compaction.c

// SPDX-License-Identifier: GPL-2.0
/*
 * linux/mm/compaction.c
 *
 * Memory compaction for the reduction of external fragmentation. Note that
 * this heavily depends upon page migration to do all the real heavy
 * lifting
 *
 * Copyright IBM Corp. 2007-2010 Mel Gorman <mel@csn.ul.ie>
 */
#include <linux/cpu.h>
#include <linux/swap.h>
#include <linux/migrate.h>
#include <linux/compaction.h>
#include <linux/mm_inline.h>
#include <linux/sched/signal.h>
#include <linux/backing-dev.h>
#include <linux/sysctl.h>
#include <linux/sysfs.h>
#include <linux/page-isolation.h>
#include <linux/kasan.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/page_owner.h>
#include <linux/psi.h>
#include "internal.h"

#ifdef CONFIG_COMPACTION
static inline void count_compact_event(enum vm_event_item item)
{
	count_vm_event(item);
}

static inline void count_compact_events(enum vm_event_item item, long delta)
{
	count_vm_events(item, delta);
}
#else
#define count_compact_event(item) do { } while (0)
#define count_compact_events(item, delta) do { } while (0)
#endif

#if defined CONFIG_COMPACTION || defined CONFIG_CMA

#define CREATE_TRACE_POINTS
#include <trace/events/compaction.h>

#define block_start_pfn(pfn, order)	round_down(pfn, 1UL << (order))
#define block_end_pfn(pfn, order)	ALIGN((pfn) + 1, 1UL << (order))
#define pageblock_start_pfn(pfn)	block_start_pfn(pfn, pageblock_order)
#define pageblock_end_pfn(pfn)		block_end_pfn(pfn, pageblock_order)

static unsigned long release_freepages(struct list_head *freelist)
{
	struct page *page, *next;
	unsigned long high_pfn = 0;

	list_for_each_entry_safe(page, next, freelist, lru) {
		unsigned long pfn = page_to_pfn(page);
		list_del(&page->lru);
		__free_page(page);
		if (pfn > high_pfn)
			high_pfn = pfn;
	}

	return high_pfn;
}

static void split_map_pages(struct list_head *list)
{
	unsigned int i, order, nr_pages;
	struct page *page, *next;
	LIST_HEAD(tmp_list);

	list_for_each_entry_safe(page, next, list, lru) {
		list_del(&page->lru);

		order = page_private(page);
		nr_pages = 1 << order;

		post_alloc_hook(page, order, __GFP_MOVABLE);
		if (order)
			split_page(page, order);

		for (i = 0; i < nr_pages; i++) {
			list_add(&page->lru, &tmp_list);
			page++;
		}
	}

	list_splice(&tmp_list, list);
}

#ifdef CONFIG_COMPACTION

int PageMovable(struct page *page)
{
	struct address_space *mapping;

	VM_BUG_ON_PAGE(!PageLocked(page), page);
	if (!__PageMovable(page))
		return 0;

	mapping = page_mapping(page);
	if (mapping && mapping->a_ops && mapping->a_ops->isolate_page)
		return 1;

	return 0;
}
EXPORT_SYMBOL(PageMovable);

void __SetPageMovable(struct page *page, struct address_space *mapping)
{
	VM_BUG_ON_PAGE(!PageLocked(page), page);
	VM_BUG_ON_PAGE((unsigned long)mapping & PAGE_MAPPING_MOVABLE, page);
	page->mapping = (void *)((unsigned long)mapping | PAGE_MAPPING_MOVABLE);
}
EXPORT_SYMBOL(__SetPageMovable);

void __ClearPageMovable(struct page *page)
{
	VM_BUG_ON_PAGE(!PageLocked(page), page);
	VM_BUG_ON_PAGE(!PageMovable(page), page);
	/*
	 * Clear registered address_space val with keeping PAGE_MAPPING_MOVABLE
	 * flag so that VM can catch up released page by driver after isolation.
	 * With it, VM migration doesn't try to put it back.
	 */
	page->mapping = (void *)((unsigned long)page->mapping &
				PAGE_MAPPING_MOVABLE);
}
EXPORT_SYMBOL(__ClearPageMovable);

/* Do not skip compaction more than 64 times */
#define COMPACT_MAX_DEFER_SHIFT 6

