litmus-rt.git - The LITMUS^RT kernel.

The LITMUS^RT kernel.

Bjoern Brandenburg

about summary refs log tree commit diff stats

diff options

author	Sascha Hauer <s.hauer@pengutronix.de>	2010-10-18 04:16:26 -0400
committer	Linus Torvalds <torvalds@linux-foundation.org>	2010-10-18 16:09:05 -0400
commit	63f1474c69c061f923068a25f136dca0c49cd478 (patch)
tree	2506d897c28391ffacd9ff0f32fa4f1de7126a7e /include/linux/kernel.h
parent	f68c834b045afc8c80ec167cccf48934c8970022 (diff)

mxc_nand: do not depend on disabling the irq in the interrupt handler

This patch reverts the driver to enabling/disabling the NFC interrupt mask rather than enabling/disabling the system interrupt. This cleans up the driver so that it doesn't rely on interrupts being disabled within the interrupt handler. For i.MX21 we keep the current behaviour, that is calling enable_irq/disable_irq_nosync to enable/disable interrupts. This patch is based on earlier work by John Ogness. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Acked-by: John Ogness <john.ogness@linutronix.de> Tested-by: John Ogness <john.ogness@linutronix.de> Signed-off-by: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Diffstat (limited to 'include/linux/kernel.h')

0 files changed, 0 insertions, 0 deletions

cgit.cgi/litmus-rt-ext-res.git/commit/mm/compaction.c?id=6bace090a25455cb1dffaa9ab4aabc36dbd44d4a'>6bace090a254

584200163037

06b6640a3902

584200163037

22
23

25
26

42
43

44
45
46

52
53
54

56
57

59
60

61
62

63
64

66
67

68
69

81
82

89
90

91
92

219
220

227
228

230
231

240
241

248
249

250
251

267
268

271
272

281
282
283

284
285
286

293
294

295
296

297
298

299
300

310
311

328
329

338
339

355
356

365
366

374
375

377
378

379
380
381

404
405
406

410
411
412

421
422

426
427

440
441

442
443

464
465

481
482

483
484

491
492
493

494
495

500
501

502
503
504

517
518

519
520
521

529
530
531

532
533
534

541
542

543
544

550
551
552

567
568

571
572

575
576

578
579

582
583

585
586

593
594

595
596
597

598
599

600
601

602
603

633
634
635

646
647

649
650

652
653
654

655
656

662
663
664

666
667
668

677
678

690
691
692

694
695

696
697

736
737

745
746
747

781
782

802
803
804

824
825

828
829

844
845

856
857

858
859

874
875

892
893

908
909

920
921
922

927
928

934
935
936

952
953
954

956
957

959
960

966
967

975
976
977

983
984

986
987
988

989
990
991

992
993

1000
1001

1003
1004

1017
1018
1019

1039
1040

1048
1049

1052
1053

1055
1056

1057
1058
1059

1060
1061

1065
1066

1076
1077

1078
1079
1080

1083
1084
1085

1087
1088
1089

1090
1091
1092

1101
1102

1103
1104

1105
1106

1108
1109

1115
1116

1121
1122

1126
1127

1129
1130

1197
1198
1199

1204
1205
1206

1207
1208

1218
1219

1220
1221

1242
1243

1245
1246

1257
1258
1259

1260
1261

1274
1275

1278
1279

1289
1290

1303
1304

1306
1307
1308

1310
1311

1319
1320

1333
1334

1336
1337

1375
1376

1377
1378
1379

1382
1383
1384

1391
1392

1398
1399

1402
1403

1405
1406

1408
1409

1428
1429

1430
1431

1433
1434
1435

1438
1439

1456
1457

1458
1459
1460

1503
1504
1505

1521
1522

1526
1527
1528

1535
1536
1537

1539
1540
1541

1559
1560
1561

1565
1566

1568
1569

1573
1574

1578
1579

1586
1587
1588

1594
1595

1597
1598

1607
1608

1632
1633

1643
1644
1645

1646
1647

1668
1669
1670

1671
1672

1674
1675

1682
1683
1684

1685
1686

1690
1691

1692
1693

1696
1697

1708
1709

1710
1711

1712
1713

1715
1716
1717

1719
1720
1721

1727
1728

1741
1742

1745
1746

1753
1754

1755
1756

1766
1767

1782
1783
1784

1797
1798

1799
1800

1801
1802
1803

1805
1806

1822
1823

1825
1826
1827

1829
1830
1831

1832
1833
1834

1835
1836

1851
1852
1853

1866
1867

1876
1877
1878

1880
1881
1882

1889
1890

1892
1893

1927
1928

1929
1930
1931

1933
1934

1935
1936

1955
1956

1961
1962

1963
1964

2093
2094
2095

2096
2097
2098

2102
2103
2104

2121
2122
2123

// 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 "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 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);
}

