to_page(end_pfn);

	/* This gives a shorter code than deriving page_zone(end_page) */
	if (page_zone_id(start_page) != page_zone_id(end_page))
		return NULL;

	return start_page;
}

void set_zone_contiguous(struct zone *zone)
{
	unsigned long block_start_pfn = zone->zone_start_pfn;
	unsigned long block_end_pfn;

	block_end_pfn = ALIGN(block_start_pfn + 1, pageblock_nr_pages);
	for (; block_start_pfn < zone_end_pfn(zone);
			block_start_pfn = block_end_pfn,
			 block_end_pfn += pageblock_nr_pages) {

		block_end_pfn = min(block_end_pfn, zone_end_pfn(zone));

		if (!__pageblock_pfn_to_page(block_start_pfn,
					     block_end_pfn, zone))
			return;
	}

	/* We confirm that there is no hole */
	zone->contiguous = true;
}

void clear_zone_contiguous(struct zone *zone)
{
	zone->contiguous = false;
}

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __init deferred_free_range(struct page *page,
					unsigned long pfn, int nr_pages)
{
	int i;

	if (!page)
		return;

	/* Free a large naturally-aligned chunk if possible */
	if (nr_pages == MAX_ORDER_NR_PAGES &&
	    (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) {
		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
		__free_pages_boot_core(page, pfn, MAX_ORDER-1);
		return;
	}

	for (i = 0; i < nr_pages; i++, page++, pfn++)
		__free_pages_boot_core(page, pfn, 0);
}

/* Completion tracking for deferred_init_memmap() threads */
static atomic_t pgdat_init_n_undone __initdata;
static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);

static inline void __init pgdat_init_report_one_done(void)
{
	if (atomic_dec_and_test(&pgdat_init_n_undone))
		complete(&pgdat_init_all_done_comp);
}

/* Initialise remaining memory on a node */
static int __init deferred_init_memmap(void *data)
{
	pg_data_t *pgdat = data;
	int nid = pgdat->node_id;
	struct mminit_pfnnid_cache nid_init_state = { };
	unsigned long start = jiffies;
	unsigned long nr_pages = 0;
	unsigned long walk_start, walk_end;
	int i, zid;
	struct zone *zone;
	unsigned long first_init_pfn = pgdat->first_deferred_pfn;
	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);

	if (first_init_pfn == ULONG_MAX) {
		pgdat_init_report_one_done();
		return 0;
	}

	/* Bind memory initialisation thread to a local node if possible */
	if (!cpumask_empty(cpumask))
		set_cpus_allowed_ptr(current, cpumask);

	/* Sanity check boundaries */
	BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
	BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
	pgdat->first_deferred_pfn = ULONG_MAX;

	/* Only the highest zone is deferred so find it */
	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
		zone = pgdat->node_zones + zid;
		if (first_init_pfn < zone_end_pfn(zone))
			break;
	}

	for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) {
		unsigned long pfn, end_pfn;
		struct page *page = NULL;
		struct page *free_base_page = NULL;
		unsigned long free_base_pfn = 0;
		int nr_to_free = 0;

		end_pfn = min(walk_end, zone_end_pfn(zone));
		pfn = first_init_pfn;
		if (pfn < walk_start)
			pfn = walk_start;
		if (pfn < zone->zone_start_pfn)
			pfn = zone->zone_start_pfn;

		for (; pfn < end_pfn; pfn++) {
			if (!pfn_valid_within(pfn))
				goto free_range;

			/*
			 * Ensure pfn_valid is checked every
			 * MAX_ORDER_NR_PAGES for memory holes
			 */
			if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
				if (!pfn_valid(pfn)) {
					page = NULL;
					goto free_range;
				}
			}

			if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) {
				page = NULL;
				goto free_range;
			}

			/* Minimise pfn page lookups and scheduler checks */
			if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) {
				page++;
			} else {
				nr_pages += nr_to_free;
				deferred_free_range(free_base_page,
						free_base_pfn, nr_to_free);
				free_base_page = NULL;
				free_base_pfn = nr_to_free = 0;

				page = pfn_to_page(pfn);
				cond_resched();
			}

			if (page->flags) {
				VM_BUG_ON(page_zone(page) != zone);
				goto free_range;
			}