/*
 * Compaction is deferred when compaction fails to result in a page
 * allocation success. 1 << compact_defer_limit compactions are skipped up
 * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
 */
void defer_compaction(struct zone *zone, int order)
{
	zone->compact_considered = 0;
	zone->compact_defer_shift++;

	if (order < zone->compact_order_failed)
		zone->compact_order_failed = order;

	if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
		zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;

	trace_mm_compaction_defer_compaction(zone, order);
}

/* Returns true if compaction should be skipped this time */
bool compaction_deferred(struct zone *zone, int order)
{
	unsigned long defer_limit = 1UL << zone->compact_defer_shift;

	if (order < zone->compact_order_failed)
		return false;

	/* Avoid possible overflow */
	if (++zone->compact_considered > defer_limit)
		zone->compact_considered = defer_limit;

	if (zone->compact_considered >= defer_limit)
		return false;

	trace_mm_compaction_deferred(zone, order);

	return true;
}

/*
 * Update defer tracking counters after successful compaction of given order,
 * which means an allocation either succeeded (alloc_success == true) or is
 * expected to succeed.
 */
void compaction_defer_reset(struct zone *zone, int order,
		bool alloc_success)
{
	if (alloc_success) {
		zone->compact_considered = 0;
		zone->compact_defer_shift = 0;
	}
	if (order >= zone->compact_order_failed)
		zone->compact_order_failed = order + 1;

	trace_mm_compaction_defer_reset(zone, order);
}

/* Returns true if restarting compaction after many failures */
bool compaction_restarting(struct zone *zone, int order)
{
	if (order < zone->compact_order_failed)
		return false;

	return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
		zone->compact_considered >= 1UL << zone->compact_defer_shift;
}

/* Returns true if the pageblock should be scanned for pages to isolate. */
static inline bool isolation_suitable(struct compact_control *cc,
					struct page *page)
{
	if (cc->ignore_skip_hint)
		return true;

	return !get_pageblock_skip(page);
}

static void reset_cached_positions(struct zone *zone)
{
	zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
	zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
	zone->compact_cached_free_pfn =
				pageblock_start_pfn(zone_end_pfn(zone) - 1);
}

/*
 * Compound pages of >= pageblock_order should consistenly be skipped until
 * released. It is always pointless to compact pages of such order (if they are
 * migratable), and the pageblocks they occupy cannot contain any free pages.
 */
static bool pageblock_skip_persistent(struct page *page)
{
	if (!PageCompound(page))
		return false;

	page = compound_head(page);

	if (compound_order(page) >= pageblock_order)
		return true;

	return false;
}

static bool
__reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
							bool check_target)
{
	struct page *page = pfn_to_online_page(pfn);
	struct page *end_page;
	unsigned long block_pfn;

	if (!page)
		return false;
	if (zone != page_zone(page))
		return false;
	if (pageblock_skip_persistent(page))
		return false;

	/*
	 * If skip is already cleared do no further checking once the
	 * restart points have been set.
	 */
	if (check_source && check_target && !get_pageblock_skip(page))
		return true;

	/*
	 * If clearing skip for the target scanner, do not select a
	 * non-movable pageblock as the starting point.
	 */
	if (!check_source && check_target &&
	    get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
		return false;

	/*
	 * Only clear the hint if a sample indicates there is either a
	 * free page or an LRU page in the block. One or other condition
	 * is necessary for the block to be a migration source/target.
	 */
	block_pfn = pageblock_start_pfn(pfn);
	pfn = max(block_pfn, zone->zone_start_pfn);
	page = pfn_to_page(pfn);
	if (zone != page_zone(page))
		return false;
	pfn = block_pfn + pageblock_nr_pages;
	pfn = min(pfn, zone_end_pfn(zone));
	end_page = pfn_to_page(pfn);

	do {
		if (pfn_valid_within(pfn)) {
			if (check_source && PageLRU(page)) {
				clear_pageblock_skip(page);
				return true;
			}

			if (check_target && PageBuddy(page)) {
				clear_pageblock_skip(page);
				return true;
			}
		}

		page += (1 << PAGE_ALLOC_COSTLY_ORDER);
		pfn += (1 << PAGE_ALLOC_COSTLY_ORDER);
	} while (page < end_page);

	return false;
}

/*
 * This function is called to clear all cached information on pageblocks that
 * should be skipped for page isolation when the migrate and free page scanner
 * meet.
 */
static void __reset_isolation_suitable(struct zone *zone)
{
	unsigned long migrate_pfn = zone->zone_start_pfn;
	unsigned long free_pfn = zone_end_pfn(zone);
	unsigned long reset_migrate = free_pfn;
	unsigned long reset_free = migrate_pfn;
	bool source_set = false;
	bool free_set = false;

	if (!zone->compact_blockskip_flush)
		return;

	zone->compact_blockskip_flush = false;