/*
 * 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 start_pfn = zone->zone_start_pfn;
	unsigned long end_pfn = zone_end_pfn(zone);
	unsigned long pfn;

	zone->compact_blockskip_flush = false;

	/* Walk the zone and mark every pageblock as suitable for isolation */
	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
		struct page *page;

		cond_resched();

		page = pfn_to_online_page(pfn);
		if (!page)
			continue;
		if (zone != page_zone(page))
			continue;

		clear_pageblock_skip(page);
	}

	reset_cached_positions(zone);
}

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);
	}
}

/*
 * 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 nr_isolated,
			bool migrate_scanner)
{
	struct zone *zone = cc->zone;
	unsigned long pfn;

	if (cc->ignore_skip_hint)
		return;

	if (!page)
		return;

	if (nr_isolated)
		return;

	set_pageblock_skip(page);

	pfn = page_to_pfn(page);

	/* Update where async and sync compaction should restart */
	if (migrate_scanner) {
		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;
	} else {
		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 void update_pageblock_skip(struct compact_control *cc,
			struct page *page, unsigned long nr_isolated,
			bool migrate_scanner)
{
}
#endif /* CONFIG_COMPACTION */

/*
 * Compaction requires the taking of some coarse locks that are potentially
 * very heavily contended. For async compaction, back out if the lock cannot
 * be taken immediately. For sync compaction, spin on the lock if needed.
 *
 * Returns true if the lock is held
 * Returns false if the lock is not held and compaction should abort
 */
static bool compact_trylock_irqsave(spinlock_t *lock, unsigned long *flags,
						struct compact_control *cc)
{
	if (cc->mode == MIGRATE_ASYNC) {
		if (!spin_trylock_irqsave(lock, *flags)) {
			cc->contended = true;
			return false;
		}
	} else {
		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;
	}

	if (need_resched()) {
		if (cc->mode == MIGRATE_ASYNC) {
			cc->contended = true;
			return true;
		}
		cond_resched();
	}

	return false;
}

/*
 * Aside from avoiding lock contention, compaction also periodically checks
 * need_resched() and either schedules in sync compaction or aborts async
 * compaction. This is similar to what compact_unlock_should_abort() does, but
 * is used where no lock is concerned.
 *
 * Returns false when no scheduling was needed, or sync compaction scheduled.
 * Returns true when async compaction should abort.
 */
static inline bool compact_should_abort(struct compact_control *cc)
{
	/* async compaction aborts if contended */
	if (need_resched()) {
		if (cc->mode == MIGRATE_ASYNC) {
			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,
				bool strict)
{
	int nr_scanned = 0, total_isolated = 0;
	struct page *cursor, *valid_page = NULL;
	unsigned long flags = 0;
	bool locked = false;
	unsigned long blockpfn = *start_pfn;
	unsigned int order;

	cursor = pfn_to_page(blockpfn);

	/* Isolate free pages. */
	for (; blockpfn < end_pfn; blockpfn++, cursor++) {
		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;

		if (!valid_page)
			valid_page = page;

		/*
		 * 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)) {
			unsigned int comp_order = compound_order(page);

			if (likely(comp_order < MAX_ORDER)) {
				blockpfn += (1UL << comp_order) - 1;
				cursor += (1UL << comp_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) {
			/*
			 * The zone lock must be held to isolate freepages.
			 * Unfortunately this is a very coarse lock and can be
			 * heavily contended if there are parallel allocations
			 * or parallel compactions. For async compaction do not
			 * spin on the lock and we acquire the lock as late as
			 * possible.
			 */
			locked = compact_trylock_irqsave(&cc->zone->lock,
								&flags, cc);
			if (!locked)
				break;