			__init_single_page(page, pfn, zid, nid);
			if (!free_base_page) {
				free_base_page = page;
				free_base_pfn = pfn;
				nr_to_free = 0;
			}
			nr_to_free++;

			/* Where possible, batch up pages for a single free */
			continue;
free_range:
			/* Free the current block of pages to allocator */
			nr_pages += nr_to_free;
			deferred_free_range(free_base_page, free_base_pfn,
								nr_to_free);
			free_base_page = NULL;
			free_base_pfn = nr_to_free = 0;
		}

		first_init_pfn = max(end_pfn, first_init_pfn);
	}

	/* Sanity check that the next zone really is unpopulated */
	WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));

	pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
					jiffies_to_msecs(jiffies - start));

	pgdat_init_report_one_done();
	return 0;
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */

void __init page_alloc_init_late(void)
{
	struct zone *zone;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
	int nid;

	/* There will be num_node_state(N_MEMORY) threads */
	atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
	for_each_node_state(nid, N_MEMORY) {
		kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
	}

	/* Block until all are initialised */
	wait_for_completion(&pgdat_init_all_done_comp);

	/* Reinit limits that are based on free pages after the kernel is up */
	files_maxfiles_init();
#endif

	for_each_populated_zone(zone)
		set_zone_contiguous(zone);
}

#ifdef CONFIG_CMA
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void __init init_cma_reserved_pageblock(struct page *page)
{
	unsigned i = pageblock_nr_pages;
	struct page *p = page;

	do {
		__ClearPageReserved(p);
		set_page_count(p, 0);
	} while (++p, --i);

	set_pageblock_migratetype(page, MIGRATE_CMA);

	if (pageblock_order >= MAX_ORDER) {
		i = pageblock_nr_pages;
		p = page;
		do {
			set_page_refcounted(p);
			__free_pages(p, MAX_ORDER - 1);
			p += MAX_ORDER_NR_PAGES;
		} while (i -= MAX_ORDER_NR_PAGES);
	} else {
		set_page_refcounted(page);
		__free_pages(page, pageblock_order);
	}

	adjust_managed_page_count(page, pageblock_nr_pages);
}
#endif

/*
 * The order of subdivision here is critical for the IO subsystem.
 * Please do not alter this order without good reasons and regression
 * testing. Specifically, as large blocks of memory are subdivided,
 * the order in which smaller blocks are delivered depends on the order
 * they're subdivided in this function. This is the primary factor
 * influencing the order in which pages are delivered to the IO
 * subsystem according to empirical testing, and this is also justified
 * by considering the behavior of a buddy system containing a single
 * large block of memory acted on by a series of small allocations.
 * This behavior is a critical factor in sglist merging's success.
 *
 * -- nyc
 */
static inline void expand(struct zone *zone, struct page *page,
	int low, int high, struct free_area *area,
	int migratetype)
{
	unsigned long size = 1 << high;

	while (high > low) {
		area--;
		high--;
		size >>= 1;
		VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);

		if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) &&
			debug_guardpage_enabled() &&
			high < debug_guardpage_minorder()) {
			/*
			 * Mark as guard pages (or page), that will allow to
			 * merge back to allocator when buddy will be freed.
			 * Corresponding page table entries will not be touched,
			 * pages will stay not present in virtual address space
			 */
			set_page_guard(zone, &page[size], high, migratetype);
			continue;
		}
		list_add(&page[size].lru, &area->free_list[migratetype]);
		area->nr_free++;
		set_page_order(&page[size], high);
	}
}