	/*
	 * Walk the zone and update pageblock skip information. Source looks
	 * for PageLRU while target looks for PageBuddy. When the scanner
	 * is found, both PageBuddy and PageLRU are checked as the pageblock
	 * is suitable as both source and target.
	 */
	for (; migrate_pfn < free_pfn; migrate_pfn += pageblock_nr_pages,
					free_pfn -= pageblock_nr_pages) {
		cond_resched();

		/* Update the migrate PFN */
		if (__reset_isolation_pfn(zone, migrate_pfn, true, source_set) &&
		    migrate_pfn < reset_migrate) {
			source_set = true;
			reset_migrate = migrate_pfn;
			zone->compact_init_migrate_pfn = reset_migrate;
			zone->compact_cached_migrate_pfn[0] = reset_migrate;
			zone->compact_cached_migrate_pfn[1] = reset_migrate;
		}

		/* Update the free PFN */
		if (__reset_isolation_pfn(zone, free_pfn, free_set, true) &&
		    free_pfn > reset_free) {
			free_set = true;
			reset_free = free_pfn;
			zone->compact_init_free_pfn = reset_free;
			zone->compact_cached_free_pfn = reset_free;
		}
	}

	/* Leave no distance if no suitable block was reset */
	if (reset_migrate >= reset_free) {
		zone->compact_cached_migrate_pfn[0] = migrate_pfn;
		zone->compact_cached_migrate_pfn[1] = migrate_pfn;
		zone->compact_cached_free_pfn = free_pfn;
	}
}

void reset_isolation_suitable(pg_data_t *pgdat)
{
	int zoneid;

	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
		struct zone *zone = &pgdat->node_zones[zoneid];
		if (!populated_zone(zone))
			continue;

		/* Only flush if a full compaction finished recently */
		if (zone->compact_blockskip_flush)
			__reset_isolation_suitable(zone);
	}
}

/*
 * Sets the pageblock skip bit if it was clear. Note that this is a hint as
 * locks are not required for read/writers. Returns true if it was already set.
 */
static bool test_and_set_skip(struct compact_control *cc, struct page *page,
							unsigned long pfn)
{
	bool skip;

	/* Do no update if skip hint is being ignored */
	if (cc->ignore_skip_hint)
		return false;

	if (!IS_ALIGNED(pfn, pageblock_nr_pages))
		return false;

	skip = get_pageblock_skip(page);
	if (!skip && !cc->no_set_skip_hint)
		set_pageblock_skip(page);

	return skip;
}

static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
{
	struct zone *zone = cc->zone;

	pfn = pageblock_end_pfn(pfn);

	/* Set for isolation rather than compaction */
	if (cc->no_set_skip_hint)
		return;

	if (pfn > zone->compact_cached_migrate_pfn[0])
		zone->compact_cached_migrate_pfn[0] = pfn;
	if (cc->mode != MIGRATE_ASYNC &&
	    pfn > zone->compact_cached_migrate_pfn[1])
		zone->compact_cached_migrate_pfn[1] = pfn;
}

/*
 * If no pages were isolated then mark this pageblock to be skipped in the
 * future. The information is later cleared by __reset_isolation_suitable().
 */
static void update_pageblock_skip(struct compact_control *cc,
			struct page *page, unsigned long pfn)
{
	struct zone *zone = cc->zone;

	if (cc->no_set_skip_hint)
		return;

	if (!page)
		return;

	set_pageblock_skip(page);