			/* 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;

	/* Update the pageblock-skip if the whole pageblock was scanned */
	if (blockpfn == end_pfn)
		update_pageblock_skip(cc, valid_page, total_isolated, false);

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

/**
 * isolate_freepages_range() - isolate free pages.
 * @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, 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 */
	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(struct zone *zone)
{
	unsigned long active, inactive, isolated;

	inactive = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) +
			node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON);
	active = node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE) +
			node_page_state(zone->zone_pgdat, NR_ACTIVE_ANON);
	isolated = node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE) +
			node_page_state(zone->zone_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)
{
	struct zone *zone = cc->zone;
	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;

	/*
	 * 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(zone))) {
		/* 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;
	}

	if (compact_should_abort(cc))
		return 0;

	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(zone_lru_lock(zone), flags,
								&locked, cc))
			break;

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

		page = pfn_to_page(low_pfn);

		if (!valid_page)
			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)) {
			unsigned int comp_order = compound_order(page);

			if (likely(comp_order < MAX_ORDER))
				low_pfn += (1UL << comp_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(zone_lru_lock(zone),
									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_trylock_irqsave(zone_lru_lock(zone),
								&flags, cc);
			if (!locked)
				break;

			/* 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, zone->zone_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++;

		/*
		 * Record where we could have freed pages by migration and not
		 * yet flushed them to buddy allocator.
		 * - this is the lowest page that was isolated and likely be
		 * then freed by migration.
		 */
		if (!cc->last_migrated_pfn)
			cc->last_migrated_pfn = low_pfn;

		/* Avoid isolating too much */
		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
			++low_pfn;
			break;
		}

		continue;
isolate_fail:
		if (!skip_on_failure)
			continue;

		/*
		 * We have isolated some pages, but then failed. Release them
		 * instead of migrating, as we cannot form the cc->order buddy
		 * page anyway.
		 */
		if (nr_isolated) {
			if (locked) {
				spin_unlock_irqrestore(zone_lru_lock(zone), flags);
				locked = false;
			}
			putback_movable_pages(&cc->migratepages);
			cc->nr_migratepages = 0;
			cc->last_migrated_pfn = 0;
			nr_isolated = 0;
		}

		if (low_pfn < next_skip_pfn) {
			low_pfn = next_skip_pfn - 1;
			/*
			 * The check near the loop beginning would have updated
			 * next_skip_pfn too, but this is a bit simpler.
			 */
			next_skip_pfn += 1UL << cc->order;
		}
	}

	/*
	 * The PageBuddy() check could have potentially brought us outside
	 * the range to be scanned.
	 */
	if (unlikely(low_pfn > end_pfn))
		low_pfn = end_pfn;

	if (locked)
		spin_unlock_irqrestore(zone_lru_lock(zone), flags);

	/*
	 * Update the pageblock-skip information and cached scanner pfn,
	 * if the whole pageblock was scanned without isolating any page.
	 */
	if (low_pfn == end_pfn)
		update_pageblock_skip(cc, valid_page, nr_isolated, true);

	trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
						nr_scanned, nr_isolated);

	cc->total_migrate_scanned += nr_scanned;
	if (nr_isolated)
		count_compact_events(COMPACTISOLATED, nr_isolated);

	return low_pfn;
}

/**
 * isolate_migratepages_range() - isolate migrate-able pages in a PFN range
 * @cc:        Compaction control structure.
 * @start_pfn: The first PFN to start isolating.
 * @end_pfn:   The one-past-last PFN.
 *
 * Returns zero if isolation fails fatally due to e.g. pending signal.
 * Otherwise, function returns one-past-the-last PFN of isolated page
 * (which may be greater than end_pfn if end fell in a middle of a THP page).
 */
unsigned long
isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
							unsigned long end_pfn)
{
	unsigned long pfn, block_start_pfn, block_end_pfn;

	/* Scan block by block. First and last block may be incomplete */
	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 = block_end_pfn,
				block_start_pfn = block_end_pfn,
				block_end_pfn += pageblock_nr_pages) {

		block_end_pfn = min(block_end_pfn, end_pfn);

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

		pfn = isolate_migratepages_block(cc, pfn, block_end_pfn,
							ISOLATE_UNEVICTABLE);

		if (!pfn)
			break;