/*
 * This page is about to be returned from the page allocator
 */
static inline int check_new_page(struct page *page)
{
	const char *bad_reason = NULL;
	unsigned long bad_flags = 0;

	if (unlikely(atomic_read(&page->_mapcount) != -1))
		bad_reason = "nonzero mapcount";
	if (unlikely(page->mapping != NULL))
		bad_reason = "non-NULL mapping";
	if (unlikely(page_ref_count(page) != 0))
		bad_reason = "nonzero _count";
	if (unlikely(page->flags & __PG_HWPOISON)) {
		bad_reason = "HWPoisoned (hardware-corrupted)";
		bad_flags = __PG_HWPOISON;
	}
	if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
		bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
		bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
	}
#ifdef CONFIG_MEMCG
	if (unlikely(page->mem_cgroup))
		bad_reason = "page still charged to cgroup";
#endif
	if (unlikely(bad_reason)) {
		bad_page(page, bad_reason, bad_flags);
		return 1;
	}
	return 0;
}

static inline bool free_pages_prezeroed(bool poisoned)
{
	return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) &&
		page_poisoning_enabled() && poisoned;
}

static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
								int alloc_flags)
{
	int i;
	bool poisoned = true;

	for (i = 0; i < (1 << order); i++) {
		struct page *p = page + i;
		if (unlikely(check_new_page(p)))
			return 1;
		if (poisoned)
			poisoned &= page_is_poisoned(p);
	}

	set_page_private(page, 0);
	set_page_refcounted(page);

	arch_alloc_page(page, order);
	kernel_map_pages(page, 1 << order, 1);
	kernel_poison_pages(page, 1 << order, 1);
	kasan_alloc_pages(page, order);

	if (!free_pages_prezeroed(poisoned) && (gfp_flags & __GFP_ZERO))
		for (i = 0; i < (1 << order); i++)
			clear_highpage(page + i);

	if (order && (gfp_flags & __GFP_COMP))
		prep_compound_page(page, order);

	set_page_owner(page, order, gfp_flags);

	/*
	 * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to
	 * allocate the page. The expectation is that the caller is taking
	 * steps that will free more memory. The caller should avoid the page
	 * being used for !PFMEMALLOC purposes.
	 */
	if (alloc_flags & ALLOC_NO_WATERMARKS)
		set_page_pfmemalloc(page);
	else
		clear_page_pfmemalloc(page);

	return 0;
}

/*
 * Go through the free lists for the given migratetype and remove
 * the smallest available page from the freelists
 */
static inline
struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
						int migratetype)
{
	unsigned int current_order;
	struct free_area *area;
	struct page *page;

	/* Find a page of the appropriate size in the preferred list */
	for (current_order = order; current_order < MAX_ORDER; ++current_order) {
		area = &(zone->free_area[current_order]);
		page = list_first_entry_or_null(&area->free_list[migratetype],
							struct page, lru);
		if (!page)
			continue;
		list_del(&page->lru);
		rmv_page_order(page);
		area->nr_free--;
		expand(zone, page, order, current_order, area, migratetype);
		set_pcppage_migratetype(page, migratetype);
		return page;
	}

	return NULL;
}


/*
 * This array describes the order lists are fallen back to when
 * the free lists for the desirable migrate type are depleted
 */
static int fallbacks[MIGRATE_TYPES][4] = {
	[MIGRATE_UNMOVABLE]   = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE,   MIGRATE_TYPES },
	[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE,   MIGRATE_MOVABLE,   MIGRATE_TYPES },
	[MIGRATE_MOVABLE]     = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES },
#ifdef CONFIG_CMA
	[MIGRATE_CMA]         = { MIGRATE_TYPES }, /* Never used */
#endif
#ifdef CONFIG_MEMORY_ISOLATION
	[MIGRATE_ISOLATE]     = { MIGRATE_TYPES }, /* Never used */
#endif
};

#ifdef CONFIG_CMA
static struct page *__rmqueue_cma_fallback(struct zone *zone,
					unsigned int order)
{
	return __rmqueue_smallest(zone, order, MIGRATE_CMA);
}
#else
static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
					unsigned int order) { return NULL; }
#endif

/*
 * Move the free pages in a range to the free lists of the requested type.
 * Note that start_page and end_pages are not aligned on a pageblock
 * boundary. If alignment is required, use move_freepages_block()
 */
int move_freepages(struct zone *zone,
			  struct page *start_page, struct page *end_page,
			  int migratetype)
{
	struct page *page;
	unsigned int order;
	int pages_moved = 0;