	/* Update where async and sync compaction should restart */
	if (pfn < zone->compact_cached_free_pfn)
		zone->compact_cached_free_pfn = pfn;
}
#else
static inline bool isolation_suitable(struct compact_control *cc,
					struct page *page)
{
	return true;
}

static inline bool pageblock_skip_persistent(struct page *page)
{
	return false;
}

static inline void update_pageblock_skip(struct compact_control *cc,
			struct page *page, unsigned long pfn)
{
}

static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
{
}

static bool test_and_set_skip(struct compact_control *cc, struct page *page,
							unsigned long pfn)
{
	return false;
}
#endif /* CONFIG_COMPACTION */

/*
 * Compaction requires the taking of some coarse locks that are potentially
 * very heavily contended. For async compaction, trylock and record if the
 * lock is contended. The lock will still be acquired but compaction will
 * abort when the current block is finished regardless of success rate.
 * Sync compaction acquires the lock.
 *
 * Always returns true which makes it easier to track lock state in callers.
 */
static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags,
						struct compact_control *cc)
{
	/* Track if the lock is contended in async mode */
	if (cc->mode == MIGRATE_ASYNC && !cc->contended) {
		if (spin_trylock_irqsave(lock, *flags))
			return true;

		cc->contended = true;
	}

	spin_lock_irqsave(lock, *flags);
	return true;
}

/*
 * Compaction requires the taking of some coarse locks that are potentially
 * very heavily contended. The lock should be periodically unlocked to avoid
 * having disabled IRQs for a long time, even when there is nobody waiting on
 * the lock. It might also be that allowing the IRQs will result in
 * need_resched() becoming true. If scheduling is needed, async compaction
 * aborts. Sync compaction schedules.
 * Either compaction type will also abort if a fatal signal is pending.
 * In either case if the lock was locked, it is dropped and not regained.
 *
 * Returns true if compaction should abort due to fatal signal pending, or
 *		async compaction due to need_resched()
 * Returns false when compaction can continue (sync compaction might have
 *		scheduled)
 */
static bool compact_unlock_should_abort(spinlock_t *lock,
		unsigned long flags, bool *locked, struct compact_control *cc)
{
	if (*locked) {
		spin_unlock_irqrestore(lock, flags);
		*locked = false;
	}

	if (fatal_signal_pending(current)) {
		cc->contended = true;
		return true;
	}

	cond_resched();

	return false;
}

/*
 * Isolate free pages onto a private freelist. If @strict is true, will abort
 * returning 0 on any invalid PFNs or non-free pages inside of the pageblock
 * (even though it may still end up isolating some pages).
 */
static unsigned long isolate_freepages_block(struct compact_control *cc,
				unsigned long *start_pfn,
				unsigned long end_pfn,
				struct list_head *freelist,
				unsigned int stride,
				bool strict)
{
	int nr_scanned = 0, total_isolated = 0;
	struct page *cursor;
	unsigned long flags = 0;
	bool locked = false;
	unsigned long blockpfn = *start_pfn;
	unsigned int order;

	/* Strict mode is for isolation, speed is secondary */
	if (strict)
		stride = 1;

	cursor = pfn_to_page(blockpfn);

	/* Isolate free pages. */
	for (; blockpfn < end_pfn; blockpfn += stride, cursor += stride) {
		int isolated;
		struct page *page = cursor;

		/*
		 * Periodically drop the lock (if held) regardless of its
		 * contention, to give chance to IRQs. Abort if fatal signal
		 * pending or async compaction detects need_resched()
		 */
		if (!(blockpfn % SWAP_CLUSTER_MAX)
		    && compact_unlock_should_abort(&cc->zone->lock, flags,
								&locked, cc))
			break;

		nr_scanned++;
		if (!pfn_valid_within(blockpfn))
			goto isolate_fail;

		/*
		 * For compound pages such as THP and hugetlbfs, we can save
		 * potentially a lot of iterations if we skip them at once.
		 * The check is racy, but we can consider only valid values
		 * and the only danger is skipping too much.
		 */
		if (PageCompound(page)) {
			const unsigned int order = compound_order(page);

			if (likely(order < MAX_ORDER)) {
				blockpfn += (1UL << order) - 1;
				cursor += (1UL << order) - 1;
			}
			goto isolate_fail;
		}

		if (!PageBuddy(page))
			goto isolate_fail;

		/*
		 * If we already hold the lock, we can skip some rechecking.
		 * Note that if we hold the lock now, checked_pageblock was
		 * already set in some previous iteration (or strict is true),
		 * so it is correct to skip the suitable migration target
		 * recheck as well.
		 */
		if (!locked) {
			locked = compact_lock_irqsave(&cc->zone->lock,
								&flags, cc);