		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
			break;
	}

	return pfn;
}

#endif /* CONFIG_COMPACTION || CONFIG_CMA */
#ifdef CONFIG_COMPACTION

static bool suitable_migration_source(struct compact_control *cc,
							struct page *page)
{
	int block_mt;

	if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction)
		return true;

	block_mt = get_pageblock_migratetype(page);

	if (cc->migratetype == MIGRATE_MOVABLE)
		return is_migrate_movable(block_mt);
	else
		return block_mt == cc->migratetype;
}

/* Returns true if the page is within a block suitable for migration to */
static bool suitable_migration_target(struct compact_control *cc,
							struct page *page)
{
	/* If the page is a large free page, then disallow migration */
	if (PageBuddy(page)) {
		/*
		 * We are checking page_order without zone->lock taken. But
		 * the only small danger is that we skip a potentially suitable
		 * pageblock, so it's not worth to check order for valid range.
		 */
		if (page_order_unsafe(page) >= pageblock_order)
			return false;
	}

	if (cc->ignore_block_suitable)
		return true;

	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
	if (is_migrate_movable(get_pageblock_migratetype(page)))
		return true;

	/* Otherwise skip the block */
	return false;
}

/*
 * Test whether the free scanner has reached the same or lower pageblock than
 * the migration scanner, and compaction should thus terminate.
 */
static inline bool compact_scanners_met(struct compact_control *cc)
{
	return (cc->free_pfn >> pageblock_order)
		<= (cc->migrate_pfn >> pageblock_order);
}

/*
 * Based on information in the current compact_control, find blocks
 * suitable for isolating free pages from and then isolate them.
 */
static void isolate_freepages(struct compact_control *cc)
{
	struct zone *zone = cc->zone;
	struct page *page;
	unsigned long block_start_pfn;	/* start of current pageblock */
	unsigned long isolate_start_pfn; /* exact pfn we start at */
	unsigned long block_end_pfn;	/* end of current pageblock */
	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
	struct list_head *freelist = &cc->freepages;

	/*
	 * Initialise the free scanner. The starting point is where we last
	 * successfully isolated from, zone-cached value, or the end of the
	 * zone when isolating for the first time. For looping we also need
	 * this pfn aligned down to the pageblock boundary, because we do
	 * block_start_pfn -= pageblock_nr_pages in the for loop.
	 * For ending point, take care when isolating in last pageblock of a
	 * a zone which ends in the middle of a pageblock.
	 * The low boundary is the end of the pageblock the migration scanner
	 * is using.
	 */
	isolate_start_pfn = cc->free_pfn;
	block_start_pfn = pageblock_start_pfn(cc->free_pfn);
	block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
						zone_end_pfn(zone));
	low_pfn = pageblock_end_pfn(cc->migrate_pfn);

	/*
	 * Isolate free pages until enough are available to migrate the
	 * pages on cc->migratepages. We stop searching if the migrate
	 * and free page scanners meet or enough free pages are isolated.
	 */
	for (; block_start_pfn >= low_pfn;
				block_end_pfn = block_start_pfn,
				block_start_pfn -= pageblock_nr_pages,
				isolate_start_pfn = block_start_pfn) {
		/*
		 * This can iterate a massively long zone without finding any
		 * suitable migration targets, so periodically check if we need
		 * to schedule, or even abort async compaction.
		 */
		if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
						&& compact_should_abort(cc))
			break;

		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
									zone);
		if (!page)
			continue;

		/* Check the block is suitable for migration */
		if (!suitable_migration_target(cc, page))
			continue;

		/* If isolation recently failed, do not retry */
		if (!isolation_suitable(cc, page))
			continue;

		/* Found a block suitable for isolating free pages from. */
		isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn,
					freelist, false);

		/*
		 * If we isolated enough freepages, or aborted due to lock
		 * contention, terminate.
		 */
		if ((cc->nr_freepages >= cc->nr_migratepages)
							|| cc->contended) {
			if (isolate_start_pfn >= block_end_pfn) {
				/*
				 * Restart at previous pageblock if more
				 * freepages can be isolated next time.
				 */
				isolate_start_pfn =
					block_start_pfn - pageblock_nr_pages;
			}
			break;
		} else if (isolate_start_pfn < block_end_pfn) {
			/*
			 * If isolation failed early, do not continue
			 * needlessly.
			 */
			break;
		}
	}