#ifndef CONFIG_HOLES_IN_ZONE
	/*
	 * page_zone is not safe to call in this context when
	 * CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant
	 * anyway as we check zone boundaries in move_freepages_block().
	 * Remove at a later date when no bug reports exist related to
	 * grouping pages by mobility
	 */
	VM_BUG_ON(page_zone(start_page) != page_zone(end_page));
#endif

	for (page = start_page; page <= end_page;) {
		/* Make sure we are not inadvertently changing nodes */
		VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);

		if (!pfn_valid_within(page_to_pfn(page))) {
			page++;
			continue;
		}

		if (!PageBuddy(page)) {
			page++;
			continue;
		}

		order = page_order(page);
		list_move(&page->lru,
			  &zone->free_area[order].free_list[migratetype]);
		page += 1 << order;
		pages_moved += 1 << order;
	}

	return pages_moved;
}

int move_freepages_block(struct zone *zone, struct page *page,
				int migratetype)
{
	unsigned long start_pfn, end_pfn;
	struct page *start_page, *end_page;

	start_pfn = page_to_pfn(page);
	start_pfn = start_pfn & ~(pageblock_nr_pages-1);
	start_page = pfn_to_page(start_pfn);
	end_page = start_page + pageblock_nr_pages - 1;
	end_pfn = start_pfn + pageblock_nr_pages - 1;

	/* Do not cross zone boundaries */
	if (!zone_spans_pfn(zone, start_pfn))
		start_page = page;
	if (!zone_spans_pfn(zone, end_pfn))
		return 0;

	return move_freepages(zone, start_page, end_page, migratetype);
}

static void change_pageblock_range(struct page *pageblock_page,
					int start_order, int migratetype)
{
	int nr_pageblocks = 1 << (start_order - pageblock_order);

	while (nr_pageblocks--) {
		set_pageblock_migratetype(pageblock_page, migratetype);
		pageblock_page += pageblock_nr_pages;
	}
}

/*
 * When we are falling back to another migratetype during allocation, try to
 * steal extra free pages from the same pageblocks to satisfy further
 * allocations, instead of polluting multiple pageblocks.
 *
 * If we are stealing a relatively large buddy page, it is likely there will
 * be more free pages in the pageblock, so try to steal them all. For
 * reclaimable and unmovable allocations, we steal regardless of page size,
 * as fragmentation caused by those allocations polluting movable pageblocks
 * is worse than movable allocations stealing from unmovable and reclaimable
 * pageblocks.
 */
static bool can_steal_fallback(unsigned int order, int start_mt)
{
	/*
	 * Leaving this order check is intended, although there is
	 * relaxed order check in next check. The reason is that
	 * we can actually steal whole pageblock if this condition met,
	 * but, below check doesn't guarantee it and that is just heuristic
	 * so could be changed anytime.
	 */
	if (order >= pageblock_order)
		return true;

	if (order >= pageblock_order / 2 ||
		start_mt == MIGRATE_RECLAIMABLE ||
		start_mt == MIGRATE_UNMOVABLE ||
		page_group_by_mobility_disabled)
		return true;

	return false;
}

/*
 * This function implements actual steal behaviour. If order is large enough,
 * we can steal whole pageblock. If not, we first move freepages in this
 * pageblock and check whether half of pages are moved or not. If half of
 * pages are moved, we can change migratetype of pageblock and permanently
 * use it's pages as requested migratetype in the future.
 */
static void steal_suitable_fallback(struct zone *zone, struct page *page,
							  int start_type)
{
	unsigned int current_order = page_order(page);
	int pages;

	/* Take ownership for orders >= pageblock_order */
	if (current_order >= pageblock_order) {
		change_pageblock_range(page, current_order, start_type);
		return;
	}

	pages = move_freepages_block(zone, page, start_type);

	/* Claim the whole block if over half of it is free */
	if (pages >= (1 << (pageblock_order-1)) ||
			page_group_by_mobility_disabled)
		set_pageblock_migratetype(page, start_type);
}