			/* Recheck this is a buddy page under lock */
			if (!PageBuddy(page))
				goto isolate_fail;
		}

		/* Found a free page, will break it into order-0 pages */
		order = page_order(page);
		isolated = __isolate_free_page(page, order);
		if (!isolated)
			break;
		set_page_private(page, order);

		total_isolated += isolated;
		cc->nr_freepages += isolated;
		list_add_tail(&page->lru, freelist);

		if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
			blockpfn += isolated;
			break;
		}
		/* Advance to the end of split page */
		blockpfn += isolated - 1;
		cursor += isolated - 1;
		continue;

isolate_fail:
		if (strict)
			break;
		else
			continue;

	}

	if (locked)
		spin_unlock_irqrestore(&cc->zone->lock, flags);

	/*
	 * There is a tiny chance that we have read bogus compound_order(),
	 * so be careful to not go outside of the pageblock.
	 */
	if (unlikely(blockpfn > end_pfn))
		blockpfn = end_pfn;

	trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn,
					nr_scanned, total_isolated);

	/* Record how far we have got within the block */
	*start_pfn = blockpfn;

	/*
	 * If strict isolation is requested by CMA then check that all the
	 * pages requested were isolated. If there were any failures, 0 is
	 * returned and CMA will fail.
	 */
	if (strict && blockpfn < end_pfn)
		total_isolated = 0;

	cc->total_free_scanned += nr_scanned;
	if (total_isolated)
		count_compact_events(COMPACTISOLATED, total_isolated);
	return total_isolated;
}

/**
 * isolate_freepages_range() - isolate free pages.
 * @cc:        Compaction control structure.
 * @start_pfn: The first PFN to start isolating.
 * @end_pfn:   The one-past-last PFN.
 *
 * Non-free pages, invalid PFNs, or zone boundaries within the
 * [start_pfn, end_pfn) range are considered errors, cause function to
 * undo its actions and return zero.
 *
 * Otherwise, function returns one-past-the-last PFN of isolated page
 * (which may be greater then end_pfn if end fell in a middle of
 * a free page).
 */
unsigned long
isolate_freepages_range(struct compact_control *cc,
			unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long isolated, pfn, block_start_pfn, block_end_pfn;
	LIST_HEAD(freelist);

	pfn = start_pfn;
	block_start_pfn = pageblock_start_pfn(pfn);
	if (block_start_pfn < cc->zone->zone_start_pfn)
		block_start_pfn = cc->zone->zone_start_pfn;
	block_end_pfn = pageblock_end_pfn(pfn);

	for (; pfn < end_pfn; pfn += isolated,
				block_start_pfn = block_end_pfn,
				block_end_pfn += pageblock_nr_pages) {
		/* Protect pfn from changing by isolate_freepages_block */
		unsigned long isolate_start_pfn = pfn;

		block_end_pfn = min(block_end_pfn, end_pfn);

		/*
		 * pfn could pass the block_end_pfn if isolated freepage
		 * is more than pageblock order. In this case, we adjust
		 * scanning range to right one.
		 */
		if (pfn >= block_end_pfn) {
			block_start_pfn = pageblock_start_pfn(pfn);
			block_end_pfn = pageblock_end_pfn(pfn);
			block_end_pfn = min(block_end_pfn, end_pfn);
		}

		if (!pageblock_pfn_to_page(block_start_pfn,
					block_end_pfn, cc->zone))
			break;

		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
					block_end_pfn, &freelist, 0, true);

		/*
		 * In strict mode, isolate_freepages_block() returns 0 if
		 * there are any holes in the block (ie. invalid PFNs or
		 * non-free pages).
		 */
		if (!isolated)
			break;

		/*
		 * If we managed to isolate pages, it is always (1 << n) *
		 * pageblock_nr_pages for some non-negative n.  (Max order
		 * page may span two pageblocks).
		 */
	}

	/* __isolate_free_page() does not map the pages */
	split_map_pages(&freelist);

	if (pfn < end_pfn) {
		/* Loop terminated early, cleanup. */
		release_freepages(&freelist);
		return 0;
	}