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

	/*
	 * Record where the free scanner will restart next time. Either we
	 * broke from the loop and set isolate_start_pfn based on the last
	 * call to isolate_freepages_block(), or we met the migration scanner
	 * and the loop terminated due to isolate_start_pfn < low_pfn
	 */
	cc->free_pfn = isolate_start_pfn;
}

/*
 * This is a migrate-callback that "allocates" freepages by taking pages
 * from the isolated freelists in the block we are migrating to.
 */
static struct page *compaction_alloc(struct page *migratepage,
					unsigned long data,
					int **result)
{
	struct compact_control *cc = (struct compact_control *)data;
	struct page *freepage;

	/*
	 * Isolate free pages if necessary, and if we are not aborting due to
	 * contention.
	 */
	if (list_empty(&cc->freepages)) {
		if (!cc->contended)
			isolate_freepages(cc);

		if (list_empty(&cc->freepages))
			return NULL;
	}

	freepage = list_entry(cc->freepages.next, struct page, lru);
	list_del(&freepage->lru);
	cc->nr_freepages--;

	return freepage;
}

/*
 * This is a migrate-callback that "frees" freepages back to the isolated
 * freelist.  All pages on the freelist are from the same zone, so there is no
 * special handling needed for NUMA.
 */
static void compaction_free(struct page *page, unsigned long data)
{
	struct compact_control *cc = (struct compact_control *)data;

	list_add(&page->lru, &cc->freepages);
	cc->nr_freepages++;
}

/* possible outcome of isolate_migratepages */
typedef enum {
	ISOLATE_ABORT,		/* Abort compaction now */
	ISOLATE_NONE,		/* No pages isolated, continue scanning */
	ISOLATE_SUCCESS,	/* Pages isolated, migrate */
} isolate_migrate_t;

/*
 * Allow userspace to control policy on scanning the unevictable LRU for
 * compactable pages.
 */
int sysctl_compact_unevictable_allowed __read_mostly = 1;

/*
 * Isolate all pages that can be migrated from the first suitable block,
 * starting at the block pointed to by the migrate scanner pfn within
 * compact_control.
 */
static isolate_migrate_t isolate_migratepages(struct zone *zone,
					struct compact_control *cc)
{
	unsigned long block_start_pfn;
	unsigned long block_end_pfn;
	unsigned long low_pfn;
	struct page *page;
	const isolate_mode_t isolate_mode =
		(sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
		(cc->mode != MIGRATE_SYNC ? ISOLATE_ASYNC_MIGRATE : 0);

	/*
	 * Start at where we last stopped, or beginning of the zone as
	 * initialized by compact_zone()
	 */
	low_pfn = cc->migrate_pfn;
	block_start_pfn = pageblock_start_pfn(low_pfn);
	if (block_start_pfn < zone->zone_start_pfn)
		block_start_pfn = zone->zone_start_pfn;

	/* Only scan within a pageblock boundary */
	block_end_pfn = pageblock_end_pfn(low_pfn);

	/*
	 * Iterate over whole pageblocks until we find the first suitable.
	 * Do not cross the free scanner.
	 */
	for (; block_end_pfn <= cc->free_pfn;
			low_pfn = block_end_pfn,
			block_start_pfn = block_end_pfn,
			block_end_pfn += pageblock_nr_pages) {

		/*
		 * This can potentially iterate a massively long zone with
		 * many pageblocks unsuitable, so periodically check if we
		 * need to schedule, or even abort async compaction.
		 */
		if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
						&& compact_should_abort(cc))
			break;

		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
									zone);
		if (!page)
			continue;

		/* If isolation recently failed, do not retry */
		if (!isolation_suitable(cc, page))
			continue;

		/*
		 * For async compaction, also only scan in MOVABLE blocks.
		 * Async compaction is optimistic to see if the minimum amount
		 * of work satisfies the allocation.
		 */
		if (!suitable_migration_source(cc, page))
			continue;

		/* Perform the isolation */
		low_pfn = isolate_migratepages_block(cc, low_pfn,
						block_end_pfn, isolate_mode);

		if (!low_pfn || cc->contended)
			return ISOLATE_ABORT;