/*
 * Check whether there is a suitable fallback freepage with requested order.
 * If only_stealable is true, this function returns fallback_mt only if
 * we can steal other freepages all together. This would help to reduce
 * fragmentation due to mixed migratetype pages in one pageblock.
 */
int find_suitable_fallback(struct free_area *area, unsigned int order,
			int migratetype, bool only_stealable, bool *can_steal)
{
	int i;
	int fallback_mt;

	if (area->nr_free == 0)
		return -1;

	*can_steal = false;
	for (i = 0;; i++) {
		fallback_mt = fallbacks[migratetype][i];
		if (fallback_mt == MIGRATE_TYPES)
			break;

		if (list_empty(&area->free_list[fallback_mt]))
			continue;

		if (can_steal_fallback(order, migratetype))
			*can_steal = true;

		if (!only_stealable)
			return fallback_mt;

		if (*can_steal)
			return fallback_mt;
	}

	return -1;
}

/*
 * Reserve a pageblock for exclusive use of high-order atomic allocations if
 * there are no empty page blocks that contain a page with a suitable order
 */
static void reserve_highatomic_pageblock(struct page *page, struct zone *zone,
				unsigned int alloc_order)
{
	int mt;
	unsigned long max_managed, flags;

	/*
	 * Limit the number reserved to 1 pageblock or roughly 1% of a zone.
	 * Check is race-prone but harmless.
	 */
	max_managed = (zone->managed_pages / 100) + pageblock_nr_pages;
	if (zone->nr_reserved_highatomic >= max_managed)
		return;

	spin_lock_irqsave(&zone->lock, flags);

	/* Recheck the nr_reserved_highatomic limit under the lock */
	if (zone->nr_reserved_highatomic >= max_managed)
		goto out_unlock;

	/* Yoink! */
	mt = get_pageblock_migratetype(page);
	if (mt != MIGRATE_HIGHATOMIC &&
			!is_migrate_isolate(mt) && !is_migrate_cma(mt)) {
		zone->nr_reserved_highatomic += pageblock_nr_pages;
		set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC);
		move_freepages_block(zone, page, MIGRATE_HIGHATOMIC);
	}

out_unlock:
	spin_unlock_irqrestore(&zone->lock, flags);
}

/*
 * Used when an allocation is about to fail under memory pressure. This
 * potentially hurts the reliability of high-order allocations when under
 * intense memory pressure but failed atomic allocations should be easier
 * to recover from than an OOM.
 */
static void unreserve_highatomic_pageblock(const struct alloc_context *ac)
{
	struct zonelist *zonelist = ac->zonelist;
	unsigned long flags;
	struct zoneref *z;
	struct zone *zone;
	struct page *page;
	int order;

	for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx,
								ac->nodemask) {
		/* Preserve at least one pageblock */
		if (zone->nr_reserved_highatomic <= pageblock_nr_pages)
			continue;

		spin_lock_irqsave(&zone->lock, flags);
		for (order = 0; order < MAX_ORDER; order++) {
			struct free_area *area = &(zone->free_area[order]);

			page = list_first_entry_or_null(
					&area->free_list[MIGRATE_HIGHATOMIC],
					struct page, lru);
			if (!page)
				continue;

			/*
			 * It should never happen but changes to locking could
			 * inadvertently allow a per-cpu drain to add pages
			 * to MIGRATE_HIGHATOMIC while unreserving so be safe
			 * and watch for underflows.
			 */
			zone->nr_reserved_highatomic -= min(pageblock_nr_pages,
				zone->nr_reserved_highatomic);

			/*
			 * Convert to ac->migratetype and avoid the normal
			 * pageblock stealing heuristics. Minimally, the caller
			 * is doing the work and needs the pages. More
			 * importantly, if the block was always converted to
			 * MIGRATE_UNMOVABLE or another type then the number
			 * of pageblocks that cannot be completely freed
			 * may increase.
			 */
			set_pageblock_migratetype(page, ac->migratetype);
			move_freepages_block(zone, page, ac->migratetype);
			spin_unlock_irqrestore(&zone->lock, flags);
			return;
		}
		spin_unlock_irqrestore(&zone->lock, flags);
	}
}

/* Remove an element from the buddy allocator from the fallback list */
static inline struct page *
__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
{
	struct free_area *area;
	unsigned int current_order;
	struct page *page;
	int fallback_mt;
	bool can_steal;

	/* Find the largest possible block of pages in the other list */
	for (current_order = MAX_ORDER-1;
				current_order >= order && current_order <= MAX_ORDER-1;
				--current_order) {
		area = &(zone->free_area[current_order]);
		fallback_mt = find_suitable_fallback(area, current_order,
				start_migratetype, false, &can_steal);
		if (fallback_mt == -1)
			continue;

		page = list_first_entry(&area->free_list[fallback_mt],
						struct page, lru);
		if (can_steal)
			steal_suitable_fallback(zone, page, start_migratetype);

		/* Remove the page from the freelists */
		area->nr_free--;
		list_del(&page->lru);
		rmv_page_order(page);

		expand(zone, page, order, current_order, area,
					start_migratetype);
		/*
		 * The pcppage_migratetype may differ from pageblock's
		 * migratetype depending on the decisions in
		 * find_suitable_fallback(). This is OK as long as it does not
		 * differ for MIGRATE_CMA pageblocks. Those can be used as
		 * fallback only via special __rmqueue_cma_fallback() function
		 */
		set_pcppage_migratetype(page, start_migratetype);

		trace_mm_page_alloc_extfrag(page, order, current_order,
			start_migratetype, fallback_mt);

		return page;
	}

	return NULL;
}

/*
 * Do the hard work of removing an element from the buddy allocator.
 * Call me with the zone->lock already held.
 */
static struct page *__rmqueue(struct zone *zone, unsigned int order,
				int migratetype)
{
	struct page *page;

	page = __rmqueue_smallest(zone, order, migratetype);
	if (unlikely(!page)) {
		if (migratetype == MIGRATE_MOVABLE)
			page = __rmqueue_cma_fallback(zone, order);

		if (!page)
			page = __rmqueue_fallback(zone, order, migratetype);
	}

	trace_mm_page_alloc_zone_locked(page, order, migratetype);
	return page;
}

/*
 * Obtain a specified number of elements from the buddy allocator, all under
 * a single hold of the lock, for efficiency.  Add them to the supplied list.
 * Returns the number of new pages which were placed at *list.
 */
static int rmqueue_bulk(struct zone *zone, unsigned int order,
			unsigned long count, struct list_head *list,
			int migratetype, bool cold)
{
	int i;

	spin_lock(&zone->lock);
	for (i = 0; i < count; ++i) {
		struct page *page = __rmqueue(zone, order, migratetype);
		if (unlikely(page == NULL))
			break;

		/*
		 * Split buddy pages returned by expand() are received here
		 * in physical page order. The page is added to the callers and
		 * list and the list head then moves forward. From the callers
		 * perspective, the linked list is ordered by page number in
		 * some conditions. This is useful for IO devices that can
		 * merge IO requests if the physical pages are ordered
		 * properly.
		 */
		if (likely(!cold))
			list_add(&page->lru, list);
		else
			list_add_tail(&page->lru, list);
		list = &page->lru;
		if (is_migrate_cma(get_pcppage_migratetype(page)))
			__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
					      -(1 << order));
	}
	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
	spin_unlock(&zone->lock);
	return i;
}

#ifdef CONFIG_NUMA
/*
 * Called from the vmstat counter updater to drain pagesets of this
 * currently executing processor on remote nodes after they have
 * expired.
 *
 * Note that this function must be called with the thread pinned to
 * a single processor.
 */
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
{
	unsigned long flags;
	int to_drain, batch;

	local_irq_save(flags);
	batch = READ_ONCE(pcp->batch);
	to_drain = min(pcp->count, batch);
	if (to_drain > 0) {
		free_pcppages_bulk(zone, to_drain, pcp);
		pcp->count -= to_drain;
	}
	local_irq_restore(flags);