	/* We don't use freelists for anything. */
	return pfn;
}

/* Similar to reclaim, but different enough that they don't share logic */
static bool too_many_isolated(pg_data_t *pgdat)
{
	unsigned long active, inactive, isolated;

	inactive = node_page_state(pgdat, NR_INACTIVE_FILE) +
			node_page_state(pgdat, NR_INACTIVE_ANON);
	active = node_page_state(pgdat, NR_ACTIVE_FILE) +
			node_page_state(pgdat, NR_ACTIVE_ANON);
	isolated = node_page_state(pgdat, NR_ISOLATED_FILE) +
			node_page_state(pgdat, NR_ISOLATED_ANON);

	return isolated > (inactive + active) / 2;
}

/**
 * isolate_migratepages_block() - isolate all migrate-able pages within
 *				  a single pageblock
 * @cc:		Compaction control structure.
 * @low_pfn:	The first PFN to isolate
 * @end_pfn:	The one-past-the-last PFN to isolate, within same pageblock
 * @isolate_mode: Isolation mode to be used.
 *
 * Isolate all pages that can be migrated from the range specified by
 * [low_pfn, end_pfn). The range is expected to be within same pageblock.
 * Returns zero if there is a fatal signal pending, otherwise PFN of the
 * first page that was not scanned (which may be both less, equal to or more
 * than end_pfn).
 *
 * The pages are isolated on cc->migratepages list (not required to be empty),
 * and cc->nr_migratepages is updated accordingly. The cc->migrate_pfn field
 * is neither read nor updated.
 */
static unsigned long
isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
			unsigned long end_pfn, isolate_mode_t isolate_mode)
{
	pg_data_t *pgdat = cc->zone->zone_pgdat;
	unsigned long nr_scanned = 0, nr_isolated = 0;
	struct lruvec *lruvec;
	unsigned long flags = 0;
	bool locked = false;
	struct page *page = NULL, *valid_page = NULL;
	unsigned long start_pfn = low_pfn;
	bool skip_on_failure = false;
	unsigned long next_skip_pfn = 0;
	bool skip_updated = false;

	/*
	 * Ensure that there are not too many pages isolated from the LRU
	 * list by either parallel reclaimers or compaction. If there are,
	 * delay for some time until fewer pages are isolated
	 */
	while (unlikely(too_many_isolated(pgdat))) {
		/* async migration should just abort */
		if (cc->mode == MIGRATE_ASYNC)
			return 0;

		congestion_wait(BLK_RW_ASYNC, HZ/10);

		if (fatal_signal_pending(current))
			return 0;
	}

	cond_resched();

	if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) {
		skip_on_failure = true;
		next_skip_pfn = block_end_pfn(low_pfn, cc->order);
	}

	/* Time to isolate some pages for migration */
	for (; low_pfn < end_pfn; low_pfn++) {

		if (skip_on_failure && low_pfn >= next_skip_pfn) {
			/*
			 * We have isolated all migration candidates in the
			 * previous order-aligned block, and did not skip it due
			 * to failure. We should migrate the pages now and
			 * hopefully succeed compaction.
			 */
			if (nr_isolated)
				break;

			/*
			 * We failed to isolate in the previous order-aligned
			 * block. Set the new boundary to the end of the
			 * current block. Note we can't simply increase
			 * next_skip_pfn by 1 << order, as low_pfn might have
			 * been incremented by a higher number due to skipping
			 * a compound or a high-order buddy page in the
			 * previous loop iteration.
			 */
			next_skip_pfn = block_end_pfn(low_pfn, cc->order);
		}

		/*
		 * Periodically drop the lock (if held) regardless of its
		 * contention, to give chance to IRQs. Abort async compaction
		 * if contended.
		 */
		if (!(low_pfn % SWAP_CLUSTER_MAX)
		    && compact_unlock_should_abort(&pgdat->lru_lock,
					    flags, &locked, cc))
			break;

		if (!pfn_valid_within(low_pfn))
			goto isolate_fail;
		nr_scanned++;

		page = pfn_to_page(low_pfn);

		/*
		 * Check if the pageblock has already been marked skipped.
		 * Only the aligned PFN is checked as the caller isolates
		 * COMPACT_CLUSTER_MAX at a time so the second call must
		 * not falsely conclude that the block should be skipped.
		 */
		if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) {
			if (!cc->ignore_skip_hint && get_pageblock_skip(page)) {
				low_pfn = end_pfn;
				goto isolate_abort;
			}
			valid_page = page;
		}

		/*
		 * Skip if free. We read page order here without zone lock
		 * which is generally unsafe, but the race window is small and
		 * the worst thing that can happen is that we skip some
		 * potential isolation targets.
		 */
		if (PageBuddy(page)) {
			unsigned long freepage_order = page_order_unsafe(page);

			/*
			 * Without lock, we cannot be sure that what we got is
			 * a valid page order. Consider only values in the
			 * valid order range to prevent low_pfn overflow.
			 */
			if (freepage_order > 0 && freepage_order < MAX_ORDER)
				low_pfn += (1UL << freepage_order) - 1;
			continue;
		}

		/*
		 * Regardless of being on LRU, compound pages such as THP and
		 * hugetlbfs are not to be compacted. We can potentially save
		 * a lot of iterations if we skip them at once. The check is
		 * racy, but we can consider only valid values and the only
		 * danger is skipping too much.
		 */
		if (PageCompound(page)) {
			const unsigned int order = compound_order(page);

			if (likely(order < MAX_ORDER))
				low_pfn += (1UL << order) - 1;
			goto isolate_fail;
		}

		/*
		 * Check may be lockless but that's ok as we recheck later.
		 * It's possible to migrate LRU and non-lru movable pages.
		 * Skip any other type of page
		 */
		if (!PageLRU(page)) {
			/*
			 * __PageMovable can return false positive so we need
			 * to verify it under page_lock.
			 */
			if (unlikely(__PageMovable(page)) &&
					!PageIsolated(page)) {
				if (locked) {
					spin_unlock_irqrestore(&pgdat->lru_lock,
									flags);
					locked = false;
				}

				if (!isolate_movable_page(page, isolate_mode))
					goto isolate_success;
			}

			goto isolate_fail;
		}

		/*
		 * Migration will fail if an anonymous page is pinned in memory,
		 * so avoid taking lru_lock and isolating it unnecessarily in an
		 * admittedly racy check.
		 */
		if (!page_mapping(page) &&
		    page_count(page) > page_mapcount(page))
			goto isolate_fail;

		/*
		 * Only allow to migrate anonymous pages in GFP_NOFS context
		 * because those do not depend on fs locks.
		 */
		if (!(cc->gfp_mask & __GFP_FS) && page_mapping(page))
			goto isolate_fail;

		/* If we already hold the lock, we can skip some rechecking */
		if (!locked) {
			locked = compact_lock_irqsave(&pgdat->lru_lock,
								&flags, cc);

			/* Try get exclusive access under lock */
			if (!skip_updated) {
				skip_updated = true;
				if (test_and_set_skip(cc, page, low_pfn))
					goto isolate_abort;
			}

			/* Recheck PageLRU and PageCompound under lock */
			if (!PageLRU(page))
				goto isolate_fail;

			/*
			 * Page become compound since the non-locked check,
			 * and it's on LRU. It can only be a THP so the order
			 * is safe to read and it's 0 for tail pages.
			 */
			if (unlikely(PageCompound(page))) {
				low_pfn += (1UL << compound_order(page)) - 1;
				goto isolate_fail;
			}
		}

		lruvec = mem_cgroup_page_lruvec(page, pgdat);

		/* Try isolate the page */
		if (__isolate_lru_page(page, isolate_mode) != 0)
			goto isolate_fail;

		VM_BUG_ON_PAGE(PageCompound(page), page);

		/* Successfully isolated */
		del_page_from_lru_list(page, lruvec, page_lru(page));
		inc_node_page_state(page,
				NR_ISOLATED_ANON + page_is_file_cache(page));

isolate_success:
		list_add(&page->lru, &cc->migratepages);
		cc->nr_migratepages++;
		nr_isolated++;

		/*
		 * Avoid isolating too much unless this block is being
		 * rescanned (e.g. dirty/writeback pages, parallel allocation)
		 * or a lock is contended. For contention, isolate quickly to
		 * potentially remove one source of contention.
		 */
		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX &&
		    !cc->rescan && !cc->contended) {
			++low_pfn;
			break;
		}

		continue;
isolate_fail:
		if (!skip_on_failure)