		/*
		 * Either we isolated something and proceed with migration. Or
		 * we failed and compact_zone should decide if we should
		 * continue or not.
		 */
		break;
	}

	/* Record where migration scanner will be restarted. */
	cc->migrate_pfn = low_pfn;

	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
}

/*
 * order == -1 is expected when compacting via
 * /proc/sys/vm/compact_memory
 */
static inline bool is_via_compact_memory(int order)
{
	return order == -1;
}

static enum compact_result __compact_finished(struct zone *zone,
						struct compact_control *cc)
{
	unsigned int order;
	const int migratetype = cc->migratetype;

	if (cc->contended || fatal_signal_pending(current))
		return COMPACT_CONTENDED;

	/* Compaction run completes if the migrate and free scanner meet */
	if (compact_scanners_met(cc)) {
		/* Let the next compaction start anew. */
		reset_cached_positions(zone);

		/*
		 * Mark that the PG_migrate_skip information should be cleared
		 * by kswapd when it goes to sleep. kcompactd does not set the
		 * flag itself as the decision to be clear should be directly
		 * based on an allocation request.
		 */
		if (cc->direct_compaction)
			zone->compact_blockskip_flush = true;

		if (cc->whole_zone)
			return COMPACT_COMPLETE;
		else
			return COMPACT_PARTIAL_SKIPPED;
	}

	if (is_via_compact_memory(cc->order))
		return COMPACT_CONTINUE;

	if (cc->finishing_block) {
		/*
		 * We have finished the pageblock, but better check again that
		 * we really succeeded.
		 */
		if (IS_ALIGNED(cc->migrate_pfn, pageblock_nr_pages))
			cc->finishing_block = false;
		else
			return COMPACT_CONTINUE;
	}

	/* Direct compactor: Is a suitable page free? */
	for (order = cc->order; order < MAX_ORDER; order++) {
		struct free_area *area = &zone->free_area[order];
		bool can_steal;

		/* Job done if page is free of the right migratetype */
		if (!list_empty(&area->free_list[migratetype]))
			return COMPACT_SUCCESS;

#ifdef CONFIG_CMA
		/* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */
		if (migratetype == MIGRATE_MOVABLE &&
			!list_empty(&area->free_list[MIGRATE_CMA]))
			return COMPACT_SUCCESS;
#endif
		/*
		 * Job done if allocation would steal freepages from
		 * other migratetype buddy lists.
		 */
		if (find_suitable_fallback(area, order, migratetype,
						true, &can_steal) != -1) {

			/* movable pages are OK in any pageblock */
			if (migratetype == MIGRATE_MOVABLE)
				return COMPACT_SUCCESS;

			/*
			 * We are stealing for a non-movable allocation. Make
			 * sure we finish compacting the current pageblock
			 * first so it is as free as possible and we won't
			 * have to steal another one soon. This only applies
			 * to sync compaction, as async compaction operates
			 * on pageblocks of the same migratetype.
			 */
			if (cc->mode == MIGRATE_ASYNC ||
					IS_ALIGNED(cc->migrate_pfn,
							pageblock_nr_pages)) {
				return COMPACT_SUCCESS;
			}

			cc->finishing_block = true;
			return COMPACT_CONTINUE;
		}
	}

	return COMPACT_NO_SUITABLE_PAGE;
}

static enum compact_result compact_finished(struct zone *zone,
			struct compact_control *cc)
{
	int ret;

	ret = __compact_finished(zone, cc);
	trace_mm_compaction_finished(zone, cc->order, ret);
	if (ret == COMPACT_NO_SUITABLE_PAGE)
		ret = COMPACT_CONTINUE;

	return ret;
}

/*
 * compaction_suitable: Is this suitable to run compaction on this zone now?
 * Returns
 *   COMPACT_SKIPPED  - If there are too few free pages for compaction
 *   COMPACT_SUCCESS  - If the allocation would succeed without compaction
 *   COMPACT_CONTINUE - If compaction should run now
 */
static enum compact_result __compaction_suitable(struct zone *zone, int order,
					unsigned int alloc_flags,
					int classzone_idx,
					unsigned long wmark_target)
{
	unsigned long watermark;

	if (is_via_compact_memory(order))
		return COMPACT_CONTINUE;


context:
space:
mode: